How ramyagandi1116/ai-knowledge-workspace works
AI Knowledge Workspace is a local PDF question-answering application. Users upload research PDFs for page-aware extraction, chunking, embedding, and FAISS indexing; they can then ask grounded questions or explore semantic search results, with document/page citations shown in the interface. The sampled code confirms the main orchestration and module calls. The README describes the vector explorer and document manager, while implementation details beyond the provided excerpts are not inferred.
Main entry points: rag_pipeline.py RAG Orchestrator · app.py Streamlit Workspace · retriever.py Semantic Retriever · vector_store.py FAISS Index
Components 15
Workspace UI
- Streamlit Workspace
app.py - Document Manager
app.py - Search Explorer
app.py - Citation Formatting
utils/helpers.py
Document Indexing
- PDF Loader
backend/loader.py - Text Chunker
backend/chunker.py - Embeddings
backend/embeddings.py
Question Answering
- RAG Orchestrator
backend/rag_pipeline.py - Semantic Retriever
backend/retriever.py - Grounded Prompt
backend/prompt.py - Ollama Client
backend/llm.py
Local Knowledge Store
- FAISS Index
backend/vector_store.py
Other components
- User
- Local Ollama
- Local PDF Files
Connections 20
- User → Document Manager: uploads PDFs
README.md - Document Manager → RAG Orchestrator: processes uploads
app.py - RAG Orchestrator → PDF Loader: saves and extracts
backend/rag_pipeline.py - PDF Loader → Local PDF Files: writes and reads
backend/loader.py - RAG Orchestrator → Text Chunker: chunks pages
backend/rag_pipeline.py - RAG Orchestrator → Embeddings: embeds chunks
backend/rag_pipeline.py - RAG Orchestrator → FAISS Index: persists vectors
backend/rag_pipeline.py - User → Streamlit Workspace: asks questions
README.md - Streamlit Workspace → RAG Orchestrator: submits query
app.py - RAG Orchestrator → Semantic Retriever: retrieves chunks
backend/rag_pipeline.py - Semantic Retriever → Embeddings: embeds query
backend/retriever.py - Semantic Retriever → FAISS Index: loads and searches
backend/retriever.py - RAG Orchestrator → Grounded Prompt: builds prompt
backend/rag_pipeline.py - RAG Orchestrator → Ollama Client: generates response
backend/rag_pipeline.py - Ollama Client → Local Ollama: sends prompt
backend/llm.py - RAG Orchestrator → Streamlit Workspace: returns answer and citations
app.py - Streamlit Workspace → Citation Formatting: formats citations
app.py - User → Search Explorer: explores results
README.md - Search Explorer → RAG Orchestrator: searches documents
app.py - Document Manager → FAISS Index: summarizes and clears
app.py