How sumeetsingh501/enterprise_knowledge_assistant works
This is a Streamlit employee knowledge assistant: users build a local document index, ask policy questions, and receive grounded answers with citations and inspectable retrieved context. The README documents ingestion and retrieval stages not present in the supplied file tree; those components are represented with README-listed paths where available, but their implementation and some wiring could not be verified. The runtime entry point and session-memory use are visible in app.py.
Main entry points: app.py Streamlit application
Components 18
User interface
- Streamlit application
app.py - Configuration
- Sources and context view
app.py
Document ingestion
- Company documents
- Document loaders
- Chunking and ingestion
- OpenAI embeddings
- FAISS index
Retrieval and ranking
- Vector search
- BM25 search
- Hybrid fusion
- Semantic reranking
Conversation and answers
- Query rewriting
- Session memory
- Answer orchestration
- Grounded LLM
Other components
- Employee
- OpenAI API
Connections 25
- Employee → Streamlit application: asks questions
README.md - Streamlit application → Configuration: validates settings
app.py - Streamlit application → Chunking and ingestion: builds index
app.py - Streamlit application → Answer orchestration: asks query
app.py - Streamlit application → Session memory: reads history
app.py - Answer orchestration → Session memory: rewrites with history
README.md - Company documents → Document loaders: loads files
README.md - Document loaders → Chunking and ingestion: provides documents
README.md - Chunking and ingestion → OpenAI embeddings: embeds chunks
README.md - OpenAI embeddings → OpenAI API: requests embeddings
README.md - Chunking and ingestion → FAISS index: stores vectors
README.md - Query rewriting → Vector search: searches query
README.md - Vector search → FAISS index: searches index
README.md - Query rewriting → BM25 search: searches query
README.md - Vector search → Hybrid fusion: fuses results
README.md - BM25 search → Hybrid fusion: fuses results
README.md - Hybrid fusion → Semantic reranking: ranks candidates
README.md - Answer orchestration → Query rewriting: rewrites query
README.md - Answer orchestration → Vector search: retrieves context
README.md - Answer orchestration → BM25 search: retrieves context
README.md - Answer orchestration → Semantic reranking: selects context
README.md - Answer orchestration → Grounded LLM: generates answer
README.md - Grounded LLM → OpenAI API: requests completion
README.md - Answer orchestration → Sources and context view: returns citations
README.md - Streamlit application → Sources and context view: displays results
app.py