Spaces:

trong333tn
/

chatbotai_rag

Running

App Files Files Community

187 kB

Ctrl+K

Ctrl+K

1 contributor

History: 50 commits

quoctrong's picture

perf: Downgrade model to 1.5B for faster CPU inference

9e9ace3 7 days ago

config
perf: Downgrade model to 1.5B for faster CPU inference 7 days ago
scripts
perf: Optimize Latency (Remove query translation, async cache, tune LLM threads, limit tokens) 7 days ago
src
perf: Downgrade model to 1.5B for faster CPU inference 7 days ago
tests
fix: increase max upload file size limit from 15MB to 100MB for large annual reports 8 days ago
.env.example

486 Bytes
feat: production-hardening, upload validation, admin auth, threadpool, logging & HF dataset repo integration 8 days ago
.gitignore

67 Bytes
feat: production-hardening, upload validation, admin auth, threadpool, logging & HF dataset repo integration 8 days ago
Dockerfile

344 Bytes
feat: production-hardening, upload validation, admin auth, threadpool, logging & HF dataset repo integration 8 days ago
README.md

3.94 kB
feat: production-hardening, upload validation, admin auth, threadpool, logging & HF dataset repo integration 8 days ago
SYSTEM_ARCHITECTURE.md

7.88 kB
feat: Phase 4 Upgrade - RAG Architecture Stability (mMARCO, pdfplumber, true recursive chunk, 3B LLM) 7 days ago
app.py

420 Bytes
Serve pure FastAPI HTML Web App in app.py without Gradio dependencies 9 days ago
requirements.txt

406 Bytes
fix: Use pre-compiled CPU wheel for llama-cpp-python to fix OOM issue during build 8 days ago
tai_lieu_test_tom_tat.txt

3.54 kB
feat: production-hardening, upload validation, admin auth, threadpool, logging & HF dataset repo integration 8 days ago