Unlock powerful search across your entire document library. Combine keyword precision with semantic understanding, query expansion, and reranking.
Match the exact words, the meaning, or both.
Then let AI expand your query and rerank what it finds.
Query expansion and reranking are on by default for hybrid and semantic search. Full-text stays exact.
Results stream in as they're found,
then settle once reranked.
Each result carries its passage, why it ranked,
and exactly where it came from.
The matching content, with every matched term and where it appears.
Marketing revenue grew 24% on every channel, with Europe leading the quarter on new signups.
matches: revenue, europeKnow why a result ranks where it does.
Every result points to the nodes it came from and their page, so you can show users exactly where an answer is.
The paper the passage belongs to, with your metadata, ready to filter or display.
Filter by your own metadata,
the same filters you use to list papers.
Build search into your apps and RAG pipelines,
or let AI agents search your papers on their own.
Search from SDKs or the API, filter by your own metadata, and ground your apps and RAG pipelines in the passages that matter.
Connect AI agents through our hosted MCP, and they search your papers on their own, citing the paper and page behind every answer.
Secure, compliant and built for scale.
Process one document or millions with the same API.
Your data stay yours. We never train on it.
Simple APIs, SDKs and tools to build faster.