RAG template for MongoDB Atlas Vector Search (#12526)

templates/rag-mongo/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-mongo/README.md

@@ -0,0 +1,17 @@
+# RAG Mongoß
+
+This template performs RAG using MongoDB and OpenAI.
+
+See [this notebook](https://colab.research.google.com/drive/1cr2HBAHyBmwKUerJq2if0JaNhy-hIq7I#scrollTo=TZp7_CBfxTOB) for additional context.
+
+##  Mongo
+
+This template connects to MongoDB Atlas Vector Search.
+
+Be sure that you have set a few env variables in `chain.py`:
+
+* `MONGO_URI`
+
+##  LLM
+
+Be sure that `OPENAI_API_KEY` is set in order to the OpenAI models.

templates/rag-mongo/pyproject.toml

@@ -0,0 +1,21 @@
+[tool.poetry]
+name = "rag-mongo"
+version = "0.1.0"
+description = ""
+authors = ["Lance Martin <[email protected]>"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = ">=3.8.1,<4.0"
+langchain = ">=0.0.313, <0.1"
+openai = ">=0.28.1"
+tiktoken = ">=0.5.1"
+pymongo = ">=4.5.0"
+
+[tool.langserve]
+export_module = "rag_mongo"
+export_attr = "chain"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

templates/rag-mongo/rag_mongo.ipynb

@@ -0,0 +1,52 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "681a5d1e",
+   "metadata": {},
+   "source": [
+    "## Connect to template\n",
+    "\n",
+    "In `server.py`, set -\n",
+    "```\n",
+    "add_routes(app, chain_ext, path=\"/rag_mongo\")\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d774be2a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langserve.client import RemoteRunnable\n",
+    "\n",
+    "rag_app_pinecone = RemoteRunnable(\"http://0.0.0.0:8001/rag_mongo\")\n",
+    "rag_app_pinecone.invoke(\"How does agent memory work?\")"
+   ]
+  }
+ ],
+ "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": "3.9.16"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

templates/rag-mongo/rag_mongo/__init__.py

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

templates/rag-mongo/rag_mongo/chain.py

@@ -0,0 +1,79 @@
+import os
+
+from langchain.chat_models import ChatOpenAI
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.prompts import ChatPromptTemplate
+from langchain.pydantic_v1 import BaseModel
+from langchain.schema.output_parser import StrOutputParser
+from langchain.schema.runnable import RunnableParallel, RunnablePassthrough
+from langchain.vectorstores import MongoDBAtlasVectorSearch
+from pymongo import MongoClient
+
+# Set DB
+if os.environ.get("MONGO_URI", None) is None:
+    raise Exception("Missing `MONGO_URI` environment variable.")
+MONGO_URI = os.environ["MONGO_URI"]
+
+DB_NAME = "langchain-test-2"
+COLLECTION_NAME = "test"
+ATLAS_VECTOR_SEARCH_INDEX_NAME = "default"
+
+client = MongoClient(MONGO_URI)
+db = client[DB_NAME]
+MONGODB_COLLECTION = db[COLLECTION_NAME]
+
+### Ingest code - you may need to run this the first time
+""" 
+# Load
+from langchain.document_loaders import WebBaseLoader
+loader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")
+data = loader.load()
+
+# Split
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
+all_splits = text_splitter.split_documents(data)
+
+# Add to vectorDB
+# Insert the documents in MongoDB Atlas Vector Search
+vectorstore = MongoDBAtlasVectorSearch.from_documents(
+     documents=all_splits, 
+     embedding=OpenAIEmbeddings(disallowed_special=()), 
+     collection=MONGODB_COLLECTION, 
+     index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME
+ )
+retriever = vectorstore.as_retriever()
+"""
+
+# Read from MongoDB Atlas Vector Search
+vectorstore = MongoDBAtlasVectorSearch.from_connection_string(
+    MONGO_URI,
+    DB_NAME + "." + COLLECTION_NAME,
+    OpenAIEmbeddings(disallowed_special=()),
+    index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,
+)
+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()
+)
+
+
+# Add typing for input
+class Question(BaseModel):
+    __root__: str
+
+
+chain = chain.with_types(input_type=Question)