MicrosoftDocs
Add Documentation for How to Use Azure Cosmos DB for MongoDB vCore Vector Store with Langchain
New Documentation
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 documentation for Python and Typescript users to store vectors from document embeddings generated from APIs such as Azure OpenAI Embeddings or Hugging Face on Azure when implement Q&A chatbots.
Azure Cosmos DB for MongoDB Vector Search
Document Details
⚠ Do not edit this section. It is required for learn.microsoft.com ➟ GitHub issue linking.
- ID: 5e53e4aa-c504-448b-9598-419eda127192
- Version Independent ID: 79fdea2a-5317-4996-a2b1-57662c2b9aa0
- Content: Vector search on embeddings - Azure Cosmos DB for MongoDB vCore
- Content Source: articles/cosmos-db/mongodb/vcore/vector-search.md
- Service: cosmos-db
- Sub-service: mongodb-vcore
- GitHub Login: @gahl-levy
- Microsoft Alias: gahllevy
@izzymsft Thanks for your feedback! We will investigate and update as appropriate.
Thanks @izzymsft for your feedback!
I've added an item to our backlog to discuss the benefits and effort associated with creating a tutorial that combines this API with langchain.
Since there's no immediate action item in this specific repo, I will go ahead and close this work item.
#please-close
