[Components] kindo #15729
Description
kindo
URLs
Actions
chat
Prompt
Creates a model response for the given chat conversation.
Kindo's API adheres to the OpenAI API format. Developers can use Kindo's API with the same request parameters and expected response format as the OpenAI API.
POST /chat/completions
Required Headers:
content-type: application/json
api-key: Your Kindo API key
Required Parameters:
model: The model name from Kindo's available models
messages: The messages array with roles and content
Optional Parameters:
You can also use other OpenAI API parameters such as max_tokens, stream, temperature, etc. to customize the chat completion according to your needs.
curl https://llm.kindo.ai/v1/chat/completions \
-H "api-key: <KINDO_API_KEY>" \
-H "content-type: application/json" \
-d '{
"model": "<MODEL_NAME>",
"messages": [{"role": "user", "content": "Hello, world!"}]
}'
Error Handling
Kindo API uses standard HTTP status codes to indicate the success or failure of a request. In general, 2xx status codes indicate success, 4xx indicate errors with data provided by the user (e.g. invalid input), and 5xx indicate Kindo server errors.
For some 4xx and 5xx responses, Kindo will also return a code and message indicating the error.
| Status Code | Description | Details |
|---|---|---|
| 200 | OK | Everything worked as expected. |
| 400 | Bad Request | The request was unacceptable, often due to missing a required parameter. |
| 401 | Unauthorized | The Kindo API key is wrong. |
| 403 | Forbidden | The user is not authorized to make this request. |
| 429 | Too Many Requests | The user has sent too many requests in a given amount of time. |