Spaces:

kerdosdotio
/

Custom-LLM-Chat

Running

App Files Files Community

Custom-LLM-Chat

36.4 kB

Ctrl+K

Ctrl+K

1 contributor

History: 6 commits

Bhaskar Ram

fix: model singleton cache, dedup guard, Gradio type=messages

9edd318 2 months ago

rag
fix: model singleton cache, dedup guard, Gradio type=messages 2 months ago
tests
feat: apply all 15 upgrades — BGE embeddings, cosine FAISS, streaming LLM, tenacity retry, dotenv, Dockerfile, tests 2 months ago
.env.example

496 Bytes
fix: sentence-aware chunking, score threshold, DOCX tables, streaming error handling, LLM_MODEL env var 2 months ago
.gitignore

296 Bytes
feat: apply all 15 upgrades — BGE embeddings, cosine FAISS, streaming LLM, tenacity retry, dotenv, Dockerfile, tests 2 months ago
Dockerfile

610 Bytes
feat: apply all 15 upgrades — BGE embeddings, cosine FAISS, streaming LLM, tenacity retry, dotenv, Dockerfile, tests 2 months ago
README.md

4.85 kB
feat: apply all 15 upgrades — BGE embeddings, cosine FAISS, streaming LLM, tenacity retry, dotenv, Dockerfile, tests 2 months ago
app.py

14.2 kB
fix: model singleton cache, dedup guard, Gradio type=messages 2 months ago
requirements-dev.txt

94 Bytes
feat: apply all 15 upgrades — BGE embeddings, cosine FAISS, streaming LLM, tenacity retry, dotenv, Dockerfile, tests 2 months ago
requirements.txt

173 Bytes
feat: apply all 15 upgrades — BGE embeddings, cosine FAISS, streaming LLM, tenacity retry, dotenv, Dockerfile, tests 2 months ago