juanjuandog/FinSight-AI

AI equity research agent with resilient workflows, evidence-grounded RAG, versioned reports, and automated quality evaluation.

What it solves

FinSight AI provides a structured workspace for equity research on A-share companies. It solves the problem of unreliable AI-generated financial reports by ensuring that conclusions are grounded in verifiable evidence, reports are bound to specific data snapshots to prevent staleness, and long-running AI research tasks are recoverable if they fail.

How it works

The system uses a hybrid architecture combining a Spring Boot backend for orchestration and a FastAPI sidecar for AI operations. It employs a hybrid RAG (Retrieval-Augmented Generation) pipeline that combines full-text search and vector recall with reciprocal-rank fusion (RRF) and reranking to provide accurate evidence to the LLM. To ensure reliability, it uses RabbitMQ for task dispatching, Redis for idempotency and coordination, and PostgreSQL/pgvector for storing snapshots and vectors.

Who it’s for

It is designed for financial researchers and developers looking for a reference implementation of reliable AI agents that can handle long-running tasks and evidence-based reporting.

Highlights

  • Recoverable Workflows: Uses a state machine and dead-letter handling to ensure research tasks can be resumed after failure.
  • Snapshot-Bound Reports: Binds reports to specific data versions using hashes to ensure the analysis remains consistent with the source data.
  • Hybrid RAG: Combines vector and full-text search with reranking for high-verifiability evidence retrieval.
  • Idempotency: Prevents expensive duplicate AI requests using Redis Lua leases and fencing tokens.
  • Model Agnostic: Supports Ollama, OpenAI-compatible APIs, and Anthropic via a dedicated AI sidecar.

Related

  • Project
    WILLOSCAR/research-units-pipeline-skills

    A framework for agent-assisted research that transforms research goals into verifiable, resumable runs with a full evidence trail and pinned pipeline contracts.

  • Project
    rollingSirius/equity-research-skill

    An AI-powered equity research framework that transforms AI agents into institutional-grade analysts by enforcing rigorous valuation, forensic accounting, and industry-specific research protocols.

  • Project
    DevYangJC/Argus

    Argus is an open‑source, enterprise‑grade RAG platform that ingests private documents, builds both vector and keyword indexes, and answers questions with a LLM that must cite real sources. It includes a Spring AI‑based ReactAgent for chat, hybrid retrieval with RRF fusion, multi‑level evidence scoring, role‑based security, and a Vue 3 front‑end.

  • Project
    apocas/restai

    An AI-as-a-Service platform to create and deploy RAG systems, agents, and inference endpoints via a REST API with a full management dashboard.

  • Project
    java-up-up/nexus-agent

    An enterprise-grade AI agent platform that implements a complete closed-loop of document governance, hybrid RAG retrieval, and ReAct-based autonomous agents for production environments.