langchain/libs/partners/mongodb/README.md
Casey Clements 6e9a8b188f
mongodb: Add Hybrid and Full-Text Search Retrievers, release 0.2.0 (#25057)
## Description

This pull-request extends the existing vector search strategies of
MongoDBAtlasVectorSearch to include Hybrid (Reciprocal Rank Fusion) and
Full-text via new Retrievers.

There is a small breaking change in the form of the `prefilter` kwarg to
search. For this, and because we have now added a great deal of
features, including programmatic Index creation/deletion since 0.1.0, we
plan to bump the version to 0.2.0.

### Checklist
* Unit tests have been extended
* formatting has been applied
* One mypy error remains which will either go away in CI or be
simplified.

---------

Signed-off-by: Casey Clements <casey.clements@mongodb.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-08-07 20:10:29 +00:00

1.3 KiB

langchain-mongodb

Installation

pip install -U langchain-mongodb

Usage

Using MongoDBAtlasVectorSearch

from langchain_mongodb import MongoDBAtlasVectorSearch

# Pull MongoDB Atlas URI from environment variables
MONGODB_ATLAS_CLUSTER_URI = os.environ.get("MONGODB_ATLAS_CLUSTER_URI")

DB_NAME = "langchain_db"
COLLECTION_NAME = "test"
ATLAS_VECTOR_SEARCH_INDEX_NAME = "index_name"
MONGODB_COLLECTION = client[DB_NAME][COLLECTION_NAME]

# Create the vector search via `from_connection_string`
vector_search = MongoDBAtlasVectorSearch.from_connection_string(
    MONGODB_ATLAS_CLUSTER_URI,
    DB_NAME + "." + COLLECTION_NAME,
    OpenAIEmbeddings(disallowed_special=()),
    index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,
)

# Initialize MongoDB python client
client = MongoClient(MONGODB_ATLAS_CLUSTER_URI)
# Create the vector search via instantiation
vector_search_2 = MongoDBAtlasVectorSearch(
    collection=MONGODB_COLLECTION,
    embeddings=OpenAIEmbeddings(disallowed_special=()),
    index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,
)