Skip to main content

FR06 - RAG Infrastructure Compatibility

Feature Request

Guarantee that TypingMind remains fully compatible with a RAG infrastructure comprising AzureAI Cognitive Search, Langchain RAG, and Llama Index, supporting chat completions and document uploads to backend vector stores, with the RAG infrastructure deployable from the admin panel as a specific model with a dedicated API endpoint.

Status: Completed3 comments

Log in to comment and vote

Comments3

  • Ngoc Nguyen

    Team•

    Aug 7, 2024

    as of now, this can be done via our plugin system: https://docs.typingmind.com/plugins/build-a-typingmind-plugin

  • Gold Bagel changed status to Completed
    •

    Aug 7, 2024

  • Tan Peach

    •

    Apr 4, 2024

    It would be amazing if we can run any RAG pipeline to support local models' inference too, external context and vector databases integration, (Qdrant, Pinecone, Milvus, Choma, etc)