Skip to content

v1.0.0 — Initial Release

Latest
Latest

Choose a tag to compare

View all tags
@sunilgentyala sunilgentyala released this 29 Apr 22:34
· 3 commits to main since this release
v1.0.0
72d4a76

🧠 Local RAG LLM — v1.0.0

What's included

  • Streamlit UI — upload PDFs, chat, view source citations
  • Fully local inference via Ollama (llama3 8B Q4 + nomic-embed-text)
  • Persistent ChromaDB vector store — survives app restarts
  • LCEL chain — built on LangChain 1.x Expression Language
  • Hallucination guard — model stays strictly within uploaded document context
  • Privacy-first — no data leaves your machine, no API key required

Stack

Component Version
LangChain 1.2.16
LangChain-Ollama 1.1.0
ChromaDB 1.5.8
Streamlit 1.57.0
pypdf 6.10.2

Quick Start

git clone https://github.com/sunilgentyala/local-rag-llm.git
cd local-rag-llm
python -m venv venv && venv/Scripts/activate
pip install -r requirements.txt
ollama pull llama3 && ollama pull nomic-embed-text
streamlit run app.py

Bug Fixes in this release

  • Fixed model=OLLAMA_BASE_URL and LLM_MODEL typo in get_llm()
  • Replaced deprecated langchain.chains imports with LCEL RunnablePassthrough pipeline (compatible with LangChain 1.x)
Assets 2
Loading