puj-nlp/cev-rag

How puj-nlp/cev-rag works

This repository implements a cultural-context-aware RAG system for asking questions over the Colombian Truth Commission archive. A user asks through the web chat; the frontend calls backend routes, where question answering retrieves documents, builds context, and generates an answer with references. Separate chat-session operations persist conversation history, and admin routes provide storage statistics, search, and data import/export. The graph reflects shown calls and wiring; unsampled capabilities are represented only where documented, without inferred internal links.

Main entry points: use_cases.py Question answering · dependencies.py Dependency wiring · frontend_controller.py Frontend routes · main.py FastAPI setup

Components 26

Web interface

Web app routes rag-ui/src/App.js
Chat interface rag-ui/src/pages/UnifiedChatInterface.js
API client rag-ui/src/services/api.js

API and application

FastAPI setup rag-api/src/main.py
Frontend routes rag-api/src/adapters/controllers/frontend_controller.py
Chat and question routes rag-api/src/adapters/controllers/controllers.py
Chat sessions rag-api/src/application/use_cases.py
RAG domain rag-api/src/domain/entities.py
Service contracts rag-api/src/domain/ports.py
Dependency wiring rag-api/src/infrastructure/dependencies.py
API authentication rag-api/src/infrastructure/auth.py
Runtime configuration rag-api/src/infrastructure/config.py

Retrieval and generation

Question answering rag-api/src/application/use_cases.py
Context builder rag-api/src/infrastructure/services.py
Document retrieval rag-api/src/adapters/repositories/milvus_vector_db.py
Embedding service rag-api/src/adapters/external/openai_services.py
Answer generation rag-api/src/adapters/external/openai_services.py
LLM tools rag-api/src/adapters/external/openai_tools.py

Chat and archive storage

SQLite chat store rag-api/src/adapters/repositories/sqlite_chat_repository.py
Memory chat store rag-api/src/adapters/repositories/memory_chat_repository.py
Chat data migration rag-api/src/adapters/repositories/migration.py
Database initialization rag-api/src/infrastructure/database_setup.py

Administration

Admin routes rag-api/src/adapters/controllers/admin_controller.py

Other components

Researcher
OpenAI service
Milvus vector store

Connections 38

Researcher → Web app routes: uses
Web app routes → Chat interface: routes to rag-ui/src/App.js
Chat interface → API client: calls rag-ui/src/pages/UnifiedChatInterface.js
API client → Frontend routes: requests rag-ui/src/services/api.js
FastAPI setup → Frontend routes: registers rag-api/src/main.py
FastAPI setup → Chat and question routes: registers rag-api/src/main.py
FastAPI setup → Admin routes: registers rag-api/src/main.py
Frontend routes → Chat sessions: invokes rag-api/src/adapters/controllers/frontend_controller.py
Frontend routes → Question answering: invokes rag-api/src/adapters/controllers/frontend_controller.py
Chat and question routes → Chat sessions: invokes rag-api/src/adapters/controllers/controllers.py
Chat and question routes → Question answering: invokes rag-api/src/adapters/controllers/controllers.py
Question answering → RAG domain: uses rag-api/src/application/use_cases.py
Chat sessions → RAG domain: uses rag-api/src/application/use_cases.py
Question answering → Dependency wiring: services wired by rag-api/src/infrastructure/dependencies.py
Dependency wiring → Document retrieval: constructs rag-api/src/infrastructure/dependencies.py
Dependency wiring → Embedding service: constructs rag-api/src/infrastructure/dependencies.py
Dependency wiring → Answer generation: constructs rag-api/src/infrastructure/dependencies.py
Dependency wiring → Context builder: constructs rag-api/src/infrastructure/dependencies.py
Dependency wiring → SQLite chat store: constructs rag-api/src/infrastructure/dependencies.py
Dependency wiring → Memory chat store: constructs rag-api/src/infrastructure/dependencies.py
Question answering → Document retrieval: searches documents rag-api/src/infrastructure/dependencies.py
Question answering → Embedding service: embeds questions rag-api/src/infrastructure/dependencies.py
Question answering → Context builder: builds context rag-api/src/infrastructure/dependencies.py
Question answering → Answer generation: generates answers rag-api/src/infrastructure/dependencies.py
Embedding service → OpenAI service: calls
Answer generation → OpenAI service: calls
Chat sessions → SQLite chat store: persists chats
Chat sessions → Memory chat store: stores chats
Admin routes → SQLite chat store: queries and exports rag-api/src/adapters/controllers/admin_controller.py
Admin routes → Chat data migration: imports data rag-api/src/adapters/controllers/admin_controller.py
FastAPI setup → Database initialization: initializes rag-api/src/main.py
Database initialization → Chat data migration: imports legacy data rag-api/src/infrastructure/database_setup.py
Database initialization → SQLite chat store: checks storage rag-api/src/infrastructure/database_setup.py
Runtime configuration → Milvus vector store: configures
Answer generation → LLM tools: tool support rag-api/src/adapters/external/openai_services.py
Frontend routes → API authentication: validates requests rag-api/src/adapters/controllers/frontend_controller.py
Chat and question routes → API authentication: requires key rag-api/src/adapters/controllers/controllers.py
RAG domain → Service contracts: defines contracts rag-api/src/domain/ports.py

More Jupyter Notebook diagrams: heiko-hotz/gemini-multimodal-live-dev-guide · mahmoodlab/porpoise · patrickbryant1/umol · lamm-mit/preflexor · shifts-project/shifts

Drawn by GitDiagram on September 29, 2026 from the repository's file tree, README and source files. Read as Markdown ·