Add Weaviate RAG template (#12460)

templates/rag-weaviate/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 LangChain, Inc.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

templates/rag-weaviate/README.md

@@ -0,0 +1,16 @@
+# RAG Weaviate
+
+This template performs RAG using Weaviate and OpenAI.
+
+##  Weaviate
+
+This connects to a hosted Weaviate vectorstore.
+
+Be sure that you have set a few env variables in `chain.py`:
+
+* `WEAVIATE_ENVIRONMENT`
+* `WEAVIATE_API_KEY`
+
+##  LLM
+
+Be sure that `OPENAI_API_KEY` is set in order to the OpenAI models.

templates/rag-weaviate/pyproject.toml

@@ -0,0 +1,24 @@
+[tool.poetry]
+name = "rag_weaviate"
+version = "0.1.0"
+description = ""
+authors = ["Erika Cardenas <erika@weaviate.io"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = ">=3.8.1,<4.0"
+langchain = ">=0.0.313"
+openai = "^0.28.1"
+tiktoken = "^0.5.1"
+weaviate-client = ">=3.24.2"
+
+[tool.poetry.group.dev.dependencies]
+python-dotenv = { extras = ["cli"], version = "^1.0.0" }
+
+[tool.langserve]
+export_module = "rag_weaviate"
+export_attr = "chain"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

templates/rag-weaviate/rag_weaviate.ipynb

@@ -0,0 +1,56 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "8692a430",
+   "metadata": {},
+   "source": [
+    "# Run Template\n",
+    "\n",
+    "In `server.py`, set -\n",
+    "```\n",
+    "add_routes(app, chain_ext, path=\"/rag-weaviate\")\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "41db5e30",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langserve.client import RemoteRunnable\n",
+    "rag_app_weaviate = RemoteRunnable(\"http://localhost:8000/rag-weaviate\")\n",
+    "rag_app_weaviate.invoke(\"How does agent memory work?\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.11.6 64-bit",
+   "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": "3.11.6"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "aee8b7b246df8f9039afb4144a1f6fd8d2ca17a180786b69acc140d282b71a49"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

templates/rag-weaviate/rag_weaviate/__init__.py

@@ -0,0 +1,3 @@
+from rag_weaviate.chain import chain
+
+__all__ = ["chain"]

templates/rag-weaviate/rag_weaviate/chain.py

@@ -0,0 +1,52 @@
+import os
+
+from langchain.chat_models import ChatOpenAI
+from langchain.document_loaders import WebBaseLoader
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.prompts import ChatPromptTemplate
+from langchain.schema.output_parser import StrOutputParser
+from langchain.schema.runnable import RunnableParallel, RunnablePassthrough
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import Weaviate
+
+if os.environ.get("WEAVIATE_API_KEY", None) is None:
+    raise Exception("Missing `WEAVIATE_API_KEY` environment variable.")
+
+if os.environ.get("WEAVIATE_ENVIRONMENT", None) is None:
+    raise Exception("Missing `WEAVIATE_ENVIRONMENT` environment variable.")
+
+WEAVIATE_INDEX_NAME = os.environ.get("WEAVIATE_INDEX", "langchain-test")
+
+### Ingest code - you may need to run this the first time
+# Load
+loader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")
+data = loader.load()
+
+# # Split
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
+all_splits = text_splitter.split_documents(data)
+
+# # Add to vectorDB
+vectorstore = Weaviate.from_documents(
+     documents=all_splits, embedding=OpenAIEmbeddings(), index_name=WEAVIATE_INDEX_NAME
+)
+retriever = vectorstore.as_retriever()
+
+vectorstore = Weaviate.from_existing_index(WEAVIATE_INDEX_NAME, OpenAIEmbeddings())
+retriever = vectorstore.as_retriever()
+
+# RAG prompt
+template = """Answer the question based only on the following context:
+{context}
+Question: {question}
+"""
+prompt = ChatPromptTemplate.from_template(template)
+
+# RAG
+model = ChatOpenAI()
+chain = (
+    RunnableParallel({"context": retriever, "question": RunnablePassthrough()})
+    | prompt
+    | model
+    | StrOutputParser()
+)