How sourangshupal/8hr-marathon works
Enterprise Agentic RAG accepts user questions through a Streamlit chat or the API, applies guardrails, then runs a LangGraph planner that either answers conversationally or retrieves technical context before generating a response. Document ingestion parses local files, chunks text, embeds it, and indexes it for later search. The product also exposes health and metrics endpoints and includes a separate RAGAS evaluation suite. Edges reflect the excerpts, SOURCE INDEX references, and README; some documented capabilities, including API protection and observability, have no sampled implementation detail.
Main entry points: graph.py LangGraph workflow · main.py FastAPI API · processor.py Ingestion processor · app.py Evaluation demo
Components 25
API and UI
- Streamlit chat
ui/app.py - FastAPI API
app/main.py - Input/output rails
app/guardrails/rails.py - Health checks
app/health.py - Prometheus metrics
app/main.py
Agent workflow
- LangGraph workflow
app/agents/graph.py - Conversation state
app/agents/state.py - Query planner
app/agents/nodes/planner.py - Technical retriever
app/agents/nodes/retriever.py - Answer generator
app/agents/nodes/responder.py
Knowledge indexing
- Ingestion processor
app/ingestion/processor.py - Document loaders
app/ingestion/loaders - Text chunker
app/ingestion/chunking/splitter.py
Stores and integrations
- Portkey LLM client
app/gateway/client.py - Checkpoint store
app/agents/graph.py - Qdrant vector store
app/services/retrieval/qdrant_service.py - Embedding service
app/services/retrieval/embedding.py - Semantic reranker
app/services/retrieval/ranking_service.py
Evaluation
- Evaluation demo
evals/app.py - Live pipeline eval
evals/pipeline.py - RAGAS metrics
evals/metrics.py - Guardrails eval
evals/guardrails_eval.py
Other components
- User
- Jina embedding API
- Jina reranker API
Connections 26
- User → Streamlit chat: asks via
README.md - Streamlit chat → FastAPI API: submits query
README.md - FastAPI API → Input/output rails: filters input
README.md - FastAPI API → LangGraph workflow: invokes workflow
app/main.py - FastAPI API → Prometheus metrics: exposes metrics
README.md - FastAPI API → Health checks: serves health
app/main.py - LangGraph workflow → Query planner: dispatches
app/agents/graph.py - LangGraph workflow → Technical retriever: routes technical
app/agents/graph.py - LangGraph workflow → Answer generator: routes conversational
app/agents/graph.py - LangGraph workflow → Answer generator: routes retrieved
app/agents/graph.py - LangGraph workflow → Checkpoint store: checkpoints state
app/agents/graph.py - Query planner → Portkey LLM client: calls LLM
app/agents/nodes/planner.py - Answer generator → Portkey LLM client: calls LLM
app/agents/nodes/responder.py - Technical retriever → Qdrant vector store: searches vectors
app/agents/nodes/retriever.py - Technical retriever → Semantic reranker: reranks results
app/agents/nodes/retriever.py - Qdrant vector store → Embedding service: embeds query
app/services/retrieval/qdrant_service.py - Embedding service → Jina embedding API: requests embeddings
app/services/retrieval/embedding.py - Semantic reranker → Jina reranker API: requests ranking
app/services/retrieval/ranking_service.py - Ingestion processor → Document loaders: parses files
app/ingestion/processor.py - Ingestion processor → Text chunker: chunks text
app/ingestion/processor.py - Ingestion processor → Embedding service: embeds chunks
app/ingestion/processor.py - Ingestion processor → Qdrant vector store: indexes vectors
app/ingestion/processor.py - Evaluation demo → Live pipeline eval: runs pipeline
evals/app.py - Evaluation demo → RAGAS metrics: computes metrics
evals/app.py - Evaluation demo → Guardrails eval: evaluates rails
evals/app.py - Live pipeline eval → FastAPI API: queries endpoint
evals/pipeline.py