iblai-agent-datasets

name: iblai-agent-datasets description: Manage an ibl.ai agent's training datasets (RAG) via the platform API — list training docs, add resources (file, URL, YouTube, Blackboard, website crawl, GitHub), train/untrain, set visibility and retrain schedule, and delete. Use when feeding an agent knowledge.

iblai-agent-datasets

Manage an agent's training datasets (RAG) through the API: list an agent's training documents, add new resources to its knowledge base, train / untrain and set visibility, configure a retrain schedule, and delete datasets. Use when feeding an agent knowledge.

Auth & conventions

• Base URL: https://api.iblai.app
• Header: Authorization: Api-Token $IBLAI_API_KEY on every request.
• Path vars: {org} = $IBLAI_ORG, {username} = $IBLAI_USERNAME, {mentor} = the agent's unique id (e.g. d17dc729-60fd-4363-81a0-f67d9318b03e), used here as the pathway.
• Host: these endpoints live under …/dm/api/ai-index/….
• Not connected yet? Run /iblai-login first to populate IBLAI_ORG, IBLAI_USERNAME, and IBLAI_API_KEY.

Reads

• GET https://api.iblai.app/dm/api/ai-index/orgs/{org}/users/{username}/documents/pathways/{mentor}/?limit=5&offset={n}&search={q} — list training docs. Poll this every 2s while any document is pending.
• GET https://api.iblai.app/dm/api/ai-index/documents/{document_id}/settings/ — retrain schedule.
• GET https://api.github.com/repos/{owner}/{repo}/branches — list GitHub branches for a repo resource (external, no auth).

Writes

• POST https://api.iblai.app/dm/api/ai-index/orgs/{org}/users/{username}/documents/train/ — add a training resource (multipart/form-data); type varies:
  • File:

    {
      "file": "File (required)",
      "pathway": "{mentor}",
      "type": "file|<ext>",
      "user_image_description": "string"
    }
    

  • URL / YouTube / Blackboard:

    {
      "type": "url|youtube|blackboard",
      "pathway": "{mentor}",
      "url": "string (required)"
    }
    

  • Website crawl:

    {
      "type": "webcrawler",
      "pathway": "{mentor}",
      "url": "string",
      "crawler_max_depth": "number",
      "crawler_max_pages_limit": "number",
      "crawler_match_patterns": "string[]",
      "crawler_pattern_type": "glob|regex"
    }
    

  • GitHub:

    {
      "url": "repo url",
      "branch": "string",
      "pathway": "{mentor}",
      "type": "github"
    }
    

• PUT https://api.iblai.app/dm/api/ai-index/documents/{document_id}/ — train / untrain + visibility:

  {
    "pathway": "{mentor}",
    "url": "string",
    "train": "boolean",
    "access": "public|private"
  }
  

• POST https://api.iblai.app/dm/api/ai-index/documents/{document_id}/settings/ — set retrain schedule:

  {
    "retrain_interval_days": "number (required)"
  }
  

• DELETE https://api.iblai.app/dm/api/ai-index/documents/{document_id}/ — delete a dataset. Destructive — confirm with the user first.

Example

Add a YouTube video to an agent's knowledge base:

curl -X POST \
  "https://api.iblai.app/dm/api/ai-index/orgs/$IBLAI_ORG/users/$IBLAI_USERNAME/documents/train/" \
  -H "Authorization: Api-Token $IBLAI_API_KEY" \
  -F "type=youtube" \
  -F "pathway=$MENTOR" \
  -F "url=https://www.youtube.com/watch?v=dQw4w9WgXcQ"

Notes

• The list endpoint should be polled every 2s while any document is pending so newly added resources flip to trained as soon as processing finishes.
• pathway is the agent's {mentor} unique id on every train/PUT call.
• For GitHub resources, fetch the branch list from the unauthenticated api.github.com/repos/{owner}/{repo}/branches endpoint to populate branch.
• Deletion is destructive — confirm with the user first.