Modify Dockerfile to install git-lfs and zstd

Update main.yml

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

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

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

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

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

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

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

feat: Add 'Clear Chat & Ephemeral Data' button, ensure vector store persistence, and refresh agent upon new file uploads.

feat: Implement multi-file upload for DOCX, TXT, and MD documents, improve SQL table cleanup with name validation and quoting, and update file uploader UI.

feat: Refactor PDF processing to use pymupdf4llm for markdown extraction and MarkdownTextSplitter for intelligent chunking, adding necessary dependencies.

feat: Extend file ingestion to support .xlsx, .xls, .docx, .txt, and .md formats, updating dependencies accordingly.

feat: enable user upload of CSV and PDF files with options for ephemeral or persistent storage.

Removed artifacts

Clean up user prompt formatting in README

enhanced pompt

Remove license section from README

stripped artifacts

stripped artifacts

stripped of certain artifacts

added swahili language

Refactor README for better structure and readability

controlling scope

citations logic

scope guardrails + advice protocol

health economics

introduced scope guardrails and confidence scoring (0-100)

increased token limit + catch <think> tags

uses langchain core

missing dependency

Switched to use Huggingface CHAT

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

added more fallback model options

added list of candidate models

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

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

added observation logging

changed default ollama network port to match huggingface default

pdate src/app.py to prepend the sqlite:/// prefix to the database path.

added zstd compression to unpack binaries

install global tools as root user

Merge branch 'main' of https://github.com/teofizzy/mshauri-fedha

deployment 1.0

Update emoji and color settings in README

Update README with project metadata

Add GitHub Actions workflow to sync with Hugging Face Hub

prototype edits

Add README for Mshauri Fedha project

data ingestion notebook - use colab + gdrive