Answers from
your documents.
Ingest a file and it is converted, chunked and indexed for you. An agent with knowledge retrieves before every generation, so it answers from what you gave it.
Ingest a file and it is converted, chunked and indexed for you. An agent with knowledge retrieves before every generation, so it answers from what you gave it.
Scanned PDFs, images and audio are converted to searchable text on ingest, with no pipeline of your own to run.
Set a knowledge configuration on the agent and the matching chunks are in context before the model answers.
A match carries its document, its source path and, for a PDF, its page, so an answer can point at where it came from.
Run a question through knowledge search to read the exact chunks retrieval returns before touching the prompt.
Indexed storage per account: 1 GB on Free, 30 GB on Pro, 100 GB on Business. Compare plans
By the end you will have an agent that answers from a document you uploaded, proven by a question only that document can answer. Every step is one call, shown for the CLI, the SDK and curl.
Start the tutorialSign in, connect your assistant or open the quickstart, and run your first agent.
Free plan · 2,000 runs a month · no card