challenge10-pbia/rag_cognus

How challenge10-pbia/rag_cognus works

Cognus is a local RAG application for answering questions from the Databricks Gold knowledge view and evaluating retrieval and answers. The main workflow is to sync Gold data to a local snapshot, retrieve passages with BM25 or dense search, and optionally generate grounded answers; users can invoke this through the CLI or browser chat. Evaluation records per-question results and aggregate metrics in local MLflow. The graph follows the README and sampled source; some chat wiring is visible only in the source index.

Main entry points: cli.py CLI commands · evaluation.py Evaluation runner · chat_app.py Browser chat · retrieval.py Gold retriever

Components 14

User interfaces

CLI commands src/rag_cognus/cli.py
Browser chat src/rag_cognus/chat_app.py

Knowledge and retrieval

Runtime settings src/rag_cognus/config.py
Gold sync src/rag_cognus/gold.py
Gold retriever src/rag_cognus/retrieval.py

Answer generation

RAG pipeline src/rag_cognus/chain.py

Evaluation and tracking

Response judge src/rag_cognus/judges.py
Evaluation cases data/evaluation/questions.jsonl
Evaluation runner src/rag_cognus/evaluation.py
Metric scoring src/rag_cognus/metrics.py

Other components

User
Databricks Gold
Ollama models
Local MLflow

Connections 25

User → CLI commands: runs commands README.md
User → Browser chat: asks questions README.md
CLI commands → Runtime settings: loads settings src/rag_cognus/cli.py
Browser chat → Runtime settings: configures runtime src/rag_cognus/chat_app.py
CLI commands → Gold sync: syncs Gold src/rag_cognus/cli.py
Gold sync → Databricks Gold: reads view src/rag_cognus/gold.py
CLI commands → Gold sync: loads snapshot src/rag_cognus/cli.py
CLI commands → Gold retriever: builds index src/rag_cognus/cli.py
Browser chat → Gold retriever: prepares search src/rag_cognus/chat_app.py
Gold retriever → Runtime settings: reads options src/rag_cognus/retrieval.py
Gold retriever → Ollama models: embeds passages src/rag_cognus/retrieval.py
CLI commands → RAG pipeline: runs prediction src/rag_cognus/cli.py
Browser chat → RAG pipeline: generates answers src/rag_cognus/chat_app.py
RAG pipeline → Gold retriever: retrieves evidence src/rag_cognus/chain.py
RAG pipeline → Ollama models: generates response src/rag_cognus/chain.py
CLI commands → Evaluation cases: loads questions README.md
CLI commands → Evaluation runner: starts evaluation src/rag_cognus/cli.py
Browser chat → Evaluation runner: evaluates answers src/rag_cognus/chat_app.py
Evaluation runner → Gold retriever: retrieves cases src/rag_cognus/evaluation.py
Evaluation runner → RAG pipeline: predicts answers src/rag_cognus/evaluation.py
Evaluation runner → Response judge: scores responses src/rag_cognus/evaluation.py
Response judge → Ollama models: judges locally src/rag_cognus/judges.py
Evaluation runner → Metric scoring: scores retrieval src/rag_cognus/evaluation.py
Evaluation runner → Local MLflow: logs evaluations src/rag_cognus/evaluation.py
Browser chat → Local MLflow: shows run metrics README.md

Drawn by GitDiagram on November 13, 2026 from the repository's file tree, README and source files. Read as Markdown ·