Software Engineer · Backend Systems · Applied AI

Back to Portfolio

FinRAG — Finance-Domain RAG System

A retrieval-augmented generation system for querying SEC filings and earnings transcripts with grounded, source-cited answers — no hallucinated numbers.

Live on Render

How It Works

Financial documents like 10-Ks and earnings transcripts are long, dense, and full of domain-specific language that generic RAG systems handle poorly. FinRAG combines a finance-aware ingestion pipeline with a retrieval pipeline tuned for precision over recall, so answers stay grounded in the source document.

Ingest

PyMuPDF + pdfplumber fallback

Chunk

Finance-aware, table-preserving

Embed

OpenAI text-embedding-3-small

Store

ChromaDB, SHA256-deduped

Rerank

MMR, built from scratch

Answer

GPT-4o-mini, source-cited

Python FastAPI ChromaDB OpenAI GPT-4o-mini OpenAI Embeddings PyMuPDF Docker Pydantic

Try It Live

Ask a question about the indexed financial filings — or upload your own document — and get a grounded, source-cited answer from the live pipeline below.

FinRAG Query Console ● Checking…

Hosted on Render's free tier — if the server has been idle, the first query can take 20–30s to wake up. Subsequent queries are fast.

Querying pipeline…

Answer

Ask a question above to see a grounded, source-cited answer.

Powered by FinRAG — OpenAI embeddings · ChromaDB · MMR reranking · GPT-4o-mini. Answers are grounded in the indexed filings and may not reflect all available data.