> ## Documentation Index
> Fetch the complete documentation index at: https://docs.interaone.app/llms.txt
> Use this file to discover all available pages before exploring further.

# Ingest files

> Upload PDF and DOCX knowledge sources through MinIO, confirm them, monitor indexing, and troubleshoot extraction.

File ingestion uses a two-step presigned upload so document bytes move directly to MinIO while the gateway retains tenant-scoped metadata and authorization.

<Steps>
  <Step title="Request an upload">
    In **Knowledge → Static**, choose a file and provide its title/catalog information. The gateway validates the request and returns a presigned upload target plus a file key.
  </Step>

  <Step title="Upload directly to storage">
    The console sends the file to MinIO using the presigned target. The API process does not proxy the whole document body.
  </Step>

  <Step title="Confirm the document">
    The console confirms the upload. The gateway verifies metadata and enqueues the document for ingestion.
  </Step>

  <Step title="Monitor status">
    Status progresses through `queued` and `indexing` to `indexed`, or to `failed` with an error message. Use **Reindex** after correcting a transient failure.
  </Step>
</Steps>

## Extraction behavior

The agent streams objects from MinIO and uses source-specific parsers: `pdf-parse` for PDF and Mammoth for DOCX. Text is normalized and segmented before semantic chunking, then embeddings are generated in bounded concurrent batches.

<Info>
  Scanned image-only PDFs need OCR before upload; the current parser extracts embedded text and does not provide an OCR pipeline.
</Info>

## Troubleshooting

<AccordionGroup>
  <Accordion title="Upload succeeds but confirmation fails">
    Verify that gateway and agent use the same bucket and credentials, the object key was not changed, and the public/presigned MinIO URL is reachable from the browser.
  </Accordion>

  <Accordion title="Document is indexed with little content">
    Check whether the PDF contains selectable text, whether the DOCX has content in unsupported embedded objects, and inspect reported word/chunk counts.
  </Accordion>

  <Accordion title="Embedding fails">
    Confirm provider credentials, model availability, vector dimensions, and that Qdrant is healthy. Retry only after resolving the underlying mismatch.
  </Accordion>
</AccordionGroup>

Deleting a source removes its managed metadata and should remove its associated vectors/object according to the gateway service. Confirm backup and retention expectations before deletion.