Vibe Coding Discoverrenumics-rag
View on GitHubVisualization for a Retrieval-Augmented Generation (RAG) Assistant 🤖❤️📚
Python RAG demo that indexes documents into Chroma, answers questions via LangChain models, and lets you visually explore question/snippet embeddings with Renumics Spotlight and UMAP to debug and evaluate retrieval quality.
Use Cases
Build a document Q&A RAG assistant over HTML/PDF/DOCX filesIndex documents into a vector database with configurable embeddingsVisualize question and snippet embeddings with UMAP to inspect retrieval clustersEvaluate RAG retrieval quality by exploring which snippets answer which questionsCompare LLM and retriever settings interactively during Q&ARun CLI commands for create-db, retrieve, answer, and explore workflowsPrototype RAG pipelines locally before production
Built With
- Language
- Python
- Frameworks
- LangChain · Streamlit · ChromaDB · Renumics Spotlight · PyTorch · Hugging Face Transformers · sentence-transformers · unstructured · pandas · UMAP · Pydantic · Typer
Tags
rag · langchain · streamlit · visualization · embeddings · chromadb · umap · vector-search · retrieval · document-indexing · question-answering · evaluation · openai · huggingface · spotlight · python