phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-31 05:50:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
llama-stack-mirror/docs/source/providers/vector_io/mongodb.md
Ashwin Gangadhar 80d9d50954 adding mongodb vector_io module 
updated mongodb.py from print to log

add documentation for mongodb vector search module

changed insert to update mongodb

bug fix mongodb json object conversion error
2025-03-13 11:04:18 +05:30

1.2 KiB
Raw Blame History

orphan
true

MongoDB Atlas

MongoDB Atlas is a cloud database service that can be used as a vector store provider for Llama Stack. It supports vector search capabilities through its Atlas Vector Search feature, allowing you to store and query vectors within your MongoDB database.

Features

MongoDB Atlas Vector Search supports:

  • Store embeddings and their metadata
  • Vector search with multiple algorithms (cosine similarity, euclidean distance, dot product)
  • Hybrid search (combining vector and keyword search)
  • Metadata filtering
  • Scalable vector indexing
  • Managed cloud infrastructure

Usage

To use MongoDB Atlas in your Llama Stack project, follow these steps:

  1. Create a MongoDB Atlas account and cluster.
  2. Configure your Atlas cluster to enable Vector Search.
  3. Configure your Llama Stack project to use MongoDB Atlas.
  4. Start storing and querying vectors.

Installation

You can install the MongoDB Python driver using pip:

pip install pymongo

Documentation

See MongoDB Atlas Vector Search documentation for more details about vector search capabilities in MongoDB Atlas.