Training Settings

Create & Update Clustering Training Settings

This endpoint allows clients to define or update the LLM provider settings used during clustering model training. By specifying the provider and related API credentials, customers can bring their own keys to control cost, performance, and data privacy.

Important Notes

If this endpoint is not called, the system defaults to the legacy behavior using the built-in provider configuration. Settings defined here override the llm parameter sent during training and are passed as environment variables to the training pods.

Token Endpoint:

URL: {{baseUrl}}/sestekai-api/api/external/llm-configurations
HTTP Method: POST
Content-Type: application/json
Authorization: Bearer <token>

Request parameters	Description
`projectName`	Name of the project
`model`	Specific model to use for text clustering
`providerSettings`	Chosen provider and required configuration settings. Possible values for providers are: `OpenAi`, `AzureOpenAi`, `AwsBedrock`, `GoogleGemini`, `TogetherAi`, `Groq`, `Vllm`, `Sestek`
`moduleName`	Cluster

Examples

Here's an example of a request:

curl --location '{{baseUrl}}/sestekai-api/api/external/llm-configurations' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer <token>' \
--data '{
  "productName": "CA", 
  "moduleName": "cluster", 
  "model": "string",
  "providerSettings": {  
      "provider": "", 
      "OPENAI_API_KEY": "string",
      "AZURE_API_KEY": "string",
      "AZURE_API_BASE": "string",
      "AZURE_API_VERSION": "string",
      "AWS_ACCESS_KEY_ID": "string",
      "AWS_SECRET_ACCESS_KEY": "string",
      "AWS_REGION_NAME": "string",
      "GEMINI_API_KEY": "string",
      "TOGETHERAI_API_KEY": "string",
      "GROQ_API_KEY": "string"
    }
}'

Expected Response: 200 OK