Spaces:

trong333tn
/

chatbotai_rag

Running

App Files Files Community

chatbotai_rag / src /core

87.8 kB

Ctrl+K

Ctrl+K

1 contributor

History: 40 commits

quoctrong's picture

perf: Downgrade model to 1.5B for faster CPU inference

9e9ace3 7 days ago

__init__.py

24 Bytes
DocBrain RAG official release for HF Space 9 days ago
bm25_store.py

3.79 kB
feat: Implement Phase 2 - pyvi tokenizer, Global FAISS Index, and Hierarchical Summary 8 days ago
cache.py

3.93 kB
perf: Optimize Latency (Remove query translation, async cache, tune LLM threads, limit tokens) 7 days ago
chunker.py

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

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

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

2.87 kB
Optimize LLM lazy loading and refine RAG prompt for full sentences 8 days ago
hf_storage.py

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

15.3 kB
feat: Enhance RAG LLM prompt with few-shot examples to enforce polite and complete sentences 8 days ago
local_llm_engine.py

2.79 kB
perf: Downgrade model to 1.5B for faster CPU inference 7 days ago
rag_pipeline.py

12.7 kB
perf: Optimize Latency (Remove query translation, async cache, tune LLM threads, limit tokens) 7 days ago
retriever.py

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

5.96 kB
Revert hardcoded samples and set intent threshold to 0.70 8 days ago
session_manager.py

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

3.18 kB
perf: Optimize Latency (Remove query translation, async cache, tune LLM threads, limit tokens) 7 days ago
vector_store.py

7.1 kB
feat: Implement Phase 2 - pyvi tokenizer, Global FAISS Index, and Hierarchical Summary 8 days ago
win_fix.py

1.09 kB
DocBrain RAG official release for HF Space 9 days ago