Loading content...
A document-analysis prototype for asking grounded questions and extracting useful information from contracts.
Legal AI combines a Streamlit interface with a FastAPI backend and LLM-assisted document analysis. Users can upload supported contract documents, create retrievable chunks and ask questions about the uploaded material. The project demonstrates document ingestion, semantic retrieval and structured prompting, but it is not a substitute for legal advice and has no verified attorney-reviewed accuracy benchmark.
Translating ambiguous multi-stakeholder requirements into deterministic, verifiable software under strict latency, cost, and usability boundaries.
Separate the interactive Streamlit interface from backend processing through FastAPI.
Ground responses in uploaded documents instead of relying only on model memory.
Keep vector-store fallback behaviour available for lightweight development.
Avoid publishing legal-accuracy claims without an expert-annotated evaluation set.
Test the RAG retrieval pipeline by asking specific questions about this case study: