How harishneel1/vectorless-rag works
Vectorless RAG is a single-notebook workflow for answering questions over documents without embeddings or a vector store. A user runs the notebook, which loads documents, asks an LLM to identify relevant passages, then uses that context to generate a grounded answer. The README describes these stages, but the notebook source was not provided, so implementation-level calls cannot be verified; edges below reflect documented behavior only.
Main entry points: vectorless_rag.ipynb Passage routing · assets Source documents
Components 7
RAG workflow
- Pipeline notebook
vectorless_rag.ipynb - Source documents
assets - Document loading
vectorless_rag.ipynb - Passage routing
vectorless_rag.ipynb - Grounded answer
vectorless_rag.ipynb
Other components
- Notebook user
- LLM service
Connections 7
- Notebook user → Pipeline notebook: runs
README.md - Source documents → Document loading: reads
README.md - Pipeline notebook → Document loading: runs pipeline
README.md - Document loading → Passage routing: then routes
README.md - Passage routing → LLM service: prompts for relevance
README.md - Passage routing → Grounded answer: passes context
README.md - Grounded answer → LLM service: generates answer
README.md