Project 01

Evidence-Grounded RAG Agent

A local-LLM-compatible document-analysis and question-answering agent for financial filings, structured facts, and traceable evidence.

Stack FastAPI, LangGraph, ChromaDB, DuckDB

Corpus 980 SEC filings, 88K+ chunks

Data 150K+ financial facts

System

Retrieval plus tools before generation

Maps user questions into target companies, analysis intent, required evidence, and tool calls before answer generation.
Combines ChromaDB vector search with DuckDB financial facts and price/event data.
Keeps numerical reasoning in deterministic Python tools with dependency tracing and provenance tracking.

Reliability

Checks citation validity, numeric grounding, and missing-evidence disclosure at runtime.
Separates financial analysis from investment advice with explicit non-advisory boundaries.
Designed for local-LLM compatibility rather than depending on one hosted model provider.

Workflow

Extract company, intent, evidence needs, and tool plan.

Search filing chunks, facts, prices, and events.

Run deterministic financial metric tools outside free-form generation.

Check grounding, citations, missing evidence, and advisory boundaries.

Demo Preview

Analyze NVIDIA's cash flow quality, valuation boundary, and major risks.

The agent should return structured analysis with cited facts, tool-derived metrics, missing-evidence notes, and non-advisory boundaries.