whitepaper-ai

y-emam/whitepaper-ai

★ 0 stars TypeScript 🤖 AI/LLM Updated today

Citation-grounded RAG search across AWS whitepapers. Hybrid pgvector+FTS retrieval. Next.js web UI + MCP server for Claude Desktop.

View on GitHub →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "whitepaper-ai": {
      "command": "npx",
      "args": [
        "-y",
        "y-emam/whitepaper-ai"
      ]
    }
  }
}

README Excerpt

> Citation-grounded RAG search across 21 AWS whitepapers, with a polished Next.js web UI and a Claude-Desktop-compatible MCP server. Same hybrid retrieval (pgvector + Postgres FTS) powers both. **Live demo:** [whitepaper-ai.vercel.app](https://whitepaper-ai.vercel.app) --- Every claim in the answer is an inline `[c#]` badge. Click one and the exact source passage opens in a drawer — paper title, page, section heading, and the literal excerpt that grounded the claim:

Tools (13)

GEMINI_API_KEYGEMINI_LLM_MODELINGEST_CONCURRENCYNEXT_PUBLIC_SUPABASE_ANON_KEYNEXT_PUBLIC_SUPABASE_URLRETRIEVAL_FTS_WEIGHTRETRIEVAL_REFUSAL_THRESHOLDRETRIEVAL_TOP_KRETRIEVAL_VECTOR_WEIGHTSUPABASE_SERVICE_ROLE_KEYVOYAGE_API_KEYVOYAGE_EMBED_DIMENSIONSVOYAGE_EMBED_MODEL

whitepaper-ai

Quick Install

README Excerpt

Tools (13)

Related AI/LLM Servers