How sridhar281/vivaforge works
VivaForge turns uploaded lectures and documents into grounded study materials and adaptive practice. The main path is upload, media/document extraction, chunking and indexing, then summary/concept generation; learners use those outputs for viva sessions, flashcards, explain-back, knowledge-gap views and revision planning. The frontend reaches FastAPI routes, while PostgreSQL stores relational records and Chroma supports scoped retrieval. Feature-service internals beyond the sampled excerpts are represented from the README and SOURCE INDEX; those sources establish documented capabilities and imports, not every runtime call.
Main entry points: processing_service.py Processing pipeline · retriever.py RAG retriever · summary_service.py Summary and concepts · main.py FastAPI app
Components 25
Learner experience
- Next.js app
frontend/app - API services
frontend/services - HTTP client
frontend/lib/api-client.ts
API and identity
- FastAPI app
backend/app/main.py - Auth routes
backend/app/api/auth.py - Content routes
backend/app/api/content.py - Learning routes
backend/app/api - Auth service
backend/app/services/auth_service.py - Content service
backend/app/services/content_service.py
Content ingestion
- Processing pipeline
backend/app/services/processing_service.py - Media extraction
backend/app/media - Chunking
backend/app/rag/chunker.py
Learning features
- Summary and concepts
backend/app/services/summary_service.py - Adaptive viva
backend/app/services/viva_session_service.py - Study features
backend/app/services - Viva PDF
backend/app/services/viva_pdf_service.py
AI and persistence
- RAG retriever
backend/app/rag/retriever.py - Embeddings
backend/app/rag/embeddings.py - Vector store
backend/app/rag/vector_store.py - LLM client
backend/app/ai/llm_client.py - PostgreSQL
- Chroma
- Artifact files
Other components
- Learner
- Groq API
Connections 32
- Learner → Next.js app: uses
README.md - Next.js app → API services: requests
README.md - API services → HTTP client: uses
- HTTP client → FastAPI app: calls API
README.md - FastAPI app → Auth routes: routes to
backend/app/main.py - FastAPI app → Content routes: routes to
backend/app/main.py - FastAPI app → Learning routes: routes to
backend/app/main.py - Auth routes → Auth service: delegates to
backend/app/api/auth.py - Content routes → Content service: delegates to
backend/app/api/content.py - Content routes → Processing pipeline: starts processing
backend/app/api/content.py - Processing pipeline → Media extraction: extracts text
backend/app/services/processing_service.py - Processing pipeline → Chunking: chunks source
backend/app/services/processing_service.py - Processing pipeline → Summary and concepts: generates materials
backend/app/services/processing_service.py - Processing pipeline → Embeddings: embeds chunks
backend/app/services/processing_service.py - Processing pipeline → Vector store: stores chunks
backend/app/services/processing_service.py - Summary and concepts → RAG retriever: reads chunks
backend/app/services/summary_service.py - Summary and concepts → LLM client: generates outputs
backend/app/services/summary_service.py - Summary and concepts → PostgreSQL: saves concepts
- Summary and concepts → Artifact files: writes summary
backend/app/services/summary_service.py - RAG retriever → Embeddings: embeds query
backend/app/rag/retriever.py - RAG retriever → Vector store: queries vectors
backend/app/rag/retriever.py - RAG retriever → PostgreSQL: loads chunks
backend/app/rag/retriever.py - Vector store → Chroma: queries and stores
README.md - LLM client → Groq API: calls
backend/app/ai/llm_client.py - Learning routes → Adaptive viva: starts adaptive viva
backend/app/api/viva.py - Adaptive viva → RAG retriever: retrieves context
backend/app/services/viva_session_service.py - Adaptive viva → LLM client: generates and evaluates
backend/app/services/viva_session_service.py - Adaptive viva → PostgreSQL: updates session mastery
- Learning routes → Study features: serves study features
README.md - Learning routes → Viva PDF: generates PDF
backend/app/api/viva.py - Study features → RAG retriever: uses retrieval
backend/app/rag/retriever.py - Content service → PostgreSQL: reads content