How aniketpatel161161/rag_pipeline- works
This repository is a notebook-based RAG application. Its documented workflow loads text and PDF documents, chunks and embeds them into persistent vector storage, then embeds a user query, retrieves and ranks relevant chunks, and sends augmented context to an OpenAI model for an answer. The notebook is the only source file in the tree, so its distinct responsibilities share that path. Relationships are based on the README; notebook implementation details were not available for inspection.
Main entry points: RAG_PIPELINE.ipynb RAG Retriever
Components 12
Document Ingestion
- TXT and PDF Files
- Document Loaders
RAG_PIPELINE.ipynb - Recursive Chunking
RAG_PIPELINE.ipynb
Embedding and Storage
- Embedding Manager
RAG_PIPELINE.ipynb - Sentence Transformer
- Vector Store Manager
RAG_PIPELINE.ipynb - Persistent ChromaDB
Retrieval and Context
- RAG Retriever
RAG_PIPELINE.ipynb
Answer Generation
- Context Prompt
RAG_PIPELINE.ipynb - OpenAI LLM
- Generated Answer
RAG_PIPELINE.ipynb
Other components
- User
Connections 14
- TXT and PDF Files → Document Loaders: loads
README.md - Document Loaders → Recursive Chunking: provides documents
README.md - Recursive Chunking → Embedding Manager: provides chunks
README.md - Embedding Manager → Sentence Transformer: generates vectors
README.md - Embedding Manager → Vector Store Manager: provides embeddings
README.md - Vector Store Manager → Persistent ChromaDB: persists chunks
README.md - User → RAG Retriever: submits query
README.md - RAG Retriever → Embedding Manager: embeds query
README.md - RAG Retriever → Vector Store Manager: searches vectors
README.md - Vector Store Manager → Persistent ChromaDB: searches collection
README.md - RAG Retriever → Context Prompt: returns ranked chunks
README.md - Context Prompt → OpenAI LLM: sends augmented prompt
README.md - OpenAI LLM → Generated Answer: generates response
README.md - User → Context Prompt: asks question
README.md