pip install -qU langchain-mongodb pymongo

import getpass

MONGODB_ATLAS_CLUSTER_URI = getpass.getpass("MongoDB Atlas Cluster URI:")

os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
os.environ["LANGSMITH_TRACING"] = "true"

# | output: false
# | echo: false
from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings()

from langchain_mongodb import MongoDBAtlasVectorSearch
from pymongo import MongoClient

# initialize MongoDB python client
client = MongoClient(MONGODB_ATLAS_CLUSTER_URI)

DB_NAME = "langchain_test_db"
COLLECTION_NAME = "langchain_test_vectorstores"
ATLAS_VECTOR_SEARCH_INDEX_NAME = "langchain-test-index-vectorstores"

MONGODB_COLLECTION = client[DB_NAME][COLLECTION_NAME]

vector_store = MongoDBAtlasVectorSearch(
    collection=MONGODB_COLLECTION,
    embedding=embeddings,
    index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,
    relevance_score_fn="cosine",
)

# Create vector search index on the collection
# Since we are using the default OpenAI embedding model (ada-v2) we need to specify the dimensions as 1536
vector_store.create_vector_search_index(dimensions=1536)

{
  "fields":[
    {
      "type": "vector",
      "path": "embedding",
      "numDimensions": 1536,
      "similarity": "cosine"
    }
  ]
}

from uuid import uuid4

from langchain_core.documents import Document

document_1 = Document(
    page_content="I had chocolate chip pancakes and scrambled eggs for breakfast this morning.",
    metadata={"source": "tweet"},
)

document_2 = Document(
    page_content="The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees.",
    metadata={"source": "news"},
)

document_3 = Document(
    page_content="Building an exciting new project with LangChain - come check it out!",
    metadata={"source": "tweet"},
)

document_4 = Document(
    page_content="Robbers broke into the city bank and stole $1 million in cash.",
    metadata={"source": "news"},
)

document_5 = Document(
    page_content="Wow! That was an amazing movie. I can't wait to see it again.",
    metadata={"source": "tweet"},
)

document_6 = Document(
    page_content="Is the new iPhone worth the price? Read this review to find out.",
    metadata={"source": "website"},
)

document_7 = Document(
    page_content="The top 10 soccer players in the world right now.",
    metadata={"source": "website"},
)

document_8 = Document(
    page_content="LangGraph is the best framework for building stateful, agentic applications!",
    metadata={"source": "tweet"},
)

document_9 = Document(
    page_content="The stock market is down 500 points today due to fears of a recession.",
    metadata={"source": "news"},
)

document_10 = Document(
    page_content="I have a bad feeling I am going to get deleted :(",
    metadata={"source": "tweet"},
)

documents = [
    document_1,
    document_2,
    document_3,
    document_4,
    document_5,
    document_6,
    document_7,
    document_8,
    document_9,
    document_10,
]
uuids = [str(uuid4()) for _ in range(len(documents))]

vector_store.add_documents(documents=documents, ids=uuids)

['03ad81e8-32a0-46f0-b7d8-f5b977a6b52a',
 '8396a68d-f4a3-4176-a581-a1a8c303eea4',
 'e7d95150-67f6-499f-b611-84367c50fa60',
 '8c31b84e-2636-48b6-8b99-9fccb47f7051',
 'aa02e8a2-a811-446a-9785-8cea0faba7a9',
 '19bd72ff-9766-4c3b-b1fd-195c732c562b',
 '642d6f2f-3e34-4efa-a1ed-c4ba4ef0da8d',
 '7614bb54-4eb5-4b3b-990c-00e35cb31f99',
 '69e18c67-bf1b-43e5-8a6e-64fb3f240e52',
 '30d599a7-4a1a-47a9-bbf8-6ed393e2e33c']

vector_store.delete(ids=[uuids[-1]])

True

results = vector_store.similarity_search(
    "LangChain provides abstractions to make working with LLMs easy", k=2
)
for res in results:
    print(f"* {res.page_content} [{res.metadata}]")

* Building an exciting new project with LangChain - come check it out! [{'_id': 'e7d95150-67f6-499f-b611-84367c50fa60', 'source': 'tweet'}]
* LangGraph is the best framework for building stateful, agentic applications! [{'_id': '7614bb54-4eb5-4b3b-990c-00e35cb31f99', 'source': 'tweet'}]

results = vector_store.similarity_search_with_score("Will it be hot tomorrow?", k=1)
for res, score in results:
    print(f"* [SIM={score:3f}] {res.page_content} [{res.metadata}]")

* [SIM=0.784560] The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees. [{'_id': '8396a68d-f4a3-4176-a581-a1a8c303eea4', 'source': 'news'}]

vectorstore.create_vector_search_index(
  dimensions=1536,
  filters=[{"type":"filter", "path":"source"}],
  update=True
)

{
  "fields":[
    {
      "type": "vector",
      "path": "embedding",
      "numDimensions": 1536,
      "similarity": "cosine"
    },
    {
      "type": "filter",
      "path": "source"
    }
  ]
}

results = vector_store.similarity_search(query="foo", k=1, pre_filter={"source": {"$eq": "https://example.com"}})
for doc in results:
    print(f"* {doc.page_content} [{doc.metadata}]")

retriever = vector_store.as_retriever(
    search_type="similarity_score_threshold",
    search_kwargs={"k": 1, "score_threshold": 0.2},
)
retriever.invoke("Stealing from the bank is a crime")

[Document(metadata={'_id': '8c31b84e-2636-48b6-8b99-9fccb47f7051', 'source': 'news'}, page_content='Robbers broke into the city bank and stole $1 million in cash.')]