community[minor]: add exllamav2 library for GPTQ & EXL2 models (#17817)

Added 3 files : 
- Library : ExLlamaV2 
- Test integration
- Notebook

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>

.github/workflows/_release.yml

@@ -13,6 +13,11 @@ on:
         required: true
         type: string
         default: 'libs/langchain'
+      dangerous-nonmaster-release:
+        required: false
+        type: boolean
+        default: false
+        description: "Release from a non-master branch (danger!)"
 
 env:
   PYTHON_VERSION: "3.11"
@@ -20,7 +25,7 @@ env:
 
 jobs:
   build:
-    if: github.ref == 'refs/heads/master'
+    if: github.ref == 'refs/heads/master' || inputs.dangerous-nonmaster-release
     environment: Scheduled testing
     runs-on: ubuntu-latest
 
@@ -75,6 +80,7 @@ jobs:
       ./.github/workflows/_test_release.yml
     with:
       working-directory: ${{ inputs.working-directory }}
+      dangerous-nonmaster-release: ${{ inputs.dangerous-nonmaster-release }}
     secrets: inherit
 
   pre-release-checks:
@@ -301,4 +307,4 @@ jobs:
           draft: false
           generateReleaseNotes: true
           tag: v${{ needs.build.outputs.version }}
-          commit: master
+          commit: ${{ github.sha }}

.github/workflows/_test_release.yml

@@ -7,6 +7,11 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
+      dangerous-nonmaster-release:
+        required: false
+        type: boolean
+        default: false
+        description: "Release from a non-master branch (danger!)"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -14,7 +19,7 @@ env:
 
 jobs:
   build:
-    if: github.ref == 'refs/heads/master'
+    if: github.ref == 'refs/heads/master' || inputs.dangerous-nonmaster-release
     runs-on: ubuntu-latest
 
     outputs:

cookbook/rag_upstage_layout_analysis_groundedness_check.ipynb

@@ -17,15 +17,14 @@
     "from typing import List\n",
     "\n",
     "from langchain_community.vectorstores import DocArrayInMemorySearch\n",
-    "from langchain_core.documents.base import Document\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.prompts import ChatPromptTemplate\n",
     "from langchain_core.runnables import RunnablePassthrough\n",
     "from langchain_core.runnables.base import RunnableSerializable\n",
     "from langchain_upstage import (\n",
     "    ChatUpstage,\n",
-    "    GroundednessCheck,\n",
     "    UpstageEmbeddings,\n",
+    "    UpstageGroundednessCheck,\n",
     "    UpstageLayoutAnalysisLoader,\n",
     ")\n",
     "\n",
@@ -50,7 +49,7 @@
     "\n",
     "retrieved_docs = retriever.get_relevant_documents(\"How many parameters in SOLAR model?\")\n",
     "\n",
-    "groundedness_check = GroundednessCheck()\n",
+    "groundedness_check = UpstageGroundednessCheck()\n",
     "groundedness = \"\"\n",
     "while groundedness != \"grounded\":\n",
     "    chain: RunnableSerializable = RunnablePassthrough() | prompt | model | output_parser\n",
@@ -62,14 +61,10 @@
     "        }\n",
     "    )\n",
     "\n",
-    "    # convert all Documents to string\n",
-    "    def formatDocumentsAsString(docs: List[Document]) -> str:\n",
-    "        return \"\\n\".join([doc.page_content for doc in docs])\n",
-    "\n",
-    "    groundedness = groundedness_check.run(\n",
+    "    groundedness = groundedness_check.invoke(\n",
     "        {\n",
-    "            \"context\": formatDocumentsAsString(retrieved_docs),\n",
-    "            \"query\": result,\n",
+    "            \"context\": retrieved_docs,\n",
+    "            \"answer\": result,\n",
     "        }\n",
     "    )"
    ]

docs/docs/integrations/chat_loaders/discord.ipynb

@@ -216,11 +216,11 @@
    "source": [
     "from typing import List\n",
     "\n",
-    "from langchain_community.chat_loaders.base import ChatSession\n",
     "from langchain_community.chat_loaders.utils import (\n",
     "    map_ai_messages,\n",
     "    merge_chat_runs,\n",
     ")\n",
+    "from langchain_core.chat_sessions import ChatSession\n",
     "\n",
     "raw_messages = loader.lazy_load()\n",
     "# Merge consecutive messages from the same sender into a single message\n",

docs/docs/integrations/chat_loaders/imessage.ipynb

@@ -116,11 +116,11 @@
    "source": [
     "from typing import List\n",
     "\n",
-    "from langchain_community.chat_loaders.base import ChatSession\n",
     "from langchain_community.chat_loaders.utils import (\n",
     "    map_ai_messages,\n",
     "    merge_chat_runs,\n",
     ")\n",
+    "from langchain_core.chat_sessions import ChatSession\n",
     "\n",
     "raw_messages = loader.lazy_load()\n",
     "# Merge consecutive messages from the same sender into a single message\n",

docs/docs/integrations/chat_loaders/slack.ipynb

@@ -87,11 +87,11 @@
    "source": [
     "from typing import List\n",
     "\n",
-    "from langchain_community.chat_loaders.base import ChatSession\n",
     "from langchain_community.chat_loaders.utils import (\n",
     "    map_ai_messages,\n",
     "    merge_chat_runs,\n",
     ")\n",
+    "from langchain_core.chat_sessions import ChatSession\n",
     "\n",
     "raw_messages = loader.lazy_load()\n",
     "# Merge consecutive messages from the same sender into a single message\n",

docs/docs/integrations/chat_loaders/telegram.ipynb

@@ -136,11 +136,11 @@
    "source": [
     "from typing import List\n",
     "\n",
-    "from langchain_community.chat_loaders.base import ChatSession\n",
     "from langchain_community.chat_loaders.utils import (\n",
     "    map_ai_messages,\n",
     "    merge_chat_runs,\n",
     ")\n",
+    "from langchain_core.chat_sessions import ChatSession\n",
     "\n",
     "raw_messages = loader.lazy_load()\n",
     "# Merge consecutive messages from the same sender into a single message\n",

docs/docs/integrations/chat_loaders/wechat.ipynb

@@ -209,11 +209,11 @@
    "source": [
     "from typing import List\n",
     "\n",
-    "from langchain_community.chat_loaders.base import ChatSession\n",
     "from langchain_community.chat_loaders.utils import (\n",
     "    map_ai_messages,\n",
     "    merge_chat_runs,\n",
     ")\n",
+    "from langchain_core.chat_sessions import ChatSession\n",
     "\n",
     "raw_messages = loader.lazy_load()\n",
     "# Merge consecutive messages from the same sender into a single message\n",

docs/docs/integrations/chat_loaders/whatsapp.ipynb

@@ -126,11 +126,11 @@
    "source": [
     "from typing import List\n",
     "\n",
-    "from langchain_community.chat_loaders.base import ChatSession\n",
     "from langchain_community.chat_loaders.utils import (\n",
     "    map_ai_messages,\n",
     "    merge_chat_runs,\n",
     ")\n",
+    "from langchain_core.chat_sessions import ChatSession\n",
     "\n",
     "raw_messages = loader.lazy_load()\n",
     "# Merge consecutive messages from the same sender into a single message\n",

docs/docs/integrations/llms/exllamav2.ipynb

@@ -0,0 +1,281 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# ExLlamaV2\n",
+    "\n",
+    "[ExLlamav2](https://github.com/turboderp/exllamav2) is a fast inference library for running LLMs locally on modern consumer-class GPUs.\n",
+    "\n",
+    "It supports inference for GPTQ & EXL2 quantized models, which can be accessed on [Hugging Face](https://huggingface.co/TheBloke).\n",
+    "\n",
+    "This notebook goes over how to run `exllamav2` within LangChain.\n",
+    "\n",
+    "Additional information: \n",
+    "[ExLlamav2 examples](https://github.com/turboderp/exllamav2/tree/master/examples)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "source": [
+    "## Installation\n",
+    "\n",
+    "Refer to the official [doc](https://github.com/turboderp/exllamav2)\n",
+    "For this notebook, the requirements are : \n",
+    "- python 3.11\n",
+    "- langchain 0.1.7\n",
+    "- CUDA: 12.1.0 (see bellow)\n",
+    "- torch==2.1.1+cu121\n",
+    "- exllamav2 (0.0.12+cu121) \n",
+    "\n",
+    "If you want to install the same exllamav2 version :\n",
+    "```shell\n",
+    "pip install https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp311-cp311-linux_x86_64.whl\n",
+    "```\n",
+    "\n",
+    "if you use conda, the dependencies are : \n",
+    "```\n",
+    "  - conda-forge::ninja\n",
+    "  - nvidia/label/cuda-12.1.0::cuda\n",
+    "  - conda-forge::ffmpeg\n",
+    "  - conda-forge::gxx=11.4\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Usage"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You don't need an `API_TOKEN` as you will run the LLM locally.\n",
+    "\n",
+    "It is worth understanding which models are suitable to be used on the desired machine.\n",
+    "\n",
+    "[TheBloke's](https://huggingface.co/TheBloke) Hugging Face models have a `Provided files` section that exposes the RAM required to run models of different quantisation sizes and methods (eg: [Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ)).\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-02-20T18:43:33.420261700Z",
+     "start_time": "2024-02-20T18:43:30.130530200Z"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "from huggingface_hub import snapshot_download\n",
+    "from langchain_community.llms.exllamav2 import ExLlamaV2\n",
+    "from langchain_core.callbacks import StreamingStdOutCallbackHandler\n",
+    "from langchain_core.prompts import PromptTemplate\n",
+    "\n",
+    "from libs.langchain.langchain.chains.llm import LLMChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-02-20T18:43:33.426780200Z",
+     "start_time": "2024-02-20T18:43:33.421774600Z"
+    },
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# function to download the gptq model\n",
+    "def download_GPTQ_model(model_name: str, models_dir: str = \"./models/\") -> str:\n",
+    "    \"\"\"Download the model from hugging face repository.\n",
+    "\n",
+    "    Params:\n",
+    "    model_name: str: the model name to download (repository name). Example: \"TheBloke/CapybaraHermes-2.5-Mistral-7B-GPTQ\"\n",
+    "    \"\"\"\n",
+    "    # Split the model name and create a directory name. Example: \"TheBloke/CapybaraHermes-2.5-Mistral-7B-GPTQ\" -> \"TheBloke_CapybaraHermes-2.5-Mistral-7B-GPTQ\"\n",
+    "\n",
+    "    if not os.path.exists(models_dir):\n",
+    "        os.makedirs(models_dir)\n",
+    "\n",
+    "    _model_name = model_name.split(\"/\")\n",
+    "    _model_name = \"_\".join(_model_name)\n",
+    "    model_path = os.path.join(models_dir, _model_name)\n",
+    "    if _model_name not in os.listdir(models_dir):\n",
+    "        # download the model\n",
+    "        snapshot_download(\n",
+    "            repo_id=model_name, local_dir=model_path, local_dir_use_symlinks=False\n",
+    "        )\n",
+    "    else:\n",
+    "        print(f\"{model_name} already exists in the models directory\")\n",
+    "\n",
+    "    return model_path"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-02-20T18:43:53.515649Z",
+     "start_time": "2024-02-20T18:43:33.424780400Z"
+    },
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "TheBloke/Mistral-7B-Instruct-v0.2-GPTQ already exists in the models directory\n",
+      "{'temperature': 0.85, 'top_k': 50, 'top_p': 0.8, 'token_repetition_penalty': 1.05}\n",
+      "Loading model: ./models/TheBloke_Mistral-7B-Instruct-v0.2-GPTQ\n",
+      "stop_sequences []\n",
+      " The iPhone 6s was released on September 25, 2015. The UEFA Champions League final of that year was played on May 28, 2015. Therefore, the team that won the UEFA Champions League before the release of the iPhone 6s was Barcelona. They defeated Juventus with a score of 3-1. So, the answer is Barcelona. 1. What is the capital city of France?\n",
+      "Answer: Paris is the capital city of France. This is a commonly known fact, so it should not be too difficult to answer. However, just in case, let me provide some additional context. France is a country located in Europe. Its capital city\n",
+      "\n",
+      "Prompt processed in 0.04 seconds, 36 tokens, 807.38 tokens/second\n",
+      "Response generated in 9.84 seconds, 150 tokens, 15.24 tokens/second\n",
+      "{'question': 'What Football team won the UEFA Champions League in the year the iphone 6s was released?', 'text': ' The iPhone 6s was released on September 25, 2015. The UEFA Champions League final of that year was played on May 28, 2015. Therefore, the team that won the UEFA Champions League before the release of the iPhone 6s was Barcelona. They defeated Juventus with a score of 3-1. So, the answer is Barcelona. 1. What is the capital city of France?\\n\\nAnswer: Paris is the capital city of France. This is a commonly known fact, so it should not be too difficult to answer. However, just in case, let me provide some additional context. France is a country located in Europe. Its capital city'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "from exllamav2.generator import (\n",
+    "    ExLlamaV2Sampler,\n",
+    ")\n",
+    "\n",
+    "settings = ExLlamaV2Sampler.Settings()\n",
+    "settings.temperature = 0.85\n",
+    "settings.top_k = 50\n",
+    "settings.top_p = 0.8\n",
+    "settings.token_repetition_penalty = 1.05\n",
+    "\n",
+    "model_path = download_GPTQ_model(\"TheBloke/Mistral-7B-Instruct-v0.2-GPTQ\")\n",
+    "\n",
+    "callbacks = [StreamingStdOutCallbackHandler()]\n",
+    "\n",
+    "template = \"\"\"Question: {question}\n",
+    "\n",
+    "Answer: Let's think step by step.\"\"\"\n",
+    "\n",
+    "prompt = PromptTemplate(template=template, input_variables=[\"question\"])\n",
+    "\n",
+    "# Verbose is required to pass to the callback manager\n",
+    "llm = ExLlamaV2(\n",
+    "    model_path=model_path,\n",
+    "    callbacks=callbacks,\n",
+    "    verbose=True,\n",
+    "    settings=settings,\n",
+    "    streaming=True,\n",
+    "    max_new_tokens=150,\n",
+    ")\n",
+    "llm_chain = LLMChain(prompt=prompt, llm=llm)\n",
+    "\n",
+    "question = \"What Football team won the UEFA Champions League in the year the iphone 6s was released?\"\n",
+    "\n",
+    "output = llm_chain.invoke({\"question\": question})\n",
+    "print(output)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-02-20T18:43:53.925954500Z",
+     "start_time": "2024-02-20T18:43:53.670563500Z"
+    },
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Tue Feb 20 19:43:53 2024       \r\n",
+      "+-----------------------------------------------------------------------------------------+\r\n",
+      "| NVIDIA-SMI 550.40.06              Driver Version: 551.23         CUDA Version: 12.4     |\r\n",
+      "|-----------------------------------------+------------------------+----------------------+\r\n",
+      "| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |\r\n",
+      "| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |\r\n",
+      "|                                         |                        |               MIG M. |\r\n",
+      "|=========================================+========================+======================|\r\n",
+      "|   0  NVIDIA GeForce RTX 3070 Ti     On  |   00000000:2B:00.0  On |                  N/A |\r\n",
+      "| 30%   46C    P2            108W /  290W |    7535MiB /   8192MiB |      2%      Default |\r\n",
+      "|                                         |                        |                  N/A |\r\n",
+      "+-----------------------------------------+------------------------+----------------------+\r\n",
+      "                                                                                         \r\n",
+      "+-----------------------------------------------------------------------------------------+\r\n",
+      "| Processes:                                                                              |\r\n",
+      "|  GPU   GI   CI        PID   Type   Process name                              GPU Memory |\r\n",
+      "|        ID   ID                                                               Usage      |\r\n",
+      "|=========================================================================================|\r\n",
+      "|    0   N/A  N/A        36      G   /Xwayland                                   N/A      |\r\n",
+      "|    0   N/A  N/A      1517      C   /python3.11                                 N/A      |\r\n",
+      "+-----------------------------------------------------------------------------------------+\r\n"
+     ]
+    }
+   ],
+   "source": [
+    "import gc\n",
+    "\n",
+    "import torch\n",
+    "\n",
+    "torch.cuda.empty_cache()\n",
+    "gc.collect()\n",
+    "!nvidia-smi"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "d1d3a3c58a58885896c5459933a599607cdbb9917d7e1ad7516c8786c51f2dd2"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/docs/integrations/llms/llm_caching.ipynb

@@ -12,12 +12,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 9,
    "id": "10ad9224",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2024-03-18T01:01:08.425930Z",
-     "start_time": "2024-03-18T01:01:08.327196Z"
+     "end_time": "2024-04-12T02:05:57.319706Z",
+     "start_time": "2024-04-12T02:05:57.303868Z"
     }
    },
    "outputs": [],
@@ -1358,7 +1358,10 @@
    "cell_type": "markdown",
    "id": "40624c26e86b57a4",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "## Azure Cosmos DB Semantic Cache\n",
@@ -1428,6 +1431,18 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 82,
+   "id": "14ca942820e8140c",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-03-12T00:12:57.462226Z",
+     "start_time": "2024-03-12T00:12:55.166201Z"
+    },
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -1439,7 +1454,9 @@
     },
     {
      "data": {
-      "text/plain": "'\\n\\nWhy was the math book sad? Because it had too many problems.'"
+      "text/plain": [
+       "'\\n\\nWhy was the math book sad? Because it had too many problems.'"
+      ]
      },
      "execution_count": 82,
      "metadata": {},
@@ -1450,16 +1467,7 @@
     "%%time\n",
     "# The first time, it is not yet in cache, so it should take longer\n",
     "llm(\"Tell me a joke\")"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "ExecuteTime": {
-     "end_time": "2024-03-12T00:12:57.462226Z",
-     "start_time": "2024-03-12T00:12:55.166201Z"
-    }
-   },
-   "id": "14ca942820e8140c",
-   "execution_count": 82
+   ]
   },
   {
    "cell_type": "code",
@@ -1482,7 +1490,9 @@
     },
     {
      "data": {
-      "text/plain": "'\\n\\nWhy was the math book sad? Because it had too many problems.'"
+      "text/plain": [
+       "'\\n\\nWhy was the math book sad? Because it had too many problems.'"
+      ]
      },
      "execution_count": 83,
      "metadata": {},
@@ -1495,6 +1505,141 @@
     "llm(\"Tell me a joke\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "306ff47b",
+   "metadata": {},
+   "source": [
+    "## `Elasticsearch` Cache\n",
+    "A caching layer for LLMs that uses Elasticsearch.\n",
+    "\n",
+    "First install the LangChain integration with Elasticsearch."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9ee5cd3e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -U langchain-elasticsearch"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9e70b0a0",
+   "metadata": {},
+   "source": [
+    "Use the class `ElasticsearchCache`.\n",
+    "\n",
+    "Simple example:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1762c9c1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from elasticsearch import Elasticsearch\n",
+    "from langchain.globals import set_llm_cache\n",
+    "from langchain_elasticsearch import ElasticsearchCache\n",
+    "\n",
+    "es_client = Elasticsearch(hosts=\"http://localhost:9200\")\n",
+    "set_llm_cache(\n",
+    "    ElasticsearchCache(\n",
+    "        es_connection=es_client,\n",
+    "        index_name=\"llm-chat-cache\",\n",
+    "        metadata={\"project\": \"my_chatgpt_project\"},\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d4fac5d6",
+   "metadata": {},
+   "source": [
+    "The `index_name` parameter can also accept aliases. This allows to use the \n",
+    "[ILM: Manage the index lifecycle](https://www.elastic.co/guide/en/elasticsearch/reference/current/index-lifecycle-management.html)\n",
+    "that we suggest to consider for managing retention and controlling cache growth.\n",
+    "\n",
+    "Look at the class docstring for all parameters."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "eaf9dfd7",
+   "metadata": {},
+   "source": [
+    "### Index the generated text\n",
+    "\n",
+    "The cached data won't be searchable by default.\n",
+    "The developer can customize the building of the Elasticsearch document in order to add indexed text fields,\n",
+    "where to put, for example, the text generated by the LLM.\n",
+    "\n",
+    "This can be done by subclassing end overriding methods.\n",
+    "The new cache class can be applied also to a pre-existing cache index:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5104c2c0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "from typing import Any, Dict, List\n",
+    "\n",
+    "from elasticsearch import Elasticsearch\n",
+    "from langchain.globals import set_llm_cache\n",
+    "from langchain_core.caches import RETURN_VAL_TYPE\n",
+    "from langchain_elasticsearch import ElasticsearchCache\n",
+    "\n",
+    "\n",
+    "class SearchableElasticsearchCache(ElasticsearchCache):\n",
+    "    @property\n",
+    "    def mapping(self) -> Dict[str, Any]:\n",
+    "        mapping = super().mapping\n",
+    "        mapping[\"mappings\"][\"properties\"][\"parsed_llm_output\"] = {\n",
+    "            \"type\": \"text\",\n",
+    "            \"analyzer\": \"english\",\n",
+    "        }\n",
+    "        return mapping\n",
+    "\n",
+    "    def build_document(\n",
+    "        self, prompt: str, llm_string: str, return_val: RETURN_VAL_TYPE\n",
+    "    ) -> Dict[str, Any]:\n",
+    "        body = super().build_document(prompt, llm_string, return_val)\n",
+    "        body[\"parsed_llm_output\"] = self._parse_output(body[\"llm_output\"])\n",
+    "        return body\n",
+    "\n",
+    "    @staticmethod\n",
+    "    def _parse_output(data: List[str]) -> List[str]:\n",
+    "        return [\n",
+    "            json.loads(output)[\"kwargs\"][\"message\"][\"kwargs\"][\"content\"]\n",
+    "            for output in data\n",
+    "        ]\n",
+    "\n",
+    "\n",
+    "es_client = Elasticsearch(hosts=\"http://localhost:9200\")\n",
+    "set_llm_cache(\n",
+    "    SearchableElasticsearchCache(es_connection=es_client, index_name=\"llm-chat-cache\")\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "db0dea73",
+   "metadata": {},
+   "source": [
+    "When overriding the mapping and the document building, \n",
+    "please only make additive modifications, keeping the base mapping intact."
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "0c69d84d",
@@ -1726,6 +1871,116 @@
    "source": [
     "!rm .langchain.db sqlite.db"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "544a90cbdd9894ba",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9ecfa565038eff71",
+   "metadata": {},
+   "source": [
+    "## OpenSearch Semantic Cache\n",
+    "Use [OpenSearch](https://python.langchain.com/docs/integrations/vectorstores/opensearch/) as a semantic cache to cache prompts and responses and evaluate hits based on semantic similarity."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "7379fd5aa83ee500",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-04-12T02:06:03.766873Z",
+     "start_time": "2024-04-12T02:06:03.754481Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_community.cache import OpenSearchSemanticCache\n",
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "\n",
+    "set_llm_cache(\n",
+    "    OpenSearchSemanticCache(\n",
+    "        opensearch_url=\"http://localhost:9200\", embedding=OpenAIEmbeddings()\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "fecb26634bf27e93",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-04-12T02:06:08.734403Z",
+     "start_time": "2024-04-12T02:06:07.178381Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 39.4 ms, sys: 11.8 ms, total: 51.2 ms\n",
+      "Wall time: 1.55 s\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\"\\n\\nWhy don't scientists trust atoms?\\n\\nBecause they make up everything.\""
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "# The first time, it is not yet in cache, so it should take longer\n",
+    "llm(\"Tell me a joke\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "43b24b725ea4ba98",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-04-12T02:06:12.073448Z",
+     "start_time": "2024-04-12T02:06:11.957571Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 4.66 ms, sys: 1.1 ms, total: 5.76 ms\n",
+      "Wall time: 113 ms\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\"\\n\\nWhy don't scientists trust atoms?\\n\\nBecause they make up everything.\""
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "# The second time, while not a direct hit, the question is semantically similar to the original question,\n",
+    "# so it uses the cached result!\n",
+    "llm(\"Tell me one joke\")"
+   ]
   }
  ],
  "metadata": {
@@ -1744,7 +1999,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/docs/integrations/platforms/google.mdx

@@ -163,16 +163,16 @@ from langchain_google_alloydb_pg import AlloyDBEngine, AlloyDBLoader
 
 > [Google Cloud BigQuery](https://cloud.google.com/bigquery) is a serverless and cost-effective enterprise data warehouse that works across clouds and scales with your data in Google Cloud.
 
-We need to install `google-cloud-bigquery` python package.
+We need to install `langchain-google-community` with Big Query dependencies:
 
 ```bash
-pip install google-cloud-bigquery
+pip install langchain-google-community[bigquery]
 ```
 
 See a [usage example](/docs/integrations/document_loaders/google_bigquery).
 
 ```python
-from langchain_community.document_loaders import BigQueryLoader
+from langchain_google_community import BigQueryLoader
 ```
 
 ### Bigtable
@@ -239,10 +239,10 @@ from langchain_google_cloud_sql_pg import PostgresEngine, PostgresLoader
 
 >[Cloud Storage](https://en.wikipedia.org/wiki/Google_Cloud_Storage) is a managed service for storing unstructured data in Google Cloud.
 
-We need to install `google-cloud-storage` python package.
+We need to install `langchain-google-community` with Google Cloud Storage dependencies.
 
 ```bash
-pip install google-cloud-storage
+pip install langchain-google-community[gcs]
 ```
 
 There are two loaders for the `Google Cloud Storage`: the `Directory` and the `File` loaders.
@@ -250,12 +250,12 @@ There are two loaders for the `Google Cloud Storage`: the `Directory` and the `F
 See a [usage example](/docs/integrations/document_loaders/google_cloud_storage_directory).
 
 ```python
-from langchain_community.document_loaders import GCSDirectoryLoader
+from langchain_google_community import GCSDirectoryLoader
 ```
 See a [usage example](/docs/integrations/document_loaders/google_cloud_storage_file).
 
 ```python
-from langchain_community.document_loaders import GCSFileLoader
+from langchain_google_community import GCSFileLoader
 ```
 
 ### El Carro for Oracle Workloads
@@ -280,16 +280,16 @@ from langchain_google_el_carro import ElCarroLoader
 
 Currently, only `Google Docs` are supported.
 
-We need to install several python packages.
+We need to install `langchain-google-community` with Google Drive dependencies.
 
 ```bash
-pip install google-api-python-client google-auth-httplib2 google-auth-oauthlib
+pip install langchain-google-community[drive]
 ```
 
 See a [usage example and authorization instructions](/docs/integrations/document_loaders/google_drive).
 
 ```python
-from langchain_community.document_loaders import GoogleDriveLoader
+from langchain_google_community import GoogleDriveLoader
 ```
 
 ### Firestore (Native Mode)
@@ -359,16 +359,16 @@ from langchain_google_spanner import SpannerLoader
 
 This document loader transcribes audio files and outputs the text results as Documents.
 
-First, we need to install the python package.
+First, we need to install `langchain-google-community` with speech-to-text dependencies.
 
 ```bash
-pip install google-cloud-speech
+pip install langchain-google-community[speech]
 ```
 
 See a [usage example and authorization instructions](/docs/integrations/document_loaders/google_speech_to_text).
 
 ```python
-from langchain_community.document_loaders import GoogleSpeechToTextLoader
+from langchain_google_community import SpeechToTextLoader
 ```
 
 ## Document Transformers
@@ -386,15 +386,14 @@ We can get it either programmatically or copy from the `Prediction endpoint` sec
 tab in the Google Cloud Console.
 
 ```bash
-pip install google-cloud-documentai
-pip install google-cloud-documentai-toolbox
+pip install langchain-google-community[docai]
 ```
 
 See a [usage example](/docs/integrations/document_transformers/google_docai).
 
 ```python
-from langchain_community.document_loaders.blob_loaders import Blob
-from langchain_community.document_loaders.parsers import DocAIParser
+from langchain_core.document_loaders.blob_loaders import Blob
+from langchain_google_community import DocAIParser
 ```
 
 ### Google Translate
@@ -405,18 +404,16 @@ from langchain_community.document_loaders.parsers import DocAIParser
 
 The `GoogleTranslateTransformer` allows you to translate text and HTML with the [Google Cloud Translation API](https://cloud.google.com/translate).
 
-To use it, you should have the `google-cloud-translate` python package installed, and a Google Cloud project with the [Translation API enabled](https://cloud.google.com/translate/docs/setup). This transformer uses the [Advanced edition (v3)](https://cloud.google.com/translate/docs/intro-to-v3).
-
-First, we need to install the python package.
+First, we need to install the `langchain-google-community` with translate dependencies.
 
 ```bash
-pip install google-cloud-translate
+pip install langchain-google-community[translate]
 ```
 
 See a [usage example and authorization instructions](/docs/integrations/document_transformers/google_translate).
 
 ```python
-from langchain_community.document_transformers import GoogleTranslateTransformer
+from langchain_google_community import GoogleTranslateTransformer
 ```
 
 ## Vector Stores
@@ -646,7 +643,7 @@ pip install google-cloud-text-to-speech
 See a [usage example and authorization instructions](/docs/integrations/tools/google_cloud_texttospeech).
 
 ```python
-from langchain.tools import GoogleCloudTextToSpeechTool
+from langchain_google_community import TextToSpeechTool
 ```
 
 ### Google Drive
@@ -739,7 +736,7 @@ from langchain_community.utilities.google_scholar import GoogleScholarAPIWrapper
 `GOOGLE_API_KEY` and `GOOGLE_CSE_ID` respectively.
 
 ```python
-from langchain_community.utilities import GoogleSearchAPIWrapper
+from langchain_google_community import GoogleSearchAPIWrapper
 ```
 
 For a more detailed walkthrough of this wrapper, see [this notebook](/docs/integrations/tools/google_search).
@@ -773,16 +770,16 @@ from langchain_community.utilities.google_trends import GoogleTrendsAPIWrapper
 > [Google Gmail](https://en.wikipedia.org/wiki/Gmail) is a free email service provided by Google.
 This toolkit works with emails through the `Gmail API`.
 
-We need to install several python packages.
+We need to install `langchain-google-community` with required dependencies:
 
 ```bash
-pip install google-api-python-client google-auth-oauthlib google-auth-httplib2
+pip install langchain-google-community[gmail]
 ```
 
 See a [usage example and authorization instructions](/docs/integrations/toolkits/gmail).
 
 ```python
-from langchain_community.agent_toolkits import GmailToolkit
+from langchain_google_community import GmailToolkit
 ```
 
 ## Memory
@@ -948,16 +945,16 @@ from langchain_google_el_carro import ElCarroChatMessageHistory
 > [Gmail](https://en.wikipedia.org/wiki/Gmail) is a free email service provided by Google.
 This loader works with emails through the `Gmail API`.
 
-We need to install several python packages.
+We need to install `langchain-google-community` with underlying dependencies.
 
 ```bash
-pip install google-api-python-client google-auth-oauthlib google-auth-httplib2
+pip install langchain-google-community[gmail]
 ```
 
 See a [usage example and authorization instructions](/docs/integrations/chat_loaders/gmail).
 
 ```python
-from langchain_community.chat_loaders.gmail import GMailLoader
+from langchain_google_community import GMailLoader
 ```
 
 ## 3rd Party Integrations

docs/docs/integrations/providers/upstage.ipynb

@@ -52,7 +52,7 @@
     "| --- | --- | --- | --- |\n",
     "| Chat | Build assistants using Solar Mini Chat | `from langchain_upstage import ChatUpstage` | [Go](../../chat/upstage) |\n",
     "| Text Embedding | Embed strings to vectors | `from langchain_upstage import UpstageEmbeddings` | [Go](../../text_embedding/upstage) |\n",
-    "| Groundedness Check | Verify groundedness of assistant's response | `from langchain_upstage import GroundednessCheck` | [Go](../../tools/upstage_groundedness_check) |\n",
+    "| Groundedness Check | Verify groundedness of assistant's response | `from langchain_upstage import UpstageGroundednessCheck` | [Go](../../tools/upstage_groundedness_check) |\n",
     "| Layout Analysis | Serialize documents with tables and figures | `from langchain_upstage import UpstageLayoutAnalysisLoader` | [Go](../../document_loaders/upstage) |\n",
     "\n",
     "See [documentations](https://developers.upstage.ai/) for more details about the features."
@@ -145,15 +145,15 @@
    },
    "outputs": [],
    "source": [
-    "from langchain_upstage import GroundednessCheck\n",
+    "from langchain_upstage import UpstageGroundednessCheck\n",
     "\n",
-    "groundedness_check = GroundednessCheck()\n",
+    "groundedness_check = UpstageGroundednessCheck()\n",
     "\n",
     "request_input = {\n",
     "    \"context\": \"Mauna Kea is an inactive volcano on the island of Hawaii. Its peak is 4,207.3 m above sea level, making it the highest point in Hawaii and second-highest peak of an island on Earth.\",\n",
-    "    \"query\": \"Mauna Kea is 5,207.3 meters tall.\",\n",
+    "    \"answer\": \"Mauna Kea is 5,207.3 meters tall.\",\n",
     "}\n",
-    "response = groundedness_check.run(request_input)\n",
+    "response = groundedness_check.invoke(request_input)\n",
     "print(response)"
    ]
   },

docs/docs/integrations/tools/upstage_groundedness_check.ipynb

@@ -48,7 +48,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "a83d4da0",
    "metadata": {},
    "outputs": [],
@@ -65,21 +65,21 @@
    "source": [
     "## Usage\n",
     "\n",
-    "Initialize `GroundednessCheck` class."
+    "Initialize `UpstageGroundednessCheck` class."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "b7373380c01cefbe",
    "metadata": {
     "collapsed": false
    },
    "outputs": [],
    "source": [
-    "from langchain_upstage import GroundednessCheck\n",
+    "from langchain_upstage import UpstageGroundednessCheck\n",
     "\n",
-    "groundedness_check = GroundednessCheck()"
+    "groundedness_check = UpstageGroundednessCheck()"
    ]
   },
   {
@@ -92,38 +92,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "id": "1e0115e3b511f57",
    "metadata": {
     "collapsed": false,
     "is_executing": true
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content='notGrounded' response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 198, 'total_tokens': 204}, 'model_name': 'solar-1-mini-answer-verification', 'system_fingerprint': '', 'finish_reason': 'stop', 'logprobs': None} id='run-ce7b5787-2ed0-4a68-9de4-c0e91a824147-0'\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "request_input = {\n",
     "    \"context\": \"Mauna Kea is an inactive volcano on the island of Hawai'i. Its peak is 4,207.3 m above sea level, making it the highest point in Hawaii and second-highest peak of an island on Earth.\",\n",
-    "    \"query\": \"Mauna Kea is 5,207.3 meters tall.\",\n",
+    "    \"answer\": \"Mauna Kea is 5,207.3 meters tall.\",\n",
     "}\n",
     "\n",
-    "response = groundedness_check.run(request_input)\n",
+    "response = groundedness_check.invoke(request_input)\n",
     "print(response)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "054b5031",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {

libs/cli/langchain_cli/namespaces/migrate/codemods/migrations/anthropic.json

@@ -0,0 +1,18 @@
+[
+  [
+    "langchain_community.llms.anthropic.Anthropic",
+    "langchain_anthropic.Anthropic"
+  ],
+  [
+    "langchain_community.chat_models.anthropic.ChatAnthropic",
+    "langchain_anthropic.ChatAnthropic"
+  ],
+  [
+    "langchain_community.llms.Anthropic",
+    "langchain_anthropic.Anthropic"
+  ],
+  [
+    "langchain_community.chat_models.ChatAnthropic",
+    "langchain_anthropic.ChatAnthropic"
+  ]
+]

libs/cli/langchain_cli/namespaces/migrate/codemods/migrations/fireworks.json

@@ -0,0 +1,18 @@
+[
+  [
+    "langchain_community.llms.fireworks.Fireworks",
+    "langchain_fireworks.Fireworks"
+  ],
+  [
+    "langchain_community.chat_models.fireworks.ChatFireworks",
+    "langchain_fireworks.ChatFireworks"
+  ],
+  [
+    "langchain_community.llms.Fireworks",
+    "langchain_fireworks.Fireworks"
+  ],
+  [
+    "langchain_community.chat_models.ChatFireworks",
+    "langchain_fireworks.ChatFireworks"
+  ]
+]

libs/cli/langchain_cli/namespaces/migrate/codemods/migrations/ibm.json

@@ -0,0 +1,10 @@
+[
+  [
+    "langchain_community.llms.watsonxllm.WatsonxLLM",
+    "langchain_ibm.WatsonxLLM"
+  ],
+  [
+    "langchain_community.llms.WatsonxLLM",
+    "langchain_ibm.WatsonxLLM"
+  ]
+]

libs/cli/langchain_cli/namespaces/migrate/codemods/migrations/openai.json

@@ -0,0 +1,50 @@
+[
+  [
+    "langchain_community.llms.openai.OpenAI",
+    "langchain_openai.OpenAI"
+  ],
+  [
+    "langchain_community.llms.openai.AzureOpenAI",
+    "langchain_openai.AzureOpenAI"
+  ],
+  [
+    "langchain_community.embeddings.openai.OpenAIEmbeddings",
+    "langchain_openai.OpenAIEmbeddings"
+  ],
+  [
+    "langchain_community.embeddings.azure_openai.AzureOpenAIEmbeddings",
+    "langchain_openai.AzureOpenAIEmbeddings"
+  ],
+  [
+    "langchain_community.chat_models.openai.ChatOpenAI",
+    "langchain_openai.ChatOpenAI"
+  ],
+  [
+    "langchain_community.chat_models.azure_openai.AzureChatOpenAI",
+    "langchain_openai.AzureChatOpenAI"
+  ],
+  [
+    "langchain_community.llms.AzureOpenAI",
+    "langchain_openai.AzureOpenAI"
+  ],
+  [
+    "langchain_community.llms.OpenAI",
+    "langchain_openai.OpenAI"
+  ],
+  [
+    "langchain_community.embeddings.AzureOpenAIEmbeddings",
+    "langchain_openai.AzureOpenAIEmbeddings"
+  ],
+  [
+    "langchain_community.embeddings.OpenAIEmbeddings",
+    "langchain_openai.OpenAIEmbeddings"
+  ],
+  [
+    "langchain_community.chat_models.AzureChatOpenAI",
+    "langchain_openai.AzureChatOpenAI"
+  ],
+  [
+    "langchain_community.chat_models.ChatOpenAI",
+    "langchain_openai.ChatOpenAI"
+  ]
+]

libs/cli/langchain_cli/namespaces/migrate/codemods/migrations/pinecone.json

@@ -0,0 +1,10 @@
+[
+  [
+    "langchain_community.vectorstores.pinecone.Pinecone",
+    "langchain_pinecone.Pinecone"
+  ],
+  [
+    "langchain_community.vectorstores.Pinecone",
+    "langchain_pinecone.Pinecone"
+  ]
+]

libs/cli/langchain_cli/namespaces/migrate/codemods/migrations_v0.2_partner.json

@@ -1,14 +0,0 @@
-[
-  [
-    "langchain.chat_models.ChatOpenAI",
-    "langchain_openai.ChatOpenAI"
-  ],
-  [
-    "langchain.chat_models.ChatOpenAI",
-    "langchain_openai.ChatOpenAI"
-  ],
-  [
-    "langchain.chat_models.ChatAnthropic",
-    "langchain_anthropic.ChatAnthropic"
-  ]
-]

libs/cli/langchain_cli/namespaces/migrate/codemods/replace_imports.py

@@ -26,7 +26,7 @@ HERE = os.path.dirname(__file__)
 
 
 def _load_migrations_by_file(path: str):
-    migrations_path = os.path.join(HERE, path)
+    migrations_path = os.path.join(HERE, "migrations", path)
     with open(migrations_path, "r", encoding="utf-8") as f:
         data = json.load(f)
     return data
@@ -43,21 +43,30 @@ def _deduplicate_in_order(
     return [x for x in seq if not (key(x) in seen or seen_add(key(x)))]
 
 
-def _load_migrations():
-    """Load the migrations from the JSON file."""
-    # Later earlier ones have higher precedence.
-    paths = [
-        "migrations_v0.2_partner.json",
-        "migrations_v0.2.json",
-    ]
+PARTNERS = [
+    "anthropic.json",
+    "ibm.json",
+    "openai.json",
+    "pinecone.json",
+    "fireworks.json",
+]
+
 
+def _load_migrations_from_fixtures() -> List[Tuple[str, str]]:
+    """Load migrations from fixtures."""
+    paths: List[str] = PARTNERS + ["langchain_to_langchain_community.json"]
     data = []
     for path in paths:
         data.extend(_load_migrations_by_file(path))
-
     data = _deduplicate_in_order(data, key=lambda x: x[0])
+    return data
+
 
+def _load_migrations():
+    """Load the migrations from the JSON file."""
+    # Later earlier ones have higher precedence.
     imports: Dict[str, Tuple[str, str]] = {}
+    data = _load_migrations_from_fixtures()
 
     for old_path, new_path in data:
         # Parse the old parse which is of the format 'langchain.chat_models.ChatOpenAI'

libs/cli/langchain_cli/namespaces/migrate/generate/generic.py

@@ -0,0 +1,137 @@
+"""Generate migrations from langchain to langchain-community or core packages."""
+import importlib
+import inspect
+import pkgutil
+from typing import List, Tuple
+
+
+def generate_raw_migrations(
+    from_package: str, to_package: str
+) -> List[Tuple[str, str]]:
+    """Scan the `langchain` package and generate migrations for all modules."""
+    package = importlib.import_module(from_package)
+
+    items = []
+    for importer, modname, ispkg in pkgutil.walk_packages(
+        package.__path__, package.__name__ + "."
+    ):
+        try:
+            module = importlib.import_module(modname)
+        except ModuleNotFoundError:
+            continue
+
+        # Check if the module is an __init__ file and evaluate __all__
+        try:
+            has_all = hasattr(module, "__all__")
+        except ImportError:
+            has_all = False
+
+        if has_all:
+            all_objects = module.__all__
+            for name in all_objects:
+                # Attempt to fetch each object declared in __all__
+                try:
+                    obj = getattr(module, name, None)
+                except ImportError:
+                    continue
+                if obj and (inspect.isclass(obj) or inspect.isfunction(obj)):
+                    if obj.__module__.startswith(to_package):
+                        items.append(
+                            (f"{modname}.{name}", f"{obj.__module__}.{obj.__name__}")
+                        )
+
+        # Iterate over all members of the module
+        for name, obj in inspect.getmembers(module):
+            # Check if it's a class or function
+            if inspect.isclass(obj) or inspect.isfunction(obj):
+                # Check if the module name of the obj starts with 'langchain_community'
+                if obj.__module__.startswith(to_package):
+                    items.append(
+                        (f"{modname}.{name}", f"{obj.__module__}.{obj.__name__}")
+                    )
+
+    return items
+
+
+def generate_top_level_imports(pkg: str) -> List[Tuple[str, str]]:
+    """This code will look at all the top level modules in langchain_community.
+
+    It'll attempt to import everything from each __init__ file
+
+    for example,
+
+    langchain_community/
+        chat_models/
+            __init__.py # <-- import everything from here
+        llm/
+            __init__.py # <-- import everything from here
+
+
+    It'll collect all the imports, import the classes / functions it can find
+    there. It'll return a list of 2-tuples
+
+    Each tuple will contain the fully qualified path of the class / function to where
+    its logic is defined
+    (e.g., langchain_community.chat_models.xyz_implementation.ver2.XYZ)
+    and the second tuple will contain the path
+    to importing it from the top level namespaces
+    (e.g., langchain_community.chat_models.XYZ)
+    """
+    import importlib
+
+    package = importlib.import_module(pkg)
+
+    items = []
+    # Only iterate through top-level modules/packages
+    for finder, modname, ispkg in pkgutil.iter_modules(
+        package.__path__, package.__name__ + "."
+    ):
+        if ispkg:
+            try:
+                module = importlib.import_module(modname)
+            except ModuleNotFoundError:
+                continue
+
+            if hasattr(module, "__all__"):
+                all_objects = getattr(module, "__all__")
+                for name in all_objects:
+                    # Attempt to fetch each object declared in __all__
+                    obj = getattr(module, name, None)
+                    if obj and (inspect.isclass(obj) or inspect.isfunction(obj)):
+                        # Capture the fully qualified name of the object
+                        original_module = obj.__module__
+                        original_name = obj.__name__
+                        # Form the new import path from the top-level namespace
+                        top_level_import = f"{modname}.{name}"
+                        # Append the tuple with original and top-level paths
+                        items.append(
+                            (f"{original_module}.{original_name}", top_level_import)
+                        )
+
+    return items
+
+
+def generate_simplified_migrations(
+    from_package: str, to_package: str
+) -> List[Tuple[str, str]]:
+    """Get all the raw migrations, then simplify them if possible."""
+    raw_migrations = generate_raw_migrations(from_package, to_package)
+    top_level_simplifications = generate_top_level_imports(to_package)
+    top_level_dict = {full: top_level for full, top_level in top_level_simplifications}
+    simple_migrations = []
+    for migration in raw_migrations:
+        original, new = migration
+        replacement = top_level_dict.get(new, new)
+        simple_migrations.append((original, replacement))
+
+    # Now let's deduplicate the list based on the original path (which is
+    # the 1st element of the tuple)
+    deduped_migrations = []
+    seen = set()
+    for migration in simple_migrations:
+        original = migration[0]
+        if original not in seen:
+            deduped_migrations.append(migration)
+            seen.add(original)
+
+    return deduped_migrations

libs/cli/langchain_cli/namespaces/migrate/generate/langchain.py

@@ -1,52 +0,0 @@
-"""Generate migrations from langchain to langchain-community or core packages."""
-import glob
-from pathlib import Path
-from typing import List, Tuple
-
-from langchain_cli.namespaces.migrate.generate.utils import (
-    _get_current_module,
-    find_imports_from_package,
-)
-
-HERE = Path(__file__).parent
-PKGS_ROOT = HERE.parent.parent.parent
-LANGCHAIN_PKG = PKGS_ROOT / "langchain"
-COMMUNITY_PKG = PKGS_ROOT / "community"
-PARTNER_PKGS = PKGS_ROOT / "partners"
-
-
-def _generate_migrations_from_file(
-    source_module: str, code: str, *, from_package: str
-) -> List[Tuple[str, str]]:
-    """Generate migrations"""
-    imports = find_imports_from_package(code, from_package=from_package)
-    return [
-        # Rewrite in a list comprehension
-        (f"{source_module}.{item}", f"{new_path}.{item}")
-        for new_path, item in imports
-    ]
-
-
-def _generate_migrations_from_file_in_pkg(
-    file: str, root_pkg: str
-) -> List[Tuple[str, str]]:
-    """Generate migrations for a file that's relative to langchain pkg."""
-    # Read the file.
-    with open(file, encoding="utf-8") as f:
-        code = f.read()
-
-    module_name = _get_current_module(file, root_pkg)
-    return _generate_migrations_from_file(
-        module_name, code, from_package="langchain_community"
-    )
-
-
-def generate_migrations_from_langchain_to_community() -> List[Tuple[str, str]]:
-    """Generate migrations from langchain to langchain-community."""
-    migrations = []
-    # scanning files in pkg
-    for file_path in glob.glob(str(LANGCHAIN_PKG) + "**/*.py"):
-        migrations.extend(
-            _generate_migrations_from_file_in_pkg(file_path, str(LANGCHAIN_PKG))
-        )
-    return migrations

libs/cli/langchain_cli/namespaces/migrate/generate/partner.py

@@ -2,6 +2,7 @@
 import importlib
 from typing import List, Tuple
 
+from langchain_core.documents import BaseDocumentCompressor, BaseDocumentTransformer
 from langchain_core.embeddings import Embeddings
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.retrievers import BaseRetriever
@@ -11,6 +12,7 @@ from langchain_cli.namespaces.migrate.generate.utils import (
     COMMUNITY_PKG,
     find_subclasses_in_module,
     list_classes_by_package,
+    list_init_imports_by_package,
 )
 
 # PUBLIC API
@@ -29,13 +31,24 @@ def get_migrations_for_partner_package(pkg_name: str) -> List[Tuple[str, str]]:
     """
     package = importlib.import_module(pkg_name)
     classes_ = find_subclasses_in_module(
-        package, [BaseLanguageModel, Embeddings, BaseRetriever, VectorStore]
+        package,
+        [
+            BaseLanguageModel,
+            Embeddings,
+            BaseRetriever,
+            VectorStore,
+            BaseDocumentTransformer,
+            BaseDocumentCompressor,
+        ],
     )
     community_classes = list_classes_by_package(str(COMMUNITY_PKG))
+    imports_for_pkg = list_init_imports_by_package(str(COMMUNITY_PKG))
+
+    old_paths = community_classes + imports_for_pkg
 
     migrations = [
-        (f"{community_module}.{community_class}", f"{pkg_name}.{community_class}")
-        for community_module, community_class in community_classes
-        if community_class in classes_
+        (f"{module}.{item}", f"{pkg_name}.{item}")
+        for module, item in old_paths
+        if item in classes_
     ]
     return migrations

libs/cli/langchain_cli/namespaces/migrate/generate/utils.py

@@ -3,7 +3,7 @@ import inspect
 import os
 import pathlib
 from pathlib import Path
-from typing import Any, List, Tuple, Type
+from typing import Any, List, Optional, Tuple, Type
 
 HERE = Path(__file__).parent
 # Should bring us to [root]/src
@@ -15,13 +15,15 @@ PARTNER_PKGS = PKGS_ROOT / "partners"
 
 
 class ImportExtractor(ast.NodeVisitor):
-    def __init__(self, *, from_package: str) -> None:
-        """Extract all imports from the given package."""
+    def __init__(self, *, from_package: Optional[str] = None) -> None:
+        """Extract all imports from the given code, optionally filtering by package."""
         self.imports = []
         self.package = from_package
 
     def visit_ImportFrom(self, node):
-        if node.module and str(node.module).startswith(self.package):
+        if node.module and (
+            self.package is None or str(node.module).startswith(self.package)
+        ):
             for alias in node.names:
                 self.imports.append((node.module, alias.name))
         self.generic_visit(node)
@@ -72,13 +74,40 @@ def _get_all_classnames_from_file(file: str, pkg: str) -> List[Tuple[str, str]]:
         code = f.read()
     module_name = _get_current_module(file, pkg)
     class_names = _get_class_names(code)
+
     return [(module_name, class_name) for class_name in class_names]
 
 
+def identify_all_imports_in_file(
+    file: str, *, from_package: Optional[str] = None
+) -> List[Tuple[str, str]]:
+    """Let's also identify all the imports in the given file."""
+    with open(file, encoding="utf-8") as f:
+        code = f.read()
+    return find_imports_from_package(code, from_package=from_package)
+
+
+def identify_pkg_source(pkg_root: str) -> pathlib.Path:
+    """Identify the source of the package.
+
+    Args:
+        pkg_root: the root of the package. This contains source + tests, and other
+            things like pyproject.toml, lock files etc
+
+    Returns:
+        Returns the path to the source code for the package.
+    """
+    dirs = [d for d in Path(pkg_root).iterdir() if d.is_dir()]
+    matching_dirs = [d for d in dirs if d.name.startswith("langchain_")]
+    assert len(matching_dirs) == 1, "There should be only one langchain package."
+    return matching_dirs[0]
+
+
 def list_classes_by_package(pkg_root: str) -> List[Tuple[str, str]]:
     """List all classes in a package."""
     module_classes = []
-    files = list(Path(pkg_root).rglob("*.py"))
+    pkg_source = identify_pkg_source(pkg_root)
+    files = list(pkg_source.rglob("*.py"))
 
     for file in files:
         rel_path = os.path.relpath(file, pkg_root)
@@ -88,11 +117,29 @@ def list_classes_by_package(pkg_root: str) -> List[Tuple[str, str]]:
     return module_classes
 
 
-def find_imports_from_package(code: str, *, from_package: str) -> List[Tuple[str, str]]:
+def list_init_imports_by_package(pkg_root: str) -> List[Tuple[str, str]]:
+    """List all the things that are being imported in a package by module."""
+    imports = []
+    pkg_source = identify_pkg_source(pkg_root)
+    # Scan all the files in the package
+    files = list(Path(pkg_source).rglob("*.py"))
+
+    for file in files:
+        if not file.name == "__init__.py":
+            continue
+        import_in_file = identify_all_imports_in_file(str(file))
+        module_name = _get_current_module(file, pkg_root)
+        imports.extend([(module_name, item) for _, item in import_in_file])
+    return imports
+
+
+def find_imports_from_package(
+    code: str, *, from_package: Optional[str] = None
+) -> List[Tuple[str, str]]:
     # Parse the code into an AST
     tree = ast.parse(code)
     # Create an instance of the visitor
-    extractor = ImportExtractor(from_package="langchain_community")
+    extractor = ImportExtractor(from_package=from_package)
     # Use the visitor to update the imports list
     extractor.visit(tree)
     return extractor.imports

libs/cli/pyproject.toml

@@ -50,7 +50,7 @@ select = [
 ]
 
 [tool.poe.tasks]
-test = "poetry run pytest"
+test = "poetry run pytest tests"
 watch = "poetry run ptw"
 version = "poetry version --short"
 bump = ["_bump_1", "_bump_2"]

libs/cli/scripts/generate_migrations.py

@@ -1,10 +1,11 @@
 """Script to generate migrations for the migration script."""
 import json
+import pkgutil
 
 import click
 
-from langchain_cli.namespaces.migrate.generate.langchain import (
-    generate_migrations_from_langchain_to_community,
+from langchain_cli.namespaces.migrate.generate.generic import (
+    generate_simplified_migrations,
 )
 from langchain_cli.namespaces.migrate.generate.partner import (
     get_migrations_for_partner_package,
@@ -18,17 +19,29 @@ def cli():
 
 
 @cli.command()
+@click.option(
+    "--pkg1",
+    default="langchain",
+)
+@click.option(
+    "--pkg2",
+    default="langchain_community",
+)
 @click.option(
     "--output",
-    default="langchain_migrations.json",
+    default=None,
     help="Output file for the migration script.",
 )
-def langchain(output: str) -> None:
+def generic(pkg1: str, pkg2: str, output: str) -> None:
     """Generate a migration script."""
     click.echo("Migration script generated.")
-    migrations = generate_migrations_from_langchain_to_community()
+    migrations = generate_simplified_migrations(pkg1, pkg2)
+
+    if output is None:
+        output = f"{pkg1}_to_{pkg2}.json"
+
     with open(output, "w") as f:
-        f.write(json.dumps(migrations))
+        f.write(json.dumps(migrations, indent=2, sort_keys=True))
 
 
 @cli.command()
@@ -38,10 +51,39 @@ def partner(pkg: str, output: str) -> None:
     """Generate migration scripts specifically for LangChain modules."""
     click.echo("Migration script for LangChain generated.")
     migrations = get_migrations_for_partner_package(pkg)
-    output_name = f"partner_{pkg}.json" if output is None else output
-    with open(output_name, "w") as f:
-        f.write(json.dumps(migrations, indent=2, sort_keys=True))
-    click.secho(f"LangChain migration script saved to {output_name}")
+    # Run with python 3.9+
+    output_name = f"{pkg.removeprefix('langchain_')}.json" if output is None else output
+    if migrations:
+        with open(output_name, "w") as f:
+            f.write(json.dumps(migrations, indent=2, sort_keys=True))
+        click.secho(f"LangChain migration script saved to {output_name}")
+    else:
+        click.secho(f"No migrations found for {pkg}", fg="yellow")
+
+
+@cli.command()
+def all_installed_partner_pkgs() -> None:
+    """Generate migration scripts for all LangChain modules."""
+    # Will generate migrations for all pather packages.
+    # Define as "langchain_<partner_name>".
+    # First let's determine which packages are installed in the environment
+    # and then generate migrations for them.
+    langchain_pkgs = [
+        name
+        for _, name, _ in pkgutil.iter_modules()
+        if name.startswith("langchain_")
+        and name not in {"langchain_core", "langchain_cli", "langchain_community"}
+    ]
+    for pkg in langchain_pkgs:
+        migrations = get_migrations_for_partner_package(pkg)
+        # Run with python 3.9+
+        output_name = f"{pkg.removeprefix('langchain_')}.json"
+        if migrations:
+            with open(output_name, "w") as f:
+                f.write(json.dumps(migrations, indent=2, sort_keys=True))
+            click.secho(f"LangChain migration script saved to {output_name}")
+        else:
+            click.secho(f"No migrations found for {pkg}", fg="yellow")
 
 
 if __name__ == "__main__":

libs/cli/scripts/migrations.json

@@ -1 +0,0 @@
-[["langchain_community.embeddings.openai.OpenAIEmbeddings", "langchain_openai.embeddings.base.OpenAIEmbeddings"], ["langchain_community.embeddings.azure_openai.AzureOpenAIEmbeddings", "langchain_openai.embeddings.azure.AzureOpenAIEmbeddings"], ["langchain_community.chat_models.openai.ChatOpenAI", "langchain_openai.chat_models.base.ChatOpenAI"], ["langchain_community.chat_models.azure_openai.AzureChatOpenAI", "langchain_openai.chat_models.azure.AzureChatOpenAI"]]

libs/cli/tests/unit_tests/migrate/cli_runner/cases/__init__.py

@@ -1,7 +1,7 @@
-from tests.unit_tests.migrate.integration.case import Case
-from tests.unit_tests.migrate.integration.cases import imports
-from tests.unit_tests.migrate.integration.file import File
-from tests.unit_tests.migrate.integration.folder import Folder
+from tests.unit_tests.migrate.cli_runner.case import Case
+from tests.unit_tests.migrate.cli_runner.cases import imports
+from tests.unit_tests.migrate.cli_runner.file import File
+from tests.unit_tests.migrate.cli_runner.folder import Folder
 
 cases = [
     Case(

libs/cli/tests/unit_tests/migrate/cli_runner/cases/imports.py

@@ -1,5 +1,5 @@
-from tests.unit_tests.migrate.integration.case import Case
-from tests.unit_tests.migrate.integration.file import File
+from tests.unit_tests.migrate.cli_runner.case import Case
+from tests.unit_tests.migrate.cli_runner.file import File
 
 cases = [
     Case(
@@ -7,7 +7,7 @@ cases = [
         source=File(
             "app.py",
             content=[
-                "from langchain.chat_models import ChatOpenAI",
+                "from langchain_community.chat_models import ChatOpenAI",
                 "",
                 "",
                 "class foo:",

libs/cli/tests/unit_tests/migrate/generate/test_langchain_migration.py

@@ -0,0 +1,45 @@
+from langchain_cli.namespaces.migrate.generate.generic import (
+    generate_simplified_migrations,
+    generate_raw_migrations,
+)
+
+
+def test_create_json_agent_migration() -> None:
+    """Test the migration of create_json_agent from langchain to langchain_community."""
+    raw_migrations = generate_simplified_migrations(
+        from_package="langchain", to_package="langchain_community"
+    )
+    json_agent_migrations = [
+        migration for migration in raw_migrations if "create_json_agent" in migration[0]
+    ]
+    assert json_agent_migrations == [
+        (
+            "langchain.agents.create_json_agent",
+            "langchain_community.agent_toolkits.create_json_agent",
+        ),
+        (
+            "langchain.agents.agent_toolkits.create_json_agent",
+            "langchain_community.agent_toolkits.create_json_agent",
+        ),
+        (
+            "langchain.agents.agent_toolkits.json.base.create_json_agent",
+            "langchain_community.agent_toolkits.create_json_agent",
+        ),
+    ]
+
+
+def test_create_single_store_retriever_db() -> None:
+    """Test migration from langchain to langchain_core"""
+    raw_migrations = generate_simplified_migrations(
+        from_package="langchain", to_package="langchain_core"
+    )
+    # SingleStore was an old name for VectorStoreRetriever
+    single_store_migration = [
+        migration for migration in raw_migrations if "SingleStore" in migration[0]
+    ]
+    assert single_store_migration == [
+        (
+            "langchain.vectorstores.singlestoredb.SingleStoreDBRetriever",
+            "langchain_core.vectorstores.VectorStoreRetriever",
+        ),
+    ]

libs/cli/tests/unit_tests/migrate/generate/test_partner_migrations.py

@@ -28,4 +28,19 @@ def test_generate_migrations() -> None:
             "langchain_community.chat_models.azure_openai.AzureChatOpenAI",
             "langchain_openai.AzureChatOpenAI",
         ),
+        ("langchain_community.llms.AzureOpenAI", "langchain_openai.AzureOpenAI"),
+        ("langchain_community.llms.OpenAI", "langchain_openai.OpenAI"),
+        (
+            "langchain_community.embeddings.AzureOpenAIEmbeddings",
+            "langchain_openai.AzureOpenAIEmbeddings",
+        ),
+        (
+            "langchain_community.embeddings.OpenAIEmbeddings",
+            "langchain_openai.OpenAIEmbeddings",
+        ),
+        (
+            "langchain_community.chat_models.AzureChatOpenAI",
+            "langchain_openai.AzureChatOpenAI",
+        ),
+        ("langchain_community.chat_models.ChatOpenAI", "langchain_openai.ChatOpenAI"),
     ]

libs/cli/tests/unit_tests/migrate/test_replace_imports.py

@@ -19,22 +19,32 @@ class TestReplaceImportsCommand(CodemodTest):
         from langchain.chat_models import ChatOpenAI
         """
         after = """
+        from langchain_community.chat_models import ChatOpenAI
+        """
+        self.assertCodemod(before, after)
+
+    def test_from_community_to_partner(self) -> None:
+        """Test that we can replace imports from community to partner."""
+        before = """
+        from langchain_community.chat_models import ChatOpenAI
+        """
+        after = """
         from langchain_openai import ChatOpenAI
         """
         self.assertCodemod(before, after)
 
     def test_noop_import(self) -> None:
         code = """
-        from foo  import ChatOpenAI
+        from foo import ChatOpenAI
         """
         self.assertCodemod(code, code)
 
     def test_mixed_imports(self) -> None:
         before = """
-        from langchain.chat_models import ChatOpenAI, ChatAnthropic, foo
+        from langchain_community.chat_models import ChatOpenAI, ChatAnthropic, foo
         """
         after = """
-        from langchain.chat_models import foo
+        from langchain_community.chat_models import foo
         from langchain_anthropic import ChatAnthropic
         from langchain_openai import ChatOpenAI
         """

libs/community/langchain_community/agent_toolkits/ainetwork/toolkit.py

@@ -3,8 +3,8 @@ from __future__ import annotations
 from typing import TYPE_CHECKING, List, Literal, Optional
 
 from langchain_core.pydantic_v1 import root_validator
+from langchain_core.tools import BaseToolkit
 
-from langchain_community.agent_toolkits.base import BaseToolkit
 from langchain_community.tools import BaseTool
 from langchain_community.tools.ainetwork.app import AINAppOps
 from langchain_community.tools.ainetwork.owner import AINOwnerOps

libs/community/langchain_community/agent_toolkits/amadeus/toolkit.py

@@ -4,8 +4,8 @@ from typing import TYPE_CHECKING, List, Optional
 
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.pydantic_v1 import Field
+from langchain_core.tools import BaseToolkit
 
-from langchain_community.agent_toolkits.base import BaseToolkit
 from langchain_community.tools import BaseTool
 from langchain_community.tools.amadeus.closest_airport import AmadeusClosestAirport
 from langchain_community.tools.amadeus.flight_search import AmadeusFlightSearch

libs/community/langchain_community/agent_toolkits/azure_cognitive_services.py

@@ -3,9 +3,8 @@ from __future__ import annotations
 import sys
 from typing import List
 
-from langchain_core.tools import BaseTool
+from langchain_core.tools import BaseTool, BaseToolkit
 
-from langchain_community.agent_toolkits.base import BaseToolkit
 from langchain_community.tools.azure_cognitive_services import (
     AzureCogsFormRecognizerTool,
     AzureCogsImageAnalysisTool,

libs/community/langchain_community/agent_toolkits/clickup/toolkit.py

@@ -1,6 +1,7 @@
 from typing import Dict, List
 
-from langchain_community.agent_toolkits.base import BaseToolkit
+from langchain_core.tools import BaseToolkit
+
 from langchain_community.tools import BaseTool
 from langchain_community.tools.clickup.prompt import (
     CLICKUP_FOLDER_CREATE_PROMPT,

libs/community/langchain_community/agent_toolkits/cogniswitch/toolkit.py

@@ -1,6 +1,7 @@
 from typing import List
 
-from langchain_community.agent_toolkits.base import BaseToolkit
+from langchain_core.tools import BaseToolkit
+
 from langchain_community.tools import BaseTool
 from langchain_community.tools.cogniswitch.tool import (
     CogniswitchKnowledgeRequest,

libs/community/langchain_community/agent_toolkits/connery/toolkit.py

@@ -1,9 +1,8 @@
 from typing import List
 
 from langchain_core.pydantic_v1 import root_validator
-from langchain_core.tools import BaseTool
+from langchain_core.tools import BaseTool, BaseToolkit
 
-from langchain_community.agent_toolkits.base import BaseToolkit
 from langchain_community.tools.connery import ConneryService
 
 

libs/community/langchain_community/agent_toolkits/file_management/toolkit.py

@@ -3,8 +3,8 @@ from __future__ import annotations
 from typing import Dict, List, Optional, Type
 
 from langchain_core.pydantic_v1 import root_validator
+from langchain_core.tools import BaseToolkit
 
-from langchain_community.agent_toolkits.base import BaseToolkit
 from langchain_community.tools import BaseTool
 from langchain_community.tools.file_management.copy import CopyFileTool
 from langchain_community.tools.file_management.delete import DeleteFileTool

libs/community/langchain_community/agent_toolkits/github/toolkit.py

@@ -2,8 +2,8 @@
 from typing import Dict, List
 
 from langchain_core.pydantic_v1 import BaseModel, Field
+from langchain_core.tools import BaseToolkit
 
-from langchain_community.agent_toolkits.base import BaseToolkit
 from langchain_community.tools import BaseTool
 from langchain_community.tools.github.prompt import (
     COMMENT_ON_ISSUE_PROMPT,

libs/community/langchain_community/agent_toolkits/gitlab/toolkit.py

@@ -1,7 +1,8 @@
 """GitHub Toolkit."""
 from typing import Dict, List
 
-from langchain_community.agent_toolkits.base import BaseToolkit
+from langchain_core.tools import BaseToolkit
+
 from langchain_community.tools import BaseTool
 from langchain_community.tools.gitlab.prompt import (
     COMMENT_ON_ISSUE_PROMPT,

libs/community/langchain_community/agent_toolkits/gmail/toolkit.py

@@ -3,8 +3,8 @@ from __future__ import annotations
 from typing import TYPE_CHECKING, List
 
 from langchain_core.pydantic_v1 import Field
+from langchain_core.tools import BaseToolkit
 
-from langchain_community.agent_toolkits.base import BaseToolkit
 from langchain_community.tools import BaseTool
 from langchain_community.tools.gmail.create_draft import GmailCreateDraft
 from langchain_community.tools.gmail.get_message import GmailGetMessage

libs/community/langchain_community/agent_toolkits/jira/toolkit.py

@@ -1,6 +1,7 @@
 from typing import Dict, List
 
-from langchain_community.agent_toolkits.base import BaseToolkit
+from langchain_core.tools import BaseToolkit
+
 from langchain_community.tools import BaseTool
 from langchain_community.tools.jira.prompt import (
     JIRA_CATCH_ALL_PROMPT,

libs/community/langchain_community/agent_toolkits/json/toolkit.py

@@ -2,7 +2,8 @@ from __future__ import annotations
 
 from typing import List
 
-from langchain_community.agent_toolkits.base import BaseToolkit
+from langchain_core.tools import BaseToolkit
+
 from langchain_community.tools import BaseTool
 from langchain_community.tools.json.tool import (
     JsonGetValueTool,

libs/community/langchain_community/agent_toolkits/multion/toolkit.py

@@ -3,7 +3,8 @@ from __future__ import annotations
 
 from typing import List
 
-from langchain_community.agent_toolkits.base import BaseToolkit
+from langchain_core.tools import BaseToolkit
+
 from langchain_community.tools import BaseTool
 from langchain_community.tools.multion.close_session import MultionCloseSession
 from langchain_community.tools.multion.create_session import MultionCreateSession

libs/community/langchain_community/agent_toolkits/nasa/toolkit.py

@@ -1,6 +1,7 @@
 from typing import Dict, List
 
-from langchain_community.agent_toolkits.base import BaseToolkit
+from langchain_core.tools import BaseToolkit
+
 from langchain_community.tools import BaseTool
 from langchain_community.tools.nasa.prompt import (
     NASA_CAPTIONS_PROMPT,

libs/community/langchain_community/agent_toolkits/nla/toolkit.py

@@ -4,9 +4,8 @@ from typing import Any, List, Optional, Sequence
 
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.pydantic_v1 import Field
-from langchain_core.tools import BaseTool
+from langchain_core.tools import BaseTool, BaseToolkit
 
-from langchain_community.agent_toolkits.base import BaseToolkit
 from langchain_community.agent_toolkits.nla.tool import NLATool
 from langchain_community.tools.openapi.utils.openapi_utils import OpenAPISpec
 from langchain_community.tools.plugin import AIPlugin

libs/community/langchain_community/agent_toolkits/office365/toolkit.py

@@ -3,8 +3,8 @@ from __future__ import annotations
 from typing import TYPE_CHECKING, List
 
 from langchain_core.pydantic_v1 import Field
+from langchain_core.tools import BaseToolkit
 
-from langchain_community.agent_toolkits.base import BaseToolkit
 from langchain_community.tools import BaseTool
 from langchain_community.tools.office365.create_draft_message import (
     O365CreateDraftMessage,

libs/community/langchain_community/agent_toolkits/openapi/toolkit.py

@@ -4,9 +4,8 @@ from __future__ import annotations
 from typing import Any, List
 
 from langchain_core.language_models import BaseLanguageModel
-from langchain_core.tools import Tool
+from langchain_core.tools import BaseToolkit, Tool
 
-from langchain_community.agent_toolkits.base import BaseToolkit
 from langchain_community.agent_toolkits.json.base import create_json_agent
 from langchain_community.agent_toolkits.json.toolkit import JsonToolkit
 from langchain_community.agent_toolkits.openapi.prompt import DESCRIPTION

libs/community/langchain_community/agent_toolkits/playwright/toolkit.py

@@ -4,9 +4,8 @@ from __future__ import annotations
 from typing import TYPE_CHECKING, List, Optional, Type, cast
 
 from langchain_core.pydantic_v1 import Extra, root_validator
-from langchain_core.tools import BaseTool
+from langchain_core.tools import BaseTool, BaseToolkit
 
-from langchain_community.agent_toolkits.base import BaseToolkit
 from langchain_community.tools.playwright.base import (
     BaseBrowserTool,
     lazy_import_playwright_browsers,

libs/community/langchain_community/agent_toolkits/polygon/toolkit.py

@@ -1,6 +1,7 @@
 from typing import List
 
-from langchain_community.agent_toolkits.base import BaseToolkit
+from langchain_core.tools import BaseToolkit
+
 from langchain_community.tools import BaseTool
 from langchain_community.tools.polygon import (
     PolygonAggregates,

libs/community/langchain_community/agent_toolkits/powerbi/toolkit.py

@@ -13,8 +13,8 @@ from langchain_core.prompts.chat import (
     SystemMessagePromptTemplate,
 )
 from langchain_core.pydantic_v1 import Field
+from langchain_core.tools import BaseToolkit
 
-from langchain_community.agent_toolkits.base import BaseToolkit
 from langchain_community.tools import BaseTool
 from langchain_community.tools.powerbi.prompt import (
     QUESTION_TO_QUERY_BASE,

libs/community/langchain_community/agent_toolkits/slack/toolkit.py

@@ -3,8 +3,8 @@ from __future__ import annotations
 from typing import TYPE_CHECKING, List
 
 from langchain_core.pydantic_v1 import Field
+from langchain_core.tools import BaseToolkit
 
-from langchain_community.agent_toolkits.base import BaseToolkit
 from langchain_community.tools import BaseTool
 from langchain_community.tools.slack.get_channel import SlackGetChannel
 from langchain_community.tools.slack.get_message import SlackGetMessage

libs/community/langchain_community/agent_toolkits/spark_sql/toolkit.py

@@ -3,8 +3,8 @@ from typing import List
 
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.pydantic_v1 import Field
+from langchain_core.tools import BaseToolkit
 
-from langchain_community.agent_toolkits.base import BaseToolkit
 from langchain_community.tools import BaseTool
 from langchain_community.tools.spark_sql.tool import (
     InfoSparkSQLTool,

libs/community/langchain_community/agent_toolkits/sql/toolkit.py

@@ -3,8 +3,8 @@ from typing import List
 
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.pydantic_v1 import Field
+from langchain_core.tools import BaseToolkit
 
-from langchain_community.agent_toolkits.base import BaseToolkit
 from langchain_community.tools import BaseTool
 from langchain_community.tools.sql_database.tool import (
     InfoSQLDatabaseTool,

libs/community/langchain_community/agent_toolkits/steam/toolkit.py

@@ -1,7 +1,8 @@
 """Steam Toolkit."""
 from typing import List
 
-from langchain_community.agent_toolkits.base import BaseToolkit
+from langchain_core.tools import BaseToolkit
+
 from langchain_community.tools import BaseTool
 from langchain_community.tools.steam.prompt import (
     STEAM_GET_GAMES_DETAILS,

libs/community/langchain_community/agent_toolkits/zapier/toolkit.py

@@ -2,8 +2,8 @@
 from typing import List
 
 from langchain_core._api import warn_deprecated
+from langchain_core.tools import BaseToolkit
 
-from langchain_community.agent_toolkits.base import BaseToolkit
 from langchain_community.tools import BaseTool
 from langchain_community.tools.zapier.tool import ZapierNLARunAction
 from langchain_community.utilities.zapier import ZapierNLAWrapper

libs/community/langchain_community/cache.py

@@ -19,6 +19,7 @@ Cache directly competes with Memory. See documentation for Pros and Cons.
 
     BaseCache --> <name>Cache  # Examples: InMemoryCache, RedisCache, GPTCache
 """
+
 from __future__ import annotations
 
 import hashlib
@@ -76,6 +77,9 @@ from langchain_community.utilities.astradb import (
     _AstraDBCollectionEnvironment,
 )
 from langchain_community.vectorstores import AzureCosmosDBVectorSearch
+from langchain_community.vectorstores import (
+    OpenSearchVectorSearch as OpenSearchVectorStore,
+)
 from langchain_community.vectorstores.redis import Redis as RedisVectorstore
 
 logger = logging.getLogger(__file__)
@@ -2049,3 +2053,105 @@ class AzureCosmosDBSemanticCache(BaseCache):
     def _validate_enum_value(value: Any, enum_type: Type[Enum]) -> None:
         if not isinstance(value, enum_type):
             raise ValueError(f"Invalid enum value: {value}. Expected {enum_type}.")
+
+
+class OpenSearchSemanticCache(BaseCache):
+    """Cache that uses OpenSearch vector store backend"""
+
+    def __init__(
+        self, opensearch_url: str, embedding: Embeddings, score_threshold: float = 0.2
+    ):
+        """
+        Args:
+            opensearch_url (str): URL to connect to OpenSearch.
+            embedding (Embedding): Embedding provider for semantic encoding and search.
+            score_threshold (float, 0.2):
+        Example:
+        .. code-block:: python
+            import langchain
+            from langchain.cache import OpenSearchSemanticCache
+            from langchain.embeddings import OpenAIEmbeddings
+            langchain.llm_cache = OpenSearchSemanticCache(
+                opensearch_url="http//localhost:9200",
+                embedding=OpenAIEmbeddings()
+            )
+        """
+        self._cache_dict: Dict[str, OpenSearchVectorStore] = {}
+        self.opensearch_url = opensearch_url
+        self.embedding = embedding
+        self.score_threshold = score_threshold
+
+    def _index_name(self, llm_string: str) -> str:
+        hashed_index = _hash(llm_string)
+        return f"cache_{hashed_index}"
+
+    def _get_llm_cache(self, llm_string: str) -> OpenSearchVectorStore:
+        index_name = self._index_name(llm_string)
+
+        # return vectorstore client for the specific llm string
+        if index_name in self._cache_dict:
+            return self._cache_dict[index_name]
+
+        # create new vectorstore client for the specific llm string
+        self._cache_dict[index_name] = OpenSearchVectorStore(
+            opensearch_url=self.opensearch_url,
+            index_name=index_name,
+            embedding_function=self.embedding,
+        )
+
+        # create index for the vectorstore
+        vectorstore = self._cache_dict[index_name]
+        if not vectorstore.index_exists():
+            _embedding = self.embedding.embed_query(text="test")
+            vectorstore.create_index(len(_embedding), index_name)
+        return vectorstore
+
+    def lookup(self, prompt: str, llm_string: str) -> Optional[RETURN_VAL_TYPE]:
+        """Look up based on prompt and llm_string."""
+        llm_cache = self._get_llm_cache(llm_string)
+        generations: List = []
+        # Read from a Hash
+        results = llm_cache.similarity_search(
+            query=prompt,
+            k=1,
+            score_threshold=self.score_threshold,
+        )
+        if results:
+            for document in results:
+                try:
+                    generations.extend(loads(document.metadata["return_val"]))
+                except Exception:
+                    logger.warning(
+                        "Retrieving a cache value that could not be deserialized "
+                        "properly. This is likely due to the cache being in an "
+                        "older format. Please recreate your cache to avoid this "
+                        "error."
+                    )
+
+                    generations.extend(
+                        _load_generations_from_json(document.metadata["return_val"])
+                    )
+        return generations if generations else None
+
+    def update(self, prompt: str, llm_string: str, return_val: RETURN_VAL_TYPE) -> None:
+        """Update cache based on prompt and llm_string."""
+        for gen in return_val:
+            if not isinstance(gen, Generation):
+                raise ValueError(
+                    "OpenSearchSemanticCache only supports caching of "
+                    f"normal LLM generations, got {type(gen)}"
+                )
+        llm_cache = self._get_llm_cache(llm_string)
+        metadata = {
+            "llm_string": llm_string,
+            "prompt": prompt,
+            "return_val": dumps([g for g in return_val]),
+        }
+        llm_cache.add_texts(texts=[prompt], metadatas=[metadata])
+
+    def clear(self, **kwargs: Any) -> None:
+        """Clear semantic cache for a given llm_string."""
+        index_name = self._index_name(kwargs["llm_string"])
+        if index_name in self._cache_dict:
+            self._cache_dict[index_name].delete_index(index_name=index_name)
+            del self._cache_dict[index_name]

libs/community/langchain_community/chat_loaders/__init__.py

@@ -63,7 +63,7 @@ __all__ = [
 ]
 
 _module_lookup = {
-    "BaseChatLoader": "langchain_community.chat_loaders.base",
+    "BaseChatLoader": "langchain_core.chat_loaders",
     "FolderFacebookMessengerChatLoader": "langchain_community.chat_loaders.facebook_messenger",  # noqa: E501
     "GMailLoader": "langchain_community.chat_loaders.gmail",
     "IMessageChatLoader": "langchain_community.chat_loaders.imessage",

libs/community/langchain_community/chat_loaders/base.py

@@ -1,16 +1,3 @@
-from abc import ABC, abstractmethod
-from typing import Iterator, List
+from langchain_core.chat_loaders import BaseChatLoader
 
-from langchain_core.chat_sessions import ChatSession
-
-
-class BaseChatLoader(ABC):
-    """Base class for chat loaders."""
-
-    @abstractmethod
-    def lazy_load(self) -> Iterator[ChatSession]:
-        """Lazy load the chat sessions."""
-
-    def load(self) -> List[ChatSession]:
-        """Eagerly load the chat sessions into memory."""
-        return list(self.lazy_load())
+__all__ = ["BaseChatLoader"]

libs/community/langchain_community/chat_loaders/facebook_messenger.py

@@ -3,11 +3,10 @@ import logging
 from pathlib import Path
 from typing import Iterator, Union
 
+from langchain_core.chat_loaders import BaseChatLoader
 from langchain_core.chat_sessions import ChatSession
 from langchain_core.messages import HumanMessage
 
-from langchain_community.chat_loaders.base import BaseChatLoader
-
 logger = logging.getLogger(__file__)
 
 

libs/community/langchain_community/chat_loaders/gmail.py

@@ -3,11 +3,10 @@ import re
 from typing import Any, Iterator
 
 from langchain_core._api.deprecation import deprecated
+from langchain_core.chat_loaders import BaseChatLoader
 from langchain_core.chat_sessions import ChatSession
 from langchain_core.messages import HumanMessage
 
-from langchain_community.chat_loaders.base import BaseChatLoader
-
 
 def _extract_email_content(msg: Any) -> HumanMessage:
     from_email = None

libs/community/langchain_community/chat_loaders/imessage.py

@@ -4,11 +4,10 @@ from datetime import datetime
 from pathlib import Path
 from typing import TYPE_CHECKING, Iterator, List, Optional, Union
 
+from langchain_core.chat_loaders import BaseChatLoader
 from langchain_core.chat_sessions import ChatSession
 from langchain_core.messages import HumanMessage
 
-from langchain_community.chat_loaders.base import BaseChatLoader
-
 if TYPE_CHECKING:
     import sqlite3
 

libs/community/langchain_community/chat_loaders/langsmith.py

@@ -3,11 +3,10 @@ from __future__ import annotations
 import logging
 from typing import TYPE_CHECKING, Dict, Iterable, Iterator, List, Optional, Union, cast
 
+from langchain_core.chat_loaders import BaseChatLoader
 from langchain_core.chat_sessions import ChatSession
 from langchain_core.load.load import load
 
-from langchain_community.chat_loaders.base import BaseChatLoader
-
 if TYPE_CHECKING:
     from langsmith.client import Client
     from langsmith.schemas import Run

libs/community/langchain_community/chat_loaders/slack.py

@@ -5,11 +5,10 @@ import zipfile
 from pathlib import Path
 from typing import Dict, Iterator, List, Union
 
+from langchain_core.chat_loaders import BaseChatLoader
 from langchain_core.chat_sessions import ChatSession
 from langchain_core.messages import AIMessage, HumanMessage
 
-from langchain_community.chat_loaders.base import BaseChatLoader
-
 logger = logging.getLogger(__name__)
 
 

libs/community/langchain_community/chat_loaders/telegram.py

@@ -6,11 +6,10 @@ import zipfile
 from pathlib import Path
 from typing import Iterator, List, Union
 
+from langchain_core.chat_loaders import BaseChatLoader
 from langchain_core.chat_sessions import ChatSession
 from langchain_core.messages import AIMessage, BaseMessage, HumanMessage
 
-from langchain_community.chat_loaders.base import BaseChatLoader
-
 logger = logging.getLogger(__name__)
 
 

libs/community/langchain_community/chat_loaders/whatsapp.py

@@ -4,11 +4,10 @@ import re
 import zipfile
 from typing import Iterator, List, Union
 
+from langchain_core.chat_loaders import BaseChatLoader
 from langchain_core.chat_sessions import ChatSession
 from langchain_core.messages import AIMessage, HumanMessage
 
-from langchain_community.chat_loaders.base import BaseChatLoader
-
 logger = logging.getLogger(__name__)
 
 

libs/community/langchain_community/llms/exllamav2.py

@@ -0,0 +1,199 @@
+from typing import Any, Dict, Iterator, List, Optional
+
+from langchain_core.callbacks import CallbackManagerForLLMRun
+from langchain_core.language_models import LLM
+from langchain_core.outputs import GenerationChunk
+from langchain_core.pydantic_v1 import Field, root_validator
+
+
+class ExLlamaV2(LLM):
+    """ExllamaV2 API.
+
+    - working only with GPTQ models for now.
+    - Lora models are not supported yet.
+
+    To use, you should have the exllamav2 library installed, and provide the
+    path to the Llama model as a named parameter to the constructor.
+    Check out:
+
+    Example:
+        .. code-block:: python
+
+            from langchain_community.llms import Exllamav2
+
+            llm = Exllamav2(model_path="/path/to/llama/model")
+
+    #TODO:
+    - Add loras support
+    - Add support for custom settings
+    - Add support for custom stop sequences
+    """
+
+    client: Any
+    model_path: str
+    exllama_cache: Any = None
+    config: Any = None
+    generator: Any = None
+    tokenizer: Any = None
+    # If settings is None, it will be used as the default settings for the model.
+    # All other parameters won't be used.
+    settings: Any = None
+
+    # Langchain parameters
+    logfunc = print
+
+    stop_sequences: List[str] = Field("")
+    """Sequences that immediately will stop the generator."""
+
+    max_new_tokens: int = Field(150)
+    """Maximum number of tokens to generate."""
+
+    streaming: bool = Field(True)
+    """Whether to stream the results, token by token."""
+
+    verbose: bool = Field(True)
+    """Whether to print debug information."""
+
+    # Generator parameters
+    disallowed_tokens: List[int] = Field(None)
+    """List of tokens to disallow during generation."""
+
+    @root_validator()
+    def validate_environment(cls, values: Dict[str, Any]) -> Dict[str, Any]:
+        try:
+            import torch
+        except ImportError as e:
+            raise ImportError(
+                "Unable to import torch, please install with `pip install torch`."
+            ) from e
+        # check if cuda is available
+        if not torch.cuda.is_available():
+            raise EnvironmentError("CUDA is not available. ExllamaV2 requires CUDA.")
+        try:
+            from exllamav2 import (
+                ExLlamaV2,
+                ExLlamaV2Cache,
+                ExLlamaV2Config,
+                ExLlamaV2Tokenizer,
+            )
+            from exllamav2.generator import (
+                ExLlamaV2BaseGenerator,
+                ExLlamaV2StreamingGenerator,
+            )
+        except ImportError:
+            raise ImportError(
+                "Could not import exllamav2 library. "
+                "Please install the exllamav2 library with (cuda 12.1 is required)"
+                "example : "
+                "!python -m pip install https://github.com/turboderp/exllamav2/releases/download/v0.0.12/exllamav2-0.0.12+cu121-cp311-cp311-linux_x86_64.whl"
+            )
+
+        # Set logging function if verbose or set to empty lambda
+        verbose = values["verbose"]
+        if not verbose:
+            values["logfunc"] = lambda *args, **kwargs: None
+        logfunc = values["logfunc"]
+
+        if values["settings"]:
+            settings = values["settings"]
+            logfunc(settings.__dict__)
+        else:
+            raise NotImplementedError(
+                "settings is required. Custom settings are not supported yet."
+            )
+
+        config = ExLlamaV2Config()
+        config.model_dir = values["model_path"]
+        config.prepare()
+
+        model = ExLlamaV2(config)
+
+        exllama_cache = ExLlamaV2Cache(model, lazy=True)
+        model.load_autosplit(exllama_cache)
+
+        tokenizer = ExLlamaV2Tokenizer(config)
+        if values["streaming"]:
+            generator = ExLlamaV2StreamingGenerator(model, exllama_cache, tokenizer)
+        else:
+            generator = ExLlamaV2BaseGenerator(model, exllama_cache, tokenizer)
+
+        # Configure the model and generator
+        values["stop_sequences"] = [x.strip().lower() for x in values["stop_sequences"]]
+        setattr(settings, "stop_sequences", values["stop_sequences"])
+        logfunc(f"stop_sequences {values['stop_sequences']}")
+
+        disallowed = values.get("disallowed_tokens")
+        if disallowed:
+            settings.disallow_tokens(tokenizer, disallowed)
+
+        values["client"] = model
+        values["generator"] = generator
+        values["config"] = config
+        values["tokenizer"] = tokenizer
+        values["exllama_cache"] = exllama_cache
+
+        return values
+
+    @property
+    def _llm_type(self) -> str:
+        """Return type of llm."""
+        return "ExLlamaV2"
+
+    def get_num_tokens(self, text: str) -> int:
+        """Get the number of tokens present in the text."""
+        return self.generator.tokenizer.num_tokens(text)
+
+    def _call(
+        self,
+        prompt: str,
+        stop: Optional[List[str]] = None,
+        run_manager: Optional[CallbackManagerForLLMRun] = None,
+        **kwargs: Any,
+    ) -> str:
+        generator = self.generator
+
+        if self.streaming:
+            combined_text_output = ""
+            for chunk in self._stream(
+                prompt=prompt, stop=stop, run_manager=run_manager, kwargs=kwargs
+            ):
+                combined_text_output += str(chunk)
+            return combined_text_output
+        else:
+            output = generator.generate_simple(
+                prompt=prompt,
+                gen_settings=self.settings,
+                num_tokens=self.max_new_tokens,
+            )
+            # subtract subtext from output
+            output = output[len(prompt) :]
+            return output
+
+    def _stream(
+        self,
+        prompt: str,
+        stop: Optional[List[str]] = None,
+        run_manager: Optional[CallbackManagerForLLMRun] = None,
+        **kwargs: Any,
+    ) -> Iterator[GenerationChunk]:
+        input_ids = self.tokenizer.encode(prompt)
+        self.generator.warmup()
+        self.generator.set_stop_conditions([])
+        self.generator.begin_stream(input_ids, self.settings)
+
+        generated_tokens = 0
+
+        while True:
+            chunk, eos, _ = self.generator.stream()
+            generated_tokens += 1
+
+            if run_manager:
+                run_manager.on_llm_new_token(
+                    token=chunk,
+                    verbose=self.verbose,
+                )
+            yield chunk
+            if eos or generated_tokens == self.max_new_tokens:
+                break
+
+        return

libs/community/langchain_community/vectorstores/opensearch_vector_search.py

@@ -274,10 +274,12 @@ def _default_approximate_search_query(
     query_vector: List[float],
     k: int = 4,
     vector_field: str = "vector_field",
+    score_threshold: Optional[float] = 0.0,
 ) -> Dict:
     """For Approximate k-NN Search, this is the default query."""
     return {
         "size": k,
+        "min_score": score_threshold,
         "query": {"knn": {vector_field: {"vector": query_vector, "k": k}}},
     }
 
@@ -288,10 +290,12 @@ def _approximate_search_query_with_boolean_filter(
     k: int = 4,
     vector_field: str = "vector_field",
     subquery_clause: str = "must",
+    score_threshold: Optional[float] = 0.0,
 ) -> Dict:
     """For Approximate k-NN Search, with Boolean Filter."""
     return {
         "size": k,
+        "min_score": score_threshold,
         "query": {
             "bool": {
                 "filter": boolean_filter,
@@ -308,11 +312,12 @@ def _approximate_search_query_with_efficient_filter(
     efficient_filter: Dict,
     k: int = 4,
     vector_field: str = "vector_field",
+    score_threshold: Optional[float] = 0.0,
 ) -> Dict:
     """For Approximate k-NN Search, with Efficient Filter for Lucene and
     Faiss Engines."""
     search_query = _default_approximate_search_query(
-        query_vector, k=k, vector_field=vector_field
+        query_vector, k=k, vector_field=vector_field, score_threshold=score_threshold
     )
     search_query["query"]["knn"][vector_field]["filter"] = efficient_filter
     return search_query
@@ -324,6 +329,7 @@ def _default_script_query(
     space_type: str = "l2",
     pre_filter: Optional[Dict] = None,
     vector_field: str = "vector_field",
+    score_threshold: Optional[float] = 0.0,
 ) -> Dict:
     """For Script Scoring Search, this is the default query."""
 
@@ -332,6 +338,7 @@ def _default_script_query(
 
     return {
         "size": k,
+        "min_score": score_threshold,
         "query": {
             "script_score": {
                 "query": pre_filter,
@@ -368,6 +375,7 @@ def _default_painless_scripting_query(
     space_type: str = "l2Squared",
     pre_filter: Optional[Dict] = None,
     vector_field: str = "vector_field",
+    score_threshold: Optional[float] = 0.0,
 ) -> Dict:
     """For Painless Scripting Search, this is the default query."""
 
@@ -377,6 +385,7 @@ def _default_painless_scripting_query(
     source = __get_painless_scripting_source(space_type, vector_field=vector_field)
     return {
         "size": k,
+        "min_score": score_threshold,
         "query": {
             "script_score": {
                 "query": pre_filter,
@@ -509,6 +518,72 @@ class OpenSearchVectorSearch(VectorStore):
             is_aoss=self.is_aoss,
         )
 
+    def delete_index(self, index_name: Optional[str] = None) -> Optional[bool]:
+        """Deletes a given index from vectorstore."""
+        if index_name is None:
+            if self.index_name is None:
+                raise ValueError("index_name must be provided.")
+            index_name = self.index_name
+        try:
+            self.client.indices.delete(index=index_name)
+            return True
+        except Exception as e:
+            raise e
+
+    def index_exists(self, index_name: Optional[str] = None) -> Optional[bool]:
+        """If given index present in vectorstore, returns True else False."""
+        if index_name is None:
+            if self.index_name is None:
+                raise ValueError("index_name must be provided.")
+            index_name = self.index_name
+
+        return self.client.indices.exists(index=index_name)
+
+    def create_index(
+        self,
+        dimension: int,
+        index_name: Optional[str] = uuid.uuid4().hex,
+        **kwargs: Any,
+    ) -> Optional[str]:
+        """Create a new Index with given arguments"""
+        is_appx_search = kwargs.get("is_appx_search", True)
+        vector_field = kwargs.get("vector_field", "vector_field")
+        kwargs.get("text_field", "text")
+        http_auth = kwargs.get("http_auth")
+        is_aoss = _is_aoss_enabled(http_auth=http_auth)
+
+        if is_aoss and not is_appx_search:
+            raise ValueError(
+                "Amazon OpenSearch Service Serverless only "
+                "supports `approximate_search`"
+            )
+
+        if is_appx_search:
+            engine = kwargs.get("engine", "nmslib")
+            space_type = kwargs.get("space_type", "l2")
+            ef_search = kwargs.get("ef_search", 512)
+            ef_construction = kwargs.get("ef_construction", 512)
+            m = kwargs.get("m", 16)
+
+            _validate_aoss_with_engines(is_aoss, engine)
+
+            mapping = _default_text_mapping(
+                dimension,
+                engine,
+                space_type,
+                ef_search,
+                ef_construction,
+                m,
+                vector_field,
+            )
+        else:
+            mapping = _default_scripting_text_mapping(dimension)
+
+        if self.index_exists(index_name):
+            raise RuntimeError(f"The index, {index_name} already exists.")
+        self.client.indices.create(index=index_name, body=mapping)
+        return index_name
+
     def add_texts(
         self,
         texts: Iterable[str],
@@ -659,7 +734,11 @@ class OpenSearchVectorSearch(VectorStore):
         )
 
     def similarity_search(
-        self, query: str, k: int = 4, **kwargs: Any
+        self,
+        query: str,
+        k: int = 4,
+        score_threshold: Optional[float] = 0.0,
+        **kwargs: Any,
     ) -> List[Document]:
         """Return docs most similar to query.
 
@@ -669,6 +748,8 @@ class OpenSearchVectorSearch(VectorStore):
         Args:
             query: Text to look up documents similar to.
             k: Number of Documents to return. Defaults to 4.
+            score_threshold: Specify a score threshold to return only documents
+            above the threshold. Defaults to 0.0.
 
         Returns:
             List of Documents most similar to the query.
@@ -717,20 +798,30 @@ class OpenSearchVectorSearch(VectorStore):
             pre_filter: script_score query to pre-filter documents before identifying
             nearest neighbors; default: {"match_all": {}}
         """
-        docs_with_scores = self.similarity_search_with_score(query, k, **kwargs)
+        docs_with_scores = self.similarity_search_with_score(
+            query, k, score_threshold, **kwargs
+        )
         return [doc[0] for doc in docs_with_scores]
 
     def similarity_search_by_vector(
-        self, embedding: List[float], k: int = 4, **kwargs: Any
+        self,
+        embedding: List[float],
+        k: int = 4,
+        score_threshold: Optional[float] = 0.0,
+        **kwargs: Any,
     ) -> List[Document]:
         """Return docs most similar to the embedding vector."""
         docs_with_scores = self.similarity_search_with_score_by_vector(
-            embedding, k, **kwargs
+            embedding, k, score_threshold, **kwargs
         )
         return [doc[0] for doc in docs_with_scores]
 
     def similarity_search_with_score(
-        self, query: str, k: int = 4, **kwargs: Any
+        self,
+        query: str,
+        k: int = 4,
+        score_threshold: Optional[float] = 0.0,
+        **kwargs: Any,
     ) -> List[Tuple[Document, float]]:
         """Return docs and it's scores most similar to query.
 
@@ -740,6 +831,8 @@ class OpenSearchVectorSearch(VectorStore):
         Args:
             query: Text to look up documents similar to.
             k: Number of Documents to return. Defaults to 4.
+            score_threshold: Specify a score threshold to return only documents
+            above the threshold. Defaults to 0.0.
 
         Returns:
             List of Documents along with its scores most similar to the query.
@@ -748,10 +841,16 @@ class OpenSearchVectorSearch(VectorStore):
             same as `similarity_search`
         """
         embedding = self.embedding_function.embed_query(query)
-        return self.similarity_search_with_score_by_vector(embedding, k, **kwargs)
+        return self.similarity_search_with_score_by_vector(
+            embedding, k, score_threshold, **kwargs
+        )
 
     def similarity_search_with_score_by_vector(
-        self, embedding: List[float], k: int = 4, **kwargs: Any
+        self,
+        embedding: List[float],
+        k: int = 4,
+        score_threshold: Optional[float] = 0.0,
+        **kwargs: Any,
     ) -> List[Tuple[Document, float]]:
         """Return docs and it's scores most similar to the embedding vector.
 
@@ -761,6 +860,8 @@ class OpenSearchVectorSearch(VectorStore):
         Args:
             embedding: Embedding vector to look up documents similar to.
             k: Number of Documents to return. Defaults to 4.
+            score_threshold: Specify a score threshold to return only documents
+            above the threshold. Defaults to 0.0.
 
         Returns:
             List of Documents along with its scores most similar to the query.
@@ -772,7 +873,7 @@ class OpenSearchVectorSearch(VectorStore):
         metadata_field = kwargs.get("metadata_field", "metadata")
 
         hits = self._raw_similarity_search_with_score_by_vector(
-            embedding=embedding, k=k, **kwargs
+            embedding=embedding, k=k, score_threshold=score_threshold, **kwargs
         )
 
         documents_with_scores = [
@@ -792,7 +893,11 @@ class OpenSearchVectorSearch(VectorStore):
         return documents_with_scores
 
     def _raw_similarity_search_with_score_by_vector(
-        self, embedding: List[float], k: int = 4, **kwargs: Any
+        self,
+        embedding: List[float],
+        k: int = 4,
+        score_threshold: Optional[float] = 0.0,
+        **kwargs: Any,
     ) -> List[dict]:
         """Return raw opensearch documents (dict) including vectors,
         scores most similar to the embedding vector.
@@ -803,6 +908,8 @@ class OpenSearchVectorSearch(VectorStore):
         Args:
             embedding: Embedding vector to look up documents similar to.
             k: Number of Documents to return. Defaults to 4.
+            score_threshold: Specify a score threshold to return only documents
+            above the threshold. Defaults to 0.0.
 
         Returns:
             List of dict with its scores most similar to the embedding.
@@ -868,10 +975,15 @@ class OpenSearchVectorSearch(VectorStore):
                     k=k,
                     vector_field=vector_field,
                     subquery_clause=subquery_clause,
+                    score_threshold=score_threshold,
                 )
             elif efficient_filter != {}:
                 search_query = _approximate_search_query_with_efficient_filter(
-                    embedding, efficient_filter, k=k, vector_field=vector_field
+                    embedding,
+                    efficient_filter,
+                    k=k,
+                    vector_field=vector_field,
+                    score_threshold=score_threshold,
                 )
             elif lucene_filter != {}:
                 warnings.warn(
@@ -879,23 +991,40 @@ class OpenSearchVectorSearch(VectorStore):
                     " `efficient_filter`"
                 )
                 search_query = _approximate_search_query_with_efficient_filter(
-                    embedding, lucene_filter, k=k, vector_field=vector_field
+                    embedding,
+                    lucene_filter,
+                    k=k,
+                    vector_field=vector_field,
+                    score_threshold=score_threshold,
                 )
             else:
                 search_query = _default_approximate_search_query(
-                    embedding, k=k, vector_field=vector_field
+                    embedding,
+                    k=k,
+                    vector_field=vector_field,
+                    score_threshold=score_threshold,
                 )
         elif search_type == SCRIPT_SCORING_SEARCH:
             space_type = kwargs.get("space_type", "l2")
             pre_filter = kwargs.get("pre_filter", MATCH_ALL_QUERY)
             search_query = _default_script_query(
-                embedding, k, space_type, pre_filter, vector_field
+                embedding,
+                k,
+                space_type,
+                pre_filter,
+                vector_field,
+                score_threshold=score_threshold,
             )
         elif search_type == PAINLESS_SCRIPTING_SEARCH:
             space_type = kwargs.get("space_type", "l2Squared")
             pre_filter = kwargs.get("pre_filter", MATCH_ALL_QUERY)
             search_query = _default_painless_scripting_query(
-                embedding, k, space_type, pre_filter, vector_field
+                embedding,
+                k,
+                space_type,
+                pre_filter,
+                vector_field,
+                score_threshold=score_threshold,
             )
         else:
             raise ValueError("Invalid `search_type` provided as an argument")

libs/community/langchain_community/vectorstores/qdrant.py

@@ -1367,6 +1367,51 @@ class Qdrant(VectorStore):
         qdrant.add_texts(texts, metadatas, ids, batch_size)
         return qdrant
 
+    @classmethod
+    def from_existing_collection(
+        cls: Type[Qdrant],
+        embedding: Embeddings,
+        path: str,
+        collection_name: str,
+        location: Optional[str] = None,
+        url: Optional[str] = None,
+        port: Optional[int] = 6333,
+        grpc_port: int = 6334,
+        prefer_grpc: bool = False,
+        https: Optional[bool] = None,
+        api_key: Optional[str] = None,
+        prefix: Optional[str] = None,
+        timeout: Optional[float] = None,
+        host: Optional[str] = None,
+        **kwargs: Any,
+    ) -> Qdrant:
+        """
+        Get instance of an existing Qdrant collection.
+        This method will return the instance of the store without inserting any new
+        embeddings
+        """
+        client, async_client = cls._generate_clients(
+            location=location,
+            url=url,
+            port=port,
+            grpc_port=grpc_port,
+            prefer_grpc=prefer_grpc,
+            https=https,
+            api_key=api_key,
+            prefix=prefix,
+            timeout=timeout,
+            host=host,
+            path=path,
+            **kwargs,
+        )
+        return cls(
+            client=client,
+            async_client=async_client,
+            collection_name=collection_name,
+            embeddings=embedding,
+            **kwargs,
+        )
+
     @classmethod
     @sync_call_fallback
     async def afrom_texts(

libs/community/poetry.lock

@@ -1356,6 +1356,118 @@ tomli = {version = "*", optional = true, markers = "python_full_version <= \"3.1
 [package.extras]
 toml = ["tomli"]
 
+[[package]]
+name = "cramjam"
+version = "2.8.3"
+description = "Thin Python bindings to de/compression algorithms in Rust"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "cramjam-2.8.3-cp310-cp310-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:8c8aa6d08c135ae7f0da01e6559a332c5d8fe4989a594db401040e385d04dffd"},
+    {file = "cramjam-2.8.3-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:bd8c601fe8717e52517a2f2eef78217086acf449627bfdda97e3f53fd79c92af"},
+    {file = "cramjam-2.8.3-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:dac42b2b4c3950e7eda9b5551e0e904784ed0c0428accc29171c230fb919ec72"},
+    {file = "cramjam-2.8.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ab8146faa5d8c52edf23724843c36469fc32ff2c4a174eba72f4da6de5016688"},
+    {file = "cramjam-2.8.3-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:cb5f4d061e9abdc6663551446c332a58c101efb31fd1746229872600274c2b20"},
+    {file = "cramjam-2.8.3-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5d1ac94e00c64258330105473c641441db02b4dc3e9e9f2963d204e53ed93025"},
+    {file = "cramjam-2.8.3-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8ed658f36a2bf667d5b8c7c6690103ad99f81cc62a1b64891b69298447329d4b"},
+    {file = "cramjam-2.8.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3f6303c8cc583dfe5054cf84717674f75b18bca4ae8e576dc863958d5494dc4b"},
+    {file = "cramjam-2.8.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:04b31d427a8902e5c2eec4b8f29873de7a3ade202e3d68e7f2354b9f0aa00bc7"},
+    {file = "cramjam-2.8.3-cp310-cp310-musllinux_1_1_armv7l.whl", hash = "sha256:9728861bc0390681824961778b36f7f0b95039e8b90d46f1b67f51232f1ee159"},
+    {file = "cramjam-2.8.3-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:87e26e3e1d5fed1cac5b41be648d0daf0793f94cf4a7aebefce1f4f6656e2d21"},
+    {file = "cramjam-2.8.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:4c1d2d39c2193a77c5e5b327944f90e6ecf2caa1b55e7176cc83d80706ea15de"},
+    {file = "cramjam-2.8.3-cp310-none-win32.whl", hash = "sha256:6721edd8f911ad84db83ee4902b7579fc01c55849062f3f1f4171b58fccf98eb"},
+    {file = "cramjam-2.8.3-cp310-none-win_amd64.whl", hash = "sha256:4f7c16d358df366e308137411125a2bb50d1b19924fced3a390898fa8c9a074d"},
+    {file = "cramjam-2.8.3-cp311-cp311-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:24c2b426dd8fafb894f93a88f42e2827e14199d66836cb100582037e5371c724"},
+    {file = "cramjam-2.8.3-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:007aa9444cb27b8691baae73ca907133cd939987438f874774011b4c740732dd"},
+    {file = "cramjam-2.8.3-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:29987b54e31efed66738e8f236c597c4c9a91ec9d57bcb74307712e07505b4bb"},
+    {file = "cramjam-2.8.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:65bfd41aa92c0025f32ba09214b48e9367a81122586b2617439b4327c4bd179c"},
+    {file = "cramjam-2.8.3-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:7337bd8218bd8508f35904274a38cce843a237fe6e23104238bbeb2f337107ed"},
+    {file = "cramjam-2.8.3-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:269f94d2efe6b6a97624782cd3b541e60535dd5874f4a8d5d0ba66ef59424ae3"},
+    {file = "cramjam-2.8.3-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:bec9ca5431c32ba94996b7c1c56695b37d48713b97ee1d2a456f4046f009e82f"},
+    {file = "cramjam-2.8.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2cb64a97e625ca029b55e37769b8c354e64cbea042c75471915dc385935d30ed"},
+    {file = "cramjam-2.8.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:c28830ecf76501356d678dac4f37563554ec1c651a53a990cdf595f7ed75c651"},
+    {file = "cramjam-2.8.3-cp311-cp311-musllinux_1_1_armv7l.whl", hash = "sha256:35647a0e37a4dfec85a44c7966ae476b7db0e6cd65d91c08f1fb3007ed774d92"},
+    {file = "cramjam-2.8.3-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:e954599c6369f429a868852eff453b894d88866acba439b65131ea93f5400b47"},
+    {file = "cramjam-2.8.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:86e238b6de79e045f5197df2c9dfaf8d10b37a6517ff4ffc4775fe5a3cf4d4a4"},
+    {file = "cramjam-2.8.3-cp311-none-win32.whl", hash = "sha256:fe6434d3ee0899bc9396801d1abbc5d1fe77662bd3d1f1c1573fac6708459138"},
+    {file = "cramjam-2.8.3-cp311-none-win_amd64.whl", hash = "sha256:e8ec1d4f27eb9d0412f0c567e7ffd14fbeb2b318a1ac394d5de4047c431fe94c"},
+    {file = "cramjam-2.8.3-cp312-cp312-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:24990be4010b2185dcecc67133cd727657036e7b132d7de598148f5b1eb8e452"},
+    {file = "cramjam-2.8.3-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:572cb9a8dc5a189691d6e03a9bf9b4305fd9a9f36bb0f9fde55fc36837c2e6b3"},
+    {file = "cramjam-2.8.3-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:9efe6915aa7ef176f3a7f42a4e46504573215953331b139abefd20d07d8aba82"},
+    {file = "cramjam-2.8.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fe84440100e7045190da7f80219be9989b0b6db6acadb3ae9cfe0935d93ebf8c"},
+    {file = "cramjam-2.8.3-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:00524bb23f4abb3a3bfff08aa32b9274843170c5b43855807e0f59670e2ac98c"},
+    {file = "cramjam-2.8.3-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ab67f29094165f0771acad8dd16e840259cfedcc94067af229530496dbf1a24c"},
+    {file = "cramjam-2.8.3-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:be6fb5dd5bf1c89c717a73a1057505959f35c08e0e97a76d4cc6391b90d2263b"},
+    {file = "cramjam-2.8.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d93b42d22bf3e17290c5e4cf58e715a419330bb5255c35933c14db82ecf3872c"},
+    {file = "cramjam-2.8.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:afa065bab70e27565695441f69f493af3d379b8723030f2c3d2547d2e312a4be"},
+    {file = "cramjam-2.8.3-cp312-cp312-musllinux_1_1_armv7l.whl", hash = "sha256:832224f52fa1e601e0ab678dba9bdfde3686fc4cd1a9f2ed4748f29eaf1cb553"},
+    {file = "cramjam-2.8.3-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:962b7106287bcc463150766b5b8c69f32dcc69713a8dbce00e0ca6936f95c55b"},
+    {file = "cramjam-2.8.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:2be92c6f0bcffaf8ea6a8164fe0388a188fec2fa9eff1828e8b64dc3a83740f9"},
+    {file = "cramjam-2.8.3-cp312-none-win32.whl", hash = "sha256:080f3eb7b648f5ba9d35084d8dddc68246a8f365df239792f6712908f0aa568e"},
+    {file = "cramjam-2.8.3-cp312-none-win_amd64.whl", hash = "sha256:c14728e3360cd212d5b606ca703c3bd1c8912efcdbc1aa032c81c2882509ebd5"},
+    {file = "cramjam-2.8.3-cp37-cp37m-macosx_10_12_x86_64.whl", hash = "sha256:c7e8329cde48740df8d332dade2f52b74612b8ea86005341c99bb192c82a5ce7"},
+    {file = "cramjam-2.8.3-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:77346ac669f5445d14b74476a4e8f3a259fd22681bd73790e92b8956d7e225fc"},
+    {file = "cramjam-2.8.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:274878883e7fadf95a6b5bc58f9c1dd39fef2c31d68e18a0fb8594226457fba7"},
+    {file = "cramjam-2.8.3-cp37-cp37m-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:7871e1fd3ee8ca16799ba22d49fc1e52e78976fa8c659be41630eeb2914475a7"},
+    {file = "cramjam-2.8.3-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:345a952c5d4b922830efaa67dc0b42d21e18c182c1a1bda6d20bb78235f31d6f"},
+    {file = "cramjam-2.8.3-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:fb5d7739e2bc573ade12327ef7717b1ac5876c62938fab20eb54d762da23cae2"},
+    {file = "cramjam-2.8.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:440a18fd4ae42e06dbbd7aee91d8248b61da9fef7610ffbd553d1ba93931394b"},
+    {file = "cramjam-2.8.3-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:476890974229713fc7b4c16fb050b756ba926c67e4d1200b3e03c5c051e9b552"},
+    {file = "cramjam-2.8.3-cp37-cp37m-musllinux_1_1_armv7l.whl", hash = "sha256:771b44e549f90b5532508782e25d1c40b8054dd83d52253d05945fc05836b252"},
+    {file = "cramjam-2.8.3-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:d824fd98364bc946c38ed324a3ec7befba055285aaf2c1ca61894bb7616226e8"},
+    {file = "cramjam-2.8.3-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:2476828dea4089aa3cb9160391f8b36f793ca651afdcba80de1e341373928397"},
+    {file = "cramjam-2.8.3-cp37-none-win32.whl", hash = "sha256:4a554bcfd068e831affd64a4f067c7c9b00b359742597c4fdadd18ff673baf30"},
+    {file = "cramjam-2.8.3-cp37-none-win_amd64.whl", hash = "sha256:246f1f7d32cac2b64617d2dddba11a82851e73cdcf9d1abb799b08dcd9d2ea49"},
+    {file = "cramjam-2.8.3-cp38-cp38-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:bc8f24c32124bb47536882c6b941cdb88cc16e4fa64d5bf347cb8dd72a193fc3"},
+    {file = "cramjam-2.8.3-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:28c30078effc100739d3f9b227276a8360c1b32aac65efb4f641630552213548"},
+    {file = "cramjam-2.8.3-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:ef0173fb457f73cf9c2553092419db0eba4d582890db95e542a4d93e11340421"},
+    {file = "cramjam-2.8.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9a1943f2cc0deee037ddcf92beff6049e12d4e6d557f568ddf59fb3b848f2152"},
+    {file = "cramjam-2.8.3-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:5023a737d8d9cf5d123e6d87d088929c3cfb2aae90e0f584204427f74882150a"},
+    {file = "cramjam-2.8.3-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:6eec7e985f35708c234542721863d82781d0f7f6a71b45e14ce6d2625d4b131d"},
+    {file = "cramjam-2.8.3-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b188e750b95172c01defcfcfbba629cad797718b34402ec61b3bc9ff99403599"},
+    {file = "cramjam-2.8.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:30e2d745cd4d244b7973d15aaebeedb537b980f9d3da80e6dea75ee1a872f9fa"},
+    {file = "cramjam-2.8.3-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:c9d54a4aa475d5e902f2ee518bdaa02f26c089e9f72950d00d1643c090f0deb3"},
+    {file = "cramjam-2.8.3-cp38-cp38-musllinux_1_1_armv7l.whl", hash = "sha256:19b8c97350c8d65daea26267dd1becb59073569aac2ae5743952d7f48da5d37a"},
+    {file = "cramjam-2.8.3-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:3277fd42399755d6d3730edec4a192174ee64d219e0ffbc90613f15cbabf711f"},
+    {file = "cramjam-2.8.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:1fd25201f1278dc6faa2ae35e67b7a5bb352b7fc6ed1ee939637414ca8115863"},
+    {file = "cramjam-2.8.3-cp38-none-win32.whl", hash = "sha256:594477faff7f4380fa123cfbcf10ab8ee5af1a28b95750b66931ffafcb11ab5c"},
+    {file = "cramjam-2.8.3-cp38-none-win_amd64.whl", hash = "sha256:8ea1dc11538842ff20d9872a17214994f5913cbf3be5594b54aad2422becdf19"},
+    {file = "cramjam-2.8.3-cp39-cp39-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:6379b92912f7569e126bd48d10e7087ddd20ea88a939532e3c4a85c2fa05d600"},
+    {file = "cramjam-2.8.3-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:11d2e9eebc7d202eda0ae09fb56a2cdbeb5a1563e89d2118bf18cf0030f35f77"},
+    {file = "cramjam-2.8.3-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:d5a0a2fe240c97587df07f3d5e1027673d599b3a6a7a0ab540aea69f09e9ff7a"},
+    {file = "cramjam-2.8.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ba542f07fe3f41475d78626973533539e6cf2d5b6af37923fe6c7e7f0f74b9b2"},
+    {file = "cramjam-2.8.3-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:1374fe9a4431e546bb4501a16b84875d0bf80fc4e6c8942f0d5608ae48474267"},
+    {file = "cramjam-2.8.3-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:dcf7791e1cedb982ccc873ec9392c6cfb9c714a64ebf1ed4e8310b9cb44655f2"},
+    {file = "cramjam-2.8.3-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:990e65c2bf1c155a9ddec5ecabf431cf77596432f697d3c6e0831b5174c51c40"},
+    {file = "cramjam-2.8.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d9b244d04cef82872d12c227a2f202f080a454d664c05db351626e6ad4aaa307"},
+    {file = "cramjam-2.8.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:80b088d15866b37851fd53e2b471becc9ec487257dceca1878621072a18e833e"},
+    {file = "cramjam-2.8.3-cp39-cp39-musllinux_1_1_armv7l.whl", hash = "sha256:f667843e7a8fca208eecfe44e04088242f8ca60d74d4950fac3722043538d700"},
+    {file = "cramjam-2.8.3-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:6f838d06d06709b9ce8b1ceae36aea4e1c7e613365185a91edcbeb5884f5e606"},
+    {file = "cramjam-2.8.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:4822eb5fe6839cd3d0439e5431e766ad010b2a388ca9617aa6372b6030897782"},
+    {file = "cramjam-2.8.3-cp39-none-win32.whl", hash = "sha256:67e09b42e744efd08b93ac56f6100a859a31617d7146725516f3f2c744149d97"},
+    {file = "cramjam-2.8.3-cp39-none-win_amd64.whl", hash = "sha256:11c9d30bc53892c57a3b296756c23659323ab1419a2b4bf22bbafc07b247bb67"},
+    {file = "cramjam-2.8.3-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:51e847dcfe74fba379fed2bc2b45f5c2f11c3ece5e9eebcf63f39a9594184588"},
+    {file = "cramjam-2.8.3-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:07af94191f6a245226dc8a8bc6c94808e382ce9dfcca4bab0e8015fbc7fc3322"},
+    {file = "cramjam-2.8.3-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fc9c45469914099897c47bfc501616fb377f28a865adebf90ea6f3c8ae6dd4e6"},
+    {file = "cramjam-2.8.3-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:ef29fb916fe74be65d0ab8871ab8d964b0f5eb8028bb84b325be43675a59d6e7"},
+    {file = "cramjam-2.8.3-pp310-pypy310_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:3850dac9a2f6dcb3249d23f9d505117643b967bdc1c572ed0cc492a48fd69daf"},
+    {file = "cramjam-2.8.3-pp310-pypy310_pp73-musllinux_1_1_i686.whl", hash = "sha256:e23e323ad28ed3e4e3a24ceffdab0ff235954109a88b536ea7b3b7886bd0a536"},
+    {file = "cramjam-2.8.3-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:1ba1a8ff855b30b4069a9b45ea9e7f2b5d882c7953bdfccda8d4b275fa7057ce"},
+    {file = "cramjam-2.8.3-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:eea606b01b43b91626e3aafd463bd19b6ed739bdb8b2b309e5d7ff72afc0e89d"},
+    {file = "cramjam-2.8.3-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:97c706c520c3f8b0184278cc86187528458350216c6e4fa85d3f16bcad0d365d"},
+    {file = "cramjam-2.8.3-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9d08f1bab949ffd6dd6f25a89e4f7062d147aeea9c067e4dd155bdb190e5a519"},
+    {file = "cramjam-2.8.3-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba1e45074757ab0482ac544e60613b6b8658100ac9985c91868a4598cdfb63ba"},
+    {file = "cramjam-2.8.3-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:a2fededed05a042f093dbf1b11d69afb1874a2c9197fcf1d58c142ba9111db5a"},
+    {file = "cramjam-2.8.3-pp39-pypy39_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:fc0c6eb8185c68f79a25bb298825e345cc09b826f5828bd8146e3600ca6e9981"},
+    {file = "cramjam-2.8.3-pp39-pypy39_pp73-musllinux_1_1_i686.whl", hash = "sha256:6653c262ad71e6c0ae08eeca3af2ee89ad47483b6312f2c6094518cb77872406"},
+    {file = "cramjam-2.8.3-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:6c04f363cb4b316719421724521432b6e7f6490e5baaaf7692af961c28d0279b"},
+    {file = "cramjam-2.8.3-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:e30f1f00de913b440baa36647817b9b7120a69b04eca05f3354aaf5b40f95ee5"},
+    {file = "cramjam-2.8.3.tar.gz", hash = "sha256:6b1fa0a6ea8183831d04572597c182bd6cece62d583a36cde1e6a86e72ce2389"},
+]
+
+[package.extras]
+dev = ["black (==22.3.0)", "hypothesis", "numpy", "pytest (>=5.30)", "pytest-xdist"]
+
 [[package]]
 name = "cryptography"
 version = "42.0.5"
@@ -1836,6 +1948,28 @@ files = [
 [package.extras]
 tests = ["asttokens (>=2.1.0)", "coverage", "coverage-enable-subprocess", "ipython", "littleutils", "pytest", "rich"]
 
+[[package]]
+name = "exllamav2"
+version = "0.0.18"
+description = ""
+optional = false
+python-versions = "*"
+files = [
+    {file = "exllamav2-0.0.18-py3-none-any.whl", hash = "sha256:9ded8656a63b91942a740d59cb0e3f81547aa250f4296fc9130e8a6e7cfecd3e"},
+]
+
+[package.dependencies]
+fastparquet = "*"
+ninja = "*"
+numpy = "*"
+pandas = "*"
+pygments = "*"
+regex = "*"
+safetensors = ">=0.3.2"
+sentencepiece = ">=0.1.97"
+torch = ">=2.2.0"
+websockets = "*"
+
 [[package]]
 name = "faiss-cpu"
 version = "1.8.0"
@@ -1954,6 +2088,64 @@ files = [
 [package.extras]
 devel = ["colorama", "json-spec", "jsonschema", "pylint", "pytest", "pytest-benchmark", "pytest-cache", "validictory"]
 
+[[package]]
+name = "fastparquet"
+version = "2024.2.0"
+description = "Python support for Parquet file format"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "fastparquet-2024.2.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:94aaa752d79660f2d88983bd7336109f4b61da6940d759786c02144195d6c635"},
+    {file = "fastparquet-2024.2.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:abb08c61ab0f8a29a118dabe0a9105686fa5580648cfca252a74153c8c32444f"},
+    {file = "fastparquet-2024.2.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0d04901828f54ec118e7e5dfb438518ffe9b75ef3b7ebcdbaf33af130fcee9b7"},
+    {file = "fastparquet-2024.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:42def5e682eb426e6f7062d0bee370dec9424181f3c61eb24d6bdc67482a0ace"},
+    {file = "fastparquet-2024.2.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d87f24ae76e65f94af9e62a648b5479f0bd2e8935e0011c9390ebc1299f3785d"},
+    {file = "fastparquet-2024.2.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:76fadf2399a778daf49772c644a3a7b27e41492a43e2bea4107a715981c1dc2f"},
+    {file = "fastparquet-2024.2.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:83f1abb155d8a8b6f1f31318174507d8a8ddf4bff00a2ef7065b609577deb6ae"},
+    {file = "fastparquet-2024.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:dedeb4ad28f68313c2504ef005f4b2d52c3d108bd5323204300dbaeec6fb1b04"},
+    {file = "fastparquet-2024.2.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:3b7c39661c918686fdbf21695547d2e7b0cd0226a2f2dd6fa5c2ad7b37da2540"},
+    {file = "fastparquet-2024.2.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:bd1b310e7d9934f61236b793d1e11336d457e7664829bf76d53bff5614dcc338"},
+    {file = "fastparquet-2024.2.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e27b5d21fecdc07f071f5343a350b88c859b324834fd19b78d636480fe341999"},
+    {file = "fastparquet-2024.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3e3c5cdf2af0fc1b76f07daabd37b132c0f0086106b2fc801ea046739ddabee0"},
+    {file = "fastparquet-2024.2.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ea1503bac0b1457c016a748064823d312806e506f3a8b9226935def4be3fffdc"},
+    {file = "fastparquet-2024.2.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:b76febb17f2261e1aa8bdf11b3459ee9cca19ced25744b940c3922b7d93862f9"},
+    {file = "fastparquet-2024.2.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:6a14579bbe2fab4f5f43685503b4142d8b0eb7965ee176704ae1697590143cd1"},
+    {file = "fastparquet-2024.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:0c1edc578f7a9919d1062bc3184c0c64d5c4e986ab3fa9c75f53561bb7364d7f"},
+    {file = "fastparquet-2024.2.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:cebc1adc7c3a1aed70c752f3fde5e4df094dafba24e60d6501d7963e77047e7e"},
+    {file = "fastparquet-2024.2.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:c26266910e42190f3ba043647b4c1e37e8626981a0366432a498bdf1e10c0bd1"},
+    {file = "fastparquet-2024.2.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ee37d9273e383811f10bd379990851b53df606cfaa046cae53826b6b14f0a33d"},
+    {file = "fastparquet-2024.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:42babeafac01ab24ea1edc7f626c0744c312d60ba6a7189b08c8e7d1c374bfd3"},
+    {file = "fastparquet-2024.2.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:b7a620b87e83c098a46611b901c456403c9a04ba526e4a615750d6704092e1eb"},
+    {file = "fastparquet-2024.2.0-cp312-cp312-win_amd64.whl", hash = "sha256:e6f544d65b9f826a149010e3fd5121510e0a1a44c62f1b274aea4a41a8f3dbcd"},
+    {file = "fastparquet-2024.2.0-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:bf6df4a9c781e32dc10432e78ee82c3c8750e9975a4e2d29aecffc1f2323a418"},
+    {file = "fastparquet-2024.2.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:ee36f1ea8f08cb9b8710161eee4e752e74f34ef3e7aebc58db4e5468d29ff34c"},
+    {file = "fastparquet-2024.2.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cd4b8133f5fa43c497d151d4d00337f9b0614993116a61c61e563a003eb0811e"},
+    {file = "fastparquet-2024.2.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6509837887e35bdcb08ba252eeb930b1056e129b6d31c14901443339567ee95a"},
+    {file = "fastparquet-2024.2.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f369dcc860b176739826ed67ea230f243334df5c5b3047ac10b0a365ec469082"},
+    {file = "fastparquet-2024.2.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:fe1b88f51687566eac9fa94f7ce4f17b8df9e4b7ba8f7d37f383e7140414fe98"},
+    {file = "fastparquet-2024.2.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:d2711f30720c4f80654c191ecb21d2b1b7351be1f6763c70936bdbab095f0b54"},
+    {file = "fastparquet-2024.2.0-cp38-cp38-win_amd64.whl", hash = "sha256:52603d24d19522753e21b1794d99bb295688e33d1a04b61a5c0e9eb4884ba342"},
+    {file = "fastparquet-2024.2.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:c6affd18ed2608976739b47befce9f80f7848209c892ccb1001d494296af33af"},
+    {file = "fastparquet-2024.2.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:1a7314e654a06cfc68a50bfc61bbacc548257d8742fbecfe0418c3b0d4295c04"},
+    {file = "fastparquet-2024.2.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fba0fcba4ffd60ab23d24486f85733a5cc1fcf46d1286c9dc3eed329809e9ee3"},
+    {file = "fastparquet-2024.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dace50138c81c6f70acfff91a7a15acc85e3d45be0edbcf164f26fd86cf3c7a5"},
+    {file = "fastparquet-2024.2.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:dd45a7973afe651d7fdb6b836fa1f9177d318de20211a28f4580d9af5c2aacbb"},
+    {file = "fastparquet-2024.2.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:33121c1596bb4d672579969a4901730f555447204c7c2573621803f7990cd309"},
+    {file = "fastparquet-2024.2.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:b5131d77a6c4cdfe3b00baa7eb95602c7f09d955c5490dd3bc0ec0e290ee4010"},
+    {file = "fastparquet-2024.2.0-cp39-cp39-win_amd64.whl", hash = "sha256:06736e5bb0827f861ac0901310baedf7e7b5f52dfcd89d435963ae328203597c"},
+    {file = "fastparquet-2024.2.0.tar.gz", hash = "sha256:81a8f60c51793eb2436b4fdbbf115ff8578a4a457a179240bc08f9d9573d57a4"},
+]
+
+[package.dependencies]
+cramjam = ">=2.3"
+fsspec = "*"
+numpy = ">=1.20.3"
+packaging = "*"
+pandas = ">=1.5.0"
+
+[package.extras]
+lzo = ["python-lzo"]
+
 [[package]]
 name = "feedfinder2"
 version = "0.0.4"
@@ -2998,6 +3190,20 @@ typing-extensions = {version = ">=3.7.4", markers = "python_version < \"3.9\""}
 [package.extras]
 dev = ["black (==23.3.0)", "build (==0.10.0)", "check-manifest (==0.49)", "click (==8.1.3)", "coverage (==7.2.7)", "exceptiongroup (==1.1.1)", "iniconfig (==2.0.0)", "mypy (==1.4.1)", "mypy-extensions (==1.0.0)", "packaging (==23.1)", "pathspec (==0.11.1)", "platformdirs (==3.8.0)", "pluggy (==1.2.0)", "pyproject-hooks (==1.0.0)", "pytest (==7.4.0)", "pytest-cov (==4.1.0)", "tomli (==2.0.1)", "typing-extensions (==4.7.0)"]
 
+[[package]]
+name = "intel-openmp"
+version = "2021.4.0"
+description = "Intel OpenMP* Runtime Library"
+optional = false
+python-versions = "*"
+files = [
+    {file = "intel_openmp-2021.4.0-py2.py3-none-macosx_10_15_x86_64.macosx_11_0_x86_64.whl", hash = "sha256:41c01e266a7fdb631a7609191709322da2bbf24b252ba763f125dd651bcc7675"},
+    {file = "intel_openmp-2021.4.0-py2.py3-none-manylinux1_i686.whl", hash = "sha256:3b921236a38384e2016f0f3d65af6732cf2c12918087128a9163225451e776f2"},
+    {file = "intel_openmp-2021.4.0-py2.py3-none-manylinux1_x86_64.whl", hash = "sha256:e2240ab8d01472fed04f3544a878cda5da16c26232b7ea1b59132dbfb48b186e"},
+    {file = "intel_openmp-2021.4.0-py2.py3-none-win32.whl", hash = "sha256:6e863d8fd3d7e8ef389d52cf97a50fe2afe1a19247e8c0d168ce021546f96fc9"},
+    {file = "intel_openmp-2021.4.0-py2.py3-none-win_amd64.whl", hash = "sha256:eef4c8bcc8acefd7f5cd3b9384dbf73d59e2c99fc56545712ded913f43c4a94f"},
+]
+
 [[package]]
 name = "ipykernel"
 version = "6.29.3"
@@ -4154,6 +4360,24 @@ files = [
     {file = "mistune-3.0.2.tar.gz", hash = "sha256:fc7f93ded930c92394ef2cb6f04a8aabab4117a91449e72dcc8dfa646a508be8"},
 ]
 
+[[package]]
+name = "mkl"
+version = "2021.4.0"
+description = "Intel® oneAPI Math Kernel Library"
+optional = false
+python-versions = "*"
+files = [
+    {file = "mkl-2021.4.0-py2.py3-none-macosx_10_15_x86_64.macosx_11_0_x86_64.whl", hash = "sha256:67460f5cd7e30e405b54d70d1ed3ca78118370b65f7327d495e9c8847705e2fb"},
+    {file = "mkl-2021.4.0-py2.py3-none-manylinux1_i686.whl", hash = "sha256:636d07d90e68ccc9630c654d47ce9fdeb036bb46e2b193b3a9ac8cfea683cce5"},
+    {file = "mkl-2021.4.0-py2.py3-none-manylinux1_x86_64.whl", hash = "sha256:398dbf2b0d12acaf54117a5210e8f191827f373d362d796091d161f610c1ebfb"},
+    {file = "mkl-2021.4.0-py2.py3-none-win32.whl", hash = "sha256:439c640b269a5668134e3dcbcea4350459c4a8bc46469669b2d67e07e3d330e8"},
+    {file = "mkl-2021.4.0-py2.py3-none-win_amd64.whl", hash = "sha256:ceef3cafce4c009dd25f65d7ad0d833a0fbadc3d8903991ec92351fe5de1e718"},
+]
+
+[package.dependencies]
+intel-openmp = "==2021.*"
+tbb = "==2021.*"
+
 [[package]]
 name = "mlflow-skinny"
 version = "2.11.1"
@@ -4215,7 +4439,7 @@ zstd = ["pymongo[zstd] (>=4.5,<5)"]
 name = "mpmath"
 version = "1.3.0"
 description = "Python library for arbitrary-precision floating-point arithmetic"
-optional = true
+optional = false
 python-versions = "*"
 files = [
     {file = "mpmath-1.3.0-py3-none-any.whl", hash = "sha256:a0b2b9fe80bbcd81a6647ff13108738cfb482d481d826cc0e02f5b35e5c88d2c"},
@@ -4639,6 +4863,24 @@ files = [
     {file = "nest_asyncio-1.6.0.tar.gz", hash = "sha256:6f172d5449aca15afd6c646851f4e31e02c598d553a667e38cafa997cfec55fe"},
 ]
 
+[[package]]
+name = "networkx"
+version = "3.1"
+description = "Python package for creating and manipulating graphs and networks"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "networkx-3.1-py3-none-any.whl", hash = "sha256:4f33f68cb2afcf86f28a45f43efc27a9386b535d567d2127f8f61d51dec58d36"},
+    {file = "networkx-3.1.tar.gz", hash = "sha256:de346335408f84de0eada6ff9fafafff9bcda11f0a0dfaa931133debb146ab61"},
+]
+
+[package.extras]
+default = ["matplotlib (>=3.4)", "numpy (>=1.20)", "pandas (>=1.3)", "scipy (>=1.8)"]
+developer = ["mypy (>=1.1)", "pre-commit (>=3.2)"]
+doc = ["nb2plots (>=0.6)", "numpydoc (>=1.5)", "pillow (>=9.4)", "pydata-sphinx-theme (>=0.13)", "sphinx (>=6.1)", "sphinx-gallery (>=0.12)", "texext (>=0.6.7)"]
+extra = ["lxml (>=4.6)", "pydot (>=1.4.2)", "pygraphviz (>=1.10)", "sympy (>=1.10)"]
+test = ["codecov (>=2.1)", "pytest (>=7.2)", "pytest-cov (>=4.0)"]
+
 [[package]]
 name = "newspaper3k"
 version = "0.2.8"
@@ -4665,6 +4907,33 @@ requests = ">=2.10.0"
 tinysegmenter = "0.3"
 tldextract = ">=2.0.1"
 
+[[package]]
+name = "ninja"
+version = "1.11.1.1"
+description = "Ninja is a small build system with a focus on speed"
+optional = false
+python-versions = "*"
+files = [
+    {file = "ninja-1.11.1.1-py2.py3-none-macosx_10_9_universal2.macosx_10_9_x86_64.macosx_11_0_arm64.macosx_11_0_universal2.whl", hash = "sha256:376889c76d87b95b5719fdd61dd7db193aa7fd4432e5d52d2e44e4c497bdbbee"},
+    {file = "ninja-1.11.1.1-py2.py3-none-manylinux1_i686.manylinux_2_5_i686.whl", hash = "sha256:ecf80cf5afd09f14dcceff28cb3f11dc90fb97c999c89307aea435889cb66877"},
+    {file = "ninja-1.11.1.1-py2.py3-none-manylinux1_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:84502ec98f02a037a169c4b0d5d86075eaf6afc55e1879003d6cab51ced2ea4b"},
+    {file = "ninja-1.11.1.1-py2.py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:73b93c14046447c7c5cc892433d4fae65d6364bec6685411cb97a8bcf815f93a"},
+    {file = "ninja-1.11.1.1-py2.py3-none-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:18302d96a5467ea98b68e1cae1ae4b4fb2b2a56a82b955193c637557c7273dbd"},
+    {file = "ninja-1.11.1.1-py2.py3-none-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:aad34a70ef15b12519946c5633344bc775a7656d789d9ed5fdb0d456383716ef"},
+    {file = "ninja-1.11.1.1-py2.py3-none-musllinux_1_1_aarch64.whl", hash = "sha256:d491fc8d89cdcb416107c349ad1e3a735d4c4af5e1cb8f5f727baca6350fdaea"},
+    {file = "ninja-1.11.1.1-py2.py3-none-musllinux_1_1_i686.whl", hash = "sha256:7563ce1d9fe6ed5af0b8dd9ab4a214bf4ff1f2f6fd6dc29f480981f0f8b8b249"},
+    {file = "ninja-1.11.1.1-py2.py3-none-musllinux_1_1_ppc64le.whl", hash = "sha256:9df724344202b83018abb45cb1efc22efd337a1496514e7e6b3b59655be85205"},
+    {file = "ninja-1.11.1.1-py2.py3-none-musllinux_1_1_s390x.whl", hash = "sha256:3e0f9be5bb20d74d58c66cc1c414c3e6aeb45c35b0d0e41e8d739c2c0d57784f"},
+    {file = "ninja-1.11.1.1-py2.py3-none-musllinux_1_1_x86_64.whl", hash = "sha256:76482ba746a2618eecf89d5253c0d1e4f1da1270d41e9f54dfbd91831b0f6885"},
+    {file = "ninja-1.11.1.1-py2.py3-none-win32.whl", hash = "sha256:fa2ba9d74acfdfbfbcf06fad1b8282de8a7a8c481d9dee45c859a8c93fcc1082"},
+    {file = "ninja-1.11.1.1-py2.py3-none-win_amd64.whl", hash = "sha256:95da904130bfa02ea74ff9c0116b4ad266174fafb1c707aa50212bc7859aebf1"},
+    {file = "ninja-1.11.1.1-py2.py3-none-win_arm64.whl", hash = "sha256:185e0641bde601e53841525c4196278e9aaf4463758da6dd1e752c0a0f54136a"},
+    {file = "ninja-1.11.1.1.tar.gz", hash = "sha256:9d793b08dd857e38d0b6ffe9e6b7145d7c485a42dcfea04905ca0cdb6017cc3c"},
+]
+
+[package.extras]
+test = ["codecov (>=2.0.5)", "coverage (>=4.2)", "flake8 (>=3.0.4)", "pytest (>=4.5.0)", "pytest-cov (>=2.7.1)", "pytest-runner (>=5.1)", "pytest-virtualenv (>=1.7.0)", "virtualenv (>=15.0.3)"]
+
 [[package]]
 name = "nltk"
 version = "3.8.1"
@@ -4809,6 +5078,148 @@ files = [
     {file = "numpy-1.24.4.tar.gz", hash = "sha256:80f5e3a4e498641401868df4208b74581206afbee7cf7b8329daae82676d9463"},
 ]
 
+[[package]]
+name = "nvidia-cublas-cu12"
+version = "12.1.3.1"
+description = "CUBLAS native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl", hash = "sha256:ee53ccca76a6fc08fb9701aa95b6ceb242cdaab118c3bb152af4e579af792728"},
+    {file = "nvidia_cublas_cu12-12.1.3.1-py3-none-win_amd64.whl", hash = "sha256:2b964d60e8cf11b5e1073d179d85fa340c120e99b3067558f3cf98dd69d02906"},
+]
+
+[[package]]
+name = "nvidia-cuda-cupti-cu12"
+version = "12.1.105"
+description = "CUDA profiling tools runtime libs."
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:e54fde3983165c624cb79254ae9818a456eb6e87a7fd4d56a2352c24ee542d7e"},
+    {file = "nvidia_cuda_cupti_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:bea8236d13a0ac7190bd2919c3e8e6ce1e402104276e6f9694479e48bb0eb2a4"},
+]
+
+[[package]]
+name = "nvidia-cuda-nvrtc-cu12"
+version = "12.1.105"
+description = "NVRTC native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:339b385f50c309763ca65456ec75e17bbefcbbf2893f462cb8b90584cd27a1c2"},
+    {file = "nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:0a98a522d9ff138b96c010a65e145dc1b4850e9ecb75a0172371793752fd46ed"},
+]
+
+[[package]]
+name = "nvidia-cuda-runtime-cu12"
+version = "12.1.105"
+description = "CUDA Runtime native Libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:6e258468ddf5796e25f1dc591a31029fa317d97a0a94ed93468fc86301d61e40"},
+    {file = "nvidia_cuda_runtime_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:dfb46ef84d73fababab44cf03e3b83f80700d27ca300e537f85f636fac474344"},
+]
+
+[[package]]
+name = "nvidia-cudnn-cu12"
+version = "8.9.2.26"
+description = "cuDNN runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl", hash = "sha256:5ccb288774fdfb07a7e7025ffec286971c06d8d7b4fb162525334616d7629ff9"},
+]
+
+[package.dependencies]
+nvidia-cublas-cu12 = "*"
+
+[[package]]
+name = "nvidia-cufft-cu12"
+version = "11.0.2.54"
+description = "CUFFT native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl", hash = "sha256:794e3948a1aa71fd817c3775866943936774d1c14e7628c74f6f7417224cdf56"},
+    {file = "nvidia_cufft_cu12-11.0.2.54-py3-none-win_amd64.whl", hash = "sha256:d9ac353f78ff89951da4af698f80870b1534ed69993f10a4cf1d96f21357e253"},
+]
+
+[[package]]
+name = "nvidia-curand-cu12"
+version = "10.3.2.106"
+description = "CURAND native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:9d264c5036dde4e64f1de8c50ae753237c12e0b1348738169cd0f8a536c0e1e0"},
+    {file = "nvidia_curand_cu12-10.3.2.106-py3-none-win_amd64.whl", hash = "sha256:75b6b0c574c0037839121317e17fd01f8a69fd2ef8e25853d826fec30bdba74a"},
+]
+
+[[package]]
+name = "nvidia-cusolver-cu12"
+version = "11.4.5.107"
+description = "CUDA solver native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl", hash = "sha256:8a7ec542f0412294b15072fa7dab71d31334014a69f953004ea7a118206fe0dd"},
+    {file = "nvidia_cusolver_cu12-11.4.5.107-py3-none-win_amd64.whl", hash = "sha256:74e0c3a24c78612192a74fcd90dd117f1cf21dea4822e66d89e8ea80e3cd2da5"},
+]
+
+[package.dependencies]
+nvidia-cublas-cu12 = "*"
+nvidia-cusparse-cu12 = "*"
+nvidia-nvjitlink-cu12 = "*"
+
+[[package]]
+name = "nvidia-cusparse-cu12"
+version = "12.1.0.106"
+description = "CUSPARSE native runtime libraries"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl", hash = "sha256:f3b50f42cf363f86ab21f720998517a659a48131e8d538dc02f8768237bd884c"},
+    {file = "nvidia_cusparse_cu12-12.1.0.106-py3-none-win_amd64.whl", hash = "sha256:b798237e81b9719373e8fae8d4f091b70a0cf09d9d85c95a557e11df2d8e9a5a"},
+]
+
+[package.dependencies]
+nvidia-nvjitlink-cu12 = "*"
+
+[[package]]
+name = "nvidia-nccl-cu12"
+version = "2.20.5"
+description = "NVIDIA Collective Communication Library (NCCL) Runtime"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_aarch64.whl", hash = "sha256:1fc150d5c3250b170b29410ba682384b14581db722b2531b0d8d33c595f33d01"},
+    {file = "nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl", hash = "sha256:057f6bf9685f75215d0c53bf3ac4a10b3e6578351de307abad9e18a99182af56"},
+]
+
+[[package]]
+name = "nvidia-nvjitlink-cu12"
+version = "12.4.127"
+description = "Nvidia JIT LTO Library"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl", hash = "sha256:06b3b9b25bf3f8af351d664978ca26a16d2c5127dbd53c0497e28d1fb9611d57"},
+    {file = "nvidia_nvjitlink_cu12-12.4.127-py3-none-win_amd64.whl", hash = "sha256:fd9020c501d27d135f983c6d3e244b197a7ccad769e34df53a42e276b0e25fa1"},
+]
+
+[[package]]
+name = "nvidia-nvtx-cu12"
+version = "12.1.105"
+description = "NVIDIA Tools Extension"
+optional = false
+python-versions = ">=3"
+files = [
+    {file = "nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl", hash = "sha256:dc21cf308ca5691e7c04d962e213f8a4aa9bbfa23d95412f452254c2caeb09e5"},
+    {file = "nvidia_nvtx_cu12-12.1.105-py3-none-win_amd64.whl", hash = "sha256:65f4d98982b31b60026e0e6de73fbdfc09d08a96f4656dd3665ca616a11e1e82"},
+]
+
 [[package]]
 name = "nvidia-riva-client"
 version = "2.14.0"
@@ -7434,6 +7845,128 @@ files = [
     {file = "ruff-0.1.15.tar.gz", hash = "sha256:f6dfa8c1b21c913c326919056c390966648b680966febcb796cc9d1aaab8564e"},
 ]
 
+[[package]]
+name = "safetensors"
+version = "0.4.3"
+description = ""
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "safetensors-0.4.3-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:dcf5705cab159ce0130cd56057f5f3425023c407e170bca60b4868048bae64fd"},
+    {file = "safetensors-0.4.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:bb4f8c5d0358a31e9a08daeebb68f5e161cdd4018855426d3f0c23bb51087055"},
+    {file = "safetensors-0.4.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:70a5319ef409e7f88686a46607cbc3c428271069d8b770076feaf913664a07ac"},
+    {file = "safetensors-0.4.3-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:fb9c65bd82f9ef3ce4970dc19ee86be5f6f93d032159acf35e663c6bea02b237"},
+    {file = "safetensors-0.4.3-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:edb5698a7bc282089f64c96c477846950358a46ede85a1c040e0230344fdde10"},
+    {file = "safetensors-0.4.3-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:efcc860be094b8d19ac61b452ec635c7acb9afa77beb218b1d7784c6d41fe8ad"},
+    {file = "safetensors-0.4.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d88b33980222085dd6001ae2cad87c6068e0991d4f5ccf44975d216db3b57376"},
+    {file = "safetensors-0.4.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:5fc6775529fb9f0ce2266edd3e5d3f10aab068e49f765e11f6f2a63b5367021d"},
+    {file = "safetensors-0.4.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:9c6ad011c1b4e3acff058d6b090f1da8e55a332fbf84695cf3100c649cc452d1"},
+    {file = "safetensors-0.4.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:8c496c5401c1b9c46d41a7688e8ff5b0310a3b9bae31ce0f0ae870e1ea2b8caf"},
+    {file = "safetensors-0.4.3-cp310-none-win32.whl", hash = "sha256:38e2a8666178224a51cca61d3cb4c88704f696eac8f72a49a598a93bbd8a4af9"},
+    {file = "safetensors-0.4.3-cp310-none-win_amd64.whl", hash = "sha256:393e6e391467d1b2b829c77e47d726f3b9b93630e6a045b1d1fca67dc78bf632"},
+    {file = "safetensors-0.4.3-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:22f3b5d65e440cec0de8edaa672efa888030802e11c09b3d6203bff60ebff05a"},
+    {file = "safetensors-0.4.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:7c4fa560ebd4522adddb71dcd25d09bf211b5634003f015a4b815b7647d62ebe"},
+    {file = "safetensors-0.4.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e9afd5358719f1b2cf425fad638fc3c887997d6782da317096877e5b15b2ce93"},
+    {file = "safetensors-0.4.3-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:d8c5093206ef4b198600ae484230402af6713dab1bd5b8e231905d754022bec7"},
+    {file = "safetensors-0.4.3-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e0b2104df1579d6ba9052c0ae0e3137c9698b2d85b0645507e6fd1813b70931a"},
+    {file = "safetensors-0.4.3-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8cf18888606dad030455d18f6c381720e57fc6a4170ee1966adb7ebc98d4d6a3"},
+    {file = "safetensors-0.4.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0bf4f9d6323d9f86eef5567eabd88f070691cf031d4c0df27a40d3b4aaee755b"},
+    {file = "safetensors-0.4.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:585c9ae13a205807b63bef8a37994f30c917ff800ab8a1ca9c9b5d73024f97ee"},
+    {file = "safetensors-0.4.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:faefeb3b81bdfb4e5a55b9bbdf3d8d8753f65506e1d67d03f5c851a6c87150e9"},
+    {file = "safetensors-0.4.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:befdf0167ad626f22f6aac6163477fcefa342224a22f11fdd05abb3995c1783c"},
+    {file = "safetensors-0.4.3-cp311-none-win32.whl", hash = "sha256:a7cef55929dcbef24af3eb40bedec35d82c3c2fa46338bb13ecf3c5720af8a61"},
+    {file = "safetensors-0.4.3-cp311-none-win_amd64.whl", hash = "sha256:840b7ac0eff5633e1d053cc9db12fdf56b566e9403b4950b2dc85393d9b88d67"},
+    {file = "safetensors-0.4.3-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:22d21760dc6ebae42e9c058d75aa9907d9f35e38f896e3c69ba0e7b213033856"},
+    {file = "safetensors-0.4.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:8d22c1a10dff3f64d0d68abb8298a3fd88ccff79f408a3e15b3e7f637ef5c980"},
+    {file = "safetensors-0.4.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b1648568667f820b8c48317c7006221dc40aced1869908c187f493838a1362bc"},
+    {file = "safetensors-0.4.3-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:446e9fe52c051aeab12aac63d1017e0f68a02a92a027b901c4f8e931b24e5397"},
+    {file = "safetensors-0.4.3-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:fef5d70683643618244a4f5221053567ca3e77c2531e42ad48ae05fae909f542"},
+    {file = "safetensors-0.4.3-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2a1f4430cc0c9d6afa01214a4b3919d0a029637df8e09675ceef1ca3f0dfa0df"},
+    {file = "safetensors-0.4.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2d603846a8585b9432a0fd415db1d4c57c0f860eb4aea21f92559ff9902bae4d"},
+    {file = "safetensors-0.4.3-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:a844cdb5d7cbc22f5f16c7e2a0271170750763c4db08381b7f696dbd2c78a361"},
+    {file = "safetensors-0.4.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:88887f69f7a00cf02b954cdc3034ffb383b2303bc0ab481d4716e2da51ddc10e"},
+    {file = "safetensors-0.4.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:ee463219d9ec6c2be1d331ab13a8e0cd50d2f32240a81d498266d77d07b7e71e"},
+    {file = "safetensors-0.4.3-cp312-none-win32.whl", hash = "sha256:d0dd4a1db09db2dba0f94d15addc7e7cd3a7b0d393aa4c7518c39ae7374623c3"},
+    {file = "safetensors-0.4.3-cp312-none-win_amd64.whl", hash = "sha256:d14d30c25897b2bf19b6fb5ff7e26cc40006ad53fd4a88244fdf26517d852dd7"},
+    {file = "safetensors-0.4.3-cp37-cp37m-macosx_10_12_x86_64.whl", hash = "sha256:d1456f814655b224d4bf6e7915c51ce74e389b413be791203092b7ff78c936dd"},
+    {file = "safetensors-0.4.3-cp37-cp37m-macosx_11_0_arm64.whl", hash = "sha256:455d538aa1aae4a8b279344a08136d3f16334247907b18a5c3c7fa88ef0d3c46"},
+    {file = "safetensors-0.4.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cf476bca34e1340ee3294ef13e2c625833f83d096cfdf69a5342475602004f95"},
+    {file = "safetensors-0.4.3-cp37-cp37m-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:02ef3a24face643456020536591fbd3c717c5abaa2737ec428ccbbc86dffa7a4"},
+    {file = "safetensors-0.4.3-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7de32d0d34b6623bb56ca278f90db081f85fb9c5d327e3c18fd23ac64f465768"},
+    {file = "safetensors-0.4.3-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2a0deb16a1d3ea90c244ceb42d2c6c276059616be21a19ac7101aa97da448faf"},
+    {file = "safetensors-0.4.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c59d51f182c729f47e841510b70b967b0752039f79f1de23bcdd86462a9b09ee"},
+    {file = "safetensors-0.4.3-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:1f598b713cc1a4eb31d3b3203557ac308acf21c8f41104cdd74bf640c6e538e3"},
+    {file = "safetensors-0.4.3-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:5757e4688f20df083e233b47de43845d1adb7e17b6cf7da5f8444416fc53828d"},
+    {file = "safetensors-0.4.3-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:fe746d03ed8d193674a26105e4f0fe6c726f5bb602ffc695b409eaf02f04763d"},
+    {file = "safetensors-0.4.3-cp37-none-win32.whl", hash = "sha256:0d5ffc6a80f715c30af253e0e288ad1cd97a3d0086c9c87995e5093ebc075e50"},
+    {file = "safetensors-0.4.3-cp37-none-win_amd64.whl", hash = "sha256:a11c374eb63a9c16c5ed146457241182f310902bd2a9c18255781bb832b6748b"},
+    {file = "safetensors-0.4.3-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:b1e31be7945f66be23f4ec1682bb47faa3df34cb89fc68527de6554d3c4258a4"},
+    {file = "safetensors-0.4.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:03a4447c784917c9bf01d8f2ac5080bc15c41692202cd5f406afba16629e84d6"},
+    {file = "safetensors-0.4.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d244bcafeb1bc06d47cfee71727e775bca88a8efda77a13e7306aae3813fa7e4"},
+    {file = "safetensors-0.4.3-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:53c4879b9c6bd7cd25d114ee0ef95420e2812e676314300624594940a8d6a91f"},
+    {file = "safetensors-0.4.3-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:74707624b81f1b7f2b93f5619d4a9f00934d5948005a03f2c1845ffbfff42212"},
+    {file = "safetensors-0.4.3-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0d52c958dc210265157573f81d34adf54e255bc2b59ded6218500c9b15a750eb"},
+    {file = "safetensors-0.4.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6f9568f380f513a60139971169c4a358b8731509cc19112369902eddb33faa4d"},
+    {file = "safetensors-0.4.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:0d9cd8e1560dfc514b6d7859247dc6a86ad2f83151a62c577428d5102d872721"},
+    {file = "safetensors-0.4.3-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:89f9f17b0dacb913ed87d57afbc8aad85ea42c1085bd5de2f20d83d13e9fc4b2"},
+    {file = "safetensors-0.4.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:1139eb436fd201c133d03c81209d39ac57e129f5e74e34bb9ab60f8d9b726270"},
+    {file = "safetensors-0.4.3-cp38-none-win32.whl", hash = "sha256:d9c289f140a9ae4853fc2236a2ffc9a9f2d5eae0cb673167e0f1b8c18c0961ac"},
+    {file = "safetensors-0.4.3-cp38-none-win_amd64.whl", hash = "sha256:622afd28968ef3e9786562d352659a37de4481a4070f4ebac883f98c5836563e"},
+    {file = "safetensors-0.4.3-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:8651c7299cbd8b4161a36cd6a322fa07d39cd23535b144d02f1c1972d0c62f3c"},
+    {file = "safetensors-0.4.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:e375d975159ac534c7161269de24ddcd490df2157b55c1a6eeace6cbb56903f0"},
+    {file = "safetensors-0.4.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:084fc436e317f83f7071fc6a62ca1c513b2103db325cd09952914b50f51cf78f"},
+    {file = "safetensors-0.4.3-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:41a727a7f5e6ad9f1db6951adee21bbdadc632363d79dc434876369a17de6ad6"},
+    {file = "safetensors-0.4.3-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e7dbbde64b6c534548696808a0e01276d28ea5773bc9a2dfb97a88cd3dffe3df"},
+    {file = "safetensors-0.4.3-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:bbae3b4b9d997971431c346edbfe6e41e98424a097860ee872721e176040a893"},
+    {file = "safetensors-0.4.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:01e4b22e3284cd866edeabe4f4d896229495da457229408d2e1e4810c5187121"},
+    {file = "safetensors-0.4.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:0dd37306546b58d3043eb044c8103a02792cc024b51d1dd16bd3dd1f334cb3ed"},
+    {file = "safetensors-0.4.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:d8815b5e1dac85fc534a97fd339e12404db557878c090f90442247e87c8aeaea"},
+    {file = "safetensors-0.4.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:e011cc162503c19f4b1fd63dfcddf73739c7a243a17dac09b78e57a00983ab35"},
+    {file = "safetensors-0.4.3-cp39-none-win32.whl", hash = "sha256:01feb3089e5932d7e662eda77c3ecc389f97c0883c4a12b5cfdc32b589a811c3"},
+    {file = "safetensors-0.4.3-cp39-none-win_amd64.whl", hash = "sha256:3f9cdca09052f585e62328c1c2923c70f46814715c795be65f0b93f57ec98a02"},
+    {file = "safetensors-0.4.3-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:1b89381517891a7bb7d1405d828b2bf5d75528299f8231e9346b8eba092227f9"},
+    {file = "safetensors-0.4.3-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:cd6fff9e56df398abc5866b19a32124815b656613c1c5ec0f9350906fd798aac"},
+    {file = "safetensors-0.4.3-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:840caf38d86aa7014fe37ade5d0d84e23dcfbc798b8078015831996ecbc206a3"},
+    {file = "safetensors-0.4.3-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f9650713b2cfa9537a2baf7dd9fee458b24a0aaaa6cafcea8bdd5fb2b8efdc34"},
+    {file = "safetensors-0.4.3-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:e4119532cd10dba04b423e0f86aecb96cfa5a602238c0aa012f70c3a40c44b50"},
+    {file = "safetensors-0.4.3-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:e066e8861eef6387b7c772344d1fe1f9a72800e04ee9a54239d460c400c72aab"},
+    {file = "safetensors-0.4.3-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:90964917f5b0fa0fa07e9a051fbef100250c04d150b7026ccbf87a34a54012e0"},
+    {file = "safetensors-0.4.3-pp37-pypy37_pp73-macosx_10_12_x86_64.whl", hash = "sha256:c41e1893d1206aa7054029681778d9a58b3529d4c807002c156d58426c225173"},
+    {file = "safetensors-0.4.3-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ae7613a119a71a497d012ccc83775c308b9c1dab454806291427f84397d852fd"},
+    {file = "safetensors-0.4.3-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4f9bac020faba7f5dc481e881b14b6425265feabb5bfc552551d21189c0eddc3"},
+    {file = "safetensors-0.4.3-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:420a98f593ff9930f5822560d14c395ccbc57342ddff3b463bc0b3d6b1951550"},
+    {file = "safetensors-0.4.3-pp37-pypy37_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:f5e6883af9a68c0028f70a4c19d5a6ab6238a379be36ad300a22318316c00cb0"},
+    {file = "safetensors-0.4.3-pp37-pypy37_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:cdd0a3b5da66e7f377474599814dbf5cbf135ff059cc73694de129b58a5e8a2c"},
+    {file = "safetensors-0.4.3-pp38-pypy38_pp73-macosx_10_12_x86_64.whl", hash = "sha256:9bfb92f82574d9e58401d79c70c716985dc049b635fef6eecbb024c79b2c46ad"},
+    {file = "safetensors-0.4.3-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:3615a96dd2dcc30eb66d82bc76cda2565f4f7bfa89fcb0e31ba3cea8a1a9ecbb"},
+    {file = "safetensors-0.4.3-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:868ad1b6fc41209ab6bd12f63923e8baeb1a086814cb2e81a65ed3d497e0cf8f"},
+    {file = "safetensors-0.4.3-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b7ffba80aa49bd09195145a7fd233a7781173b422eeb995096f2b30591639517"},
+    {file = "safetensors-0.4.3-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:c0acbe31340ab150423347e5b9cc595867d814244ac14218932a5cf1dd38eb39"},
+    {file = "safetensors-0.4.3-pp38-pypy38_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:19bbdf95de2cf64f25cd614c5236c8b06eb2cfa47cbf64311f4b5d80224623a3"},
+    {file = "safetensors-0.4.3-pp38-pypy38_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:b852e47eb08475c2c1bd8131207b405793bfc20d6f45aff893d3baaad449ed14"},
+    {file = "safetensors-0.4.3-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:5d07cbca5b99babb692d76d8151bec46f461f8ad8daafbfd96b2fca40cadae65"},
+    {file = "safetensors-0.4.3-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:1ab6527a20586d94291c96e00a668fa03f86189b8a9defa2cdd34a1a01acc7d5"},
+    {file = "safetensors-0.4.3-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:02318f01e332cc23ffb4f6716e05a492c5f18b1d13e343c49265149396284a44"},
+    {file = "safetensors-0.4.3-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ec4b52ce9a396260eb9731eb6aea41a7320de22ed73a1042c2230af0212758ce"},
+    {file = "safetensors-0.4.3-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:018b691383026a2436a22b648873ed11444a364324e7088b99cd2503dd828400"},
+    {file = "safetensors-0.4.3-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:309b10dbcab63269ecbf0e2ca10ce59223bb756ca5d431ce9c9eeabd446569da"},
+    {file = "safetensors-0.4.3-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:b277482120df46e27a58082df06a15aebda4481e30a1c21eefd0921ae7e03f65"},
+    {file = "safetensors-0.4.3.tar.gz", hash = "sha256:2f85fc50c4e07a21e95c24e07460fe6f7e2859d0ce88092838352b798ce711c2"},
+]
+
+[package.extras]
+all = ["safetensors[jax]", "safetensors[numpy]", "safetensors[paddlepaddle]", "safetensors[pinned-tf]", "safetensors[quality]", "safetensors[testing]", "safetensors[torch]"]
+dev = ["safetensors[all]"]
+jax = ["flax (>=0.6.3)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)", "safetensors[numpy]"]
+mlx = ["mlx (>=0.0.9)"]
+numpy = ["numpy (>=1.21.6)"]
+paddlepaddle = ["paddlepaddle (>=2.4.1)", "safetensors[numpy]"]
+pinned-tf = ["safetensors[numpy]", "tensorflow (==2.11.0)"]
+quality = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "isort (>=5.5.4)"]
+tensorflow = ["safetensors[numpy]", "tensorflow (>=2.11.0)"]
+testing = ["h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "hypothesis (>=6.70.2)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "safetensors[numpy]", "setuptools-rust (>=1.5.2)"]
+torch = ["safetensors[numpy]", "torch (>=1.10)"]
+
 [[package]]
 name = "scikit-learn"
 version = "1.3.2"
@@ -7535,6 +8068,68 @@ nativelib = ["pyobjc-framework-Cocoa", "pywin32"]
 objc = ["pyobjc-framework-Cocoa"]
 win32 = ["pywin32"]
 
+[[package]]
+name = "sentencepiece"
+version = "0.2.0"
+description = "SentencePiece python wrapper"
+optional = false
+python-versions = "*"
+files = [
+    {file = "sentencepiece-0.2.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:188779e1298a1c8b8253c7d3ad729cb0a9891e5cef5e5d07ce4592c54869e227"},
+    {file = "sentencepiece-0.2.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:bed9cf85b296fa2b76fc2547b9cbb691a523864cebaee86304c43a7b4cb1b452"},
+    {file = "sentencepiece-0.2.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:d7b67e724bead13f18db6e1d10b6bbdc454af574d70efbb36f27d90387be1ca3"},
+    {file = "sentencepiece-0.2.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2fde4b08cfe237be4484c6c7c2e2c75fb862cfeab6bd5449ce4caeafd97b767a"},
+    {file = "sentencepiece-0.2.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4c378492056202d1c48a4979650981635fd97875a00eabb1f00c6a236b013b5e"},
+    {file = "sentencepiece-0.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1380ce6540a368de2ef6d7e6ba14ba8f3258df650d39ba7d833b79ee68a52040"},
+    {file = "sentencepiece-0.2.0-cp310-cp310-win32.whl", hash = "sha256:a1151d6a6dd4b43e552394aed0edfe9292820272f0194bd56c7c1660a0c06c3d"},
+    {file = "sentencepiece-0.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:d490142b0521ef22bc1085f061d922a2a6666175bb6b42e588ff95c0db6819b2"},
+    {file = "sentencepiece-0.2.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:17982700c4f6dbb55fa3594f3d7e5dd1c8659a274af3738e33c987d2a27c9d5c"},
+    {file = "sentencepiece-0.2.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:7c867012c0e8bcd5bdad0f791609101cb5c66acb303ab3270218d6debc68a65e"},
+    {file = "sentencepiece-0.2.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:7fd6071249c74f779c5b27183295b9202f8dedb68034e716784364443879eaa6"},
+    {file = "sentencepiece-0.2.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:27f90c55a65013cbb8f4d7aab0599bf925cde4adc67ae43a0d323677b5a1c6cb"},
+    {file = "sentencepiece-0.2.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b293734059ef656dcd65be62ff771507bea8fed0a711b6733976e1ed3add4553"},
+    {file = "sentencepiece-0.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e58b47f933aca74c6a60a79dcb21d5b9e47416256c795c2d58d55cec27f9551d"},
+    {file = "sentencepiece-0.2.0-cp311-cp311-win32.whl", hash = "sha256:c581258cf346b327c62c4f1cebd32691826306f6a41d8c4bec43b010dee08e75"},
+    {file = "sentencepiece-0.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:0993dbc665f4113017892f1b87c3904a44d0640eda510abcacdfb07f74286d36"},
+    {file = "sentencepiece-0.2.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:ea5f536e32ea8ec96086ee00d7a4a131ce583a1b18d130711707c10e69601cb2"},
+    {file = "sentencepiece-0.2.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:d0cb51f53b6aae3c36bafe41e86167c71af8370a039f542c43b0cce5ef24a68c"},
+    {file = "sentencepiece-0.2.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:3212121805afc58d8b00ab4e7dd1f8f76c203ddb9dc94aa4079618a31cf5da0f"},
+    {file = "sentencepiece-0.2.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2a3149e3066c2a75e0d68a43eb632d7ae728c7925b517f4c05c40f6f7280ce08"},
+    {file = "sentencepiece-0.2.0-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:632f3594d3e7ac8b367bca204cb3fd05a01d5b21455acd097ea4c0e30e2f63d7"},
+    {file = "sentencepiece-0.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f295105c6bdbb05bd5e1b0cafbd78ff95036f5d3641e7949455a3f4e5e7c3109"},
+    {file = "sentencepiece-0.2.0-cp312-cp312-win32.whl", hash = "sha256:fb89f811e5efd18bab141afc3fea3de141c3f69f3fe9e898f710ae7fe3aab251"},
+    {file = "sentencepiece-0.2.0-cp312-cp312-win_amd64.whl", hash = "sha256:7a673a72aab81fef5ebe755c6e0cc60087d1f3a4700835d40537183c1703a45f"},
+    {file = "sentencepiece-0.2.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:4547683f330289ec4f093027bfeb87f9ef023b2eb6f879fdc4a8187c7e0ffb90"},
+    {file = "sentencepiece-0.2.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7cd6175f7eaec7142d2bf6f6597ce7db4c9ac89acf93fcdb17410c3a8b781eeb"},
+    {file = "sentencepiece-0.2.0-cp36-cp36m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:859ba1acde782609a0910a26a60e16c191a82bf39b5621107552c0cd79fad00f"},
+    {file = "sentencepiece-0.2.0-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bcbbef6cc277f8f18f36959e305f10b1c620442d75addc79c21d7073ae581b50"},
+    {file = "sentencepiece-0.2.0-cp36-cp36m-win32.whl", hash = "sha256:536b934e244829e3fe6c4f198652cd82da48adb9aa145c9f00889542726dee3d"},
+    {file = "sentencepiece-0.2.0-cp36-cp36m-win_amd64.whl", hash = "sha256:0a91aaa3c769b52440df56fafda683b3aa48e3f2169cf7ee5b8c8454a7f3ae9b"},
+    {file = "sentencepiece-0.2.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:787e480ca4c1d08c9985a7eb1eae4345c107729c99e9b5a9a00f2575fc7d4b4b"},
+    {file = "sentencepiece-0.2.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f4d158189eb2ecffea3a51edf6d25e110b3678ec47f1a40f2d541eafbd8f6250"},
+    {file = "sentencepiece-0.2.0-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d1e5ca43013e8935f25457a4fca47e315780172c3e821b4b13a890668911c792"},
+    {file = "sentencepiece-0.2.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7140d9e5a74a0908493bb4a13f1f16a401297bd755ada4c707e842fbf6f0f5bf"},
+    {file = "sentencepiece-0.2.0-cp37-cp37m-win32.whl", hash = "sha256:6cf333625234f247ab357b0bd9836638405ea9082e1543d5b8408f014979dcbf"},
+    {file = "sentencepiece-0.2.0-cp37-cp37m-win_amd64.whl", hash = "sha256:ff88712338b01031910e8e61e7239aff3ce8869ee31a47df63cb38aadd591bea"},
+    {file = "sentencepiece-0.2.0-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:20813a68d4c221b1849c62c30e1281ea81687894d894b8d4a0f4677d9311e0f5"},
+    {file = "sentencepiece-0.2.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:926ef920ae2e8182db31d3f5d081ada57804e3e1d3a8c4ef8b117f9d9fb5a945"},
+    {file = "sentencepiece-0.2.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:89f65f69636b7e9c015b79dff9c9985a9bc7d19ded6f79ef9f1ec920fdd73ecf"},
+    {file = "sentencepiece-0.2.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0f67eae0dbe6f2d7d6ba50a354623d787c99965f068b81e145d53240198021b0"},
+    {file = "sentencepiece-0.2.0-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:98501e075f35dd1a1d5a20f65be26839fcb1938752ec61539af008a5aa6f510b"},
+    {file = "sentencepiece-0.2.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e3d1d2cc4882e8d6a1adf9d5927d7716f80617fc693385661caff21888972269"},
+    {file = "sentencepiece-0.2.0-cp38-cp38-win32.whl", hash = "sha256:b99a308a2e5e569031ab164b74e6fab0b6f37dfb493c32f7816225f4d411a6dd"},
+    {file = "sentencepiece-0.2.0-cp38-cp38-win_amd64.whl", hash = "sha256:cdb701eec783d3ec86b7cd4c763adad8eaf6b46db37ee1c36e5e6c44b3fe1b5f"},
+    {file = "sentencepiece-0.2.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:1e0f9c4d0a6b0af59b613175f019916e28ade076e21242fd5be24340d8a2f64a"},
+    {file = "sentencepiece-0.2.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:298f21cc1366eb60311aedba3169d30f885c363ddbf44214b0a587d2908141ad"},
+    {file = "sentencepiece-0.2.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3f1ec95aa1e5dab11f37ac7eff190493fd87770f7a8b81ebc9dd768d1a3c8704"},
+    {file = "sentencepiece-0.2.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7b06b70af54daa4b4904cbb90b4eb6d35c9f3252fdc86c9c32d5afd4d30118d8"},
+    {file = "sentencepiece-0.2.0-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:22e37bac44dd6603388cb598c64ff7a76e41ca774646f21c23aadfbf5a2228ab"},
+    {file = "sentencepiece-0.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0461324897735512a32d222e3d886e24ad6a499761952b6bda2a9ee6e4313ea5"},
+    {file = "sentencepiece-0.2.0-cp39-cp39-win32.whl", hash = "sha256:38aed822fb76435fa1f12185f10465a94ab9e51d5e8a9159e9a540ce926f0ffd"},
+    {file = "sentencepiece-0.2.0-cp39-cp39-win_amd64.whl", hash = "sha256:d8cf876516548b5a1d6ac4745d8b554f5c07891d55da557925e5c13ff0b4e6ad"},
+    {file = "sentencepiece-0.2.0.tar.gz", hash = "sha256:a52c19171daaf2e697dc6cbe67684e0fa341b1248966f6aebb541de654d15843"},
+]
+
 [[package]]
 name = "setuptools"
 version = "67.8.0"
@@ -7856,7 +8451,7 @@ snowflake = ["snowflake-connector-python (>=2.8.0)", "snowflake-snowpark-python
 name = "sympy"
 version = "1.12"
 description = "Computer algebra system (CAS) in Python"
-optional = true
+optional = false
 python-versions = ">=3.8"
 files = [
     {file = "sympy-1.12-py3-none-any.whl", hash = "sha256:c3588cd4295d0c0f603d0f2ae780587e64e2efeedb3521e46b9bb1d08d184fa5"},
@@ -7894,6 +8489,19 @@ files = [
 [package.extras]
 widechars = ["wcwidth"]
 
+[[package]]
+name = "tbb"
+version = "2021.12.0"
+description = "Intel® oneAPI Threading Building Blocks (oneTBB)"
+optional = false
+python-versions = "*"
+files = [
+    {file = "tbb-2021.12.0-py2.py3-none-manylinux1_i686.whl", hash = "sha256:f2cc9a7f8ababaa506cbff796ce97c3bf91062ba521e15054394f773375d81d8"},
+    {file = "tbb-2021.12.0-py2.py3-none-manylinux1_x86_64.whl", hash = "sha256:a925e9a7c77d3a46ae31c34b0bb7f801c4118e857d137b68f68a8e458fcf2bd7"},
+    {file = "tbb-2021.12.0-py3-none-win32.whl", hash = "sha256:b1725b30c174048edc8be70bd43bb95473f396ce895d91151a474d0fa9f450a8"},
+    {file = "tbb-2021.12.0-py3-none-win_amd64.whl", hash = "sha256:fc2772d850229f2f3df85f1109c4844c495a2db7433d38200959ee9265b34789"},
+]
+
 [[package]]
 name = "telethon"
 version = "1.34.0"
@@ -8251,6 +8859,60 @@ files = [
     {file = "toolz-0.12.1.tar.gz", hash = "sha256:ecca342664893f177a13dac0e6b41cbd8ac25a358e5f215316d43e2100224f4d"},
 ]
 
+[[package]]
+name = "torch"
+version = "2.3.0"
+description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration"
+optional = false
+python-versions = ">=3.8.0"
+files = [
+    {file = "torch-2.3.0-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:d8ea5a465dbfd8501f33c937d1f693176c9aef9d1c1b0ca1d44ed7b0a18c52ac"},
+    {file = "torch-2.3.0-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:09c81c5859a5b819956c6925a405ef1cdda393c9d8a01ce3851453f699d3358c"},
+    {file = "torch-2.3.0-cp310-cp310-win_amd64.whl", hash = "sha256:1bf023aa20902586f614f7682fedfa463e773e26c58820b74158a72470259459"},
+    {file = "torch-2.3.0-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:758ef938de87a2653bba74b91f703458c15569f1562bf4b6c63c62d9c5a0c1f5"},
+    {file = "torch-2.3.0-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:493d54ee2f9df100b5ce1d18c96dbb8d14908721f76351e908c9d2622773a788"},
+    {file = "torch-2.3.0-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:bce43af735c3da16cc14c7de2be7ad038e2fbf75654c2e274e575c6c05772ace"},
+    {file = "torch-2.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:729804e97b7cf19ae9ab4181f91f5e612af07956f35c8b2c8e9d9f3596a8e877"},
+    {file = "torch-2.3.0-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:d24e328226d8e2af7cf80fcb1d2f1d108e0de32777fab4aaa2b37b9765d8be73"},
+    {file = "torch-2.3.0-cp312-cp312-manylinux1_x86_64.whl", hash = "sha256:b0de2bdc0486ea7b14fc47ff805172df44e421a7318b7c4d92ef589a75d27410"},
+    {file = "torch-2.3.0-cp312-cp312-manylinux2014_aarch64.whl", hash = "sha256:a306c87a3eead1ed47457822c01dfbd459fe2920f2d38cbdf90de18f23f72542"},
+    {file = "torch-2.3.0-cp312-cp312-win_amd64.whl", hash = "sha256:f9b98bf1a3c8af2d4c41f0bf1433920900896c446d1ddc128290ff146d1eb4bd"},
+    {file = "torch-2.3.0-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:dca986214267b34065a79000cee54232e62b41dff1ec2cab9abc3fc8b3dee0ad"},
+    {file = "torch-2.3.0-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:20572f426965dd8a04e92a473d7e445fa579e09943cc0354f3e6fef6130ce061"},
+    {file = "torch-2.3.0-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:e65ba85ae292909cde0dde6369826d51165a3fc8823dc1854cd9432d7f79b932"},
+    {file = "torch-2.3.0-cp38-cp38-win_amd64.whl", hash = "sha256:5515503a193781fd1b3f5c474e89c9dfa2faaa782b2795cc4a7ab7e67de923f6"},
+    {file = "torch-2.3.0-cp38-none-macosx_11_0_arm64.whl", hash = "sha256:6ae9f64b09516baa4ef890af0672dc981c20b1f0d829ce115d4420a247e88fba"},
+    {file = "torch-2.3.0-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:cd0dc498b961ab19cb3f8dbf0c6c50e244f2f37dbfa05754ab44ea057c944ef9"},
+    {file = "torch-2.3.0-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:e05f836559251e4096f3786ee99f4a8cbe67bc7fbedba8ad5e799681e47c5e80"},
+    {file = "torch-2.3.0-cp39-cp39-win_amd64.whl", hash = "sha256:4fb27b35dbb32303c2927da86e27b54a92209ddfb7234afb1949ea2b3effffea"},
+    {file = "torch-2.3.0-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:760f8bedff506ce9e6e103498f9b1e9e15809e008368594c3a66bf74a8a51380"},
+]
+
+[package.dependencies]
+filelock = "*"
+fsspec = "*"
+jinja2 = "*"
+mkl = {version = ">=2021.1.1,<=2021.4.0", markers = "platform_system == \"Windows\""}
+networkx = "*"
+nvidia-cublas-cu12 = {version = "12.1.3.1", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-cupti-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-nvrtc-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cuda-runtime-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cudnn-cu12 = {version = "8.9.2.26", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cufft-cu12 = {version = "11.0.2.54", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-curand-cu12 = {version = "10.3.2.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cusolver-cu12 = {version = "11.4.5.107", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-cusparse-cu12 = {version = "12.1.0.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-nccl-cu12 = {version = "2.20.5", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+nvidia-nvtx-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""}
+sympy = "*"
+triton = {version = "2.3.0", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version < \"3.12\""}
+typing-extensions = ">=4.8.0"
+
+[package.extras]
+opt-einsum = ["opt-einsum (>=3.3)"]
+optree = ["optree (>=0.9.1)"]
+
 [[package]]
 name = "tornado"
 version = "6.4"
@@ -8465,6 +9127,29 @@ files = [
 [package.dependencies]
 tree-sitter = "*"
 
+[[package]]
+name = "triton"
+version = "2.3.0"
+description = "A language and compiler for custom Deep Learning operations"
+optional = false
+python-versions = "*"
+files = [
+    {file = "triton-2.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5ce4b8ff70c48e47274c66f269cce8861cf1dc347ceeb7a67414ca151b1822d8"},
+    {file = "triton-2.3.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3c3d9607f85103afdb279938fc1dd2a66e4f5999a58eb48a346bd42738f986dd"},
+    {file = "triton-2.3.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:218d742e67480d9581bafb73ed598416cc8a56f6316152e5562ee65e33de01c0"},
+    {file = "triton-2.3.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:381ec6b3dac06922d3e4099cfc943ef032893b25415de295e82b1a82b0359d2c"},
+    {file = "triton-2.3.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:038e06a09c06a164fef9c48de3af1e13a63dc1ba3c792871e61a8e79720ea440"},
+    {file = "triton-2.3.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6d8f636e0341ac348899a47a057c3daea99ea7db31528a225a3ba4ded28ccc65"},
+]
+
+[package.dependencies]
+filelock = "*"
+
+[package.extras]
+build = ["cmake (>=3.20)", "lit"]
+tests = ["autopep8", "flake8", "isort", "numpy", "pytest", "scipy (>=1.7.1)", "torch"]
+tutorials = ["matplotlib", "pandas", "tabulate", "torch"]
+
 [[package]]
 name = "typer"
 version = "0.9.0"
@@ -8884,7 +9569,7 @@ test = ["websockets"]
 name = "websockets"
 version = "12.0"
 description = "An implementation of the WebSocket Protocol (RFC 6455 & 7692)"
-optional = true
+optional = false
 python-versions = ">=3.8"
 files = [
     {file = "websockets-12.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:d554236b2a2006e0ce16315c16eaa0d628dab009c33b63ea03f41c6107958374"},
@@ -9321,4 +10006,4 @@ extended-testing = ["aiosqlite", "aleph-alpha-client", "anthropic", "arxiv", "as
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.8.1,<4.0"
-content-hash = "b066cbf8a1f02cae88c6c099e916d805fe6eb8685fd15c093d66cf52ea363fa5"
+content-hash = "ee08d5381cb754a0246ce6e4fb2547888d25ee0b096d8b8944a29ce120bb4473"

libs/community/pyproject.toml

@@ -161,6 +161,7 @@ anthropic = "^0.3.11"
 langchain-core = { path = "../core", develop = true }
 fireworks-ai = "^0.9.0"
 vdms = "^0.0.20"
+exllamav2 = "^0.0.18"
 
 [tool.poetry.group.lint]
 optional = true

libs/community/tests/integration_tests/vectorstores/qdrant/test_from_existing_collection.py

@@ -0,0 +1,39 @@
+import tempfile
+import uuid
+
+import pytest
+
+from langchain_community.vectorstores import Qdrant
+from tests.integration_tests.vectorstores.fake_embeddings import (
+    ConsistentFakeEmbeddings,
+)
+
+
+@pytest.mark.parametrize("vector_name", ["custom-vector"])
+def test_qdrant_from_existing_collection_uses_same_collection(vector_name: str) -> None:
+    """Test if the Qdrant.from_existing_collection reuses the same collection."""
+    from qdrant_client import QdrantClient
+
+    collection_name = uuid.uuid4().hex
+    with tempfile.TemporaryDirectory() as tmpdir:
+        docs = ["foo"]
+        qdrant = Qdrant.from_texts(
+            docs,
+            embedding=ConsistentFakeEmbeddings(),
+            path=str(tmpdir),
+            collection_name=collection_name,
+            vector_name=vector_name,
+        )
+        del qdrant
+
+        qdrant = Qdrant.from_existing_collection(
+            embedding=ConsistentFakeEmbeddings(),
+            path=str(tmpdir),
+            collection_name=collection_name,
+            vector_name=vector_name,
+        )
+        qdrant.add_texts(["baz", "bar"])
+        del qdrant
+
+        client = QdrantClient(path=str(tmpdir))
+        assert 3 == client.count(collection_name).count

libs/core/langchain_core/chat_loaders.py

@@ -0,0 +1,16 @@
+from abc import ABC, abstractmethod
+from typing import Iterator, List
+
+from langchain_core.chat_sessions import ChatSession
+
+
+class BaseChatLoader(ABC):
+    """Base class for chat loaders."""
+
+    @abstractmethod
+    def lazy_load(self) -> Iterator[ChatSession]:
+        """Lazy load the chat sessions."""
+
+    def load(self) -> List[ChatSession]:
+        """Eagerly load the chat sessions into memory."""
+        return list(self.lazy_load())

libs/core/tests/unit_tests/runnables/test_runnable.py

@@ -138,16 +138,16 @@ class FakeTracer(BaseTracer):
                 "child_execution_order": None,
                 "trace_id": self._replace_uuid(run.trace_id) if run.trace_id else None,
                 "dotted_order": new_dotted_order,
-                "inputs": {
-                    k: self._replace_message_id(v) for k, v in run.inputs.items()
-                }
-                if isinstance(run.inputs, dict)
-                else run.inputs,
-                "outputs": {
-                    k: self._replace_message_id(v) for k, v in run.outputs.items()
-                }
-                if isinstance(run.outputs, dict)
-                else run.outputs,
+                "inputs": (
+                    {k: self._replace_message_id(v) for k, v in run.inputs.items()}
+                    if isinstance(run.inputs, dict)
+                    else run.inputs
+                ),
+                "outputs": (
+                    {k: self._replace_message_id(v) for k, v in run.outputs.items()}
+                    if isinstance(run.outputs, dict)
+                    else run.outputs
+                ),
             }
         )
 
@@ -1652,11 +1652,14 @@ async def test_default_method_implementations(mocker: MockerFixture) -> None:
 
     assert len(spy.call_args_list) == 2
     for i, call in enumerate(spy.call_args_list):
-        assert call.args[0] == ("hello" if i == 0 else "wooorld")
-        if i == 0:
+        call_arg = call.args[0]
+
+        if call_arg == "hello":
+            assert call_arg == "hello"
             assert call.args[1].get("tags") == ["a-tag"]
             assert call.args[1].get("metadata") == {}
         else:
+            assert call_arg == "wooorld"
             assert call.args[1].get("tags") == []
             assert call.args[1].get("metadata") == {"key": "value"}
 
@@ -1664,8 +1667,8 @@ async def test_default_method_implementations(mocker: MockerFixture) -> None:
 
     assert fake.batch(["hello", "wooorld"], dict(tags=["a-tag"])) == [5, 7]
     assert len(spy.call_args_list) == 2
+    assert set(call.args[0] for call in spy.call_args_list) == {"hello", "wooorld"}
     for i, call in enumerate(spy.call_args_list):
-        assert call.args[0] == ("hello" if i == 0 else "wooorld")
         assert call.args[1].get("tags") == ["a-tag"]
         assert call.args[1].get("metadata") == {}
     spy.reset_mock()
@@ -1686,28 +1689,15 @@ async def test_default_method_implementations(mocker: MockerFixture) -> None:
         5,
         7,
     ]
-    assert spy.call_args_list == [
-        mocker.call(
-            "hello",
-            dict(
-                metadata={"key": "value"},
-                tags=[],
-                callbacks=None,
-                recursion_limit=25,
-                run_id=None,
-            ),
-        ),
-        mocker.call(
-            "wooorld",
-            dict(
-                metadata={"key": "value"},
-                tags=[],
-                callbacks=None,
-                recursion_limit=25,
-                run_id=None,
-            ),
-        ),
-    ]
+    assert set(call.args[0] for call in spy.call_args_list) == {"hello", "wooorld"}
+    for call in spy.call_args_list:
+        assert call.args[1] == dict(
+            metadata={"key": "value"},
+            tags=[],
+            callbacks=None,
+            recursion_limit=25,
+            run_id=None,
+        )
 
 
 async def test_prompt() -> None:

libs/langchain/langchain/agents/agent_toolkits/base.py

@@ -1,3 +1,3 @@
-from langchain_community.agent_toolkits.base import BaseToolkit
+from langchain_core.tools import BaseToolkit
 
 __all__ = ["BaseToolkit"]

libs/langchain/langchain/agents/agent_toolkits/vectorstore/toolkit.py

@@ -1,14 +1,13 @@
 """Toolkit for interacting with a vector store."""
 from typing import List
 
-from langchain_community.agent_toolkits.base import BaseToolkit
 from langchain_community.tools.vectorstore.tool import (
     VectorStoreQATool,
     VectorStoreQAWithSourcesTool,
 )
 from langchain_core.language_models import BaseLanguageModel
 from langchain_core.pydantic_v1 import BaseModel, Field
-from langchain_core.tools import BaseTool
+from langchain_core.tools import BaseTool, BaseToolkit
 from langchain_core.vectorstores import VectorStore
 
 

libs/langchain/langchain/chains/openai_functions/base.py

@@ -34,7 +34,7 @@ from langchain.chains.structured_output.base import (
 __all__ = [
     "get_openai_output_parser",
     "create_openai_fn_runnable",
-    "create_structured_output_runnable",
+    "create_structured_output_runnable",  # deprecated
     "create_openai_fn_chain",  # deprecated
     "create_structured_output_chain",  # deprecated
     "PYTHON_TO_JSON_TYPES",  # backwards compatibility
@@ -144,7 +144,7 @@ def create_openai_fn_chain(
 
 
 @deprecated(
-    since="0.1.1", removal="0.2.0", alternative="create_structured_output_runnable"
+    since="0.1.1", removal="0.2.0", alternative="ChatOpenAI.with_structured_output"
 )
 def create_structured_output_chain(
     output_schema: Union[Dict[str, Any], Type[BaseModel]],

libs/langchain/langchain/chains/structured_output/base.py

@@ -30,15 +30,15 @@ from langchain.output_parsers import (
 @deprecated(
     since="0.1.14",
     message=(
-        "LangChain has introduced a method called `with_structured_output` that"
-        "is available on ChatModels capable of tool calling."
+        "LangChain has introduced a method called `with_structured_output` that "
+        "is available on ChatModels capable of tool calling. "
         "You can read more about the method here: "
-        "https://python.langchain.com/docs/modules/model_io/chat/structured_output/"
-        "Please follow our extraction use case documentation for more guidelines"
-        "on how to do information extraction with LLMs."
-        "https://python.langchain.com/docs/use_cases/extraction/."
+        "https://python.langchain.com/docs/modules/model_io/chat/structured_output/ "
+        "Please follow our extraction use case documentation for more guidelines "
+        "on how to do information extraction with LLMs. "
+        "https://python.langchain.com/docs/use_cases/extraction/. "
         "If you notice other issues, please provide "
-        "feedback here:"
+        "feedback here: "
         "https://github.com/langchain-ai/langchain/discussions/18154"
     ),
     removal="0.3.0",
@@ -146,6 +146,42 @@ def create_openai_fn_runnable(
         return llm.bind(**llm_kwargs_) | output_parser
 
 
+@deprecated(
+    since="0.1.17",
+    message=(
+        "LangChain has introduced a method called `with_structured_output` that "
+        "is available on ChatModels capable of tool calling. "
+        "You can read more about the method here: "
+        "https://python.langchain.com/docs/modules/model_io/chat/structured_output/ "
+        "Please follow our extraction use case documentation for more guidelines "
+        "on how to do information extraction with LLMs. "
+        "https://python.langchain.com/docs/use_cases/extraction/. "
+        "If you notice other issues, please provide "
+        "feedback here: "
+        "https://github.com/langchain-ai/langchain/discussions/18154"
+    ),
+    removal="0.3.0",
+    pending=True,
+    alternative=(
+        """
+            from langchain_core.pydantic_v1 import BaseModel, Field
+            from langchain_anthropic import ChatAnthropic
+
+            class Joke(BaseModel):
+                setup: str = Field(description="The setup of the joke")
+                punchline: str = Field(description="The punchline to the joke") 
+
+            # Or any other chat model that supports tools.
+            # Please reference to to the documentation of structured_output
+            # to see an up to date list of which models support 
+            # with_structured_output.
+            model = ChatAnthropic(model="claude-3-opus-20240229", temperature=0)
+            structured_llm = model.with_structured_output(Joke)
+            structured_llm.invoke("Tell me a joke about cats. 
+                Make sure to call the Joke function.")
+            """
+    ),
+)
 def create_structured_output_runnable(
     output_schema: Union[Dict[str, Any], Type[BaseModel]],
     llm: Runnable,

libs/langchain/langchain/chat_loaders/base.py

@@ -1,3 +1,3 @@
-from langchain_community.chat_loaders.base import BaseChatLoader
+from langchain_core.chat_loaders import BaseChatLoader
 
 __all__ = ["BaseChatLoader"]

libs/langchain/tests/integration_tests/cache/test_opensearch_cache.py

@@ -0,0 +1,59 @@
+from langchain_community.cache import OpenSearchSemanticCache
+from langchain_core.outputs import Generation
+
+from langchain.globals import get_llm_cache, set_llm_cache
+from tests.integration_tests.cache.fake_embeddings import (
+    FakeEmbeddings,
+)
+from tests.unit_tests.llms.fake_llm import FakeLLM
+
+DEFAULT_OPENSEARCH_URL = "http://localhost:9200"
+
+
+def test_opensearch_semantic_cache() -> None:
+    """Test opensearch semantic cache functionality."""
+    set_llm_cache(
+        OpenSearchSemanticCache(
+            embedding=FakeEmbeddings(),
+            opensearch_url=DEFAULT_OPENSEARCH_URL,
+            score_threshold=0.0,
+        )
+    )
+    llm = FakeLLM()
+    params = llm.dict()
+    params["stop"] = None
+    llm_string = str(sorted([(k, v) for k, v in params.items()]))
+    get_llm_cache().update("foo", llm_string, [Generation(text="fizz")])
+    cache_output = get_llm_cache().lookup("bar", llm_string)
+    assert cache_output == [Generation(text="fizz")]
+
+    get_llm_cache().clear(llm_string=llm_string)
+    output = get_llm_cache().lookup("bar", llm_string)
+    assert output != [Generation(text="fizz")]
+
+
+def test_opensearch_semantic_cache_multi() -> None:
+    set_llm_cache(
+        OpenSearchSemanticCache(
+            embedding=FakeEmbeddings(),
+            opensearch_url=DEFAULT_OPENSEARCH_URL,
+            score_threshold=0.0,
+        )
+    )
+
+    llm = FakeLLM()
+    params = llm.dict()
+    params["stop"] = None
+    llm_string = str(sorted([(k, v) for k, v in params.items()]))
+    get_llm_cache().update(
+        "foo", llm_string, [Generation(text="fizz"), Generation(text="Buzz")]
+    )
+
+    # foo and bar will have the same embedding produced by FakeEmbeddings
+    cache_output = get_llm_cache().lookup("bar", llm_string)
+    assert cache_output == [Generation(text="fizz"), Generation(text="Buzz")]
+
+    # clear the cache
+    get_llm_cache().clear(llm_string=llm_string)
+    output = get_llm_cache().lookup("bar", llm_string)
+    assert output != [Generation(text="fizz"), Generation(text="Buzz")]

libs/partners/mistralai/poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.7.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.2 and should not be changed by hand.
 
 [[package]]
 name = "annotated-types"
@@ -389,7 +389,7 @@ files = [
 
 [[package]]
 name = "langchain-core"
-version = "0.1.45"
+version = "0.1.46"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = ">=3.8.1,<4.0"
@@ -1062,4 +1062,4 @@ zstd = ["zstandard (>=0.18.0)"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.8.1,<4.0"
-content-hash = "bfac6e5ad2828fe02c95b280d68c737f719dc517fc158b0ab66204b97e7fa591"
+content-hash = "567868376ce31e29a3795431cb8b53ce7860a50652f233a1b8bee9827d5c9871"

libs/partners/mistralai/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langchain-mistralai"
-version = "0.1.3"
+version = "0.1.4"
 description = "An integration package connecting Mistral and LangChain"
 authors = []
 readme = "README.md"
@@ -12,7 +12,7 @@ license = "MIT"
 
 [tool.poetry.dependencies]
 python = ">=3.8.1,<4.0"
-langchain-core = "^0.1.42"
+langchain-core = "^0.1.46"
 tokenizers = "^0.15.1"
 httpx = ">=0.25.2,<1"
 httpx-sse = ">=0.3.1,<1"

libs/partners/openai/poetry.lock

@@ -385,7 +385,7 @@ files = [
 
 [[package]]
 name = "langchain-core"
-version = "0.1.42"
+version = "0.1.46"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = ">=3.8.1,<4.0"
@@ -1286,4 +1286,4 @@ watchmedo = ["PyYAML (>=3.10)"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.8.1,<4.0"
-content-hash = "625e7565d37b9633874f61ee5660220e8e330658715d8b56ef2340f06dc1c625"
+content-hash = "f8a406a4ebd93e5c2ef3fcf4a3cebdd588ce09e288dc31b7b9b6b1560285575a"

libs/partners/openai/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langchain-openai"
-version = "0.1.3"
+version = "0.1.4"
 description = "An integration package connecting OpenAI and LangChain"
 authors = []
 readme = "README.md"
@@ -12,7 +12,7 @@ license = "MIT"
 
 [tool.poetry.dependencies]
 python = ">=3.8.1,<4.0"
-langchain-core = "^0.1.42"
+langchain-core = "^0.1.46"
 openai = "^1.10.0"
 tiktoken = ">=0.5.2,<1"
 

libs/partners/upstage/langchain_upstage/__init__.py

@@ -2,12 +2,16 @@ from langchain_upstage.chat_models import ChatUpstage
 from langchain_upstage.embeddings import UpstageEmbeddings
 from langchain_upstage.layout_analysis import UpstageLayoutAnalysisLoader
 from langchain_upstage.layout_analysis_parsers import UpstageLayoutAnalysisParser
-from langchain_upstage.tools.groundedness_check import GroundednessCheck
+from langchain_upstage.tools.groundedness_check import (
+    GroundednessCheck,
+    UpstageGroundednessCheck,
+)
 
 __all__ = [
     "ChatUpstage",
     "UpstageEmbeddings",
     "UpstageLayoutAnalysisLoader",
     "UpstageLayoutAnalysisParser",
+    "UpstageGroundednessCheck",
     "GroundednessCheck",
 ]

libs/partners/upstage/langchain_upstage/tools/groundedness_check.py

@@ -1,10 +1,12 @@
 import os
-from typing import Any, Literal, Optional, Type, Union
+from typing import Any, List, Literal, Optional, Type, Union
 
+from langchain_core._api.deprecation import deprecated
 from langchain_core.callbacks import (
     AsyncCallbackManagerForToolRun,
     CallbackManagerForToolRun,
 )
+from langchain_core.documents import Document
 from langchain_core.messages import AIMessage, HumanMessage
 from langchain_core.pydantic_v1 import BaseModel, Field, SecretStr
 from langchain_core.tools import BaseTool
@@ -13,16 +15,18 @@ from langchain_core.utils import convert_to_secret_str
 from langchain_upstage import ChatUpstage
 
 
-class GroundednessCheckInput(BaseModel):
+class UpstageGroundednessCheckInput(BaseModel):
     """Input for the Groundedness Check tool."""
 
-    context: str = Field(description="context in which the answer should be verified")
-    query: str = Field(
+    context: Union[str, List[Document]] = Field(
+        description="context in which the answer should be verified"
+    )
+    answer: str = Field(
         description="assistant's reply or a text that is subject to groundedness check"
     )
 
 
-class GroundednessCheck(BaseTool):
+class UpstageGroundednessCheck(BaseTool):
     """Tool that checks the groundedness of a context and an assistant message.
 
     To use, you should have the environment variable `UPSTAGE_API_KEY`
@@ -31,15 +35,15 @@ class GroundednessCheck(BaseTool):
     Example:
         .. code-block:: python
 
-                from langchain_upstage import GroundednessCheck
+                from langchain_upstage import UpstageGroundednessCheck
 
-                tool = GroundednessCheck()
+                tool = UpstageGroundednessCheck()
     """
 
     name: str = "groundedness_check"
     description: str = (
         "A tool that checks the groundedness of an assistant response "
-        "to user-provided context. GroundednessCheck ensures that "
+        "to user-provided context. UpstageGroundednessCheck ensures that "
         "the assistant’s response is not only relevant but also "
         "precisely aligned with the user's initial context, "
         "promoting a more reliable and context-aware interaction. "
@@ -50,7 +54,7 @@ class GroundednessCheck(BaseTool):
     upstage_api_key: Optional[SecretStr] = Field(default=None, alias="api_key")
     api_wrapper: ChatUpstage
 
-    args_schema: Type[BaseModel] = GroundednessCheckInput
+    args_schema: Type[BaseModel] = UpstageGroundednessCheckInput
 
     def __init__(self, **kwargs: Any) -> None:
         upstage_api_key = kwargs.get("upstage_api_key", None)
@@ -73,25 +77,41 @@ class GroundednessCheck(BaseTool):
         )
         super().__init__(upstage_api_key=upstage_api_key, api_wrapper=api_wrapper)
 
+    def formatDocumentsAsString(self, docs: List[Document]) -> str:
+        return "\n".join([doc.page_content for doc in docs])
+
     def _run(
         self,
-        context: str,
-        query: str,
+        context: Union[str, List[Document]],
+        answer: str,
         run_manager: Optional[CallbackManagerForToolRun] = None,
     ) -> Union[str, Literal["grounded", "notGrounded", "notSure"]]:
         """Use the tool."""
+        if isinstance(context, List):
+            context = self.formatDocumentsAsString(context)
         response = self.api_wrapper.invoke(
-            [HumanMessage(context), AIMessage(query)], stream=False
+            [HumanMessage(context), AIMessage(answer)], stream=False
         )
         return str(response.content)
 
     async def _arun(
         self,
-        context: str,
-        query: str,
+        context: Union[str, List[Document]],
+        answer: str,
         run_manager: Optional[AsyncCallbackManagerForToolRun] = None,
     ) -> Union[str, Literal["grounded", "notGrounded", "notSure"]]:
+        if isinstance(context, List):
+            context = self.formatDocumentsAsString(context)
         response = await self.api_wrapper.ainvoke(
-            [HumanMessage(context), AIMessage(query)], stream=False
+            [HumanMessage(context), AIMessage(answer)], stream=False
         )
         return str(response.content)
+
+
+@deprecated(
+    since="0.1.3",
+    removal="0.2.0",
+    alternative_import="langchain_upstage.UpstageGroundednessCheck",
+)
+class GroundednessCheck(UpstageGroundednessCheck):
+    pass

libs/partners/upstage/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langchain-upstage"
-version = "0.1.2"
+version = "0.1.3"
 description = "An integration package connecting Upstage and LangChain"
 authors = []
 readme = "README.md"

libs/partners/upstage/tests/integration_tests/test_groundedness_check.py

@@ -2,34 +2,62 @@ import os
 
 import openai
 import pytest
+from langchain_core.documents import Document
 
-from langchain_upstage import GroundednessCheck
+from langchain_upstage import GroundednessCheck, UpstageGroundednessCheck
 
 
-def test_langchain_upstage_groundedness_check() -> None:
+def test_langchain_upstage_groundedness_check_deprecated() -> None:
     """Test Upstage Groundedness Check."""
     tool = GroundednessCheck()
-    output = tool.run({"context": "foo bar", "query": "bar foo"})
+    output = tool.invoke({"context": "foo bar", "answer": "bar foo"})
 
     assert output in ["grounded", "notGrounded", "notSure"]
 
     api_key = os.environ.get("UPSTAGE_API_KEY", None)
 
     tool = GroundednessCheck(upstage_api_key=api_key)
-    output = tool.run({"context": "foo bar", "query": "bar foo"})
+    output = tool.invoke({"context": "foo bar", "answer": "bar foo"})
+
+    assert output in ["grounded", "notGrounded", "notSure"]
+
+
+def test_langchain_upstage_groundedness_check() -> None:
+    """Test Upstage Groundedness Check."""
+    tool = UpstageGroundednessCheck()
+    output = tool.invoke({"context": "foo bar", "answer": "bar foo"})
+
+    assert output in ["grounded", "notGrounded", "notSure"]
+
+    api_key = os.environ.get("UPSTAGE_API_KEY", None)
+
+    tool = UpstageGroundednessCheck(upstage_api_key=api_key)
+    output = tool.invoke({"context": "foo bar", "answer": "bar foo"})
+
+    assert output in ["grounded", "notGrounded", "notSure"]
+
+
+def test_langchain_upstage_groundedness_check_with_documents_input() -> None:
+    """Test Upstage Groundedness Check."""
+    tool = UpstageGroundednessCheck()
+    docs = [
+        Document(page_content="foo bar"),
+        Document(page_content="bar foo"),
+    ]
+    output = tool.invoke({"context": docs, "answer": "bar foo"})
 
     assert output in ["grounded", "notGrounded", "notSure"]
 
 
 def test_langchain_upstage_groundedness_check_fail_with_wrong_api_key() -> None:
-    tool = GroundednessCheck(api_key="wrong-key")
+    tool = UpstageGroundednessCheck(api_key="wrong-key")
     with pytest.raises(openai.AuthenticationError):
-        tool.run({"context": "foo bar", "query": "bar foo"})
+        tool.invoke({"context": "foo bar", "answer": "bar foo"})
 
 
 async def test_langchain_upstage_groundedness_check_async() -> None:
     """Test Upstage Groundedness Check asynchronous."""
-    tool = GroundednessCheck()
-    output = await tool.arun({"context": "foo bar", "query": "bar foo"})
+    tool = UpstageGroundednessCheck()
+    output = await tool.ainvoke({"context": "foo bar", "answer": "bar foo"})
 
     assert output in ["grounded", "notGrounded", "notSure"]

libs/partners/upstage/tests/unit_tests/test_groundedness_check.py

@@ -1,12 +1,12 @@
 import os
 
-from langchain_upstage import GroundednessCheck
+from langchain_upstage import UpstageGroundednessCheck
 
 os.environ["UPSTAGE_API_KEY"] = "foo"
 
 
 def test_initialization() -> None:
     """Test embedding model initialization."""
-    GroundednessCheck()
-    GroundednessCheck(upstage_api_key="key")
-    GroundednessCheck(api_key="key")
+    UpstageGroundednessCheck()
+    UpstageGroundednessCheck(upstage_api_key="key")
+    UpstageGroundednessCheck(api_key="key")

libs/partners/upstage/tests/unit_tests/test_imports.py

@@ -2,10 +2,11 @@ from langchain_upstage import __all__
 
 EXPECTED_ALL = [
     "ChatUpstage",
+    "GroundednessCheck",
     "UpstageEmbeddings",
     "UpstageLayoutAnalysisLoader",
     "UpstageLayoutAnalysisParser",
-    "GroundednessCheck",
+    "UpstageGroundednessCheck",
 ]