gpt_chat_stream
Send a message to GPT and receive streaming responses. Configure model, temperature, max tokens, and system prompt for tailored output.
Instructions
Send a message to GPT and get a streaming response
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"message": "<message>"
},
"name": "gpt_chat_stream"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | GPT model to use (default: gpt-3.5-turbo) | gpt-3.5-turbo |
| message | Yes | The message to send to GPT | |
| max_tokens | No | Maximum number of tokens in the response (default: 1000) | |
| temperature | No | Temperature for response randomness (0-2, default: 1) | |
| system_prompt | No | System prompt to set context for GPT |