RAG Pipeline

Retrieval-Augmented Generation — from document ingestion to grounded response

graph TD classDef yellow fill:#FFFDE7,stroke:#1A1A1A,stroke-width:2px; classDef blue fill:#E3F2FD,stroke:#1A1A1A,stroke-width:2px; classDef green fill:#E8F5E9,stroke:#1A1A1A,stroke-width:2px; classDef purple fill:#F3E5F5,stroke:#1A1A1A,stroke-width:2px; classDef teal fill:#E0F7FA,stroke:#1A1A1A,stroke-width:2px; classDef orange fill:#FFF3E0,stroke:#1A1A1A,stroke-width:2px; classDef note fill:#FFF9C4,stroke:#FBC02D,stroke-dasharray:4; User([User Query]):::yellow subgraph Ingest ["Ingestion Pipeline"] Crawler[Document Crawler]:::orange Chunker[Text Chunker]:::orange EmbedIngest[Embedding Model]:::blue VectorDB[(Vector Store)]:::green DocStore[(Document Store)]:::green Crawler --> Chunker --> EmbedIngest --> VectorDB Chunker --> DocStore end subgraph Retrieve ["Query & Retrieval"] EmbedQuery[Query Embedder]:::blue Search[Similarity Search]:::teal Reranker[Reranker]:::teal Context[Context Builder]:::teal end subgraph Generate ["Generation"] LLM[LLM]:::purple Response([Response]):::yellow end User --> EmbedQuery EmbedQuery --> Search VectorDB --> Search Search --> Reranker DocStore --> Reranker Reranker --> Context Context --> LLM User --> LLM LLM --> Response