# run-llama/sec-insights

A real world full-stack application using LlamaIndex

Repository: https://github.com/run-llama/sec-insights
Canonical: https://ross.abutalabs.com/products/sec-insights
Homepage: https://www.secinsights.ai/
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2025-03-12T15:53:29+00:00

## Health v2 (maintenance only)
Score: 33/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 11, release rhythm 35, longevity 78
- inputs: {"age_days": 1093, "days_push": 539, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2609, forks 694 (observed 2026-08-28T04:07:04.223548+00:00)

## What it is
SEC Insights is a full-stack reference application built by LlamaIndex that uses RAG to answer questions about SEC 10-K and 10-Q financial documents. It features a React/Next.js frontend with a PDF viewer and citation highlighting, plus a FastAPI backend with streaming LLM responses and tool-based quantitative answers.

## Use cases
- ask questions about SEC 10-K and 10-Q filings
- build a production RAG application from a reference codebase
- chat with multiple financial documents simultaneously
- view paragraph-level citations with PDF highlighting
- deploy a full-stack LLM app to Vercel and Render
- learn how to stream LLM responses with server-sent events

## When to choose
- you want a complete real-world example of a production RAG application
- you need document Q&A with source citations over PDFs
- you want to fork a solid foundation for your own LlamaIndex-based app
- you need multi-document comparison chat with reasoning step streaming

## When to avoid
- you need a lightweight library to embed in an existing app rather than a full application
- your documents are not financial filings and you don't want to adapt the ingestion pipeline
- you need on-premise LLM inference without API-based models or tools

## Facets
- artifact type: application
- maturity: active
- function: rag, chatbot, llm-inference, pdf-viewer, web-framework, api-framework, search-engine
- domain: large-language-models, fintech, pdf, web-development, artificial-intelligence
- platform: self-hosted, python, cross-platform
- tags: llamaindex, sec-filings, financial-documents, nextjs, fastapi, citation-highlighting, streaming, full-stack-example, vercel, render, retrieval-augmented-generation, web-server, docker, nodejs

## Member repositories
- run-llama/sec-insights (main) score 33

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:04.223548+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:20:54.782587+00:00, confidence not recorded.
  - readme: https://github.com/run-llama/sec-insights (fetched 2026-08-28T04:07:04.223548+00:00, sha eb49696aa471)
  - homepage: https://www.secinsights.ai/ (fetched 2026-08-29T10:03:52.437635+00:00, sha 04bf41731f7c)
- Data as of 2026-08-30T08:39:29.467469+00:00.