search

langchain-ai / langchainjs

🦜🔗 Build context-aware reasoning applications 🦜🔗
https://js.langchain.com/docs/
MIT License
12.41k stars 2.1k forks source link

Add AzureCosmosDBVectorSearch VectorStore #1449

Closed izzymsft closed 1 year ago

izzymsft commented 1 year ago

New Feature Request

Azure Cosmos DB for MongoDB vCore enables users to efficiently store, index, and query high dimensional vector data stored directly in Azure Cosmos DB for MongoDB vCore. It contains similarity measures such as COS (cosine distance), L2 (Euclidean distance) or IP (inner product) which measures the distance between the data vectors and your query vector. The data vectors that are closest to your query vector are the ones that are found to be most similar semantically and retrieved during query time. The accompanying PR would add support for Langchain Javascript/TypeScript users to store vectors from document embeddings generated from APIs such as Azure OpenAI Embeddings or Hugging Face on Azure.

Motivation

This capability described in the feature request is currently not available for Langchain TypeScript/JavaScript.

Contribution

I will be submitting a PR for this feature request

Azure Cosmos DB for MongoDB vCore

jacoblee93 commented 1 year ago

Looking forward to seeing it!

dosubot[bot] commented 1 year ago

Hi, @izzymsft! I'm Dosu, and I'm helping the LangChain team manage their backlog. I wanted to let you know that we are marking this issue as stale.

From what I understand, this issue is a feature request to add support for Azure Cosmos DB for MongoDB vCore's VectorSearch VectorStore in Langchain JavaScript/TypeScript. You mentioned that you plan to submit a pull request to contribute this feature, and Jacoblee93 expressed excitement and anticipation for it.

Before we close this issue, we wanted to check with you if it is still relevant to the latest version of the LangChain repository. If it is, please let us know by commenting on the issue. Otherwise, feel free to close the issue yourself, or it will be automatically closed in 7 days.

Thank you for your contribution and support!