Archives/langchain
2
0
Fork 1
mirror of https://github.com/hwchase17/langchain synced 2024-11-06 03:20:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into deepsense/text-to-speech

Browse Source
This commit is contained in:
Mateusz Wosinski 2023-09-08 08:09:01 +02:00 committed by GitHub
commit 69fe0621d4
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
60 changed files with 4527 additions and 2056 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/docs_skeleton/vercel.json
View File

@ -2216,6 +2216,10 @@
"source": "/docs/modules/data_connection/text_embedding/integrations/tensorflowhub", "source": "/docs/modules/data_connection/text_embedding/integrations/tensorflowhub",
"destination": "/docs/integrations/text_embedding/tensorflowhub" "destination": "/docs/integrations/text_embedding/tensorflowhub"
}, },
{
"source": "/docs/integrations/text_embedding/Awa",
"destination": "/docs/integrations/text_embedding/awadb"
},
{ {
"source": "/en/latest/modules/indexes/vectorstores/examples/analyticdb.html", "source": "/en/latest/modules/indexes/vectorstores/examples/analyticdb.html",
"destination": "/docs/integrations/vectorstores/analyticdb" "destination": "/docs/integrations/vectorstores/analyticdb"

1831
docs/extras/expression_language/cookbook.ipynb
View File

File diff suppressed because it is too large Load Diff

119
docs/extras/expression_language/cookbook/code_writing.ipynb Normal file
View File

@ -0,0 +1,119 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "f09fd305",
"metadata": {},
"source": [
"# Code writing\n",
"\n",
"Example of how to use LCEL to write Python code."
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "bd7c259a",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.prompts import ChatPromptTemplate, SystemMessagePromptTemplate, HumanMessagePromptTemplate\n",
"from langchain.schema.output_parser import StrOutputParser\n",
"from langchain.utilities import PythonREPL"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "73795d2d",
"metadata": {},
"outputs": [],
"source": [
"template = \"\"\"Write some python code to solve the user's problem. \n",
"\n",
"Return only python code in Markdown format, e.g.:\n",
"\n",
"```python\n",
"....\n",
"```\"\"\"\n",
"prompt = ChatPromptTemplate.from_messages(\n",
" [(\"system\", template), (\"human\", \"{input}\")]\n",
")\n",
"\n",
"model = ChatOpenAI()"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "42859e8a",
"metadata": {},
"outputs": [],
"source": [
"def _sanitize_output(text: str):\n",
" _, after = text.split(\"```python\")\n",
" return after.split(\"```\")[0]"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "5ded1a86",
"metadata": {},
"outputs": [],
"source": [
"chain = prompt | model | StrOutputParser() | _sanitize_output | PythonREPL().run"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "208c2b75",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Python REPL can execute arbitrary code. Use with caution.\n"
]
},
{
"data": {
"text/plain": [
"'4\\n'"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.invoke({\"input\": \"whats 2 plus 2\"})"
]
}
],
"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"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

11
docs/extras/expression_language/cookbook/index.mdx Normal file
View File

@ -0,0 +1,11 @@
---
sidebar_position: 2
---
# Cookbook
import DocCardList from "@theme/DocCardList";
Example code for accomplishing common tasks with the LangChain Expression Language (LCEL). These examples show how to compose different Runnable (the core LCEL interface) components to achieve various tasks. If you're just getting acquainted with LCEL, the [Prompt + LLM](/docs/expression_language/cookbook/prompt_llm_parser) page is a good place to start.
<DocCardList />

180
docs/extras/expression_language/cookbook/memory.ipynb Normal file
View File

@ -0,0 +1,180 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "5062941a",
"metadata": {},
"source": [
"# Adding memory\n",
"\n",
"This shows how to add memory to an arbitrary chain. Right now, you can use the memory classes but need to hook it up manually"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "7998efd8",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.memory import ConversationBufferMemory\n",
"from langchain.schema.runnable import RunnableMap\n",
"from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
"\n",
"model = ChatOpenAI()\n",
"prompt = ChatPromptTemplate.from_messages([\n",
" (\"system\", \"You are a helpful chatbot\"),\n",
" MessagesPlaceholder(variable_name=\"history\"),\n",
" (\"human\", \"{input}\")\n",
"])"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "fa0087f3",
"metadata": {},
"outputs": [],
"source": [
"memory = ConversationBufferMemory(return_messages=True)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "06b531ae",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'history': []}"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"memory.load_memory_variables({})"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "d9437af6",
"metadata": {},
"outputs": [],
"source": [
"chain = RunnableMap({\n",
" \"input\": lambda x: x[\"input\"],\n",
" \"memory\": memory.load_memory_variables\n",
"}) | {\n",
" \"input\": lambda x: x[\"input\"],\n",
" \"history\": lambda x: x[\"memory\"][\"history\"]\n",
"} | prompt | model"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "bed1e260",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content='Hello Bob! How can I assist you today?', additional_kwargs={}, example=False)"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"inputs = {\"input\": \"hi im bob\"}\n",
"response = chain.invoke(inputs)\n",
"response"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "890475b4",
"metadata": {},
"outputs": [],
"source": [
"memory.save_context(inputs, {\"output\": response.content})"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "e8fcb77f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'history': [HumanMessage(content='hi im bob', additional_kwargs={}, example=False),\n",
" AIMessage(content='Hello Bob! How can I assist you today?', additional_kwargs={}, example=False)]}"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"memory.load_memory_variables({})"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "d837d5c3",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content='Your name is Bob.', additional_kwargs={}, example=False)"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"inputs = {\"input\": \"whats my name\"}\n",
"response = chain.invoke(inputs)\n",
"response"
]
}
],
"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"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

133
docs/extras/expression_language/cookbook/moderation.ipynb Normal file
View File

@ -0,0 +1,133 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "4927a727-b4c8-453c-8c83-bd87b4fcac14",
"metadata": {},
"source": [
"# Adding moderation\n",
"\n",
"This shows how to add in moderation (or other safeguards) around your LLM application."
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "4f5f6449-940a-4f5c-97c0-39b71c3e2a68",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains import OpenAIModerationChain\n",
"from langchain.llms import OpenAI\n",
"from langchain.prompts import ChatPromptTemplate"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "fcb8312b-7e7a-424f-a3ec-76738c9a9d21",
"metadata": {},
"outputs": [],
"source": [
"moderate = OpenAIModerationChain()"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "b24b9148-f6b0-4091-8ea8-d3fb281bd950",
"metadata": {},
"outputs": [],
"source": [
"model = OpenAI()\n",
"prompt = ChatPromptTemplate.from_messages([\n",
" (\"system\", \"repeat after me: {input}\")\n",
"])"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "1c8ed87c-9ca6-4559-bf60-d40e94a0af08",
"metadata": {},
"outputs": [],
"source": [
"chain = prompt | model"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "5256b9bd-381a-42b0-bfa8-7e6d18f853cb",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'\\n\\nYou are stupid.'"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.invoke({\"input\": \"you are stupid\"})"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "fe6e3b33-dc9a-49d5-b194-ba750c58a628",
"metadata": {},
"outputs": [],
"source": [
"moderated_chain = chain | moderate"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "d8ba0cbd-c739-4d23-be9f-6ae092bd5ffb",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'input': '\\n\\nYou are stupid',\n",
" 'output': \"Text was found that violates OpenAI's content policy.\"}"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"moderated_chain.invoke({\"input\": \"you are stupid\"})"
]
}
],
"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"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

240
docs/extras/expression_language/cookbook/multiple_chains.ipynb Normal file
View File

@ -0,0 +1,240 @@
{
"cells": [
{
"cell_type": "raw",
"id": "877102d1-02ea-4fa3-8ec7-a08e242b95b3",
"metadata": {},
"source": [
"---\n",
"sidebar_position: 2\n",
"title: Multiple chains\n",
"---"
]
},
{
"cell_type": "markdown",
"id": "0f2bf8d3",
"metadata": {},
"source": [
"Runnables can easily be used to string together multiple Chains"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "d65d4e9e",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'El país donde se encuentra la ciudad de Honolulu, donde nació Barack Obama, el 44º Presidente de los Estados Unidos, es Estados Unidos. Honolulu se encuentra en la isla de Oahu, en el estado de Hawái.'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from operator import itemgetter\n",
"\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.prompts import ChatPromptTemplate\n",
"from langchain.schema import StrOutputParser\n",
"\n",
"prompt1 = ChatPromptTemplate.from_template(\"what is the city {person} is from?\")\n",
"prompt2 = ChatPromptTemplate.from_template(\"what country is the city {city} in? respond in {language}\")\n",
"\n",
"model = ChatOpenAI()\n",
"\n",
"chain1 = prompt1 | model | StrOutputParser()\n",
"\n",
"chain2 = {\"city\": chain1, \"language\": itemgetter(\"language\")} | prompt2 | model | StrOutputParser()\n",
"\n",
"chain2.invoke({\"person\": \"obama\", \"language\": \"spanish\"})"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "878f8176",
"metadata": {},
"outputs": [],
"source": [
"from langchain.schema.runnable import RunnableMap, RunnablePassthrough\n",
"\n",
"prompt1 = ChatPromptTemplate.from_template(\"generate a {attribute} color. Return the name of the color and nothing else:\")\n",
"prompt2 = ChatPromptTemplate.from_template(\"what is a fruit of color: {color}. Return the name of the fruit and nothing else:\")\n",
"prompt3 = ChatPromptTemplate.from_template(\"what is a country with a flag that has the color: {color}. Return the name of the country and nothing else:\")\n",
"prompt4 = ChatPromptTemplate.from_template(\"What is the color of {fruit} and the flag of {country}?\")\n",
"\n",
"model_parser = model | StrOutputParser()\n",
"\n",
"color_generator = {\"attribute\": RunnablePassthrough()} | prompt1 | {\"color\": model_parser}\n",
"color_to_fruit = prompt2 | model_parser\n",
"color_to_country = prompt3 | model_parser\n",
"question_generator = color_generator | {\"fruit\": color_to_fruit, \"country\": color_to_country} | prompt4"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "d621a870",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"ChatPromptValue(messages=[HumanMessage(content='What is the color of strawberry and the flag of China?', additional_kwargs={}, example=False)])"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"question_generator.invoke({\"warm\"})"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "b4a9812b-bead-4fd9-ae27-0b8be57e5dc1",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content='The color of an apple is typically red or green. The flag of China is predominantly red with a large yellow star in the upper left corner and four smaller yellow stars surrounding it.', additional_kwargs={}, example=False)"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"prompt = question_generator.invoke({\"warm\"})\n",
"model.invoke(prompt)"
]
},
{
"cell_type": "markdown",
"id": "6d75a313-f1c8-4e94-9a17-24e0bf4a2bdc",
"metadata": {},
"source": [
"### Branching and Merging\n",
"\n",
"You may want the output of one component to be processed by 2 or more other components. [RunnableMaps](https://api.python.langchain.com/en/latest/schema/langchain.schema.runnable.base.RunnableMap.html) let you split or fork the chain so multiple components can process the input in parallel. Later, other components can join or merge the results to synthesize a final response. This type of chain creates a computation graph that looks like the following:\n",
"\n",
"```text\n",
" Input\n",
" / \\\n",
" / \\\n",
" Branch1 Branch2\n",
" \\ /\n",
" \\ /\n",
" Combine\n",
"```"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "247fa0bd-4596-4063-8cb3-1d7fc119d982",
"metadata": {},
"outputs": [],
"source": [
"planner = (\n",
" ChatPromptTemplate.from_template(\n",
" \"Generate an argument about: {input}\"\n",
" )\n",
" | ChatOpenAI()\n",
" | StrOutputParser()\n",
" | {\"base_response\": RunnablePassthrough()}\n",
")\n",
"\n",
"arguments_for = (\n",
" ChatPromptTemplate.from_template(\n",
" \"List the pros or positive aspects of {base_response}\"\n",
" )\n",
" | ChatOpenAI()\n",
" | StrOutputParser()\n",
")\n",
"arguments_against = (\n",
" ChatPromptTemplate.from_template(\n",
" \"List the cons or negative aspects of {base_response}\"\n",
" )\n",
" | ChatOpenAI()\n",
" | StrOutputParser()\n",
")\n",
"\n",
"final_responder = (\n",
" ChatPromptTemplate.from_messages(\n",
" [\n",
" (\"ai\", \"{original_response}\"),\n",
" (\"human\", \"Pros:\\n{results_1}\\n\\nCons:\\n{results_2}\"),\n",
" (\"system\", \"Generate a final response given the critique\"),\n",
" ]\n",
" )\n",
" | ChatOpenAI()\n",
" | StrOutputParser()\n",
")\n",
"\n",
"chain = (\n",
" planner \n",
" | {\n",
" \"results_1\": arguments_for,\n",
" \"results_2\": arguments_against,\n",
" \"original_response\": itemgetter(\"base_response\"),\n",
" }\n",
" | final_responder\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "2564f310-0674-4bb1-9c4e-d7848ca73511",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'While Scrum has its potential cons and challenges, many organizations have successfully embraced and implemented this project management framework to great effect. The cons mentioned above can be mitigated or overcome with proper training, support, and a commitment to continuous improvement. It is also important to note that not all cons may be applicable to every organization or project.\\n\\nFor example, while Scrum may be complex initially, with proper training and guidance, teams can quickly grasp the concepts and practices. The lack of predictability can be mitigated by implementing techniques such as velocity tracking and release planning. The limited documentation can be addressed by maintaining a balance between lightweight documentation and clear communication among team members. The dependency on team collaboration can be improved through effective communication channels and regular team-building activities.\\n\\nScrum can be scaled and adapted to larger projects by using frameworks like Scrum of Scrums or LeSS (Large Scale Scrum). Concerns about speed versus quality can be addressed by incorporating quality assurance practices, such as continuous integration and automated testing, into the Scrum process. Scope creep can be managed by having a well-defined and prioritized product backlog, and a strong product owner can be developed through training and mentorship.\\n\\nResistance to change can be overcome by providing proper education and communication to stakeholders and involving them in the decision-making process. Ultimately, the cons of Scrum can be seen as opportunities for growth and improvement, and with the right mindset and support, they can be effectively managed.\\n\\nIn conclusion, while Scrum may have its challenges and potential cons, the benefits and advantages it offers in terms of collaboration, flexibility, adaptability, transparency, and customer satisfaction make it a widely adopted and successful project management framework. With proper implementation and continuous improvement, organizations can leverage Scrum to drive innovation, efficiency, and project success.'"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.invoke({\"input\": \"scrum\"})"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "poetry-venv",
"language": "python",
"name": "poetry-venv"
},
"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"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

431
docs/extras/expression_language/cookbook/prompt_llm_parser.ipynb Normal file
View File

@ -0,0 +1,431 @@
{
"cells": [
{
"cell_type": "raw",
"id": "abf7263d-3a62-4016-b5d5-b157f92f2070",
"metadata": {},
"source": [
"---\n",
"sidebar_position: 0\n",
"title: Prompt + LLM\n",
"---"
]
},
{
"cell_type": "markdown",
"id": "9a434f2b-9405-468c-9dfd-254d456b57a6",
"metadata": {},
"source": [
"The most common and valuable composition is taking:\n",
"\n",
"``PromptTemplate`` / ``ChatPromptTemplate`` -> ``LLM`` / ``ChatModel`` -> ``OutputParser``\n",
"\n",
"Almost any other chains you build will use this building block."
]
},
{
"cell_type": "markdown",
"id": "93aa2c87",
"metadata": {},
"source": [
"## PromptTemplate + LLM\n",
"\n",
"The simplest composition is just combing a prompt and model to create a chain that takes user input, adds it to a prompt, passes it to a model, and returns the raw model input.\n",
"\n",
"Note, you can mix and match PromptTemplate/ChatPromptTemplates and LLMs/ChatModels as you like here."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "466b65b3",
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts import ChatPromptTemplate\n",
"from langchain.chat_models import ChatOpenAI\n",
"\n",
"prompt = ChatPromptTemplate.from_template(\"tell me a joke about {foo}\")\n",
"model = ChatOpenAI()\n",
"chain = prompt | model"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "e3d0a6cd",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content=\"Why don't bears wear shoes?\\n\\nBecause they have bear feet!\", additional_kwargs={}, example=False)"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.invoke({\"foo\": \"bears\"})"
]
},
{
"cell_type": "markdown",
"id": "7eb9ef50",
"metadata": {},
"source": [
"Often times we want to attach kwargs that'll be passed to each model call. Here's a few examples of that:"
]
},
{
"cell_type": "markdown",
"id": "0b1d8f88",
"metadata": {},
"source": [
"### Attaching Stop Sequences"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "562a06bf",
"metadata": {},
"outputs": [],
"source": [
"chain = prompt | model.bind(stop=[\"\\n\"])"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "43f5d04c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content='Why did the bear never wear shoes?', additional_kwargs={}, example=False)"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.invoke({\"foo\": \"bears\"})"
]
},
{
"cell_type": "markdown",
"id": "f3eaf88a",
"metadata": {},
"source": [
"### Attaching Function Call information"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "f94b71b2",
"metadata": {},
"outputs": [],
"source": [
"functions = [\n",
" {\n",
" \"name\": \"joke\",\n",
" \"description\": \"A joke\",\n",
" \"parameters\": {\n",
" \"type\": \"object\",\n",
" \"properties\": {\n",
" \"setup\": {\n",
" \"type\": \"string\",\n",
" \"description\": \"The setup for the joke\"\n",
" },\n",
" \"punchline\": {\n",
" \"type\": \"string\",\n",
" \"description\": \"The punchline for the joke\"\n",
" }\n",
" },\n",
" \"required\": [\"setup\", \"punchline\"]\n",
" }\n",
" }\n",
" ]\n",
"chain = prompt | model.bind(function_call= {\"name\": \"joke\"}, functions= functions)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "decf7710",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content='', additional_kwargs={'function_call': {'name': 'joke', 'arguments': '{\\n \"setup\": \"Why don\\'t bears wear shoes?\",\\n \"punchline\": \"Because they have bear feet!\"\\n}'}}, example=False)"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.invoke({\"foo\": \"bears\"}, config={})"
]
},
{
"cell_type": "markdown",
"id": "9098c5ed",
"metadata": {},
"source": [
"## PromptTemplate + LLM + OutputParser\n",
"\n",
"We can also add in an output parser to easily trasform the raw LLM/ChatModel output into a more workable format"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "cc194c78",
"metadata": {},
"outputs": [],
"source": [
"from langchain.schema.output_parser import StrOutputParser\n",
"\n",
"chain = prompt | model | StrOutputParser()"
]
},
{
"cell_type": "markdown",
"id": "77acf448",
"metadata": {},
"source": [
"Notice that this now returns a string - a much more workable format for downstream tasks"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "e3d69a18",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\"Why don't bears wear shoes?\\n\\nBecause they have bear feet!\""
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.invoke({\"foo\": \"bears\"})"
]
},
{
"cell_type": "markdown",
"id": "c01864e5",
"metadata": {},
"source": [
"### Functions Output Parser\n",
"\n",
"When you specify the function to return, you may just want to parse that directly"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "ad0dd88e",
"metadata": {},
"outputs": [],
"source": [
"from langchain.output_parsers.openai_functions import JsonOutputFunctionsParser\n",
"\n",
"chain = (\n",
" prompt \n",
" | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
" | JsonOutputFunctionsParser()\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "1e7aa8eb",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'setup': \"Why don't bears like fast food?\",\n",
" 'punchline': \"Because they can't catch it!\"}"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.invoke({\"foo\": \"bears\"})"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "d4aa1a01",
"metadata": {},
"outputs": [],
"source": [
"from langchain.output_parsers.openai_functions import JsonKeyOutputFunctionsParser\n",
"\n",
"chain = (\n",
" prompt \n",
" | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
" | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "8b6df9ba",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\"Why don't bears wear shoes?\""
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.invoke({\"foo\": \"bears\"})"
]
},
{
"cell_type": "markdown",
"id": "023fbccb-ef7d-489e-a9ba-f98e17283d51",
"metadata": {},
"source": [
"## Simplifying input\n",
"\n",
"To make invocation even simpler, we can add a `RunnableMap` to take care of creating the prompt input dict for us:"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "9601c0f0-71f9-4bd4-a672-7bd04084b018",
"metadata": {},
"outputs": [],
"source": [
"from langchain.schema.runnable import RunnableMap, RunnablePassthrough\n",
"\n",
"map_ = RunnableMap({\"foo\": RunnablePassthrough()})\n",
"chain = (\n",
" map_ \n",
" | prompt\n",
" | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
" | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "7ec4f154-fda5-4847-9220-41aa902fdc33",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\"Why don't bears wear shoes?\""
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.invoke(\"bears\")"
]
},
{
"cell_type": "markdown",
"id": "def00bfe-0f83-4805-8c8f-8a53f99fa8ea",
"metadata": {},
"source": [
"Since we're composing our map with another Runnable, we can even use some syntactic sugar and just use a dict:"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "7bf3846a-02ee-41a3-ba1b-a708827d4f3a",
"metadata": {},
"outputs": [],
"source": [
"chain = (\n",
" {\"foo\": RunnablePassthrough()} \n",
" | prompt\n",
" | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
" | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "e566d6a1-538d-4cb5-a210-a63e082e4c74",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\"Why don't bears like fast food?\""
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.invoke(\"bears\")"
]
}
],
"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"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

461
docs/extras/expression_language/cookbook/retrieval.ipynb Normal file
View File

@ -0,0 +1,461 @@
{
"cells": [
{
"cell_type": "raw",
"id": "abe47592-909c-4844-bf44-9e55c2fb4bfa",
"metadata": {},
"source": [
"---\n",
"sidebar_position: 1\n",
"title: RAG\n",
"---"
]
},
{
"cell_type": "markdown",
"id": "91c5ef3d",
"metadata": {},
"source": [
"Let's look at adding in a retrieval step to a prompt and LLM, which adds up to a \"retrieval-augmented generation\" chain"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7f25d9e9-d192-42e9-af50-5660a4bfb0d9",
"metadata": {},
"outputs": [],
"source": [
"!pip install langchain openai faiss-cpu"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "33be32af",
"metadata": {},
"outputs": [],
"source": [
"from operator import itemgetter\n",
"\n",
"from langchain.prompts import ChatPromptTemplate\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.embeddings import OpenAIEmbeddings\n",
"from langchain.schema.output_parser import StrOutputParser\n",
"from langchain.schema.runnable import RunnablePassthrough\n",
"from langchain.vectorstores import FAISS"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "bfc47ec1",
"metadata": {},
"outputs": [],
"source": [
"vectorstore = FAISS.from_texts([\"harrison worked at kensho\"], embedding=OpenAIEmbeddings())\n",
"retriever = vectorstore.as_retriever()\n",
"\n",
"template = \"\"\"Answer the question based only on the following context:\n",
"{context}\n",
"\n",
"Question: {question}\n",
"\"\"\"\n",
"prompt = ChatPromptTemplate.from_template(template)\n",
"\n",
"model = ChatOpenAI()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "eae31755",
"metadata": {},
"outputs": [],
"source": [
"chain = (\n",
" {\"context\": retriever, \"question\": RunnablePassthrough()} \n",
" | prompt \n",
" | model \n",
" | StrOutputParser()\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "f3040b0c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Harrison worked at Kensho.'"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.invoke(\"where did harrison work?\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "e1d20c7c",
"metadata": {},
"outputs": [],
"source": [
"template = \"\"\"Answer the question based only on the following context:\n",
"{context}\n",
"\n",
"Question: {question}\n",
"\n",
"Answer in the following language: {language}\n",
"\"\"\"\n",
"prompt = ChatPromptTemplate.from_template(template)\n",
"\n",
"chain = {\n",
" \"context\": itemgetter(\"question\") | retriever, \n",
" \"question\": itemgetter(\"question\"), \n",
" \"language\": itemgetter(\"language\")\n",
"} | prompt | model | StrOutputParser()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "7ee8b2d4",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Harrison ha lavorato a Kensho.'"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.invoke({\"question\": \"where did harrison work\", \"language\": \"italian\"})"
]
},
{
"cell_type": "markdown",
"id": "f007669c",
"metadata": {},
"source": [
"## Conversational Retrieval Chain\n",
"\n",
"We can easily add in conversation history. This primarily means adding in chat_message_history"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "3f30c348",
"metadata": {},
"outputs": [],
"source": [
"from langchain.schema.runnable import RunnableMap\n",
"from langchain.schema import format_document"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "64ab1dbf",
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts.prompt import PromptTemplate\n",
"\n",
"_template = \"\"\"Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question, in its original language.\n",
"\n",
"Chat History:\n",
"{chat_history}\n",
"Follow Up Input: {question}\n",
"Standalone question:\"\"\"\n",
"CONDENSE_QUESTION_PROMPT = PromptTemplate.from_template(_template)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "7d628c97",
"metadata": {},
"outputs": [],
"source": [
"template = \"\"\"Answer the question based only on the following context:\n",
"{context}\n",
"\n",
"Question: {question}\n",
"\"\"\"\n",
"ANSWER_PROMPT = ChatPromptTemplate.from_template(template)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "f60a5d0f",
"metadata": {},
"outputs": [],
"source": [
"DEFAULT_DOCUMENT_PROMPT = PromptTemplate.from_template(template=\"{page_content}\")\n",
"def _combine_documents(docs, document_prompt = DEFAULT_DOCUMENT_PROMPT, document_separator=\"\\n\\n\"):\n",
" doc_strings = [format_document(doc, document_prompt) for doc in docs]\n",
" return document_separator.join(doc_strings)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "7d007db6",
"metadata": {},
"outputs": [],
"source": [
"from typing import Tuple, List\n",
"def _format_chat_history(chat_history: List[Tuple]) -> str:\n",
" buffer = \"\"\n",
" for dialogue_turn in chat_history:\n",
" human = \"Human: \" + dialogue_turn[0]\n",
" ai = \"Assistant: \" + dialogue_turn[1]\n",
" buffer += \"\\n\" + \"\\n\".join([human, ai])\n",
" return buffer"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "5c32cc89",
"metadata": {},
"outputs": [],
"source": [
"_inputs = RunnableMap(\n",
" {\n",
" \"standalone_question\": {\n",
" \"question\": lambda x: x[\"question\"],\n",
" \"chat_history\": lambda x: _format_chat_history(x['chat_history'])\n",
" } | CONDENSE_QUESTION_PROMPT | ChatOpenAI(temperature=0) | StrOutputParser(),\n",
" }\n",
")\n",
"_context = {\n",
" \"context\": itemgetter(\"standalone_question\") | retriever | _combine_documents,\n",
" \"question\": lambda x: x[\"standalone_question\"]\n",
"}\n",
"conversational_qa_chain = _inputs | _context | ANSWER_PROMPT | ChatOpenAI()"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "135c8205",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content='Harrison was employed at Kensho.', additional_kwargs={}, example=False)"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversational_qa_chain.invoke({\n",
" \"question\": \"where did harrison work?\",\n",
" \"chat_history\": [],\n",
"})"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "424e7e7a",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content='Harrison worked at Kensho.', additional_kwargs={}, example=False)"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversational_qa_chain.invoke({\n",
" \"question\": \"where did he work?\",\n",
" \"chat_history\": [(\"Who wrote this notebook?\", \"Harrison\")],\n",
"})"
]
},
{
"cell_type": "markdown",
"id": "c5543183",
"metadata": {},
"source": [
"### With Memory and returning source documents\n",
"\n",
"This shows how to use memory with the above. For memory, we need to manage that outside at the memory. For returning the retrieved documents, we just need to pass them through all the way."
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "e31dd17c",
"metadata": {},
"outputs": [],
"source": [
"from langchain.memory import ConversationBufferMemory"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "d4bffe94",
"metadata": {},
"outputs": [],
"source": [
"memory = ConversationBufferMemory(return_messages=True, output_key=\"answer\", input_key=\"question\")"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "733be985",
"metadata": {},
"outputs": [],
"source": [
"# First we add a step to load memory\n",
"# This needs to be a RunnableMap because its the first input\n",
"loaded_memory = RunnableMap(\n",
" {\n",
" \"question\": itemgetter(\"question\"),\n",
" \"memory\": memory.load_memory_variables,\n",
" }\n",
")\n",
"# Next we add a step to expand memory into the variables\n",
"expanded_memory = {\n",
" \"question\": itemgetter(\"question\"),\n",
" \"chat_history\": lambda x: x[\"memory\"][\"history\"]\n",
"}\n",
"\n",
"# Now we calculate the standalone question\n",
"standalone_question = {\n",
" \"standalone_question\": {\n",
" \"question\": lambda x: x[\"question\"],\n",
" \"chat_history\": lambda x: _format_chat_history(x['chat_history'])\n",
" } | CONDENSE_QUESTION_PROMPT | ChatOpenAI(temperature=0) | StrOutputParser(),\n",
"}\n",
"# Now we retrieve the documents\n",
"retrieved_documents = {\n",
" \"docs\": itemgetter(\"standalone_question\") | retriever,\n",
" \"question\": lambda x: x[\"standalone_question\"]\n",
"}\n",
"# Now we construct the inputs for the final prompt\n",
"final_inputs = {\n",
" \"context\": lambda x: _combine_documents(x[\"docs\"]),\n",
" \"question\": itemgetter(\"question\")\n",
"}\n",
"# And finally, we do the part that returns the answers\n",
"answer = {\n",
" \"answer\": final_inputs | ANSWER_PROMPT | ChatOpenAI(),\n",
" \"docs\": itemgetter(\"docs\"),\n",
"}\n",
"# And now we put it all together!\n",
"final_chain = loaded_memory | expanded_memory | standalone_question | retrieved_documents | answer"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "806e390c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'answer': AIMessage(content='Harrison was employed at Kensho.', additional_kwargs={}, example=False),\n",
" 'docs': [Document(page_content='harrison worked at kensho', metadata={})]}"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"inputs = {\"question\": \"where did harrison work?\"}\n",
"result = final_chain.invoke(inputs)\n",
"result"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "977399fd",
"metadata": {},
"outputs": [],
"source": [
"# Note that the memory does not save automatically\n",
"# This will be improved in the future\n",
"# For now you need to save it yourself\n",
"memory.save_context(inputs, {\"answer\": result[\"answer\"].content})"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "f94f7de4",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'history': [HumanMessage(content='where did harrison work?', additional_kwargs={}, example=False),\n",
" AIMessage(content='Harrison was employed at Kensho.', additional_kwargs={}, example=False)]}"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"memory.load_memory_variables({})"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "poetry-venv",
"language": "python",
"name": "poetry-venv"
},
"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"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

227
docs/extras/expression_language/cookbook/sql_db.ipynb Normal file
View File

@ -0,0 +1,227 @@
{
"cells": [
{
"cell_type": "raw",
"id": "c14da114-1a4a-487d-9cff-e0e8c30ba366",
"metadata": {},
"source": [
"---\n",
"sidebar_position: 3\n",
"title: Querying a SQL DB\n",
"---"
]
},
{
"cell_type": "markdown",
"id": "506e9636",
"metadata": {},
"source": [
"We can replicate our SQLDatabaseChain with Runnables."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "7a927516",
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts import ChatPromptTemplate\n",
"\n",
"template = \"\"\"Based on the table schema below, write a SQL query that would answer the user's question:\n",
"{schema}\n",
"\n",
"Question: {question}\n",
"SQL Query:\"\"\"\n",
"prompt = ChatPromptTemplate.from_template(template)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "3f51f386",
"metadata": {},
"outputs": [],
"source": [
"from langchain.utilities import SQLDatabase"
]
},
{
"cell_type": "markdown",
"id": "7c3449d6-684b-416e-ba16-90a035835a88",
"metadata": {},
"source": [
"We'll need the Chinook sample DB for this example. There's many places to download it from, e.g. https://database.guide/2-sample-databases-sqlite/"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "2ccca6fc",
"metadata": {},
"outputs": [],
"source": [
"db = SQLDatabase.from_uri(\"sqlite:///./Chinook.db\")"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "05ba88ee",
"metadata": {},
"outputs": [],
"source": [
"def get_schema(_):\n",
" return db.get_table_info()"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "a4eda902",
"metadata": {},
"outputs": [],
"source": [
"def run_query(query):\n",
" return db.run(query)"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "5046cb17",
"metadata": {},
"outputs": [],
"source": [
"from operator import itemgetter\n",
"\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.schema.output_parser import StrOutputParser\n",
"from langchain.schema.runnable import RunnableLambda, RunnableMap\n",
"\n",
"model = ChatOpenAI()\n",
"\n",
"inputs = {\n",
" \"schema\": RunnableLambda(get_schema),\n",
" \"question\": itemgetter(\"question\")\n",
"}\n",
"sql_response = (\n",
" RunnableMap(inputs)\n",
" | prompt\n",
" | model.bind(stop=[\"\\nSQLResult:\"])\n",
" | StrOutputParser()\n",
" )"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "a5552039",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'SELECT COUNT(*) FROM Employee'"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sql_response.invoke({\"question\": \"How many employees are there?\"})"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "d6fee130",
"metadata": {},
"outputs": [],
"source": [
"template = \"\"\"Based on the table schema below, question, sql query, and sql response, write a natural language response:\n",
"{schema}\n",
"\n",
"Question: {question}\n",
"SQL Query: {query}\n",
"SQL Response: {response}\"\"\"\n",
"prompt_response = ChatPromptTemplate.from_template(template)"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "923aa634",
"metadata": {},
"outputs": [],
"source": [
"full_chain = (\n",
" RunnableMap({\n",
" \"question\": itemgetter(\"question\"),\n",
" \"query\": sql_response,\n",
" }) \n",
" | {\n",
" \"schema\": RunnableLambda(get_schema),\n",
" \"question\": itemgetter(\"question\"),\n",
" \"query\": itemgetter(\"query\"),\n",
" \"response\": lambda x: db.run(x[\"query\"]) \n",
" } \n",
" | prompt_response \n",
" | model\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "e94963d8",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content='There are 8 employees.', additional_kwargs={}, example=False)"
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"full_chain.invoke({\"question\": \"How many employees are there?\"})"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4f358d7b-a721-4db3-9f92-f06913428afc",
"metadata": {},
"outputs": [],
"source": []
}
],
"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"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

122
docs/extras/expression_language/cookbook/tools.ipynb Normal file
View File

@ -0,0 +1,122 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "29781123",
"metadata": {},
"source": [
"# Using tools\n",
"\n",
"You can use any Tools with Runnables easily."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a5c579dd-2e22-41b0-a789-346dfdecb5a2",
"metadata": {},
"outputs": [],
"source": [
"!pip install duckduckgo-search"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "9232d2a9",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.prompts import ChatPromptTemplate\n",
"from langchain.schema.output_parser import StrOutputParser\n",
"from langchain.tools import DuckDuckGoSearchRun"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "a0c64d2c",
"metadata": {},
"outputs": [],
"source": [
"search = DuckDuckGoSearchRun()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "391969b6",
"metadata": {},
"outputs": [],
"source": [
"template = \"\"\"turn the following user input into a search query for a search engine:\n",
"\n",
"{input}\"\"\"\n",
"prompt = ChatPromptTemplate.from_template(template)\n",
"\n",
"model = ChatOpenAI()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "e3d9d20d",
"metadata": {},
"outputs": [],
"source": [
"chain = prompt | model | StrOutputParser() | search"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "55f2967d",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'What sports games are on TV today & tonight? Watch and stream live sports on TV today, tonight, tomorrow. Today\\'s 2023 sports TV schedule includes football, basketball, baseball, hockey, motorsports, soccer and more. Watch on TV or stream online on ESPN, FOX, FS1, CBS, NBC, ABC, Peacock, Paramount+, fuboTV, local channels and many other networks. MLB Games Tonight: How to Watch on TV, Streaming & Odds - Thursday, September 7. Seattle Mariners\\' Julio Rodriguez greets teammates in the dugout after scoring against the Oakland Athletics in a ... Circle - Country Music and Lifestyle. Live coverage of all the MLB action today is available to you, with the information provided below. The Brewers will look to pick up a road win at PNC Park against the Pirates on Wednesday at 12:35 PM ET. Check out the latest odds and with BetMGM Sportsbook. Use bonus code \"GNPLAY\" for special offers! MLB Games Tonight: How to Watch on TV, Streaming & Odds - Tuesday, September 5. Houston Astros\\' Kyle Tucker runs after hitting a double during the fourth inning of a baseball game against the Los Angeles Angels, Sunday, Aug. 13, 2023, in Houston. (AP Photo/Eric Christian Smith) (APMedia) The Houston Astros versus the Texas Rangers is one of ... The second half of tonight\\'s college football schedule still has some good games remaining to watch on your television.. We\\'ve already seen an exciting one when Colorado upset TCU. And we saw some ...'"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.invoke({\"input\": \"I'd like to figure out what games are tonight\"})"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a16949cf-00ea-43c6-a6aa-797ad4f6918d",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "poetry-venv",
"language": "python",
"name": "poetry-venv"
},
"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"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

2
docs/extras/expression_language/how_to/_category_.yml Normal file
View File

@ -0,0 +1,2 @@
label: 'How to'
position: 1

158
docs/extras/expression_language/how_to/functions.ipynb Normal file
View File

@ -0,0 +1,158 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "fbc4bf6e",
"metadata": {},
"source": [
"# Run arbitrary functions\n",
"\n",
"You can use arbitrary functions in the pipeline\n",
"\n",
"Note that all inputs to these functions need to be a SINGLE argument. If you have a function that accepts multiple arguments, you should write a wrapper that accepts a single input and unpacks it into multiple argument."
]
},
{
"cell_type": "code",
"execution_count": 77,
"id": "6bb221b3",
"metadata": {},
"outputs": [],
"source": [
"from langchain.schema.runnable import RunnableLambda\n",
"\n",
"def length_function(text):\n",
" return len(text)\n",
"\n",
"def _multiple_length_function(text1, text2):\n",
" return len(text1) * len(text2)\n",
"\n",
"def multiple_length_function(_dict):\n",
" return _multiple_length_function(_dict[\"text1\"], _dict[\"text2\"])\n",
"\n",
"prompt = ChatPromptTemplate.from_template(\"what is {a} + {b}\")\n",
"\n",
"chain1 = prompt | model\n",
"\n",
"chain = {\n",
" \"a\": itemgetter(\"foo\") | RunnableLambda(length_function),\n",
" \"b\": {\"text1\": itemgetter(\"foo\"), \"text2\": itemgetter(\"bar\")} | RunnableLambda(multiple_length_function)\n",
"} | prompt | model"
]
},
{
"cell_type": "code",
"execution_count": 78,
"id": "5488ec85",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content='3 + 9 equals 12.', additional_kwargs={}, example=False)"
]
},
"execution_count": 78,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chain.invoke({\"foo\": \"bar\", \"bar\": \"gah\"})"
]
},
{
"cell_type": "markdown",
"id": "4728ddd9-914d-42ce-ae9b-72c9ce8ec940",
"metadata": {},
"source": [
"## Accepting a Runnable Config\n",
"\n",
"Runnable lambdas can optionally accept a [RunnableConfig](https://api.python.langchain.com/en/latest/schema/langchain.schema.runnable.config.RunnableConfig.html?highlight=runnableconfig#langchain.schema.runnable.config.RunnableConfig), which they can use to pass callbacks, tags, and other configuration information to nested runs."
]
},
{
"cell_type": "code",
"execution_count": 139,
"id": "80b3b5f6-5d58-44b9-807e-cce9a46bf49f",
"metadata": {},
"outputs": [],
"source": [
"from langchain.schema.runnable import RunnableConfig"
]
},
{
"cell_type": "code",
"execution_count": 149,
"id": "ff0daf0c-49dd-4d21-9772-e5fa133c5f36",
"metadata": {},
"outputs": [],
"source": [
"import json\n",
"\n",
"def parse_or_fix(text: str, config: RunnableConfig):\n",
" fixing_chain = (\n",
" ChatPromptTemplate.from_template(\n",
" \"Fix the following text:\\n\\n```text\\n{input}\\n```\\nError: {error}\"\n",
" \" Don't narrate, just respond with the fixed data.\"\n",
" )\n",
" | ChatOpenAI()\n",
" | StrOutputParser()\n",
" )\n",
" for _ in range(3):\n",
" try:\n",
" return json.loads(text)\n",
" except Exception as e:\n",
" text = fixing_chain.invoke({\"input\": text, \"error\": e}, config)\n",
" return \"Failed to parse\""
]
},
{
"cell_type": "code",
"execution_count": 152,
"id": "1a5e709e-9d75-48c7-bb9c-503251990505",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Tokens Used: 65\n",
"\tPrompt Tokens: 56\n",
"\tCompletion Tokens: 9\n",
"Successful Requests: 1\n",
"Total Cost (USD): $0.00010200000000000001\n"
]
}
],
"source": [
"from langchain.callbacks import get_openai_callback\n",
"\n",
"with get_openai_callback() as cb:\n",
" RunnableLambda(parse_or_fix).invoke(\"{foo: bar}\", {\"tags\": [\"my-tag\"], \"callbacks\": [cb]})\n",
" print(cb)"
]
}
],
"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"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

15
docs/extras/expression_language/interface.ipynb
View File

@ -1,12 +1,21 @@
{ {
"cells": [ "cells": [
{
"cell_type": "raw",
"id": "366a0e68-fd67-4fe5-a292-5c33733339ea",
"metadata": {},
"source": [
"---\n",
"sidebar_position: 0\n",
"title: Interface\n",
"---"
]
},
{ {
"cell_type": "markdown", "cell_type": "markdown",
"id": "9a9acd2e", "id": "9a9acd2e",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Interface\n",
"\n",
"In an effort to make it as easy as possible to create custom chains, we've implemented a [\"Runnable\"](https://api.python.langchain.com/en/latest/schema/langchain.schema.runnable.Runnable.html#langchain.schema.runnable.Runnable) protocol that most components implement. This is a standard interface with a few different methods, which makes it easy to define custom chains as well as making it possible to invoke them in a standard way. The standard interface exposed includes:\n", "In an effort to make it as easy as possible to create custom chains, we've implemented a [\"Runnable\"](https://api.python.langchain.com/en/latest/schema/langchain.schema.runnable.Runnable.html#langchain.schema.runnable.Runnable) protocol that most components implement. This is a standard interface with a few different methods, which makes it easy to define custom chains as well as making it possible to invoke them in a standard way. The standard interface exposed includes:\n",
"\n", "\n",
"- `stream`: stream back chunks of the response\n", "- `stream`: stream back chunks of the response\n",
@ -429,7 +438,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.10.1" "version": "3.9.1"
} }
}, },
"nbformat": 4, "nbformat": 4,

6
docs/extras/guides/privacy/presidio_data_anonymization.ipynb → docs/extras/guides/privacy/presidio_data_anonymization/index.ipynb
View File

@ -6,7 +6,7 @@
"source": [ "source": [
"# Data anonymization with Microsoft Presidio\n", "# Data anonymization with Microsoft Presidio\n",
"\n", "\n",
"[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/privacy/presidio_data_anonymization.ipynb)\n", "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/privacy/presidio_data_anonymization/index.ipynb)\n",
"\n", "\n",
"## Use case\n", "## Use case\n",
"\n", "\n",
@ -439,8 +439,6 @@
"metadata": {}, "metadata": {},
"source": [ "source": [
"## Future works\n", "## Future works\n",
"\n",
"- **deanonymization** - add the ability to reverse anonymization. For example, the workflow could look like this: `anonymize -> LLMChain -> deanonymize`. By doing this, we will retain anonymity in requests to, for example, OpenAI, and then be able restore the original data.\n",
"- **instance anonymization** - at this point, each occurrence of PII is treated as a separate entity and separately anonymized. Therefore, two occurrences of the name John Doe in the text will be changed to two different names. It is therefore worth introducing support for full instance detection, so that repeated occurrences are treated as a single object." "- **instance anonymization** - at this point, each occurrence of PII is treated as a separate entity and separately anonymized. Therefore, two occurrences of the name John Doe in the text will be changed to two different names. It is therefore worth introducing support for full instance detection, so that repeated occurrences are treated as a single object."
] ]
} }
@ -461,7 +459,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.4" "version": "3.9.1"
} }
}, },
"nbformat": 4, "nbformat": 4,

520
docs/extras/guides/privacy/presidio_data_anonymization/multi_language.ipynb Normal file
View File

@ -0,0 +1,520 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Mutli-language data anonymization with Microsoft Presidio\n",
"\n",
"[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/privacy/presidio_data_anonymization/multi_language.ipynb)\n",
"\n",
"\n",
"## Use case\n",
"\n",
"Multi-language support in data pseudonymization is essential due to differences in language structures and cultural contexts. Different languages may have varying formats for personal identifiers. For example, the structure of names, locations and dates can differ greatly between languages and regions. Furthermore, non-alphanumeric characters, accents, and the direction of writing can impact pseudonymization processes. Without multi-language support, data could remain identifiable or be misinterpreted, compromising data privacy and accuracy. Hence, it enables effective and precise pseudonymization suited for global operations.\n",
"\n",
"## Overview\n",
"\n",
"PII detection in Microsoft Presidio relies on several components - in addition to the usual pattern matching (e.g. using regex), the analyser uses a model for Named Entity Recognition (NER) to extract entities such as:\n",
"- `PERSON`\n",
"- `LOCATION`\n",
"- `DATE_TIME`\n",
"- `NRP`\n",
"- `ORGANIZATION`\n",
"\n",
"[[Source]](https://github.com/microsoft/presidio/blob/main/presidio-analyzer/presidio_analyzer/predefined_recognizers/spacy_recognizer.py)\n",
"\n",
"To handle NER in specific languages, we utilize unique models from the `spaCy` library, recognized for its extensive selection covering multiple languages and sizes. However, it's not restrictive, allowing for integration of alternative frameworks such as [Stanza](https://microsoft.github.io/presidio/analyzer/nlp_engines/spacy_stanza/) or [transformers](https://microsoft.github.io/presidio/analyzer/nlp_engines/transformers/) when necessary.\n",
"\n",
"\n",
"## Quickstart\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"# Install necessary packages\n",
"# ! pip install langchain langchain-experimental openai presidio-analyzer presidio-anonymizer spacy Faker\n",
"# ! python -m spacy download en_core_web_lg"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"from langchain_experimental.data_anonymizer import PresidioReversibleAnonymizer\n",
"\n",
"anonymizer = PresidioReversibleAnonymizer(\n",
" analyzed_fields=[\"PERSON\"],\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"By default, `PresidioAnonymizer` and `PresidioReversibleAnonymizer` use a model trained on English texts, so they handle other languages moderately well. \n",
"\n",
"For example, here the model did not detect the person:"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Me llamo Sofía'"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"anonymizer.anonymize(\"Me llamo Sofía\") # \"My name is Sofía\" in Spanish"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"They may also take words from another language as actual entities. Here, both the word *'Yo'* (*'I'* in Spanish) and *Sofía* have been classified as `PERSON`:"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Bridget Kirk soy Sally Knight'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"anonymizer.anonymize(\"Yo soy Sofía\") # \"I am Sofía\" in Spanish"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"If you want to anonymise texts from other languages, you need to download other models and add them to the anonymiser configuration:"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"# Download the models for the languages you want to use\n",
"# ! python -m spacy download en_core_web_md\n",
"# ! python -m spacy download es_core_news_md"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"nlp_config = {\n",
" \"nlp_engine_name\": \"spacy\",\n",
" \"models\": [\n",
" {\"lang_code\": \"en\", \"model_name\": \"en_core_web_md\"},\n",
" {\"lang_code\": \"es\", \"model_name\": \"es_core_news_md\"},\n",
" ],\n",
"}"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"We have therefore added a Spanish language model. Note also that we have downloaded an alternative model for English as well - in this case we have replaced the large model `en_core_web_lg` (560MB) with its smaller version `en_core_web_md` (40MB) - the size is therefore reduced by 14 times! If you care about the speed of anonymisation, it is worth considering it.\n",
"\n",
"All models for the different languages can be found in the [spaCy documentation](https://spacy.io/usage/models).\n",
"\n",
"Now pass the configuration as the `languages_config` parameter to Anonymiser. As you can see, both previous examples work flawlessly:"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Me llamo Michelle Smith\n",
"Yo soy Rachel Wright\n"
]
}
],
"source": [
"anonymizer = PresidioReversibleAnonymizer(\n",
" analyzed_fields=[\"PERSON\"],\n",
" languages_config=nlp_config,\n",
")\n",
"\n",
"print(\n",
" anonymizer.anonymize(\"Me llamo Sofía\", language=\"es\")\n",
") # \"My name is Sofía\" in Spanish\n",
"print(anonymizer.anonymize(\"Yo soy Sofía\", language=\"es\")) # \"I am Sofía\" in Spanish"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"By default, the language indicated first in the configuration will be used when anonymising text (in this case English):"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"My name is Ronnie Ayala\n"
]
}
],
"source": [
"print(anonymizer.anonymize(\"My name is John\"))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Advanced usage\n",
"\n",
"### Custom labels in NER model"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"It may be that the spaCy model has different class names than those supported by the Microsoft Presidio by default. Take Polish, for example:"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Text: Wiktoria, Start: 12, End: 20, Label: persName\n"
]
}
],
"source": [
"# ! python -m spacy download pl_core_news_md\n",
"\n",
"import spacy\n",
"\n",
"nlp = spacy.load(\"pl_core_news_md\")\n",
"doc = nlp(\"Nazywam się Wiktoria\") # \"My name is Wiktoria\" in Polish\n",
"\n",
"for ent in doc.ents:\n",
" print(\n",
" f\"Text: {ent.text}, Start: {ent.start_char}, End: {ent.end_char}, Label: {ent.label_}\"\n",
" )"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The name *Victoria* was classified as `persName`, which does not correspond to the default class names `PERSON`/`PER` implemented in Microsoft Presidio (look for `CHECK_LABEL_GROUPS` in [SpacyRecognizer implementation](https://github.com/microsoft/presidio/blob/main/presidio-analyzer/presidio_analyzer/predefined_recognizers/spacy_recognizer.py)). \n",
"\n",
"You can find out more about custom labels in spaCy models (including your own, trained ones) in [this thread](https://github.com/microsoft/presidio/issues/851).\n",
"\n",
"That's why our sentence will not be anonymized:"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Nazywam się Wiktoria\n"
]
}
],
"source": [
"nlp_config = {\n",
" \"nlp_engine_name\": \"spacy\",\n",
" \"models\": [\n",
" {\"lang_code\": \"en\", \"model_name\": \"en_core_web_md\"},\n",
" {\"lang_code\": \"es\", \"model_name\": \"es_core_news_md\"},\n",
" {\"lang_code\": \"pl\", \"model_name\": \"pl_core_news_md\"},\n",
" ],\n",
"}\n",
"\n",
"anonymizer = PresidioReversibleAnonymizer(\n",
" analyzed_fields=[\"PERSON\", \"LOCATION\", \"DATE_TIME\"],\n",
" languages_config=nlp_config,\n",
")\n",
"\n",
"print(\n",
" anonymizer.anonymize(\"Nazywam się Wiktoria\", language=\"pl\")\n",
") # \"My name is Wiktoria\" in Polish"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"To address this, create your own `SpacyRecognizer` with your own class mapping and add it to the anonymizer:"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"from presidio_analyzer.predefined_recognizers import SpacyRecognizer\n",
"\n",
"polish_check_label_groups = [\n",
" ({\"LOCATION\"}, {\"placeName\", \"geogName\"}),\n",
" ({\"PERSON\"}, {\"persName\"}),\n",
" ({\"DATE_TIME\"}, {\"date\", \"time\"}),\n",
"]\n",
"\n",
"spacy_recognizer = SpacyRecognizer(\n",
" supported_language=\"pl\",\n",
" check_label_groups=polish_check_label_groups,\n",
")\n",
"\n",
"anonymizer.add_recognizer(spacy_recognizer)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now everything works smoothly:"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Nazywam się Morgan Walters\n"
]
}
],
"source": [
"print(\n",
" anonymizer.anonymize(\"Nazywam się Wiktoria\", language=\"pl\")\n",
") # \"My name is Wiktoria\" in Polish"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Let's try on more complex example:"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Nazywam się Ernest Liu. New Taylorburgh to moje miasto rodzinne. Urodziłam się 1987-01-19\n"
]
}
],
"source": [
"print(\n",
" anonymizer.anonymize(\n",
" \"Nazywam się Wiktoria. Płock to moje miasto rodzinne. Urodziłam się dnia 6 kwietnia 2001 roku\",\n",
" language=\"pl\",\n",
" )\n",
") # \"My name is Wiktoria. Płock is my home town. I was born on 6 April 2001\" in Polish"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"As you can see, thanks to class mapping, the anonymiser can cope with different types of entities. "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Custom language-specific operators\n",
"\n",
"In the example above, the sentence has been anonymised correctly, but the fake data does not fit the Polish language at all. Custom operators can therefore be added, which will resolve the issue:"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"from faker import Faker\n",
"from presidio_anonymizer.entities import OperatorConfig\n",
"\n",
"fake = Faker(locale=\"pl_PL\") # Setting faker to provide Polish data\n",
"\n",
"new_operators = {\n",
" \"PERSON\": OperatorConfig(\"custom\", {\"lambda\": lambda _: fake.first_name_female()}),\n",
" \"LOCATION\": OperatorConfig(\"custom\", {\"lambda\": lambda _: fake.city()}),\n",
"}\n",
"\n",
"anonymizer.add_operators(new_operators)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Nazywam się Marianna. Szczecin to moje miasto rodzinne. Urodziłam się 1976-11-16\n"
]
}
],
"source": [
"print(\n",
" anonymizer.anonymize(\n",
" \"Nazywam się Wiktoria. Płock to moje miasto rodzinne. Urodziłam się dnia 6 kwietnia 2001 roku\",\n",
" language=\"pl\",\n",
" )\n",
") # \"My name is Wiktoria. Płock is my home town. I was born on 6 April 2001\" in Polish"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Limitations\n",
"\n",
"Remember - results are as good as your recognizers and as your NER models!\n",
"\n",
"Look at the example below - we downloaded the small model for Spanish (12MB) and it no longer performs as well as the medium version (40MB):"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Model: es_core_news_sm. Result: Me llamo Sofía\n",
"Model: es_core_news_md. Result: Me llamo Lawrence Davis\n"
]
}
],
"source": [
"# ! python -m spacy download es_core_news_sm\n",
"\n",
"for model in [\"es_core_news_sm\", \"es_core_news_md\"]:\n",
" nlp_config = {\n",
" \"nlp_engine_name\": \"spacy\",\n",
" \"models\": [\n",
" {\"lang_code\": \"es\", \"model_name\": model},\n",
" ],\n",
" }\n",
"\n",
" anonymizer = PresidioReversibleAnonymizer(\n",
" analyzed_fields=[\"PERSON\"],\n",
" languages_config=nlp_config,\n",
" )\n",
"\n",
" print(\n",
" f\"Model: {model}. Result: {anonymizer.anonymize('Me llamo Sofía', language='es')}\"\n",
" )"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"In many cases, even the larger models from spaCy will not be sufficient - there are already other, more complex and better methods of detecting named entities, based on transformers. You can read more about this [here](https://microsoft.github.io/presidio/analyzer/nlp_engines/transformers/)."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Future works\n",
"\n",
"- **automatic language detection** - instead of passing the language as a parameter in `anonymizer.anonymize`, we could detect the language/s beforehand and then use the corresponding NER model."
]
}
],
"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"
}
},
"nbformat": 4,
"nbformat_minor": 4
}

4
docs/extras/guides/privacy/presidio_reversible_anonymization.ipynb → docs/extras/guides/privacy/presidio_data_anonymization/reversible.ipynb
View File

@ -6,7 +6,7 @@
"source": [ "source": [
"# Reversible data anonymization with Microsoft Presidio\n", "# Reversible data anonymization with Microsoft Presidio\n",
"\n", "\n",
"[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/privacy/presidio_reversible_anonymization.ipynb)\n", "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/privacy/presidio_data_anonymization/reversible.ipynb)\n",
"\n", "\n",
"\n", "\n",
"## Use case\n", "## Use case\n",
@ -453,7 +453,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.4" "version": "3.9.1"
} }
}, },
"nbformat": 4, "nbformat": 4,

15
docs/extras/integrations/providers/awadb.md
View File

@ -9,13 +9,20 @@ pip install awadb
``` ```
## VectorStore ## Vector Store
There exists a wrapper around AwaDB vector databases, allowing you to use it as a vectorstore,
whether for semantic search or example selection.
```python ```python
from langchain.vectorstores import AwaDB from langchain.vectorstores import AwaDB
``` ```
For a more detailed walkthrough of the AwaDB wrapper, see [here](/docs/integrations/vectorstores/awadb.html). See a [usage example](/docs/integrations/vectorstores/awadb).
## Text Embedding Model
```python
from langchain.embeddings import AwaEmbeddings
```
See a [usage example](/docs/integrations/text_embedding/awadb).

14
docs/extras/integrations/providers/modelscope.mdx
View File

@ -1,20 +1,24 @@
# ModelScope # ModelScope
>[ModelScope](https://www.modelscope.cn/home) is a big repository of the models and datasets.
This page covers how to use the modelscope ecosystem within LangChain. This page covers how to use the modelscope ecosystem within LangChain.
It is broken into two parts: installation and setup, and then references to specific modelscope wrappers. It is broken into two parts: installation and setup, and then references to specific modelscope wrappers.
## Installation and Setup ## Installation and Setup
* Install the Python SDK with `pip install modelscope` Install the `modelscope` package.
## Wrappers ```bash
pip install modelscope
```
### Embeddings
There exists a modelscope Embeddings wrapper, which you can access with ## Text Embedding Models
```python ```python
from langchain.embeddings import ModelScopeEmbeddings from langchain.embeddings import ModelScopeEmbeddings
``` ```
For a more detailed walkthrough of this, see [this notebook](/docs/integrations/text_embedding/modelscope_hub.html) For a more detailed walkthrough of this, see [this notebook](/docs/integrations/text_embedding/modelscope_hub)

26
docs/extras/integrations/providers/nlpcloud.mdx
View File

@ -1,17 +1,31 @@
# NLPCloud # NLPCloud
This page covers how to use the NLPCloud ecosystem within LangChain. >[NLP Cloud](https://docs.nlpcloud.com/#introduction) is an artificial intelligence platform that allows you to use the most advanced AI engines, and even train your own engines with your own data.
It is broken into two parts: installation and setup, and then references to specific NLPCloud wrappers.
## Installation and Setup ## Installation and Setup
- Install the Python SDK with `pip install nlpcloud`
- Install the `nlpcloud` package.
```bash
pip install nlpcloud
```
- Get an NLPCloud api key and set it as an environment variable (`NLPCLOUD_API_KEY`) - Get an NLPCloud api key and set it as an environment variable (`NLPCLOUD_API_KEY`)
## Wrappers
### LLM ## LLM
See a [usage example](/docs/integrations/llms/nlpcloud).
There exists an NLPCloud LLM wrapper, which you can access with
```python ```python
from langchain.llms import NLPCloud from langchain.llms import NLPCloud
``` ```
## Text Embedding Models
See a [usage example](/docs/integrations/text_embedding/nlp_cloud)
```python
from langchain.embeddings import NLPCloudEmbeddings
```

8
docs/extras/integrations/providers/spacy.mdx
View File

@ -18,3 +18,11 @@ See a [usage example](/docs/modules/data_connection/document_transformers/text_s
```python ```python
from langchain.text_splitter import SpacyTextSplitter from langchain.text_splitter import SpacyTextSplitter
``` ```
## Text Embedding Models
See a [usage example](/docs/integrations/text_embedding/spacy_embedding)
```python
from langchain.embeddings.spacy_embeddings import SpacyEmbeddings
```

5
docs/extras/integrations/providers/vectara/index.mdx
View File

@ -11,9 +11,10 @@ What is Vectara?
- You can use Vectara's integration with LangChain as a Vector store or using the Retriever abstraction. - You can use Vectara's integration with LangChain as a Vector store or using the Retriever abstraction.
## Installation and Setup ## Installation and Setup
To use Vectara with LangChain no special installation steps are required. You just have to provide your customer_id, corpus ID, and an API key created within the Vectara console to enable indexing and searching. To use Vectara with LangChain no special installation steps are required.
To get started, follow our [quickstart](https://docs.vectara.com/docs/quickstart) guide to create an account, a corpus and an API key.
Once you have these, you can provide them as arguments to the Vectara vectorstore, or you can set them as environment variables.
Alternatively these can be provided as environment variables
- export `VECTARA_CUSTOMER_ID`="your_customer_id" - export `VECTARA_CUSTOMER_ID`="your_customer_id"
- export `VECTARA_CORPUS_ID`="your_corpus_id" - export `VECTARA_CORPUS_ID`="your_corpus_id"
- export `VECTARA_API_KEY`="your-vectara-api-key" - export `VECTARA_API_KEY`="your-vectara-api-key"

8
docs/extras/integrations/text_embedding/Awa.ipynb → docs/extras/integrations/text_embedding/awadb.ipynb
View File

@ -5,9 +5,11 @@
"id": "b14a24db", "id": "b14a24db",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# AwaEmbedding\n", "# AwaDB\n",
"\n", "\n",
"This notebook explains how to use AwaEmbedding, which is included in [awadb](https://github.com/awa-ai/awadb), to embedding texts in langchain." ">[AwaDB](https://github.com/awa-ai/awadb) is an AI Native database for the search and storage of embedding vectors used by LLM Applications.\n",
"\n",
"This notebook explains how to use `AwaEmbeddings` in LangChain."
] ]
}, },
{ {
@ -101,7 +103,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.4" "version": "3.10.12"
} }
}, },
"nbformat": 4, "nbformat": 4,

6
docs/extras/integrations/text_embedding/bedrock.ipynb
View File

@ -5,7 +5,9 @@
"id": "75e378f5-55d7-44b6-8e2e-6d7b8b171ec4", "id": "75e378f5-55d7-44b6-8e2e-6d7b8b171ec4",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Bedrock Embeddings" "# Bedrock\n",
"\n",
">[Amazon Bedrock](https://aws.amazon.com/bedrock/) is a fully managed service that makes FMs from leading AI startups and Amazon available via an API, so you can choose from a wide range of FMs to find the model that is best suited for your use case.\n"
] ]
}, },
{ {
@ -91,7 +93,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.9.13" "version": "3.10.12"
} }
}, },
"nbformat": 4, "nbformat": 4,

33
docs/extras/integrations/text_embedding/bge_huggingface.ipynb
View File

@ -5,26 +5,29 @@
"id": "719619d3", "id": "719619d3",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# BGE Hugging Face Embeddings\n", "# BGE on Hugging Face\n",
"\n", "\n",
"This notebook shows how to use BGE Embeddings through Hugging Face" ">[BGE models on the HuggingFace](https://huggingface.co/BAAI/bge-large-en) are [the best open-source embedding models](https://huggingface.co/spaces/mteb/leaderboard).\n",
">BGE model is created by the [Beijing Academy of Artificial Intelligence (BAAI)](https://www.baai.ac.cn/english.html). `BAAI` is a private non-profit organization engaged in AI research and development.\n",
"\n",
"This notebook shows how to use `BGE Embeddings` through `Hugging Face`"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": null,
"id": "f7a54279", "id": "f7a54279",
"metadata": { "metadata": {
"scrolled": true "scrolled": true
}, },
"outputs": [], "outputs": [],
"source": [ "source": [
"# !pip install sentence_transformers" "#!pip install sentence_transformers"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": null,
"id": "9e1d5b6b", "id": "9e1d5b6b",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -43,12 +46,24 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 5,
"id": "e59d1a89", "id": "e59d1a89",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [
{
"data": {
"text/plain": [
"384"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [ "source": [
"embedding = hf.embed_query(\"hi this is harrison\")" "embedding = hf.embed_query(\"hi this is harrison\")\n",
"len(embedding)"
] ]
}, },
{ {
@ -76,7 +91,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.10.1" "version": "3.10.12"
} }
}, },
"nbformat": 4, "nbformat": 4,

9
docs/extras/integrations/text_embedding/google_vertex_ai_palm.ipynb
View File

@ -1,13 +1,14 @@
{ {
"cells": [ "cells": [
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Google Cloud Platform Vertex AI PaLM \n", "# Google Vertex AI PaLM \n",
"\n", "\n",
"Note: This is seperate from the Google PaLM integration, it exposes [Vertex AI PaLM API](https://cloud.google.com/vertex-ai/docs/generative-ai/learn/overview) on Google Cloud. \n", ">[Vertex AI PaLM API](https://cloud.google.com/vertex-ai/docs/generative-ai/learn/overview) is a service on Google Cloud exposing the embedding models. \n",
"\n",
"Note: This integration is seperate from the Google PaLM integration.\n",
"\n", "\n",
"By default, Google Cloud [does not use](https://cloud.google.com/vertex-ai/docs/generative-ai/data-governance#foundation_model_development) Customer Data to train its foundation models as part of Google Cloud`s AI/ML Privacy Commitment. More details about how Google processes data can also be found in [Google's Customer Data Processing Addendum (CDPA)](https://cloud.google.com/terms/data-processing-addendum).\n", "By default, Google Cloud [does not use](https://cloud.google.com/vertex-ai/docs/generative-ai/data-governance#foundation_model_development) Customer Data to train its foundation models as part of Google Cloud`s AI/ML Privacy Commitment. More details about how Google processes data can also be found in [Google's Customer Data Processing Addendum (CDPA)](https://cloud.google.com/terms/data-processing-addendum).\n",
"\n", "\n",
@ -96,7 +97,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.9.1" "version": "3.10.12"
}, },
"vscode": { "vscode": {
"interpreter": { "interpreter": {

20
docs/extras/integrations/text_embedding/modelscope_hub.ipynb
View File

@ -1,12 +1,13 @@
{ {
"cells": [ "cells": [
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# ModelScope\n", "# ModelScope\n",
"\n", "\n",
">[ModelScope](https://www.modelscope.cn/home) is big repository of the models and datasets.\n",
"\n",
"Let's load the ModelScope Embedding class." "Let's load the ModelScope Embedding class."
] ]
}, },
@ -67,16 +68,23 @@
], ],
"metadata": { "metadata": {
"kernelspec": { "kernelspec": {
"display_name": "chatgpt", "display_name": "Python 3 (ipykernel)",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
"language_info": { "language_info": {
"name": "python", "codemirror_mode": {
"version": "3.9.15" "name": "ipython",
"version": 3
}, },
"orig_nbformat": 4 "file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.12"
}
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2 "nbformat_minor": 4
} }

17
docs/extras/integrations/text_embedding/mosaicml.ipynb
View File

@ -1,15 +1,14 @@
{ {
"cells": [ "cells": [
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# MosaicML embeddings\n", "# MosaicML\n",
"\n", "\n",
"[MosaicML](https://docs.mosaicml.com/en/latest/inference.html) offers a managed inference service. You can either use a variety of open source models, or deploy your own.\n", ">[MosaicML](https://docs.mosaicml.com/en/latest/inference.html) offers a managed inference service. You can either use a variety of open source models, or deploy your own.\n",
"\n", "\n",
"This example goes over how to use LangChain to interact with MosaicML Inference for text embedding." "This example goes over how to use LangChain to interact with `MosaicML` Inference for text embedding."
] ]
}, },
{ {
@ -94,6 +93,11 @@
} }
], ],
"metadata": { "metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": { "language_info": {
"codemirror_mode": { "codemirror_mode": {
"name": "ipython", "name": "ipython",
@ -103,9 +107,10 @@
"mimetype": "text/x-python", "mimetype": "text/x-python",
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3" "pygments_lexer": "ipython3",
"version": "3.10.12"
} }
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2 "nbformat_minor": 4
} }

6
docs/extras/integrations/text_embedding/nlp_cloud.ipynb
View File

@ -7,7 +7,7 @@
"source": [ "source": [
"# NLP Cloud\n", "# NLP Cloud\n",
"\n", "\n",
"NLP Cloud is an artificial intelligence platform that allows you to use the most advanced AI engines, and even train your own engines with your own data. \n", ">[NLP Cloud](https://docs.nlpcloud.com/#introduction) is an artificial intelligence platform that allows you to use the most advanced AI engines, and even train your own engines with your own data. \n",
"\n", "\n",
"The [embeddings](https://docs.nlpcloud.com/#embeddings) endpoint offers the following model:\n", "The [embeddings](https://docs.nlpcloud.com/#embeddings) endpoint offers the following model:\n",
"\n", "\n",
@ -80,7 +80,7 @@
], ],
"metadata": { "metadata": {
"kernelspec": { "kernelspec": {
"display_name": "Python 3.11.2 64-bit", "display_name": "Python 3 (ipykernel)",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
@ -94,7 +94,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.2" "version": "3.10.12"
}, },
"vscode": { "vscode": {
"interpreter": { "interpreter": {

10
docs/extras/integrations/text_embedding/sagemaker-endpoint.ipynb
View File

@ -5,11 +5,13 @@
"id": "1f83f273", "id": "1f83f273",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# SageMaker Endpoint Embeddings\n", "# SageMaker\n",
"\n", "\n",
"Let's load the SageMaker Endpoints Embeddings class. The class can be used if you host, e.g. your own Hugging Face model on SageMaker.\n", "Let's load the `SageMaker Endpoints Embeddings` class. The class can be used if you host, e.g. your own Hugging Face model on SageMaker.\n",
"\n", "\n",
"For instructions on how to do this, please see [here](https://www.philschmid.de/custom-inference-huggingface-sagemaker). **Note**: In order to handle batched requests, you will need to adjust the return line in the `predict_fn()` function within the custom `inference.py` script:\n", "For instructions on how to do this, please see [here](https://www.philschmid.de/custom-inference-huggingface-sagemaker). \n",
"\n",
"**Note**: In order to handle batched requests, you will need to adjust the return line in the `predict_fn()` function within the custom `inference.py` script:\n",
"\n", "\n",
"Change from\n", "Change from\n",
"\n", "\n",
@ -143,7 +145,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.9.1" "version": "3.10.12"
}, },
"vscode": { "vscode": {
"interpreter": { "interpreter": {

10
docs/extras/integrations/text_embedding/self-hosted.ipynb
View File

@ -5,8 +5,8 @@
"id": "eec4efda", "id": "eec4efda",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Self Hosted Embeddings\n", "# Self Hosted\n",
"Let's load the SelfHostedEmbeddings, SelfHostedHuggingFaceEmbeddings, and SelfHostedHuggingFaceInstructEmbeddings classes." "Let's load the `SelfHostedEmbeddings`, `SelfHostedHuggingFaceEmbeddings`, and `SelfHostedHuggingFaceInstructEmbeddings` classes."
] ]
}, },
{ {
@ -149,9 +149,7 @@
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "fc1bfd0f", "id": "fc1bfd0f",
"metadata": { "metadata": {},
"scrolled": false
},
"outputs": [], "outputs": [],
"source": [ "source": [
"query_result = embeddings.embed_query(text)" "query_result = embeddings.embed_query(text)"
@ -182,7 +180,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.9.1" "version": "3.10.12"
}, },
"vscode": { "vscode": {
"interpreter": { "interpreter": {

9
docs/extras/integrations/text_embedding/sentence_transformers.ipynb
View File

@ -1,16 +1,15 @@
{ {
"cells": [ "cells": [
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"id": "ed47bb62", "id": "ed47bb62",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Sentence Transformers Embeddings\n", "# Sentence Transformers\n",
"\n", "\n",
"[SentenceTransformers](https://www.sbert.net/) embeddings are called using the `HuggingFaceEmbeddings` integration. We have also added an alias for `SentenceTransformerEmbeddings` for users who are more familiar with directly using that package.\n", ">[SentenceTransformers](https://www.sbert.net/) embeddings are called using the `HuggingFaceEmbeddings` integration. We have also added an alias for `SentenceTransformerEmbeddings` for users who are more familiar with directly using that package.\n",
"\n", "\n",
"SentenceTransformers is a python package that can generate text and image embeddings, originating from [Sentence-BERT](https://arxiv.org/abs/1908.10084)" "`SentenceTransformers` is a python package that can generate text and image embeddings, originating from [Sentence-BERT](https://arxiv.org/abs/1908.10084)"
] ]
}, },
{ {
@ -109,7 +108,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.8.16" "version": "3.10.12"
}, },
"vscode": { "vscode": {
"interpreter": { "interpreter": {

55
docs/extras/integrations/text_embedding/spacy_embedding.ipynb
View File

@ -1,21 +1,31 @@
{ {
"cells": [ "cells": [
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"# Spacy Embedding\n", "# SpaCy\n",
"\n", "\n",
"### Loading the Spacy embedding class to generate and query embeddings" ">[spaCy](https://spacy.io/) is an open-source software library for advanced natural language processing, written in the programming languages Python and Cython.\n",
" \n",
"\n",
"## Installation and Setup"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#!pip install spacy"
] ]
}, },
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### Import the necessary classes" "Import the necessary classes"
] ]
}, },
{ {
@ -28,11 +38,12 @@
] ]
}, },
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### Initialize SpacyEmbeddings.This will load the Spacy model into memory." "## Example\n",
"\n",
"Initialize SpacyEmbeddings.This will load the Spacy model into memory."
] ]
}, },
{ {
@ -45,11 +56,10 @@
] ]
}, },
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### Define some example texts . These could be any documents that you want to analyze - for example, news articles, social media posts, or product reviews." "Define some example texts . These could be any documents that you want to analyze - for example, news articles, social media posts, or product reviews."
] ]
}, },
{ {
@ -67,11 +77,10 @@
] ]
}, },
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### Generate and print embeddings for the texts . The SpacyEmbeddings class generates an embedding for each document, which is a numerical representation of the document's content. These embeddings can be used for various natural language processing tasks, such as document similarity comparison or text classification." "Generate and print embeddings for the texts . The SpacyEmbeddings class generates an embedding for each document, which is a numerical representation of the document's content. These embeddings can be used for various natural language processing tasks, such as document similarity comparison or text classification."
] ]
}, },
{ {
@ -86,11 +95,10 @@
] ]
}, },
{ {
"attachments": {},
"cell_type": "markdown", "cell_type": "markdown",
"metadata": {}, "metadata": {},
"source": [ "source": [
"#### Generate and print an embedding for a single piece of text. You can also generate an embedding for a single piece of text, such as a search query. This can be useful for tasks like information retrieval, where you want to find documents that are similar to a given query." "Generate and print an embedding for a single piece of text. You can also generate an embedding for a single piece of text, such as a search query. This can be useful for tasks like information retrieval, where you want to find documents that are similar to a given query."
] ]
}, },
{ {
@ -106,11 +114,24 @@
} }
], ],
"metadata": { "metadata": {
"language_info": { "kernelspec": {
"name": "python" "display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
}, },
"orig_nbformat": 4 "language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.12"
}
}, },
"nbformat": 4, "nbformat": 4,
"nbformat_minor": 2 "nbformat_minor": 4
} }

48
docs/extras/integrations/vectorstores/supabase.ipynb
View File

@ -28,43 +28,41 @@
"The following function determines cosine similarity, but you can adjust to your needs.\n", "The following function determines cosine similarity, but you can adjust to your needs.\n",
"\n", "\n",
"```sql\n", "```sql\n",
" -- Enable the pgvector extension to work with embedding vectors\n", "-- Enable the pgvector extension to work with embedding vectors\n",
" create extension vector;\n", "create extension if not exists vector;\n",
"\n", "\n",
" -- Create a table to store your documents\n", "-- Create a table to store your documents\n",
" create table documents (\n", "create table\n",
" documents (\n",
" id uuid primary key,\n", " id uuid primary key,\n",
" content text, -- corresponds to Document.pageContent\n", " content text, -- corresponds to Document.pageContent\n",
" metadata jsonb, -- corresponds to Document.metadata\n", " metadata jsonb, -- corresponds to Document.metadata\n",
" embedding vector(1536) -- 1536 works for OpenAI embeddings, change if needed\n", " embedding vector (1536) -- 1536 works for OpenAI embeddings, change if needed\n",
" );\n", " );\n",
"\n", "\n",
" CREATE FUNCTION match_documents(query_embedding vector(1536), match_count int)\n", "-- Create a function to search for documents\n",
" RETURNS TABLE(\n", "create function match_documents (\n",
" query_embedding vector (1536),\n",
" filter jsonb default '{}'\n",
") returns table (\n",
" id uuid,\n", " id uuid,\n",
" content text,\n", " content text,\n",
" metadata jsonb,\n", " metadata jsonb,\n",
" -- we return matched vectors to enable maximal marginal relevance searches\n", " similarity float\n",
" embedding vector(1536),\n", ") language plpgsql as $$\n",
" similarity float)\n", "#variable_conflict use_column\n",
" LANGUAGE plpgsql\n", "begin\n",
" AS $$\n", " return query\n",
" # variable_conflict use_column\n", " select\n",
" BEGIN\n",
" RETURN query\n",
" SELECT\n",
" id,\n", " id,\n",
" content,\n", " content,\n",
" metadata,\n", " metadata,\n",
" embedding,\n", " 1 - (documents.embedding <=> query_embedding) as similarity\n",
" 1 -(documents.embedding <=> query_embedding) AS similarity\n", " from documents\n",
" FROM\n", " where metadata @> filter\n",
" documents\n", " order by documents.embedding <=> query_embedding;\n",
" ORDER BY\n", "end;\n",
" documents.embedding <=> query_embedding\n", "$$;\n",
" LIMIT match_count;\n",
" END;\n",
" $$;\n",
"```" "```"
] ]
}, },

178
docs/extras/integrations/vectorstores/vectara.ipynb
View File

@ -26,7 +26,7 @@
"source": [ "source": [
"# Setup\n", "# Setup\n",
"\n", "\n",
"You will need a Vectara account to use Vectara with LangChain. To get started, use the following steps:\n", "You will need a Vectara account to use Vectara with LangChain. To get started, use the following steps (see our [quickstart](https://docs.vectara.com/docs/quickstart) guide):\n",
"1. [Sign up](https://console.vectara.com/signup) for a Vectara account if you don't already have one. Once you have completed your sign up you will have a Vectara customer ID. You can find your customer ID by clicking on your name, on the top-right of the Vectara console window.\n", "1. [Sign up](https://console.vectara.com/signup) for a Vectara account if you don't already have one. Once you have completed your sign up you will have a Vectara customer ID. You can find your customer ID by clicking on your name, on the top-right of the Vectara console window.\n",
"2. Within your account you can create one or more corpora. Each corpus represents an area that stores text data upon ingest from input documents. To create a corpus, use the **\"Create Corpus\"** button. You then provide a name to your corpus as well as a description. Optionally you can define filtering attributes and apply some advanced options. If you click on your created corpus, you can see its name and corpus ID right on the top.\n", "2. Within your account you can create one or more corpora. Each corpus represents an area that stores text data upon ingest from input documents. To create a corpus, use the **\"Create Corpus\"** button. You then provide a name to your corpus as well as a description. Optionally you can define filtering attributes and apply some advanced options. If you click on your created corpus, you can see its name and corpus ID right on the top.\n",
"3. Next you'll need to create API keys to access the corpus. Click on the **\"Authorization\"** tab in the corpus view and then the **\"Create API Key\"** button. Give your key a name, and choose whether you want query only or query+index for your key. Click \"Create\" and you now have an active API key. Keep this key confidential. \n", "3. Next you'll need to create API keys to access the corpus. Click on the **\"Authorization\"** tab in the corpus view and then the **\"Create API Key\"** button. Give your key a name, and choose whether you want query only or query+index for your key. Click \"Create\" and you now have an active API key. Keep this key confidential. \n",
@ -47,7 +47,7 @@
"os.environ[\"VECTARA_API_KEY\"] = getpass.getpass(\"Vectara API Key:\")\n", "os.environ[\"VECTARA_API_KEY\"] = getpass.getpass(\"Vectara API Key:\")\n",
"```\n", "```\n",
"\n", "\n",
"2. Add them to the Vectara vectorstore constructor:\n", "1. Provide them as arguments when creating the Vectara vectorstore object:\n",
"\n", "\n",
"```python\n", "```python\n",
"vectorstore = Vectara(\n", "vectorstore = Vectara(\n",
@ -65,13 +65,22 @@
"source": [ "source": [
"## Connecting to Vectara from LangChain\n", "## Connecting to Vectara from LangChain\n",
"\n", "\n",
"To get started, let's ingest the documents using the from_documents() method.\n", "In this example, we assume that you've created an account and a corpus, and added your VECTARA_CUSTOMER_ID, VECTARA_CORPUS_ID and VECTARA_API_KEY (created with permissions for both indexing and query) as environment variables.\n",
"We assume here that you've added your VECTARA_CUSTOMER_ID, VECTARA_CORPUS_ID and query+indexing VECTARA_API_KEY as environment variables." "\n",
"The corpus has 3 fields defined as metadata for filtering:\n",
"* url: a string field containing the source URL of the document (where relevant)\n",
"* speech: a string field containing the name of the speech\n",
"* author: the name of the author\n",
"\n",
"Let's start by ingesting 3 documents into the corpus:\n",
"1. The State of the Union speech from 2022, available in the LangChain repository as a text file\n",
"2. The \"I have a dream\" speech by Dr. Kind\n",
"3. The \"We shall Fight on the Beaches\" speech by Winston Churchil"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 1, "execution_count": 2,
"id": "04a1f1a0", "id": "04a1f1a0",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -79,12 +88,17 @@
"from langchain.embeddings import FakeEmbeddings\n", "from langchain.embeddings import FakeEmbeddings\n",
"from langchain.text_splitter import CharacterTextSplitter\n", "from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores import Vectara\n", "from langchain.vectorstores import Vectara\n",
"from langchain.document_loaders import TextLoader" "from langchain.document_loaders import TextLoader\n",
"\n",
"from langchain.llms import OpenAI\n",
"from langchain.chains import ConversationalRetrievalChain\n",
"from langchain.retrievers.self_query.base import SelfQueryRetriever\n",
"from langchain.chains.query_constructor.base import AttributeInfo"
] ]
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 2, "execution_count": 3,
"id": "be0a4973", "id": "be0a4973",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -97,7 +111,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 3, "execution_count": 4,
"id": "8429667e", "id": "8429667e",
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
@ -111,7 +125,7 @@
"vectara = Vectara.from_documents(\n", "vectara = Vectara.from_documents(\n",
" docs,\n", " docs,\n",
" embedding=FakeEmbeddings(size=768),\n", " embedding=FakeEmbeddings(size=768),\n",
" doc_metadata={\"speech\": \"state-of-the-union\"},\n", " doc_metadata={\"speech\": \"state-of-the-union\", \"author\": \"Biden\"},\n",
")" ")"
] ]
}, },
@ -130,7 +144,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 4, "execution_count": 5,
"id": "85ef3468", "id": "85ef3468",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
@ -142,14 +156,16 @@
" [\n", " [\n",
" \"https://www.gilderlehrman.org/sites/default/files/inline-pdfs/king.dreamspeech.excerpts.pdf\",\n", " \"https://www.gilderlehrman.org/sites/default/files/inline-pdfs/king.dreamspeech.excerpts.pdf\",\n",
" \"I-have-a-dream\",\n", " \"I-have-a-dream\",\n",
" \"Dr. King\"\n",
" ],\n", " ],\n",
" [\n", " [\n",
" \"https://www.parkwayschools.net/cms/lib/MO01931486/Centricity/Domain/1578/Churchill_Beaches_Speech.pdf\",\n", " \"https://www.parkwayschools.net/cms/lib/MO01931486/Centricity/Domain/1578/Churchill_Beaches_Speech.pdf\",\n",
" \"we shall fight on the beaches\",\n", " \"we shall fight on the beaches\",\n",
" \"Churchil\"\n",
" ],\n", " ],\n",
"]\n", "]\n",
"files_list = []\n", "files_list = []\n",
"for url, _ in urls:\n", "for url, _, _ in urls:\n",
" name = tempfile.NamedTemporaryFile().name\n", " name = tempfile.NamedTemporaryFile().name\n",
" urllib.request.urlretrieve(url, name)\n", " urllib.request.urlretrieve(url, name)\n",
" files_list.append(name)\n", " files_list.append(name)\n",
@ -157,7 +173,7 @@
"docsearch: Vectara = Vectara.from_files(\n", "docsearch: Vectara = Vectara.from_files(\n",
" files=files_list,\n", " files=files_list,\n",
" embedding=FakeEmbeddings(size=768),\n", " embedding=FakeEmbeddings(size=768),\n",
" metadatas=[{\"url\": url, \"speech\": title} for url, title in urls],\n", " metadatas=[{\"url\": url, \"speech\": title, \"author\": author} for url, title, author in urls],\n",
")" ")"
] ]
}, },
@ -178,7 +194,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 5, "execution_count": 6,
"id": "a8c513ab", "id": "a8c513ab",
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
@ -197,7 +213,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 6, "execution_count": 7,
"id": "fc516993", "id": "fc516993",
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
@ -231,7 +247,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 7, "execution_count": 8,
"id": "8804a21d", "id": "8804a21d",
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
@ -249,7 +265,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 8, "execution_count": 9,
"id": "756a6887", "id": "756a6887",
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
@ -264,7 +280,7 @@
"text": [ "text": [
"Justice Breyer, thank you for your service. One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence. A former top litigator in private practice.\n", "Justice Breyer, thank you for your service. One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence. A former top litigator in private practice.\n",
"\n", "\n",
"Score: 0.786569\n" "Score: 0.8299499\n"
] ]
} }
], ],
@ -284,7 +300,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 9, "execution_count": 10,
"id": "47784de5", "id": "47784de5",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -307,7 +323,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 10, "execution_count": 11,
"id": "3e22949f", "id": "3e22949f",
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
@ -315,7 +331,7 @@
"name": "stdout", "name": "stdout",
"output_type": "stream", "output_type": "stream",
"text": [ "text": [
"With this threshold of 0.2 we have 3 documents\n" "With this threshold of 0.2 we have 5 documents\n"
] ]
} }
], ],
@ -340,7 +356,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 11, "execution_count": 12,
"id": "9427195f", "id": "9427195f",
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
@ -352,10 +368,10 @@
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"VectaraRetriever(tags=['Vectara'], metadata=None, vectorstore=<langchain.vectorstores.vectara.Vectara object at 0x1586bd330>, search_type='similarity', search_kwargs={'lambda_val': 0.025, 'k': 5, 'filter': '', 'n_sentence_context': '2'})" "VectaraRetriever(tags=['Vectara'], metadata=None, vectorstore=<langchain.vectorstores.vectara.Vectara object at 0x13b15e9b0>, search_type='similarity', search_kwargs={'lambda_val': 0.025, 'k': 5, 'filter': '', 'n_sentence_context': '2'})"
] ]
}, },
"execution_count": 11, "execution_count": 12,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -367,7 +383,7 @@
}, },
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": 12, "execution_count": 13,
"id": "f3c70c31", "id": "f3c70c31",
"metadata": { "metadata": {
"ExecuteTime": { "ExecuteTime": {
@ -379,10 +395,10 @@
{ {
"data": { "data": {
"text/plain": [ "text/plain": [
"Document(page_content='Justice Breyer, thank you for your service. One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence. A former top litigator in private practice.', metadata={'source': 'langchain', 'lang': 'eng', 'offset': '596', 'len': '97', 'speech': 'state-of-the-union'})" "Document(page_content='Justice Breyer, thank you for your service. One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence. A former top litigator in private practice.', metadata={'source': 'langchain', 'lang': 'eng', 'offset': '596', 'len': '97', 'speech': 'state-of-the-union', 'author': 'Biden'})"
] ]
}, },
"execution_count": 12, "execution_count": 13,
"metadata": {}, "metadata": {},
"output_type": "execute_result" "output_type": "execute_result"
} }
@ -392,10 +408,118 @@
"retriever.get_relevant_documents(query)[0]" "retriever.get_relevant_documents(query)[0]"
] ]
}, },
{
"cell_type": "markdown",
"id": "e944c26a",
"metadata": {},
"source": [
"## Using Vectara as a SelfQuery Retriever"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "8be674de",
"metadata": {},
"outputs": [],
"source": [
"metadata_field_info = [\n",
" AttributeInfo(\n",
" name=\"speech\",\n",
" description=\"what name of the speech\",\n",
" type=\"string or list[string]\",\n",
" ),\n",
" AttributeInfo(\n",
" name=\"author\",\n",
" description=\"author of the speech\",\n",
" type=\"string or list[string]\",\n",
" ),\n",
"]\n",
"document_content_description = \"the text of the speech\"\n",
"\n",
"vectordb = Vectara()\n",
"llm = OpenAI(temperature=0)\n",
"retriever = SelfQueryRetriever.from_llm(llm, vectara, \n",
" document_content_description, metadata_field_info, \n",
" verbose=True)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "f8938999",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/ofer/dev/langchain/libs/langchain/langchain/chains/llm.py:278: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"query='freedom' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='author', value='Biden') limit=None\n"
]
},
{
"data": {
"text/plain": [
"[Document(page_content='Well I know this nation. We will meet the test. To protect freedom and liberty, to expand fairness and opportunity. We will save democracy. As hard as these times have been, I am more optimistic about America today than I have been my whole life.', metadata={'source': 'langchain', 'lang': 'eng', 'offset': '346', 'len': '67', 'speech': 'state-of-the-union', 'author': 'Biden'}),\n",
" Document(page_content='To our fellow Ukrainian Americans who forge a deep bond that connects our two nations we stand with you. Putin may circle Kyiv with tanks, but he will never gain the hearts and souls of the Ukrainian people. He will never extinguish their love of freedom. He will never weaken the resolve of the free world. We meet tonight in an America that has lived through two of the hardest years this nation has ever faced.', metadata={'source': 'langchain', 'lang': 'eng', 'offset': '740', 'len': '47', 'speech': 'state-of-the-union', 'author': 'Biden'}),\n",
" Document(page_content='But most importantly as Americans. With a duty to one another to the American people to the Constitution. And with an unwavering resolve that freedom will always triumph over tyranny. Six days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways. But he badly miscalculated.', metadata={'source': 'langchain', 'lang': 'eng', 'offset': '413', 'len': '77', 'speech': 'state-of-the-union', 'author': 'Biden'}),\n",
" Document(page_content='We can do this. \\n\\nMy fellow Americans—tonight , we have gathered in a sacred space—the citadel of our democracy. In this Capitol, generation after generation, Americans have debated great questions amid great strife, and have done great things. We have fought for freedom, expanded liberty, defeated totalitarianism and terror. And built the strongest, freest, and most prosperous nation the world has ever known. Now is the hour. \\n\\nOur moment of responsibility.', metadata={'source': 'langchain', 'lang': 'eng', 'offset': '906', 'len': '82', 'speech': 'state-of-the-union', 'author': 'Biden'}),\n",
" Document(page_content='In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. We cannot let this happen. Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections.', metadata={'source': 'langchain', 'lang': 'eng', 'offset': '0', 'len': '63', 'speech': 'state-of-the-union', 'author': 'Biden'})]"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"retriever.get_relevant_documents(\"what did Biden say about the freedom?\")"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "a97037fb",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query='freedom' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='author', value='Dr. King') limit=None\n"
]
},
{
"data": {
"text/plain": [
"[Document(page_content='And if America is to be a great nation, this must become true. So\\nlet freedom ring from the prodigious hilltops of New Hampshire. Let freedom ring from the mighty\\nmountains of New York. Let freedom ring from the heightening Alleghenies of Pennsylvania. Let\\nfreedom ring from the snowcapped Rockies of Colorado.', metadata={'lang': 'eng', 'section': '3', 'offset': '1534', 'len': '55', 'CreationDate': '1424880481', 'Producer': 'Adobe PDF Library 10.0', 'Author': 'Sasha Rolon-Pereira', 'Title': 'Martin Luther King Jr.pdf', 'Creator': 'Acrobat PDFMaker 10.1 for Word', 'ModDate': '1424880524', 'url': 'https://www.gilderlehrman.org/sites/default/files/inline-pdfs/king.dreamspeech.excerpts.pdf', 'speech': 'I-have-a-dream', 'author': 'Dr. King', 'title': 'Martin Luther King Jr.pdf'}),\n",
" Document(page_content='And if America is to be a great nation, this must become true. So\\nlet freedom ring from the prodigious hilltops of New Hampshire. Let freedom ring from the mighty\\nmountains of New York. Let freedom ring from the heightening Alleghenies of Pennsylvania. Let\\nfreedom ring from the snowcapped Rockies of Colorado.', metadata={'lang': 'eng', 'section': '3', 'offset': '1534', 'len': '55', 'CreationDate': '1424880481', 'Producer': 'Adobe PDF Library 10.0', 'Author': 'Sasha Rolon-Pereira', 'Title': 'Martin Luther King Jr.pdf', 'Creator': 'Acrobat PDFMaker 10.1 for Word', 'ModDate': '1424880524', 'url': 'https://www.gilderlehrman.org/sites/default/files/inline-pdfs/king.dreamspeech.excerpts.pdf', 'speech': 'I-have-a-dream', 'author': 'Dr. King', 'title': 'Martin Luther King Jr.pdf'}),\n",
" Document(page_content='Let freedom ring from the curvaceous slopes of\\nCalifornia. But not only that. Let freedom ring from Stone Mountain of Georgia. Let freedom ring from Lookout\\nMountain of Tennessee. Let freedom ring from every hill and molehill of Mississippi, from every\\nmountain side. Let freedom ring . . .\\nWhen we allow freedom to ring—when we let it ring from every city and every hamlet, from every state\\nand every city, we will be able to speed up that day when all of God’s children, black men and white\\nmen, Jews and Gentiles, Protestants and Catholics, will be able to join hands and sing in the words of the\\nold Negro spiritual, “Free at last, Free at last, Great God a-mighty, We are free at last.”', metadata={'lang': 'eng', 'section': '3', 'offset': '1842', 'len': '52', 'CreationDate': '1424880481', 'Producer': 'Adobe PDF Library 10.0', 'Author': 'Sasha Rolon-Pereira', 'Title': 'Martin Luther King Jr.pdf', 'Creator': 'Acrobat PDFMaker 10.1 for Word', 'ModDate': '1424880524', 'url': 'https://www.gilderlehrman.org/sites/default/files/inline-pdfs/king.dreamspeech.excerpts.pdf', 'speech': 'I-have-a-dream', 'author': 'Dr. King', 'title': 'Martin Luther King Jr.pdf'}),\n",
" Document(page_content='Let freedom ring from the curvaceous slopes of\\nCalifornia. But not only that. Let freedom ring from Stone Mountain of Georgia. Let freedom ring from Lookout\\nMountain of Tennessee. Let freedom ring from every hill and molehill of Mississippi, from every\\nmountain side. Let freedom ring . . .\\nWhen we allow freedom to ring—when we let it ring from every city and every hamlet, from every state\\nand every city, we will be able to speed up that day when all of God’s children, black men and white\\nmen, Jews and Gentiles, Protestants and Catholics, will be able to join hands and sing in the words of the\\nold Negro spiritual, “Free at last, Free at last, Great God a-mighty, We are free at last.”', metadata={'lang': 'eng', 'section': '3', 'offset': '1842', 'len': '52', 'CreationDate': '1424880481', 'Producer': 'Adobe PDF Library 10.0', 'Author': 'Sasha Rolon-Pereira', 'Title': 'Martin Luther King Jr.pdf', 'Creator': 'Acrobat PDFMaker 10.1 for Word', 'ModDate': '1424880524', 'url': 'https://www.gilderlehrman.org/sites/default/files/inline-pdfs/king.dreamspeech.excerpts.pdf', 'speech': 'I-have-a-dream', 'author': 'Dr. King', 'title': 'Martin Luther King Jr.pdf'}),\n",
" Document(page_content='Let freedom ring from the mighty\\nmountains of New York. Let freedom ring from the heightening Alleghenies of Pennsylvania. Let\\nfreedom ring from the snowcapped Rockies of Colorado. Let freedom ring from the curvaceous slopes of\\nCalifornia. But not only that. Let freedom ring from Stone Mountain of Georgia.', metadata={'lang': 'eng', 'section': '3', 'offset': '1657', 'len': '57', 'CreationDate': '1424880481', 'Producer': 'Adobe PDF Library 10.0', 'Author': 'Sasha Rolon-Pereira', 'Title': 'Martin Luther King Jr.pdf', 'Creator': 'Acrobat PDFMaker 10.1 for Word', 'ModDate': '1424880524', 'url': 'https://www.gilderlehrman.org/sites/default/files/inline-pdfs/king.dreamspeech.excerpts.pdf', 'speech': 'I-have-a-dream', 'author': 'Dr. King', 'title': 'Martin Luther King Jr.pdf'})]"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"retriever.get_relevant_documents(\"what did Dr. King say about the freedom?\")"
]
},
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": null,
"id": "2300e785", "id": "f6d17e90",
"metadata": {}, "metadata": {},
"outputs": [], "outputs": [],
"source": [] "source": []

587
docs/extras/modules/data_connection/retrievers/self_query/supabase_self_query.ipynb Normal file
View File

@ -0,0 +1,587 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "13afcae7",
"metadata": {},
"source": [
"# Supabase Vector self-querying \n",
"\n",
">[Supabase](https://supabase.com/docs) is an open source `Firebase` alternative. \n",
"> `Supabase` is built on top of `PostgreSQL`, which offers strong `SQL` \n",
"> querying capabilities and enables a simple interface with already-existing tools and frameworks.\n",
"\n",
">[PostgreSQL](https://en.wikipedia.org/wiki/PostgreSQL) also known as `Postgres`,\n",
"> is a free and open-source relational database management system (RDBMS) \n",
"> emphasizing extensibility and `SQL` compliance.\n",
"\n",
"In the notebook we'll demo the `SelfQueryRetriever` wrapped around a Supabase vector store.\n",
"\n",
"Specifically we will:\n",
"1. Create a Supabase database\n",
"2. Enable the `pgvector` extension\n",
"3. Create a `documents` table and `match_documents` function that will be used by `SupabaseVectorStore`\n",
"4. Load sample documents into the vector store (database table)\n",
"5. Build and test a self-querying retriever"
]
},
{
"cell_type": "markdown",
"id": "347935ad",
"metadata": {},
"source": [
"## Setup Supabase Database\n",
"\n",
"1. Head over to https://database.new to provision your Supabase database.\n",
"2. In the studio, jump to the [SQL editor](https://supabase.com/dashboard/project/_/sql/new) and run the following script to enable `pgvector` and setup your database as a vector store:\n",
" ```sql\n",
" -- Enable the pgvector extension to work with embedding vectors\n",
" create extension if not exists vector;\n",
"\n",
" -- Create a table to store your documents\n",
" create table\n",
" documents (\n",
" id uuid primary key,\n",
" content text, -- corresponds to Document.pageContent\n",
" metadata jsonb, -- corresponds to Document.metadata\n",
" embedding vector (1536) -- 1536 works for OpenAI embeddings, change if needed\n",
" );\n",
"\n",
" -- Create a function to search for documents\n",
" create function match_documents (\n",
" query_embedding vector (1536),\n",
" filter jsonb default '{}'\n",
" ) returns table (\n",
" id uuid,\n",
" content text,\n",
" metadata jsonb,\n",
" similarity float\n",
" ) language plpgsql as $$\n",
" #variable_conflict use_column\n",
" begin\n",
" return query\n",
" select\n",
" id,\n",
" content,\n",
" metadata,\n",
" 1 - (documents.embedding <=> query_embedding) as similarity\n",
" from documents\n",
" where metadata @> filter\n",
" order by documents.embedding <=> query_embedding;\n",
" end;\n",
" $$;\n",
" ```"
]
},
{
"cell_type": "markdown",
"id": "68e75fb9",
"metadata": {},
"source": [
"## Creating a Supabase vector store\n",
"Next we'll want to create a Supabase vector store and seed it with some data. We've created a small demo set of documents that contain summaries of movies.\n",
"\n",
"Be sure to install the latest version of `langchain`:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "78546fd7",
"metadata": {},
"outputs": [],
"source": [
"%pip install langchain"
]
},
{
"cell_type": "markdown",
"id": "e06df198",
"metadata": {},
"source": [
"The self-query retriever requires you to have `lark` installed:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "63a8af5b",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"%pip install lark"
]
},
{
"cell_type": "markdown",
"id": "114f768f",
"metadata": {},
"source": [
"We also need the `openai` and `supabase` packages:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "434ae558",
"metadata": {},
"outputs": [],
"source": [
"%pip install openai"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "22431060-52c4-48a7-a97b-9f542b8b0928",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"%pip install supabase==1.0.0"
]
},
{
"cell_type": "markdown",
"id": "83811610-7df3-4ede-b268-68a6a83ba9e2",
"metadata": {},
"source": [
"Since we are using `SupabaseVectorStore` and `OpenAIEmbeddings`, we have to load their API keys.\n",
"\n",
"- To find your `SUPABASE_URL` and `SUPABASE_SERVICE_KEY`, head to your Supabase project's [API settings](https://supabase.com/dashboard/project/_/settings/api).\n",
" - `SUPABASE_URL` corresponds to the Project URL\n",
" - `SUPABASE_SERVICE_KEY` corresponds to the `service_role` API key\n",
"\n",
"- To get your `OPENAI_API_KEY`, navigate to [API keys](https://platform.openai.com/account/api-keys) on your OpenAI account and create a new secret key."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "dd01b61b-7d32-4a55-85d6-b2d2d4f18840",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"import os\n",
"import getpass\n",
"\n",
"os.environ[\"SUPABASE_URL\"] = getpass.getpass(\"Supabase URL:\")\n",
"os.environ[\"SUPABASE_SERVICE_KEY\"] = getpass.getpass(\"Supabase Service Key:\")\n",
"os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")"
]
},
{
"cell_type": "markdown",
"id": "3aaf5075",
"metadata": {},
"source": [
"_Optional:_ If you're storing your Supabase and OpenAI API keys in a `.env` file, you can load them with [`dotenv`](https://github.com/theskumar/python-dotenv)."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e0089221",
"metadata": {},
"outputs": [],
"source": [
"%pip install python-dotenv"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3d56c5ef",
"metadata": {},
"outputs": [],
"source": [
"from dotenv import load_dotenv\n",
"\n",
"load_dotenv()"
]
},
{
"cell_type": "markdown",
"id": "f6dd9aef",
"metadata": {},
"source": [
"First we'll create a Supabase client and instantiate a OpenAI embeddings class."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "cb4a5787",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"import os\n",
"from supabase.client import Client, create_client\n",
"from langchain.schema import Document\n",
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.vectorstores import SupabaseVectorStore\n",
"\n",
"supabase_url = os.environ.get(\"SUPABASE_URL\")\n",
"supabase_key = os.environ.get(\"SUPABASE_SERVICE_KEY\")\n",
"supabase: Client = create_client(supabase_url, supabase_key)\n",
"\n",
"embeddings = OpenAIEmbeddings()"
]
},
{
"cell_type": "markdown",
"id": "0fca9b0b",
"metadata": {},
"source": [
"Next let's create our documents."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "bcbe04d9",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"docs = [\n",
" Document(\n",
" page_content=\"A bunch of scientists bring back dinosaurs and mayhem breaks loose\",\n",
" metadata={\"year\": 1993, \"rating\": 7.7, \"genre\": \"science fiction\"},\n",
" ),\n",
" Document(\n",
" page_content=\"Leo DiCaprio gets lost in a dream within a dream within a dream within a ...\",\n",
" metadata={\"year\": 2010, \"director\": \"Christopher Nolan\", \"rating\": 8.2},\n",
" ),\n",
" Document(\n",
" page_content=\"A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea\",\n",
" metadata={\"year\": 2006, \"director\": \"Satoshi Kon\", \"rating\": 8.6},\n",
" ),\n",
" Document(\n",
" page_content=\"A bunch of normal-sized women are supremely wholesome and some men pine after them\",\n",
" metadata={\"year\": 2019, \"director\": \"Greta Gerwig\", \"rating\": 8.3},\n",
" ),\n",
" Document(\n",
" page_content=\"Toys come alive and have a blast doing so\",\n",
" metadata={\"year\": 1995, \"genre\": \"animated\"},\n",
" ),\n",
" Document(\n",
" page_content=\"Three men walk into the Zone, three men walk out of the Zone\",\n",
" metadata={\n",
" \"year\": 1979,\n",
" \"rating\": 9.9,\n",
" \"director\": \"Andrei Tarkovsky\",\n",
" \"genre\": \"science fiction\",\n",
" \"rating\": 9.9,\n",
" },\n",
" ),\n",
"]\n",
"\n",
"vectorstore = SupabaseVectorStore.from_documents(docs, embeddings, client=supabase, table_name=\"documents\", query_name=\"match_documents\")"
]
},
{
"cell_type": "markdown",
"id": "5ecaab6d",
"metadata": {},
"source": [
"## Creating our self-querying retriever\n",
"Now we can instantiate our retriever. To do this we'll need to provide some information upfront about the metadata fields that our documents support and a short description of the document contents."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "86e34dbf",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.llms import OpenAI\n",
"from langchain.retrievers.self_query.base import SelfQueryRetriever\n",
"from langchain.chains.query_constructor.base import AttributeInfo\n",
"\n",
"metadata_field_info = [\n",
" AttributeInfo(\n",
" name=\"genre\",\n",
" description=\"The genre of the movie\",\n",
" type=\"string or list[string]\",\n",
" ),\n",
" AttributeInfo(\n",
" name=\"year\",\n",
" description=\"The year the movie was released\",\n",
" type=\"integer\",\n",
" ),\n",
" AttributeInfo(\n",
" name=\"director\",\n",
" description=\"The name of the movie director\",\n",
" type=\"string\",\n",
" ),\n",
" AttributeInfo(\n",
" name=\"rating\", description=\"A 1-10 rating for the movie\", type=\"float\"\n",
" ),\n",
"]\n",
"document_content_description = \"Brief summary of a movie\"\n",
"llm = OpenAI(temperature=0)\n",
"retriever = SelfQueryRetriever.from_llm(\n",
" llm, vectorstore, document_content_description, metadata_field_info, verbose=True\n",
")"
]
},
{
"cell_type": "markdown",
"id": "ea9df8d4",
"metadata": {},
"source": [
"## Testing it out\n",
"And now we can try actually using our retriever!"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "38a126e9",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query='dinosaur' filter=None limit=None\n"
]
},
{
"data": {
"text/plain": [
"[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'genre': 'science fiction', 'rating': 7.7}),\n",
" Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'}),\n",
" Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'genre': 'science fiction', 'rating': 9.9, 'director': 'Andrei Tarkovsky'}),\n",
" Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'year': 2006, 'rating': 8.6, 'director': 'Satoshi Kon'})]"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example only specifies a relevant query\n",
"retriever.get_relevant_documents(\"What are some movies about dinosaurs\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "fc3f1e6e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query=' ' filter=Comparison(comparator=<Comparator.GT: 'gt'>, attribute='rating', value=8.5) limit=None\n"
]
},
{
"data": {
"text/plain": [
"[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'genre': 'science fiction', 'rating': 9.9, 'director': 'Andrei Tarkovsky'}),\n",
" Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'year': 2006, 'rating': 8.6, 'director': 'Satoshi Kon'})]"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example only specifies a filter\n",
"retriever.get_relevant_documents(\"I want to watch a movie rated higher than 8.5\")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "b19d4da0",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query='women' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='director', value='Greta Gerwig') limit=None\n"
]
},
{
"data": {
"text/plain": [
"[Document(page_content='A bunch of normal-sized women are supremely wholesome and some men pine after them', metadata={'year': 2019, 'rating': 8.3, 'director': 'Greta Gerwig'})]"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example specifies a query and a filter\n",
"retriever.get_relevant_documents(\"Has Greta Gerwig directed any movies about women?\")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "f900e40e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query=' ' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GTE: 'gte'>, attribute='rating', value=8.5), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='science fiction')]) limit=None\n"
]
},
{
"data": {
"text/plain": [
"[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'genre': 'science fiction', 'rating': 9.9, 'director': 'Andrei Tarkovsky'})]"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example specifies a composite filter\n",
"retriever.get_relevant_documents(\n",
" \"What's a highly rated (above 8.5) science fiction film?\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "12a51522",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query='toys' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GT: 'gt'>, attribute='year', value=1990), Comparison(comparator=<Comparator.LTE: 'lte'>, attribute='year', value=2005), Comparison(comparator=<Comparator.LIKE: 'like'>, attribute='genre', value='animated')]) limit=None\n"
]
},
{
"data": {
"text/plain": [
"[Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})]"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example specifies a query and composite filter\n",
"retriever.get_relevant_documents(\n",
" \"What's a movie after 1990 but before (or on) 2005 that's all about toys, and preferably is animated\"\n",
")"
]
},
{
"cell_type": "markdown",
"id": "39bd1de1-b9fe-4a98-89da-58d8a7a6ae51",
"metadata": {},
"source": [
"## Filter k\n",
"\n",
"We can also use the self query retriever to specify `k`: the number of documents to fetch.\n",
"\n",
"We can do this by passing `enable_limit=True` to the constructor."
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "bff36b88-b506-4877-9c63-e5a1a8d78e64",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"retriever = SelfQueryRetriever.from_llm(\n",
" llm,\n",
" vectorstore,\n",
" document_content_description,\n",
" metadata_field_info,\n",
" enable_limit=True,\n",
" verbose=True,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "2758d229-4f97-499c-819f-888acaf8ee10",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query='dinosaur' filter=None limit=2\n"
]
},
{
"data": {
"text/plain": [
"[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'genre': 'science fiction', 'rating': 7.7}),\n",
" Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})]"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example only specifies a relevant query\n",
"retriever.get_relevant_documents(\"what are two movies about dinosaurs\")"
]
}
],
"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": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

440
docs/extras/modules/data_connection/retrievers/self_query/vectara_self_query.ipynb Normal file
View File

@ -0,0 +1,440 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "13afcae7",
"metadata": {},
"source": [
"# Vectara self-querying \n",
"\n",
">[Vectara](https://docs.vectara.com/docs/) is a GenAI platform for developers. It provides a simple API to build Grounded Generation (aka Retrieval-augmented-generation) applications.\n",
"\n",
"In the notebook we'll demo the `SelfQueryRetriever` wrapped around a Vectara vector store. "
]
},
{
"cell_type": "markdown",
"id": "68e75fb9",
"metadata": {},
"source": [
"# Setup\n",
"\n",
"You will need a Vectara account to use Vectara with LangChain. To get started, use the following steps (see our [quickstart](https://docs.vectara.com/docs/quickstart) guide):\n",
"1. [Sign up](https://console.vectara.com/signup) for a Vectara account if you don't already have one. Once you have completed your sign up you will have a Vectara customer ID. You can find your customer ID by clicking on your name, on the top-right of the Vectara console window.\n",
"2. Within your account you can create one or more corpora. Each corpus represents an area that stores text data upon ingest from input documents. To create a corpus, use the **\"Create Corpus\"** button. You then provide a name to your corpus as well as a description. Optionally you can define filtering attributes and apply some advanced options. If you click on your created corpus, you can see its name and corpus ID right on the top.\n",
"3. Next you'll need to create API keys to access the corpus. Click on the **\"Authorization\"** tab in the corpus view and then the **\"Create API Key\"** button. Give your key a name, and choose whether you want query only or query+index for your key. Click \"Create\" and you now have an active API key. Keep this key confidential. \n",
"\n",
"To use LangChain with Vectara, you'll need to have these three values: customer ID, corpus ID and api_key.\n",
"You can provide those to LangChain in two ways:\n",
"\n",
"1. Include in your environment these three variables: `VECTARA_CUSTOMER_ID`, `VECTARA_CORPUS_ID` and `VECTARA_API_KEY`.\n",
"\n",
"> For example, you can set these variables using os.environ and getpass as follows:\n",
"\n",
"```python\n",
"import os\n",
"import getpass\n",
"\n",
"os.environ[\"VECTARA_CUSTOMER_ID\"] = getpass.getpass(\"Vectara Customer ID:\")\n",
"os.environ[\"VECTARA_CORPUS_ID\"] = getpass.getpass(\"Vectara Corpus ID:\")\n",
"os.environ[\"VECTARA_API_KEY\"] = getpass.getpass(\"Vectara API Key:\")\n",
"```\n",
"\n",
"1. Provide them as arguments when creating the Vectara vectorstore object:\n",
"\n",
"```python\n",
"vectorstore = Vectara(\n",
" vectara_customer_id=vectara_customer_id,\n",
" vectara_corpus_id=vectara_corpus_id,\n",
" vectara_api_key=vectara_api_key\n",
" )\n",
"```\n",
"\n",
"**Note:** The self-query retriever requires you to have `lark` installed (`pip install lark`). "
]
},
{
"cell_type": "markdown",
"id": "742ac16d",
"metadata": {},
"source": [
"## Connecting to Vectara from LangChain\n",
"\n",
"In this example, we assume that you've created an account and a corpus, and added your VECTARA_CUSTOMER_ID, VECTARA_CORPUS_ID and VECTARA_API_KEY (created with permissions for both indexing and query) as environment variables.\n",
"\n",
"The corpus has 4 fields defined as metadata for filtering: year, director, rating, and genre\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "cb4a5787",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.embeddings import FakeEmbeddings\n",
"from langchain.schema import Document\n",
"from langchain.text_splitter import CharacterTextSplitter\n",
"from langchain.vectorstores import Vectara\n",
"from langchain.document_loaders import TextLoader\n",
"\n",
"from langchain.llms import OpenAI\n",
"from langchain.chains import ConversationalRetrievalChain\n",
"from langchain.retrievers.self_query.base import SelfQueryRetriever\n",
"from langchain.chains.query_constructor.base import AttributeInfo\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "bcbe04d9",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"docs = [\n",
" Document(\n",
" page_content=\"A bunch of scientists bring back dinosaurs and mayhem breaks loose\",\n",
" metadata={\"year\": 1993, \"rating\": 7.7, \"genre\": \"science fiction\"},\n",
" ),\n",
" Document(\n",
" page_content=\"Leo DiCaprio gets lost in a dream within a dream within a dream within a ...\",\n",
" metadata={\"year\": 2010, \"director\": \"Christopher Nolan\", \"rating\": 8.2},\n",
" ),\n",
" Document(\n",
" page_content=\"A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea\",\n",
" metadata={\"year\": 2006, \"director\": \"Satoshi Kon\", \"rating\": 8.6},\n",
" ),\n",
" Document(\n",
" page_content=\"A bunch of normal-sized women are supremely wholesome and some men pine after them\",\n",
" metadata={\"year\": 2019, \"director\": \"Greta Gerwig\", \"rating\": 8.3},\n",
" ),\n",
" Document(\n",
" page_content=\"Toys come alive and have a blast doing so\",\n",
" metadata={\"year\": 1995, \"genre\": \"animated\"},\n",
" ),\n",
" Document(\n",
" page_content=\"Three men walk into the Zone, three men walk out of the Zone\",\n",
" metadata={\n",
" \"year\": 1979,\n",
" \"rating\": 9.9,\n",
" \"director\": \"Andrei Tarkovsky\",\n",
" \"genre\": \"science fiction\",\n",
" },\n",
" ),\n",
"]\n",
"\n",
"vectara = Vectara()\n",
"for doc in docs:\n",
" vectara.add_texts([doc.page_content], embedding=FakeEmbeddings(size=768), doc_metadata=doc.metadata)"
]
},
{
"cell_type": "markdown",
"id": "5ecaab6d",
"metadata": {},
"source": [
"## Creating our self-querying retriever\n",
"Now we can instantiate our retriever. To do this we'll need to provide some information upfront about the metadata fields that our documents support and a short description of the document contents."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "86e34dbf",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.llms import OpenAI\n",
"from langchain.retrievers.self_query.base import SelfQueryRetriever\n",
"from langchain.chains.query_constructor.base import AttributeInfo\n",
"\n",
"metadata_field_info = [\n",
" AttributeInfo(\n",
" name=\"genre\",\n",
" description=\"The genre of the movie\",\n",
" type=\"string or list[string]\",\n",
" ),\n",
" AttributeInfo(\n",
" name=\"year\",\n",
" description=\"The year the movie was released\",\n",
" type=\"integer\",\n",
" ),\n",
" AttributeInfo(\n",
" name=\"director\",\n",
" description=\"The name of the movie director\",\n",
" type=\"string\",\n",
" ),\n",
" AttributeInfo(\n",
" name=\"rating\", description=\"A 1-10 rating for the movie\", type=\"float\"\n",
" ),\n",
"]\n",
"document_content_description = \"Brief summary of a movie\"\n",
"llm = OpenAI(temperature=0)\n",
"retriever = SelfQueryRetriever.from_llm(\n",
" llm, vectara, document_content_description, metadata_field_info, verbose=True\n",
")"
]
},
{
"cell_type": "markdown",
"id": "ea9df8d4",
"metadata": {},
"source": [
"## Testing it out\n",
"And now we can try actually using our retriever!"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "38a126e9",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/ofer/dev/langchain/libs/langchain/langchain/chains/llm.py:278: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"query='dinosaur' filter=None limit=None\n"
]
},
{
"data": {
"text/plain": [
"[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'lang': 'eng', 'offset': '0', 'len': '66', 'year': '1993', 'rating': '7.7', 'genre': 'science fiction', 'source': 'langchain'}),\n",
" Document(page_content='Toys come alive and have a blast doing so', metadata={'lang': 'eng', 'offset': '0', 'len': '41', 'year': '1995', 'genre': 'animated', 'source': 'langchain'}),\n",
" Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'lang': 'eng', 'offset': '0', 'len': '60', 'year': '1979', 'rating': '9.9', 'director': 'Andrei Tarkovsky', 'genre': 'science fiction', 'source': 'langchain'}),\n",
" Document(page_content='Leo DiCaprio gets lost in a dream within a dream within a dream within a ...', metadata={'lang': 'eng', 'offset': '0', 'len': '76', 'year': '2010', 'director': 'Christopher Nolan', 'rating': '8.2', 'source': 'langchain'}),\n",
" Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'lang': 'eng', 'offset': '0', 'len': '116', 'year': '2006', 'director': 'Satoshi Kon', 'rating': '8.6', 'source': 'langchain'})]"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example only specifies a relevant query\n",
"retriever.get_relevant_documents(\"What are some movies about dinosaurs\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "fc3f1e6e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query=' ' filter=Comparison(comparator=<Comparator.GT: 'gt'>, attribute='rating', value=8.5) limit=None\n"
]
},
{
"data": {
"text/plain": [
"[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'lang': 'eng', 'offset': '0', 'len': '60', 'year': '1979', 'rating': '9.9', 'director': 'Andrei Tarkovsky', 'genre': 'science fiction', 'source': 'langchain'}),\n",
" Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'lang': 'eng', 'offset': '0', 'len': '116', 'year': '2006', 'director': 'Satoshi Kon', 'rating': '8.6', 'source': 'langchain'})]"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example only specifies a filter\n",
"retriever.get_relevant_documents(\"I want to watch a movie rated higher than 8.5\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "b19d4da0",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query='women' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='director', value='Greta Gerwig') limit=None\n"
]
},
{
"data": {
"text/plain": [
"[Document(page_content='A bunch of normal-sized women are supremely wholesome and some men pine after them', metadata={'lang': 'eng', 'offset': '0', 'len': '82', 'year': '2019', 'director': 'Greta Gerwig', 'rating': '8.3', 'source': 'langchain'})]"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example specifies a query and a filter\n",
"retriever.get_relevant_documents(\"Has Greta Gerwig directed any movies about women\")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "f900e40e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query=' ' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GTE: 'gte'>, attribute='rating', value=8.5), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='science fiction')]) limit=None\n"
]
},
{
"data": {
"text/plain": [
"[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'lang': 'eng', 'offset': '0', 'len': '60', 'year': '1979', 'rating': '9.9', 'director': 'Andrei Tarkovsky', 'genre': 'science fiction', 'source': 'langchain'})]"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example specifies a composite filter\n",
"retriever.get_relevant_documents(\n",
" \"What's a highly rated (above 8.5) science fiction film?\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "12a51522",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query='toys' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GT: 'gt'>, attribute='year', value=1990), Comparison(comparator=<Comparator.LT: 'lt'>, attribute='year', value=2005), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='animated')]) limit=None\n"
]
},
{
"data": {
"text/plain": [
"[Document(page_content='Toys come alive and have a blast doing so', metadata={'lang': 'eng', 'offset': '0', 'len': '41', 'year': '1995', 'genre': 'animated', 'source': 'langchain'})]"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example specifies a query and composite filter\n",
"retriever.get_relevant_documents(\n",
" \"What's a movie after 1990 but before 2005 that's all about toys, and preferably is animated\"\n",
")"
]
},
{
"cell_type": "markdown",
"id": "39bd1de1-b9fe-4a98-89da-58d8a7a6ae51",
"metadata": {},
"source": [
"## Filter k\n",
"\n",
"We can also use the self query retriever to specify `k`: the number of documents to fetch.\n",
"\n",
"We can do this by passing `enable_limit=True` to the constructor."
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "bff36b88-b506-4877-9c63-e5a1a8d78e64",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"retriever = SelfQueryRetriever.from_llm(\n",
" llm,\n",
" vectara,\n",
" document_content_description,\n",
" metadata_field_info,\n",
" enable_limit=True,\n",
" verbose=True,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "2758d229-4f97-499c-819f-888acaf8ee10",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query='dinosaur' filter=None limit=2\n"
]
},
{
"data": {
"text/plain": [
"[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'lang': 'eng', 'offset': '0', 'len': '66', 'year': '1993', 'rating': '7.7', 'genre': 'science fiction', 'source': 'langchain'}),\n",
" Document(page_content='Toys come alive and have a blast doing so', metadata={'lang': 'eng', 'offset': '0', 'len': '41', 'year': '1995', 'genre': 'animated', 'source': 'langchain'})]"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example only specifies a relevant query\n",
"retriever.get_relevant_documents(\"what are two movies about dinosaurs\")"
]
}
],
"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": "3.10.9"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

4
docs/extras/use_cases/more/graph/diffbot_graphtransformer.ipynb
View File

@ -7,7 +7,7 @@
"source": [ "source": [
"# Diffbot Graph Transformer\n", "# Diffbot Graph Transformer\n",
"\n", "\n",
"[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/use_cases/more/graph/diffbot_transformer.ipynb)\n", "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/use_cases/more/graph/diffbot_graphtransformer.ipynb)\n",
"\n", "\n",
"## Use case\n", "## Use case\n",
"\n", "\n",
@ -77,7 +77,7 @@
"id": "5e3b894a-e3ee-46c7-8116-f8377f8f0159", "id": "5e3b894a-e3ee-46c7-8116-f8377f8f0159",
"metadata": {}, "metadata": {},
"source": [ "source": [
"This code fetches Wikipedia articles about \"Baldur's Gate 3\" and then uses `DiffbotGraphTransformer` to extract entities and relationships.\n", "This code fetches Wikipedia articles about \"Warren Buffett\" and then uses `DiffbotGraphTransformer` to extract entities and relationships.\n",
"The `DiffbotGraphTransformer` outputs a structured data `GraphDocument`, which can be used to populate a graph database.\n", "The `DiffbotGraphTransformer` outputs a structured data `GraphDocument`, which can be used to populate a graph database.\n",
"Note that text chunking is avoided due to Diffbot's [character limit per API request](https://docs.diffbot.com/reference/introduction-to-natural-language-api)." "Note that text chunking is avoided due to Diffbot's [character limit per API request](https://docs.diffbot.com/reference/introduction-to-natural-language-api)."
] ]

7
libs/experimental/langchain_experimental/data_anonymizer/base.py
View File

@ -1,4 +1,5 @@
from abc import ABC, abstractmethod from abc import ABC, abstractmethod
from typing import Optional
class AnonymizerBase(ABC): class AnonymizerBase(ABC):
@ -8,12 +9,12 @@ class AnonymizerBase(ABC):
wrapping the behavior for all methods in a base class. wrapping the behavior for all methods in a base class.
""" """
def anonymize(self, text: str) -> str: def anonymize(self, text: str, language: Optional[str] = None) -> str:
"""Anonymize text""" """Anonymize text"""
return self._anonymize(text) return self._anonymize(text, language)
@abstractmethod @abstractmethod
def _anonymize(self, text: str) -> str: def _anonymize(self, text: str, language: Optional[str]) -> str:
"""Abstract method to anonymize text""" """Abstract method to anonymize text"""

4
libs/experimental/langchain_experimental/data_anonymizer/faker_presidio_mapping.py
View File

@ -27,8 +27,8 @@ def get_pseudoanonymizer_mapping(seed: Optional[int] = None) -> Dict[str, Callab
fake.random_choices(string.ascii_lowercase + string.digits, length=26) fake.random_choices(string.ascii_lowercase + string.digits, length=26)
), ),
"IP_ADDRESS": lambda _: fake.ipv4_public(), "IP_ADDRESS": lambda _: fake.ipv4_public(),
"LOCATION": lambda _: fake.address(), "LOCATION": lambda _: fake.city(),
"DATE_TIME": lambda _: fake.iso8601(), "DATE_TIME": lambda _: fake.date(),
"NRP": lambda _: str(fake.random_number(digits=8, fix_len=True)), "NRP": lambda _: str(fake.random_number(digits=8, fix_len=True)),
"MEDICAL_LICENSE": lambda _: fake.bothify(text="??######").upper(), "MEDICAL_LICENSE": lambda _: fake.bothify(text="??######").upper(),
"URL": lambda _: fake.url(), "URL": lambda _: fake.url(),

71
libs/experimental/langchain_experimental/data_anonymizer/presidio.py
View File

@ -24,6 +24,8 @@ from langchain_experimental.data_anonymizer.faker_presidio_mapping import (
try: try:
from presidio_analyzer import AnalyzerEngine from presidio_analyzer import AnalyzerEngine
from presidio_analyzer.nlp_engine import NlpEngineProvider
except ImportError as e: except ImportError as e:
raise ImportError( raise ImportError(
"Could not import presidio_analyzer, please install with " "Could not import presidio_analyzer, please install with "
@ -44,12 +46,29 @@ if TYPE_CHECKING:
from presidio_analyzer import EntityRecognizer, RecognizerResult from presidio_analyzer import EntityRecognizer, RecognizerResult
from presidio_anonymizer.entities import EngineResult from presidio_anonymizer.entities import EngineResult
# Configuring Anonymizer for multiple languages
# Detailed description and examples can be found here:
# langchain/docs/extras/guides/privacy/multi_language_anonymization.ipynb
DEFAULT_LANGUAGES_CONFIG = {
# You can also use Stanza or transformers library.
# See https://microsoft.github.io/presidio/analyzer/customizing_nlp_models/
"nlp_engine_name": "spacy",
"models": [
{"lang_code": "en", "model_name": "en_core_web_lg"},
# {"lang_code": "de", "model_name": "de_core_news_md"},
# {"lang_code": "es", "model_name": "es_core_news_md"},
# ...
# List of available models: https://spacy.io/usage/models
],
}
class PresidioAnonymizerBase(AnonymizerBase): class PresidioAnonymizerBase(AnonymizerBase):
def __init__( def __init__(
self, self,
analyzed_fields: Optional[List[str]] = None, analyzed_fields: Optional[List[str]] = None,
operators: Optional[Dict[str, OperatorConfig]] = None, operators: Optional[Dict[str, OperatorConfig]] = None,
languages_config: Dict = DEFAULT_LANGUAGES_CONFIG,
faker_seed: Optional[int] = None, faker_seed: Optional[int] = None,
): ):
""" """
@ -60,6 +79,11 @@ class PresidioAnonymizerBase(AnonymizerBase):
Operators allow for custom anonymization of detected PII. Operators allow for custom anonymization of detected PII.
Learn more: Learn more:
https://microsoft.github.io/presidio/tutorial/10_simple_anonymization/ https://microsoft.github.io/presidio/tutorial/10_simple_anonymization/
languages_config: Configuration for the NLP engine.
First language in the list will be used as the main language
in self.anonymize(...) when no language is specified.
Learn more:
https://microsoft.github.io/presidio/analyzer/customizing_nlp_models/
faker_seed: Seed used to initialize faker. faker_seed: Seed used to initialize faker.
Defaults to None, in which case faker will be seeded randomly Defaults to None, in which case faker will be seeded randomly
and provide random values. and provide random values.
@ -81,7 +105,15 @@ class PresidioAnonymizerBase(AnonymizerBase):
).items() ).items()
} }
) )
self._analyzer = AnalyzerEngine()
provider = NlpEngineProvider(nlp_configuration=languages_config)
nlp_engine = provider.create_engine()
self.supported_languages = list(nlp_engine.nlp.keys())
self._analyzer = AnalyzerEngine(
supported_languages=self.supported_languages, nlp_engine=nlp_engine
)
self._anonymizer = AnonymizerEngine() self._anonymizer = AnonymizerEngine()
def add_recognizer(self, recognizer: EntityRecognizer) -> None: def add_recognizer(self, recognizer: EntityRecognizer) -> None:
@ -103,18 +135,31 @@ class PresidioAnonymizerBase(AnonymizerBase):
class PresidioAnonymizer(PresidioAnonymizerBase): class PresidioAnonymizer(PresidioAnonymizerBase):
def _anonymize(self, text: str) -> str: def _anonymize(self, text: str, language: Optional[str] = None) -> str:
"""Anonymize text. """Anonymize text.
Each PII entity is replaced with a fake value. Each PII entity is replaced with a fake value.
Each time fake values will be different, as they are generated randomly. Each time fake values will be different, as they are generated randomly.
Args: Args:
text: text to anonymize text: text to anonymize
language: language to use for analysis of PII
If None, the first (main) language in the list
of languages specified in the configuration will be used.
""" """
if language is None:
language = self.supported_languages[0]
if language not in self.supported_languages:
raise ValueError(
f"Language '{language}' is not supported. "
f"Supported languages are: {self.supported_languages}. "
"Change your language configuration file to add more languages."
)
results = self._analyzer.analyze( results = self._analyzer.analyze(
text, text,
entities=self.analyzed_fields, entities=self.analyzed_fields,
language="en", language=language,
) )
return self._anonymizer.anonymize( return self._anonymizer.anonymize(
@ -129,9 +174,10 @@ class PresidioReversibleAnonymizer(PresidioAnonymizerBase, ReversibleAnonymizerB
self, self,
analyzed_fields: Optional[List[str]] = None, analyzed_fields: Optional[List[str]] = None,
operators: Optional[Dict[str, OperatorConfig]] = None, operators: Optional[Dict[str, OperatorConfig]] = None,
languages_config: Dict = DEFAULT_LANGUAGES_CONFIG,
faker_seed: Optional[int] = None, faker_seed: Optional[int] = None,
): ):
super().__init__(analyzed_fields, operators, faker_seed) super().__init__(analyzed_fields, operators, languages_config, faker_seed)
self._deanonymizer_mapping = DeanonymizerMapping() self._deanonymizer_mapping = DeanonymizerMapping()
@property @property
@ -191,7 +237,7 @@ class PresidioReversibleAnonymizer(PresidioAnonymizerBase, ReversibleAnonymizerB
self._deanonymizer_mapping.update(new_deanonymizer_mapping) self._deanonymizer_mapping.update(new_deanonymizer_mapping)
def _anonymize(self, text: str) -> str: def _anonymize(self, text: str, language: Optional[str] = None) -> str:
"""Anonymize text. """Anonymize text.
Each PII entity is replaced with a fake value. Each PII entity is replaced with a fake value.
Each time fake values will be different, as they are generated randomly. Each time fake values will be different, as they are generated randomly.
@ -200,11 +246,24 @@ class PresidioReversibleAnonymizer(PresidioAnonymizerBase, ReversibleAnonymizerB
Args: Args:
text: text to anonymize text: text to anonymize
language: language to use for analysis of PII
If None, the first (main) language in the list
of languages specified in the configuration will be used.
""" """
if language is None:
language = self.supported_languages[0]
if language not in self.supported_languages:
raise ValueError(
f"Language '{language}' is not supported. "
f"Supported languages are: {self.supported_languages}. "
"Change your language configuration file to add more languages."
)
analyzer_results = self._analyzer.analyze( analyzer_results = self._analyzer.analyze(
text, text,
entities=self.analyzed_fields, entities=self.analyzed_fields,
language="en", language=language,
) )
filtered_analyzer_results = ( filtered_analyzer_results = (

21
libs/langchain/langchain/chat_loaders/__init__.py
View File

@ -1,6 +1,19 @@
"""Load chat messages from common communications platforms for finetuning. """**Chat Loaders** load chat messages from common communications platforms.
This module provides functions to load chat messages from various Load chat messages from various
communications platforms such as Facebook Messenger, Telegram, and communications platforms such as Facebook Messenger, Telegram, and
WhatsApp. The loaded chat messages can be used for finetuning models. WhatsApp. The loaded chat messages can be used for fine-tuning models.
"""
**Class hierarchy:**
.. code-block::
BaseChatLoader --> <name>ChatLoader # Examples: WhatsAppChatLoader, IMessageChatLoader
**Main helpers:**
.. code-block::
ChatSession
""" # noqa: E501

9
libs/langchain/langchain/chat_loaders/base.py
View File

@ -1,10 +1,3 @@
"""Base definitions for chat loaders.
A chat loader is a class that loads chat messages from an external
source such as a file or a database. The chat messages can then be
used for finetuning.
"""
from abc import ABC, abstractmethod from abc import ABC, abstractmethod
from typing import Iterator, List, Sequence, TypedDict from typing import Iterator, List, Sequence, TypedDict
@ -12,7 +5,7 @@ from langchain.schema.messages import BaseMessage
class ChatSession(TypedDict): class ChatSession(TypedDict):
"""A chat session represents a single """Chat Session represents a single
conversation, channel, or other group of messages.""" conversation, channel, or other group of messages."""
messages: Sequence[BaseMessage] messages: Sequence[BaseMessage]

4
libs/langchain/langchain/chat_loaders/facebook_messenger.py
View File

@ -10,7 +10,7 @@ logger = logging.getLogger(__file__)
class SingleFileFacebookMessengerChatLoader(BaseChatLoader): class SingleFileFacebookMessengerChatLoader(BaseChatLoader):
"""A chat loader for loading Facebook Messenger chat data from a single file. """Load `Facebook Messenger` chat data from a single file.
Args: Args:
path (Union[Path, str]): The path to the chat file. path (Union[Path, str]): The path to the chat file.
@ -45,7 +45,7 @@ class SingleFileFacebookMessengerChatLoader(BaseChatLoader):
class FolderFacebookMessengerChatLoader(BaseChatLoader): class FolderFacebookMessengerChatLoader(BaseChatLoader):
"""A chat loader for loading Facebook Messenger chat data from a folder. """Load `Facebook Messenger` chat data from a folder.
Args: Args:
path (Union[str, Path]): The path to the directory path (Union[str, Path]): The path to the directory

2
libs/langchain/langchain/chat_loaders/gmail.py
View File

@ -62,7 +62,7 @@ def _get_message_data(service: Any, message: Any) -> ChatSession:
class GMailLoader(BaseChatLoader): class GMailLoader(BaseChatLoader):
"""This loader goes over how to load data from GMail. """Load data from `GMail`.
There are many ways you could want to load data from GMail. There are many ways you could want to load data from GMail.
This loader is currently fairly opinionated in how to do so. This loader is currently fairly opinionated in how to do so.

22
libs/langchain/langchain/chat_loaders/imessage.py
View File

@ -1,14 +1,3 @@
"""IMessage Chat Loader.
This class is used to load chat sessions from the iMessage chat.db SQLite file.
It only works on macOS when you have iMessage enabled and have the chat.db file.
The chat.db file is likely located at ~/Library/Messages/chat.db. However, your
terminal may not have permission to access this file. To resolve this, you can
copy the file to a different location, change the permissions of the file, or
grant full disk access for your terminal emulator in System Settings > Security
and Privacy > Full Disk Access.
"""
from __future__ import annotations from __future__ import annotations
from pathlib import Path from pathlib import Path
@ -22,6 +11,17 @@ if TYPE_CHECKING:
class IMessageChatLoader(chat_loaders.BaseChatLoader): class IMessageChatLoader(chat_loaders.BaseChatLoader):
"""Load chat sessions from the `iMessage` chat.db SQLite file.
It only works on macOS when you have iMessage enabled and have the chat.db file.
The chat.db file is likely located at ~/Library/Messages/chat.db. However, your
terminal may not have permission to access this file. To resolve this, you can
copy the file to a different location, change the permissions of the file, or
grant full disk access for your terminal emulator in System Settings > Security
and Privacy > Full Disk Access.
"""
def __init__(self, path: Optional[Union[str, Path]] = None): def __init__(self, path: Optional[Union[str, Path]] = None):
""" """
Initialize the IMessageChatLoader. Initialize the IMessageChatLoader.

2
libs/langchain/langchain/chat_loaders/slack.py
View File

@ -12,6 +12,8 @@ logger = logging.getLogger(__name__)
class SlackChatLoader(chat_loaders.BaseChatLoader): class SlackChatLoader(chat_loaders.BaseChatLoader):
"""Load `Slack` conversations from a dump zip file."""
def __init__( def __init__(
self, self,
path: Union[str, Path], path: Union[str, Path],

3
libs/langchain/langchain/chat_loaders/telegram.py
View File

@ -13,8 +13,7 @@ logger = logging.getLogger(__name__)
class TelegramChatLoader(chat_loaders.BaseChatLoader): class TelegramChatLoader(chat_loaders.BaseChatLoader):
"""A loading utility for converting telegram conversations """Load `telegram` conversations to LangChain chat messages.
to LangChain chat messages.
To export, use the Telegram Desktop app from To export, use the Telegram Desktop app from
https://desktop.telegram.org/, select a conversation, click the three dots https://desktop.telegram.org/, select a conversation, click the three dots

2
libs/langchain/langchain/chat_loaders/whatsapp.py
View File

@ -12,6 +12,8 @@ logger = logging.getLogger(__name__)
class WhatsAppChatLoader(chat_loaders.BaseChatLoader): class WhatsAppChatLoader(chat_loaders.BaseChatLoader):
"""Load `WhatsApp` conversations from a dump zip file or directory."""
def __init__(self, path: str): def __init__(self, path: str):
"""Initialize the WhatsAppChatLoader. """Initialize the WhatsAppChatLoader.

32
libs/langchain/langchain/memory/chat_message_histories/dynamodb.py
View File

@ -1,5 +1,7 @@
from __future__ import annotations
import logging import logging
from typing import Dict, List, Optional from typing import TYPE_CHECKING, Dict, List, Optional
from langchain.schema import ( from langchain.schema import (
BaseChatMessageHistory, BaseChatMessageHistory,
@ -11,6 +13,9 @@ from langchain.schema.messages import (
messages_to_dict, messages_to_dict,
) )
if TYPE_CHECKING:
from boto3.session import Session
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
@ -42,9 +47,17 @@ class DynamoDBChatMessageHistory(BaseChatMessageHistory):
endpoint_url: Optional[str] = None, endpoint_url: Optional[str] = None,
primary_key_name: str = "SessionId", primary_key_name: str = "SessionId",
key: Optional[Dict[str, str]] = None, key: Optional[Dict[str, str]] = None,
boto3_session: Optional[Session] = None,
): ):
if boto3_session:
client = boto3_session.resource("dynamodb")
else:
try:
import boto3 import boto3
except ImportError as e:
raise ImportError(
"Unable to import boto3, please install with `pip install boto3`."
) from e
if endpoint_url: if endpoint_url:
client = boto3.resource("dynamodb", endpoint_url=endpoint_url) client = boto3.resource("dynamodb", endpoint_url=endpoint_url)
else: else:
@ -56,7 +69,12 @@ class DynamoDBChatMessageHistory(BaseChatMessageHistory):
@property @property
def messages(self) -> List[BaseMessage]: # type: ignore def messages(self) -> List[BaseMessage]: # type: ignore
"""Retrieve the messages from DynamoDB""" """Retrieve the messages from DynamoDB"""
try:
from botocore.exceptions import ClientError from botocore.exceptions import ClientError
except ImportError as e:
raise ImportError(
"Unable to import botocore, please install with `pip install botocore`."
) from e
response = None response = None
try: try:
@ -77,7 +95,12 @@ class DynamoDBChatMessageHistory(BaseChatMessageHistory):
def add_message(self, message: BaseMessage) -> None: def add_message(self, message: BaseMessage) -> None:
"""Append the message to the record in DynamoDB""" """Append the message to the record in DynamoDB"""
try:
from botocore.exceptions import ClientError from botocore.exceptions import ClientError
except ImportError as e:
raise ImportError(
"Unable to import botocore, please install with `pip install botocore`."
) from e
messages = messages_to_dict(self.messages) messages = messages_to_dict(self.messages)
_message = _message_to_dict(message) _message = _message_to_dict(message)
@ -90,7 +113,12 @@ class DynamoDBChatMessageHistory(BaseChatMessageHistory):
def clear(self) -> None: def clear(self) -> None:
"""Clear session memory from DynamoDB""" """Clear session memory from DynamoDB"""
try:
from botocore.exceptions import ClientError from botocore.exceptions import ClientError
except ImportError as e:
raise ImportError(
"Unable to import botocore, please install with `pip install botocore`."
) from e
try: try:
self.table.delete_item(self.key) self.table.delete_item(self.key)

6
libs/langchain/langchain/retrievers/self_query/base.py
View File

@ -16,6 +16,8 @@ from langchain.retrievers.self_query.milvus import MilvusTranslator
from langchain.retrievers.self_query.myscale import MyScaleTranslator from langchain.retrievers.self_query.myscale import MyScaleTranslator
from langchain.retrievers.self_query.pinecone import PineconeTranslator from langchain.retrievers.self_query.pinecone import PineconeTranslator
from langchain.retrievers.self_query.qdrant import QdrantTranslator from langchain.retrievers.self_query.qdrant import QdrantTranslator
from langchain.retrievers.self_query.supabase import SupabaseVectorTranslator
from langchain.retrievers.self_query.vectara import VectaraTranslator
from langchain.retrievers.self_query.weaviate import WeaviateTranslator from langchain.retrievers.self_query.weaviate import WeaviateTranslator
from langchain.schema import BaseRetriever, Document from langchain.schema import BaseRetriever, Document
from langchain.schema.language_model import BaseLanguageModel from langchain.schema.language_model import BaseLanguageModel
@ -28,6 +30,8 @@ from langchain.vectorstores import (
MyScale, MyScale,
Pinecone, Pinecone,
Qdrant, Qdrant,
SupabaseVectorStore,
Vectara,
VectorStore, VectorStore,
Weaviate, Weaviate,
) )
@ -41,11 +45,13 @@ def _get_builtin_translator(vectorstore: VectorStore) -> Visitor:
Chroma: ChromaTranslator, Chroma: ChromaTranslator,
DashVector: DashvectorTranslator, DashVector: DashvectorTranslator,
Weaviate: WeaviateTranslator, Weaviate: WeaviateTranslator,
Vectara: VectaraTranslator,
Qdrant: QdrantTranslator, Qdrant: QdrantTranslator,
MyScale: MyScaleTranslator, MyScale: MyScaleTranslator,
DeepLake: DeepLakeTranslator, DeepLake: DeepLakeTranslator,
ElasticsearchStore: ElasticsearchTranslator, ElasticsearchStore: ElasticsearchTranslator,
Milvus: MilvusTranslator, Milvus: MilvusTranslator,
SupabaseVectorStore: SupabaseVectorTranslator,
} }
if vectorstore_cls not in BUILTIN_TRANSLATORS: if vectorstore_cls not in BUILTIN_TRANSLATORS:
raise ValueError( raise ValueError(

97
libs/langchain/langchain/retrievers/self_query/supabase.py Normal file
View File

@ -0,0 +1,97 @@
from typing import Any, Dict, Tuple
from langchain.chains.query_constructor.ir import (
Comparator,
Comparison,
Operation,
Operator,
StructuredQuery,
Visitor,
)
class SupabaseVectorTranslator(Visitor):
"""Translate Langchain filters to Supabase PostgREST filters."""
allowed_operators = [Operator.AND, Operator.OR]
"""Subset of allowed logical operators."""
allowed_comparators = [
Comparator.EQ,
Comparator.NE,
Comparator.GT,
Comparator.GTE,
Comparator.LT,
Comparator.LTE,
Comparator.LIKE,
]
"""Subset of allowed logical comparators."""
metadata_column = "metadata"
def _map_comparator(self, comparator: Comparator) -> str:
"""
Maps Langchain comparator to PostgREST comparator:
https://postgrest.org/en/stable/references/api/tables_views.html#operators
"""
postgrest_comparator = {
Comparator.EQ: "eq",
Comparator.NE: "neq",
Comparator.GT: "gt",
Comparator.GTE: "gte",
Comparator.LT: "lt",
Comparator.LTE: "lte",
Comparator.LIKE: "like",
}.get(comparator)
if postgrest_comparator is None:
raise Exception(
f"Comparator '{comparator}' is not currently "
"supported in Supabase Vector"
)
return postgrest_comparator
def _get_json_operator(self, value: Any) -> str:
if isinstance(value, str):
return "->>"
else:
return "->"
def visit_operation(self, operation: Operation) -> str:
args = [arg.accept(self) for arg in operation.arguments]
return f"{operation.operator.value}({','.join(args)})"
def visit_comparison(self, comparison: Comparison) -> str:
if isinstance(comparison.value, list):
return self.visit_operation(
Operation(
operator=Operator.AND,
arguments=(
Comparison(
comparator=comparison.comparator,
attribute=comparison.attribute,
value=value,
)
for value in comparison.value
),
)
)
return ".".join(
[
f"{self.metadata_column}{self._get_json_operator(comparison.value)}{comparison.attribute}",
f"{self._map_comparator(comparison.comparator)}",
f"{comparison.value}",
]
)
def visit_structured_query(
self, structured_query: StructuredQuery
) -> Tuple[str, Dict[str, str]]:
if structured_query.filter is None:
kwargs = {}
else:
kwargs = {"postgrest_filter": structured_query.filter.accept(self)}
return structured_query.query, kwargs

69
libs/langchain/langchain/retrievers/self_query/vectara.py Normal file
View File

@ -0,0 +1,69 @@
from typing import Tuple, Union
from langchain.chains.query_constructor.ir import (
Comparator,
Comparison,
Operation,
Operator,
StructuredQuery,
Visitor,
)
def process_value(value: Union[int, float, str]) -> str:
if isinstance(value, str):
return f"'{value}'"
else:
return str(value)
class VectaraTranslator(Visitor):
"""Translate `Vectara` internal query language elements to valid filters."""
allowed_operators = [Operator.AND, Operator.OR]
"""Subset of allowed logical operators."""
allowed_comparators = [
Comparator.EQ,
Comparator.NE,
Comparator.GT,
Comparator.GTE,
Comparator.LT,
Comparator.LTE,
]
"""Subset of allowed logical comparators."""
def _format_func(self, func: Union[Operator, Comparator]) -> str:
map_dict = {
Operator.AND: " and ",
Operator.OR: " or ",
Comparator.EQ: "=",
Comparator.NE: "!=",
Comparator.GT: ">",
Comparator.GTE: ">=",
Comparator.LT: "<",
Comparator.LTE: "<=",
}
self._validate_func(func)
return map_dict[func]
def visit_operation(self, operation: Operation) -> str:
args = [arg.accept(self) for arg in operation.arguments]
operator = self._format_func(operation.operator)
return "( " + operator.join(args) + " )"
def visit_comparison(self, comparison: Comparison) -> str:
comparator = self._format_func(comparison.comparator)
processed_value = process_value(comparison.value)
attribute = comparison.attribute
return (
"( " + "doc." + attribute + " " + comparator + " " + processed_value + " )"
)
def visit_structured_query(
self, structured_query: StructuredQuery
) -> Tuple[str, dict]:
if structured_query.filter is None:
kwargs = {}
else:
kwargs = {"filter": structured_query.filter.accept(self)}
return structured_query.query, kwargs

2
libs/langchain/langchain/tools/base.py
View File

@ -592,7 +592,7 @@ class StructuredTool(BaseTool):
None, partial(self.invoke, input, config, **kwargs) None, partial(self.invoke, input, config, **kwargs)
) )
return super().ainvoke(input, config, **kwargs) return await super().ainvoke(input, config, **kwargs)
# --- Tool --- # --- Tool ---

2
libs/langchain/langchain/tools/sql_database/tool.py
View File

@ -93,7 +93,7 @@ class QuerySQLCheckerTool(BaseSQLDatabaseTool, BaseTool):
name: str = "sql_db_query_checker" name: str = "sql_db_query_checker"
description: str = """ description: str = """
Use this tool to double check if your query is correct before executing it. Use this tool to double check if your query is correct before executing it.
Always use this tool before executing a query with query_sql_db! Always use this tool before executing a query with sql_db_query!
""" """
@root_validator(pre=True) @root_validator(pre=True)

56
libs/langchain/langchain/vectorstores/supabase.py
View File

@ -168,10 +168,8 @@ class SupabaseVectorStore(VectorStore):
filter: Optional[Dict[str, Any]] = None, filter: Optional[Dict[str, Any]] = None,
**kwargs: Any, **kwargs: Any,
) -> List[Document]: ) -> List[Document]:
vectors = self._embedding.embed_documents([query]) vector = self._embedding.embed_query(query)
return self.similarity_search_by_vector( return self.similarity_search_by_vector(vector, k=k, filter=filter, **kwargs)
vectors[0], k=k, filter=filter, **kwargs
)
def similarity_search_by_vector( def similarity_search_by_vector(
self, self,
@ -195,24 +193,37 @@ class SupabaseVectorStore(VectorStore):
filter: Optional[Dict[str, Any]] = None, filter: Optional[Dict[str, Any]] = None,
**kwargs: Any, **kwargs: Any,
) -> List[Tuple[Document, float]]: ) -> List[Tuple[Document, float]]:
vectors = self._embedding.embed_documents([query]) vector = self._embedding.embed_query(query)
return self.similarity_search_by_vector_with_relevance_scores( return self.similarity_search_by_vector_with_relevance_scores(
vectors[0], k=k, filter=filter vector, k=k, filter=filter
) )
def match_args( def match_args(
self, query: List[float], k: int, filter: Optional[Dict[str, Any]] self, query: List[float], filter: Optional[Dict[str, Any]]
) -> Dict[str, Any]: ) -> Dict[str, Any]:
ret = dict(query_embedding=query, match_count=k) ret: Dict[str, Any] = dict(query_embedding=query)
if filter: if filter:
ret["filter"] = filter ret["filter"] = filter
return ret return ret
def similarity_search_by_vector_with_relevance_scores( def similarity_search_by_vector_with_relevance_scores(
self, query: List[float], k: int, filter: Optional[Dict[str, Any]] = None self,
query: List[float],
k: int,
filter: Optional[Dict[str, Any]] = None,
postgrest_filter: Optional[str] = None,
) -> List[Tuple[Document, float]]: ) -> List[Tuple[Document, float]]:
match_documents_params = self.match_args(query, k, filter) match_documents_params = self.match_args(query, filter)
res = self._client.rpc(self.query_name, match_documents_params).execute() query_builder = self._client.rpc(self.query_name, match_documents_params)
if postgrest_filter:
query_builder.params = query_builder.params.set(
"and", f"({postgrest_filter})"
)
query_builder.params = query_builder.params.set("limit", k)
res = query_builder.execute()
match_result = [ match_result = [
( (
@ -229,10 +240,23 @@ class SupabaseVectorStore(VectorStore):
return match_result return match_result
def similarity_search_by_vector_returning_embeddings( def similarity_search_by_vector_returning_embeddings(
self, query: List[float], k: int, filter: Optional[Dict[str, Any]] = None self,
query: List[float],
k: int,
filter: Optional[Dict[str, Any]] = None,
postgrest_filter: Optional[str] = None,
) -> List[Tuple[Document, float, np.ndarray[np.float32, Any]]]: ) -> List[Tuple[Document, float, np.ndarray[np.float32, Any]]]:
match_documents_params = self.match_args(query, k, filter) match_documents_params = self.match_args(query, filter)
res = self._client.rpc(self.query_name, match_documents_params).execute() query_builder = self._client.rpc(self.query_name, match_documents_params)
if postgrest_filter:
query_builder.params = query_builder.params.set(
"and", f"({postgrest_filter})"
)
query_builder.params = query_builder.params.set("limit", k)
res = query_builder.execute()
match_result = [ match_result = [
( (
@ -407,9 +431,9 @@ class SupabaseVectorStore(VectorStore):
$$; $$;
``` ```
""" """
embedding = self._embedding.embed_documents([query]) embedding = self._embedding.embed_query(query)
docs = self.max_marginal_relevance_search_by_vector( docs = self.max_marginal_relevance_search_by_vector(
embedding[0], k, fetch_k, lambda_mult=lambda_mult embedding, k, fetch_k, lambda_mult=lambda_mult
) )
return docs return docs

6
libs/langchain/langchain/vectorstores/vectara.py
View File

@ -396,8 +396,12 @@ class Vectara(VectorStore):
vectara_api_key=api_key, vectara_api_key=api_key,
) )
""" """
# Note: Vectara generates its own embeddings, so we ignore the provided # Notes:
# * Vectara generates its own embeddings, so we ignore the provided
# embeddings (required by interface) # embeddings (required by interface)
# * when metadatas[] are provided they are associated with each "part"
# in Vectara. doc_metadata can be used to provide additional metadata
# for the document itself (applies to all "texts" in this call)
doc_metadata = kwargs.pop("doc_metadata", {}) doc_metadata = kwargs.pop("doc_metadata", {})
vectara = cls(**kwargs) vectara = cls(**kwargs)
vectara.add_texts(texts, metadatas, doc_metadata=doc_metadata, **kwargs) vectara.add_texts(texts, metadatas, doc_metadata=doc_metadata, **kwargs)

2
libs/langchain/tests/integration_tests/document_loaders/test_polars_dataframe.py
View File

@ -34,8 +34,6 @@ def test_load_returns_list_of_documents(sample_data_frame: pl.DataFrame) -> None
def test_load_converts_dataframe_columns_to_document_metadata( def test_load_converts_dataframe_columns_to_document_metadata(
sample_data_frame: pl.DataFrame, sample_data_frame: pl.DataFrame,
) -> None: ) -> None:
import polars as pl
loader = PolarsDataFrameLoader(sample_data_frame) loader = PolarsDataFrameLoader(sample_data_frame)
docs = loader.load() docs = loader.load()

85
libs/langchain/tests/unit_tests/retrievers/self_query/test_supabase.py Normal file
View File

@ -0,0 +1,85 @@
from typing import Dict, Tuple
from langchain.chains.query_constructor.ir import (
Comparator,
Comparison,
Operation,
Operator,
StructuredQuery,
)
from langchain.retrievers.self_query.supabase import SupabaseVectorTranslator
DEFAULT_TRANSLATOR = SupabaseVectorTranslator()
def test_visit_comparison() -> None:
comp = Comparison(comparator=Comparator.LT, attribute="foo", value=["1", "2"])
expected = "and(metadata->>foo.lt.1,metadata->>foo.lt.2)"
actual = DEFAULT_TRANSLATOR.visit_comparison(comp)
assert expected == actual
def test_visit_operation() -> None:
op = Operation(
operator=Operator.AND,
arguments=[
Comparison(comparator=Comparator.LT, attribute="foo", value=2),
Comparison(comparator=Comparator.EQ, attribute="bar", value="baz"),
Comparison(comparator=Comparator.LT, attribute="abc", value=["1", "2"]),
],
)
expected = (
"and("
"metadata->foo.lt.2,"
"metadata->>bar.eq.baz,"
"and(metadata->>abc.lt.1,metadata->>abc.lt.2)"
")"
)
actual = DEFAULT_TRANSLATOR.visit_operation(op)
assert expected == actual
def test_visit_structured_query() -> None:
query = "What is the capital of France?"
structured_query = StructuredQuery(
query=query,
filter=None,
)
expected: Tuple[str, Dict] = (query, {})
actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
assert expected == actual
comp = Comparison(comparator=Comparator.LT, attribute="foo", value=["1", "2"])
expected = (
query,
{"postgrest_filter": "and(metadata->>foo.lt.1,metadata->>foo.lt.2)"},
)
structured_query = StructuredQuery(
query=query,
filter=comp,
)
actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
assert expected == actual
op = Operation(
operator=Operator.AND,
arguments=[
Comparison(comparator=Comparator.LT, attribute="foo", value=2),
Comparison(comparator=Comparator.EQ, attribute="bar", value="baz"),
Comparison(comparator=Comparator.LT, attribute="abc", value=["1", "2"]),
],
)
structured_query = StructuredQuery(
query=query,
filter=op,
)
expected = (
query,
{
"postgrest_filter": (
"and(metadata->foo.lt.2,metadata->>bar.eq.baz,and(metadata->>abc.lt.1,metadata->>abc.lt.2))"
)
},
)
actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
assert expected == actual

71
libs/langchain/tests/unit_tests/retrievers/self_query/test_vectara.py Normal file
View File

@ -0,0 +1,71 @@
from typing import Dict, Tuple
from langchain.chains.query_constructor.ir import (
Comparator,
Comparison,
Operation,
Operator,
StructuredQuery,
)
from langchain.retrievers.self_query.vectara import VectaraTranslator
DEFAULT_TRANSLATOR = VectaraTranslator()
def test_visit_comparison() -> None:
comp = Comparison(comparator=Comparator.LT, attribute="foo", value="1")
expected = "( doc.foo < '1' )"
actual = DEFAULT_TRANSLATOR.visit_comparison(comp)
assert expected == actual
def test_visit_operation() -> None:
op = Operation(
operator=Operator.AND,
arguments=[
Comparison(comparator=Comparator.LT, attribute="foo", value=2),
Comparison(comparator=Comparator.EQ, attribute="bar", value="baz"),
Comparison(comparator=Comparator.LT, attribute="abc", value=1),
],
)
expected = "( ( doc.foo < 2 ) and ( doc.bar = 'baz' ) and ( doc.abc < 1 ) )"
actual = DEFAULT_TRANSLATOR.visit_operation(op)
assert expected == actual
def test_visit_structured_query() -> None:
query = "What is the capital of France?"
structured_query = StructuredQuery(
query=query,
filter=None,
limit=None,
)
expected: Tuple[str, Dict] = (query, {})
actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
assert expected == actual
comp = Comparison(comparator=Comparator.LT, attribute="foo", value=1)
expected = (query, {"filter": "( doc.foo < 1 )"})
structured_query = StructuredQuery(
query=query,
filter=comp,
limit=None,
)
actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
assert expected == actual
op = Operation(
operator=Operator.AND,
arguments=[
Comparison(comparator=Comparator.LT, attribute="foo", value=2),
Comparison(comparator=Comparator.EQ, attribute="bar", value="baz"),
Comparison(comparator=Comparator.LT, attribute="abc", value=1),
],
)
structured_query = StructuredQuery(query=query, filter=op, limit=None)
expected = (
query,
{"filter": "( ( doc.foo < 2 ) and ( doc.bar = 'baz' ) and ( doc.abc < 1 ) )"},
)
actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
assert expected == actual