search

deepset-ai / haystack

:mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
https://haystack.deepset.ai
Apache License 2.0
14.45k stars 1.7k forks source link

Integrate with Azure AI Search (vectorDB) #6749

Open trungtly opened 5 months ago

trungtly commented 5 months ago

Is your feature request related to a problem? Please describe. Integrate with Azure AI Search (formerly known as Azure Cognitive Search) as a vectorDB Llamaindex: https://docs.llamaindex.ai/en/stable/examples/vector_stores/CognitiveSearchIndexDemo.html Langchain: https://python.langchain.com/docs/integrations/vectorstores/azuresearch

Describe the solution you'd like Azure AI Search is fundamentally a vectorDB with its own default embedder.

Additional context Useful for enterprise use cases that rely on Azure ecosystem.

isfuku commented 3 months ago

Can you assign this to me? I already have an implementation for the document store following the protocol, and the retrievers. I closely followed the OpenSearch implementation.

cjayb-norlys commented 1 month ago

hey there, is there an update on this? +1 to the OP point on "enterprise use case" :)

touhi99 commented 1 week ago

+1 if any update on it? high demanding with Azure-stack RAG system in enterprise :)