Tool use · PrivateMind Docs

PrivateMind forwards tools and tool_choice directly to the underlying engine. The wire shape is identical to OpenAI's.

cURL

curl -s "https://api.privatemind.com/v1/chat/completions" \
  -H "Authorization: Bearer $PMIND_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "fast",
    "messages": [{"role": "user", "content": "What is the weather in Paris?"}],
    "tools": [{
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get current weather for a city",
        "parameters": {
          "type": "object",
          "properties": {"city": {"type": "string"}},
          "required": ["city"]
        }
      }
    }],
    "tool_choice": "auto"
  }'

Response when the model calls a tool

finish_reason is tool_calls and message.tool_calls contains the call(s):

JSON

{
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": null,
      "tool_calls": [{
        "id": "call_abc123",
        "type": "function",
        "function": {
          "name": "get_weather",
          "arguments": "{\"city\":\"Paris\"}"
        }
      }]
    },
    "finish_reason": "tool_calls"
  }]
}

arguments is a string containing JSON. Parse it before use.

Sending the tool result back

Append the assistant's tool-call message and a role: "tool" message with the result, then call the API again:

JSON

{
  "model": "<tool-capable-model>",
  "messages": [
    {"role": "user", "content": "What is the weather in Paris?"},
    {"role": "assistant", "content": null, "tool_calls": [
      {"id": "call_abc123", "type": "function", "function": {"name": "get_weather", "arguments": "{\"city\":\"Paris\"}"}}
    ]},
    {"role": "tool", "tool_call_id": "call_abc123", "content": "{\"temp_c\": 18, \"conditions\": \"overcast\"}"}
  ]
}

The model continues from there with a natural-language answer.

Tool choice

Value	Behaviour
`"auto"` (default)	Model decides whether to call a tool
`"none"`	Model never calls a tool
`"required"`	Model must call at least one tool
`{"type": "function", "function": {"name": "..."}}`	Model must call this specific tool

Which models support tools?

Check supported_parameters in GET /v1/models. Tool-capable models include "tools" in that array. Calling tools on a model that doesn't support them returns a 400.

Where next

Chat completions for the request shape tools rides on top of.
Streaming for how tool_calls arrive in SSE chunks.
Models to feature-detect which models accept tools.