docs/integrations/vectorstores/azure_cosmos_db/

[giscus[bot]]

docs/integrations/vectorstores/azure_cosmos_db/

This notebook shows you how to leverage this integrated vector database to store documents in collections, create indicies and perform vector search queries using approximate nearest neighbor algorithms such as COS (cosine distance), L2 (Euclidean distance), and IP (inner product) to locate documents close to the query vectors.

https://python.langchain.com/docs/integrations/vectorstores/azure_cosmos_db/

[leonardobaggio]

Was only able to filter using pre_filter in search_kwargs:

authorized_users= ['1']

user_permissions = {"metadata.authorizedUsers": {"$in": authorized_users}}
client_filter = {"metadata.customerId": 1}

combined_filter = {
    "$and": [
        user_permissions,
        client_filter
    ]
}

retriever = vector_store.as_retriever(
    search_kwargs={'k': 5, 'fetch_k': 50, 'pre_filter': combined_filter}
)