Text Connector

The text connector is the simplest source in the product.

Use it when you already have the content in hand and just want it inside a project without involving a website, package registry, or third-party integration.

Good use cases

• internal notes
• one-off runbooks
• copied documentation fragments
• structured text you want to validate quickly before building a richer ingestion path

Create the source

curl -X POST "https://api.retaindb.com/v1/projects/proj_123/sources" \
  -H "Authorization: Bearer $RETAINDB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "On-call Escalation",
    "connector_type": "text",
    "config": {
      "title": "On-call escalation",
      "content": "Page the primary engineer first. Escalate after 15 minutes if there is no response."
    }
  }'

Why this connector matters

It is the easiest way to answer:

"Is my project, source, sync, and retrieval loop healthy at all?"

Because the content is fully under your control, it removes a lot of noise from first-run debugging.

Start sync and check status

curl -X POST "https://api.retaindb.com/v1/sources/src_123/sync" \
  -H "Authorization: Bearer $RETAINDB_API_KEY"

curl "https://api.retaindb.com/v1/sources/src_123/status" \
  -H "Authorization: Bearer $RETAINDB_API_KEY"

Common mistakes

Using vague source names

If you create many text sources later, names like notes or test stop being helpful immediately.

Pasting unstructured walls of text

Add a useful title and keep the content coherent. Clean input makes validation easier.

Assuming text connector is only for demos

It is great for demos, but it is also useful for operational notes and manually curated knowledge that does not come from another system.

Next step

If your text is really a full document file, use PDF connector. If you want to store memory instead of source content, go to memory write and bulk write.