Skip to main content
POST
/
v1
/
indexes
/
train
Train an index for efficient querying. Required before optimal performance.

​
Authentication

Required - API key via X-API-Key header: 
X-API-Key: cyborg_your_api_key_here
You can get an API key from the CyborgDB Admin Dashboard. For more info, follow this guide.

​
Request Body

{
  "index_name": "my_index",
  "index_key": "64_character_hex_string_representing_32_bytes",
  "batch_size": 2048,
  "max_iters": 100,
  "tolerance": 0.000001,
  "max_memory": 0
}

​
Response

{
  "status": "success",
  "message": "Index 'my_index' trained successfully"
}

​
Exceptions

  • 401: Authentication failed (invalid API key)
  • 404: Index not found
  • 422: Invalid request parameters or insufficient vectors
  • 500: Internal server error

​
Example Usage

Basic Training: 
curl -X POST "http://localhost:8000/v1/indexes/train" \
     -H "X-API-Key: cyborg_your_api_key_here" \
     -H "Content-Type: application/json" \
     -d '{
       "index_name": "my_index",
       "index_key": "your_64_character_hex_key_here"
     }'
Custom Training Parameters: 
curl -X POST "http://localhost:8000/v1/indexes/train" \
     -H "X-API-Key: cyborg_your_api_key_here" \
     -H "Content-Type: application/json" \
     -d '{
       "index_name": "my_index",
       "index_key": "your_64_character_hex_key_here",
       "batch_size": 1024,
       "max_iters": 50,
       "tolerance": 0.0001
     }'
There must be at least 2 * n_lists vector embeddings in the index prior to training.

​
Training Requirements

  • Minimum vectors: At least 2 × n_lists vectors must be present in the index
  • Memory: Training may require significant memory depending on batch_size and dataset size
  • Time: Training duration varies based on dataset size and convergence parameters

​
Use Cases

  • Performance optimization: Enable fast approximate nearest neighbor search
  • Production preparation: Train indexes before deploying to production
  • Batch processing: Train indexes after bulk data ingestion
  • Index maintenance: Retrain indexes after significant data updates