Usage Instructions
Integrate Translate into the workflow. Can translate text to any language.
Actions
LLM Chat
Send a chat completion request to any supported LLM provider
Input
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | The model to use (e.g., gpt-4o, claude-sonnet-4-5, gemini-2.0-flash) |
systemPrompt | string | No | System prompt to set the behavior of the assistant |
context | string | Yes | The user message or context to send to the model |
apiKey | string | No | API key for the provider (uses platform key if not provided for hosted models) |
temperature | number | No | Temperature for response generation (0-2) |
maxTokens | number | No | Maximum tokens in the response |
azureEndpoint | string | No | Azure OpenAI endpoint URL |
azureApiVersion | string | No | Azure OpenAI API version |
vertexProject | string | No | Google Cloud project ID for Vertex AI |
vertexLocation | string | No | Google Cloud location for Vertex AI (defaults to us-central1) |
vertexCredential | string | No | Google Cloud OAuth credential ID for Vertex AI |
bedrockAccessKeyId | string | No | AWS Access Key ID for Bedrock |
bedrockSecretKey | string | No | AWS Secret Access Key for Bedrock |
bedrockRegion | string | No | AWS region for Bedrock (defaults to us-east-1) |
Output
| Parameter | Type | Description |
|---|---|---|
content | string | The generated response content |
model | string | The model used for generation |
tokens | object | Token usage information |
cost | object | Model cost for this call in dollars |