A simple API for storing and searching documents using vector embeddings.
gW0YM1rpPRU7v72qlyqJ8gAE1Z33VIPR7iOAqBkjBqITotal Queries
Successful
Failed
Success Rate
| Timestamp | Endpoint | Query | Results | Threshold | Time (ms) |
|---|---|---|---|---|---|
| No successful queries yet | |||||
| Timestamp | Endpoint | Query | Error | Status Code |
|---|---|---|---|---|
| No failed queries yet | ||||
Authorization: Bearer <API_TOKEN>
/api/<username>/endpoint - operates on all documents for username/api/<username>/<collection>/endpoint - operates only on specific collectionPUT /api/{username}/documents
PUT /api/{username}/{collection}/documents
{
"title": "Document Title",
"content": "Document content to be embedded"
}
POST /api/{username}/documents
POST /api/{username}/{collection}/documents
POST /api/{username}/embed
POST /api/{username}/{collection}/embed
{
"content": "Plain text content with auto-generated title"
}
GET /api/{username}/search
GET /api/{username}/{collection}/search
q (required) - Search query textthreshold (optional) - Minimum similarity score (0.0-1.0, default: 0.7)limit (optional) - Maximum results (default: 10)
GET /api/robotscooking/search?q=machine%20learning&threshold=0.8&limit=5
{
"results": [
{
"id": "uuid-string",
"title": "Document Title",
"content": "Document content...",
"similarity": 0.85,
"username": "user",
"collection": "collection_name",
"created_at": "2025-07-31T14:16:30Z"
}
],
"total": 1
}
GET /api/{username}/documents
GET /api/{username}/{collection}/documents
GET /api/{username}/logs
GET /api/{username}/{collection}/logs
{
"success": false,
"error": "Error description",
"details": "Additional error details"
}
Status Codes: 200 (OK), 400 (Bad Request), 401 (Unauthorized), 404 (Not Found), 413 (Too Large), 500 (Server Error)