Hugging Face's logo

Spaces:
alishba38
/
curemind
Sleeping

App Files Community
curemind / server

Commit History

  1. feat: implement LLM RAG chain with dynamic model selection and source-aware medical response generation

    Alishba Siddique
    a963799

  2. feat: implement RAG LLM chain with dynamic model routing and update README documentation

    Alishba Siddique
    b83ceaa

  3. Updated qwen/qwen3-32b to qwen-2.5-32b

    Alishba Siddique
    c60bd25

  1. fix: score-threshold filtering + clear sources when answering from general knowledge

    Alishba Siddique
    62eeb33

  2. feat: deduplicated, human-readable source citations with page numbers

    Alishba Siddique
    9d405f2

  3. fix: sidebar checkbox visibility + LLM falls back to general knowledge

    Alishba Siddique
    ab454b2

  1. fix: strip DeepSeek R1 <think> reasoning tags from responses

    Alishba Siddique
    8e370d1

  2. fix: replace Google embeddings with HuggingFace sentence-transformers (no API key needed)

    Alishba Siddique
    7483ad4

  3. fix: pin langchain-google-genai<2.0 to restore working embedding-001 model

    Alishba Siddique
    49150d2

  4. fix: update Google embedding model from embedding-001 to text-embedding-004

    Alishba Siddique
    36f06da

  5. fix: robust Pydantic retriever + friendly error messages in UI

    Alishba Siddique
    29da74a

  6. fix: use get_index() in ask endpoint to auto-create Pinecone index if missing

    Alishba Siddique
    8826144

  7. fix: replace deprecated langchain.text_splitter with langchain-text-splitters

    Alishba Siddique
    d8c20f3

  8. fix: use absolute import path for load_vectorstore module

    Alishba Siddique
    e96b0e3

  9. fix: update BaseRetriever import to langchain_core.retrievers

    Alishba Siddique
    6a509ca

  10. fix: lazy Pinecone init so FastAPI starts cleanly on HF Spaces

    Alishba Siddique
    1689c36

  11. feat: production deployment setup for HF Spaces

    Alishba Siddique
    e2640ca