Hugging Face's logo

Spaces:
teofizzy
/
mshauri-fedha
Sleeping

App Files Community
mshauri-fedha / src /load

Commit History

  1. Revert "feat: Implement a parallel voting ensemble for LLM selection based on Jaccard similarity, replacing the sequential fallback mechanism."⁠

    teofizzy
    868d1b6

  2. feat: Implement a parallel voting ensemble for LLM selection based on Jaccard similarity, replacing the sequential fallback mechanism.

    teofizzy
    f81b0fc

  3. feat: Enhance agent robustness by separating base and fallback LLMs, update Ollama model to 7B, and improve Docker startup reliability.

    teofizzy
    de956af

  4. feat: Enhance LLM resilience with a multi-provider fallback system, upgrade the default Ollama model to 7B, and improve vector store relevance score calculation.

    teofizzy
    5f850dc

  5. feat: Add stop parameter to chat completion requests and simplify the comment regarding `<think>` tag stripping.

    teofizzy
    48535aa

  6. Remove `Qwen/Qwen1.5-110B-Chat` from the list of candidate models.

    teofizzy
    f8e63eb

  7. feat: Augment agent prompts with uploaded file context, clarify data storage consent, and add Qwen/Qwen1.5-110B-Chat to candidate models.

    teofizzy
    f0c1010

  1. Removed artifacts

    teofizzy
    c0adb25

  1. enhanced pompt

    teofizzy
    79c6f19

  2. stripped artifacts

    teofizzy
    50324c2

  3. stripped artifacts

    teofizzy
    c71fc23

  4. stripped of certain artifacts

    teofizzy
    a09f4a1

  5. added swahili language

    teofizzy
    0830be5

  1. controlling scope

    teofizzy
    d845605

  2. citations logic

    teofizzy
    53ed90b

  3. scope guardrails + advice protocol

    teofizzy
    60cead1

  4. health economics

    teofizzy
    4280afb

  5. introduced scope guardrails and confidence scoring (0-100)

    teofizzy
    706e9aa

  6. increased token limit + catch <think> tags

    teofizzy
    f139ff4

  7. uses langchain core

    teofizzy
    e0e0aba

  8. Switched to use Huggingface CHAT

    teofizzy
    46d2574

  9. trying new models that use could possibly accept the HuggingFaceEndpoint API inference

    teofizzy
    6de20f5

  10. added more fallback model options

    teofizzy
    113bfd1

  1. added list of candidate models

    teofizzy
    2e3e101

  2. switched to qwen 32B - Instruct due to inference provider support

    teofizzy
    81d32dd

  3. changed to use huggingface serverless endpoint with local CPU as a fallback

    teofizzy
    f8266e7

  1. added observation logging

    teofizzy
    c60e74e

  2. changed default ollama network port to match huggingface default

    teofizzy
    bba20c4

  3. deployment 1.0

    teofizzy
    b860cd0

  1. prototype stage

    teofizzy
    7011b92