Sunflower Chat

Professional Sunflower inference endpoint for multilingual chat completions. This endpoint provides access to Sunbird AI's Sunflower model, specialized in: - Multilingual conversations in Ugandan languages (Luganda, Acholi, Ateso, etc.) - Cross-lingual translations and explanations - Cultural context understanding - Educational content in local languages Features: - Automatic retry with exponential backoff - Context-aware responses - Usage tracking and monitoring - Support for custom system messages - Message history management Example message list with previous chat: [ {"role": "system", "content": "You are Sunflower, a multilingual assistant for Ugandan languages made by Sunbird AI. You specialise in accurate translations, explanations, summaries and other cross-lingual tasks."}, {"role": "user", "content": "Translate 'How are you?' to Luganda."}, {"role": "assistant", "content": "In Luganda, 'How are you?' is 'Oli otya?'."}, {"role": "user", "content": "How do I say 'Good morning' in Acholi?"} ] Example message list without previous chat: [ {"role": "user", "content": "Explain the meaning of 'Ubuntu'."} ] Suggested system prompt: "You are Sunflower, a multilingual assistant for Ugandan languages made by Sunbird AI. You specialise in accurate translations, explanations, summaries and other cross-lingual tasks. Always provide clear, culturally relevant, and educational responses."

POST /tasks/sunflower_inference

Sunflower Inference

cURL

curl --request POST \
  --url https://api.sunbird.ai/tasks/sunflower_inference \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "messages": [
    {
      "role": "<string>",
      "content": "<string>"
    }
  ],
  "model_type": "qwen",
  "temperature": 0.3,
  "stream": false,
  "system_message": "<string>"
}
'

200

{
  "content": "<string>",
  "model_type": "<string>",
  "usage": {
    "completion_tokens": 123,
    "prompt_tokens": 123,
    "total_tokens": 123
  },
  "processing_time": 123,
  "inference_time": 123,
  "message_count": 123
}

Authorizations

Authorization · string · header · required

The access token received from the authorization server in the OAuth 2.0 flow.

Body

application/json

messages · SunflowerChatMessage · object[] · required

List of conversation messages

Show child attributes

model_type · string · default: qwen

Model type: 'qwen' or 'gemma'

temperature · number · default: 0.3

Sampling temperature

Required range: 0 <= x <= 2

stream · boolean · default: false

Whether to stream the response

system_message · string | null

Custom system message

Response

200

application/json

Successful Response

content · string · required

The AI's response

model_type · string · required

Model used for inference

usage · SunflowerUsageStats · object · required

Token usage statistics

Show child attributes

processing_time · number · required

Total processing time in seconds

inference_time · number · required

Model inference time in seconds

message_count · integer · required

Number of messages processed