fix: format history as string to prevent Llama 3 hallucinating assistant role during contextualization

fix: prevent LLM from hallucinating queries during contextualization

fix: preload models on startup and increase LLM timeout

fix: soften strict prompt for keyword queries

fix: handle 2D numpy array from multilingual reranker

fix: switch to multilingual reranker

fix: dockerignore and memory init

fix: change port to 7860 for huggingface spaces

fix: restore README and prepend HF config

chore: track sqlite with git-lfs for huggingface

chore: remove IS_RENDER and gemini imports

feat(rag): enable rerank model on render

feat(rag): use bkai huggingface model universally

fix(prompt): allow LLM to respond to chit-chat naturally

chore: push VectorDB and data folders for deployment

fix(rag): update prompt and reduce temperature to prevent hallucinations

fix: use models/gemini-embedding-2 with 768 dimensions for compatibility with local database

fix: correct GoogleGenerativeAIEmbeddings class name

fix: make heavy ML libraries import conditionally on Render to prevent OOM/timeouts

fix: dynamically bind to PORT and specify port 8000 in render.yaml

fix: add langchain-groq to requirements.txt

feat: add render.yaml blueprint config

clean: remove GitHub Actions workflow because test script was deleted

Delete scripts/test_supabase.py

fix: strip carriage returns from database url

feat: tích hợp supabase database và cấu hình github actions ci

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Add Optimization data files

Update README.md

Add and refactor evaluation scripts

“…I”

first commit

first commit

“…I”

Add data

“…I”

Add VectorDB

hoàn thiện Multimodal RAG chatbot với FastAPI Backend & Web UI