IEKB QA Agent
DemoDownloadData releasesLicenses
Back to IEKB
IEKB QA Agent·Inner Ear Knowledge Base·Licenses & disclaimer
QA source: Apache-2.0Back to earkb.org

Evidence-Grounded QA for Inner Ear Research

Ask complex biomedical questions in natural language. Get structured, citation-backed answers powered by the IEKB knowledge base and multi-phase AI agent pipeline.

See the DemoDownload
10+

Agent Phases

End-to-end pipeline

10-dim

Scoring System

Multi-dimensional ranking

SSE

Streaming

Real-time token output

How it works

Ask anything about inner ear genes

The QA agent connects to IEKB, resolves gene targets, retrieves evidence from multiple tables, and synthesizes a grounded answer.

Multi-phase agent pipeline: analyze, resolve, retrieve, evaluate, rank, synthesize

10-dimension candidate scoring with evidence breakdown

Streaming responses with real-time progress tracking

Capabilities

Intelligent retrieval meets structured evidence

A purpose-built question-answering system designed for inner ear research — from druggable target discovery to gene-phenotype exploration.

LLM-Powered Analysis

Ask complex biomedical questions in natural language. Compatible with OpenAI, DeepSeek, and any OpenAI-compatible API.

Multi-Phase Agent

A 10+ phase pipeline: question classification, target resolution, evidence retrieval, batch evaluation, ranking, and synthesis.

Evidence-Grounded

Every answer is backed by data from the IEKB database — gene associations, interactions, literature, and more.

Candidate Ranking

Genes scored across 10 dimensions including disease association, mechanism clarity, evidence level, and network centrality.

Candidate Support Layer

Optionally include non-probabilistic candidate rankings and deterministic relation support for hypothesis generation beyond known annotations.

Streaming Response

Watch the agent think in real time — every phase, every step, every token streamed to your browser via SSE.

Live Demo

See it in action

Watch the QA agent process a real question — from target resolution through evidence retrieval to the final ranked answer. This is a recorded session replayed in real time.

Q
IEKB QA AgentDemo
Ask a question about inner ear genes...

Get started

Up and running in minutes

Download the complete QA system, unzip, and launch with a single command. The package includes both the Python backend and the Next.js frontend.

Download iekb-qa.zip
Verify SHA-256Release metadataLicense matrix
terminal
unzip iekb-qa.zip && cd iekb-qa
# Linux / macOS
./start.sh
# Windows PowerShell
.\start.ps1

What's inside

backend/ — FastAPI + LLM agents
frontend/ — Next.js chat UI
start.sh — Linux/macOS launcher
start.ps1 — Windows launcher
RELEASE.json — source and data release IDs
SHA256SUMS — per-file integrity hashes

Prerequisites

Python 3.10+
Node.js 18+
OpenAI-compatible API key

Quick steps

  1. Download & unzip iekb-qa.zip
  2. Run ./start.sh or .\start.ps1
  3. Configure your LLM API key in the UI
  4. Open http://localhost:3000