Boosting AI: Build Your Chatbot Over Your Data With MongoDB Atlas Vector Search and LangChain Templates Using the RAG Pattern

1
pip3 install -U "langchain-cli[serve]"

1
langchain app new my-blog-article --package rag-mongo

1
from rag_mongo import chain as rag_mongo_chain
2
add_routes(app, rag_mongo_chain, path="/rag-mongo")

1
cd my-blog-article/packages/rag-mongo 

1
export OPENAI_API_KEY="xxxxxxxxxxx"
2
export MONGO_URI
3
="mongodb+srv://user:passwd@vectorsearch.abc.mongodb.net/?retryWrites=true"

1
python3 ingest.py

1
{
2
    "type": "vectorSearch",
3
    "fields": [
4
        {
5
            "path": "embedding",
6
            "dimensions": 1536,
7
            "similarity": "cosine",
8
            "type": "vector"
9
        }
10
	]
11
}

1
vectorstore = MongoDBAtlasVectorSearch.from_connection_string(
2
    MONGO_URI,
3
    DB_NAME + "." + COLLECTION_NAME,
4
    OpenAIEmbeddings(disallowed_special=()),
5
    index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,
6
)
7
retriever = vectorstore.as_retriever()

1
model = ChatOpenAI(model_name="gpt-3.5-turbo-16k-0613",temperature=0) 

1
langchain serve
2
3
INFO:     Will watch for changes in these directories: 
4
INFO:     Uvicorn running on http://127.0.0.1:8000 (Press CTRL+C to quit)
5
INFO:     Started reloader process [50552] using StatReload
6
INFO:     Started server process [50557]
7
INFO:     Waiting for application startup.
8
9
LANGSERVE: Playground for chain "/rag-mongo" is live at:
10
LANGSERVE:  │
11
LANGSERVE:  └──> /rag-mongo/playground
12
LANGSERVE:
13
LANGSERVE: See all available routes at /docs

1
http://127.0.0.1:8000/rag-mongo/playground/

1
curl -X POST "https://127.0.0.1:8000/rag-mongo/invoke" \
2
     -H "Content-Type: application/json" \
3
     -d '{"input": "Does MongoDB support transactions?"}'

1
{"output":"Yes, MongoDB supports transactions.","callback_events":[],"metadata":{"run_id":"06c70537-8861-4dd2-abcc-04a85a50bcb6"}}

1
curl -X POST "https://127.0.0.1:8000/rag-mongo/batch" \
2
     -H "Content-Type: application/json" \
3
     -d '{
4
           "inputs": [
5
             "What options do MongoDB Atlas Indexes include?",
6
             "Explain Atlas Global Cluster",
7
             "Does MongoDB Atlas provide backups?"
8
           ],
9
           "config": {},
10
           "kwargs": {}
11
         }'

1
{"output":["MongoDB Atlas Indexes include the following options:\n- Compound indexes\n- Geospatial indexes\n- Text search indexes\n- Unique indexes\n- Array indexes\n- TTL indexes\n- Sparse indexes\n- Partial indexes\n- Hash indexes\n- Collated indexes for different languages","Atlas Global Cluster is a feature provided by MongoDB Atlas, a cloud-based database service. It allows users to set up global clusters on various cloud platforms such as Amazon Web Services, Microsoft Azure, and Google Cloud Platform. \n\nWith Atlas Global Cluster, users can easily distribute their data across different regions by just a few clicks in the MongoDB Atlas UI. The deployment and management of infrastructure and database resources required for data replication and distribution are taken care of by MongoDB Atlas. \n\nFor example, if a user has an accounts collection that they want to distribute among their three regions of business, Atlas Global Cluster ensures that the data is written to and read from different regions, providing high availability and low latency access to the data.","Yes, MongoDB Atlas provides backups."],"callback_events":[],"metadata":{"run_ids":["1516ba0f-1889-4688-96a6-d7da8ff78d5e","4cca474f-3e84-4a1a-8afa-e24821fb1ec4","15cd3fba-8969-4a97-839d-34a4aa167c8b"]}}