Use case · Platform teams with a private SearxNG instance
An internal-docs answer engine
Point SearxNG at your internal indices and turn matches into cited chunks for a private assistant your employees can trust.
The problem
Your internal knowledge lives across wikis, runbooks, and doc sites, and you already run — or can run — a SearxNG instance that indexes them. What you lack is the layer that turns a SearxNG result set into cited, embeddable chunks for a private assistant, without shipping your corpus to a third-party SaaS.
How Polymathy helps
- Polymathy reads result URLs from your private SearxNG instance and never touches an external service.
- The chunk map preserves the source URL for every passage, so answers can link back to the exact internal page.
- Self-hosted and GPL-3.0, so the whole retrieval path is auditable and stays inside your network.
What the flow looks like
Employee question → internal SearxNG → Polymathy → cited chunks → internal LLM → grounded answer with links to internal docs.
A good fit when
- You can point SearxNG at your internal sources
- Data residency matters — nothing should leave your network
- You want an auditable, self-hosted retrieval layer
Reach for something else when
- You need out-of-the-box SaaS connectors (Slack, Confluence, Drive)
- You are not able to operate a SearxNG instance
Other use cases
A Perplexity-style answer UI
A Rust backend that fetches a handful of pages per query and returns them shaped for prompt-stuffing, so your UI owns the chat and the citations.
Read →A cited research assistant
Ground every generated paragraph in real source URLs, because the chunk-to-URL mapping is enforced by the response shape.
Read →A content-processor test harness
A stable HTTP harness that exercises your content-processor service against real-world URLs drawn from arbitrary queries.
Read →