mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-16 14:57:20 +00:00
e9b4278a51
This PR updates the Conversation item related types and improves a couple critical parts of the implemenation: - it creates a streaming output item for the final assistant message output by the model. until now we only added content parts and included that message in the final response. - rewrites the conversation update code completely to account for items other than messages (tool calls, outputs, etc.) ## Test Plan Used the test script from https://github.com/llamastack/llama-stack-client-python/pull/281 for this ``` TEST_API_BASE_URL=http://localhost:8321/v1 \ pytest tests/integration/test_agent_turn_step_events.py::test_client_side_function_tool -xvs ```
146 lines
4.1 KiB
JSON
Generated
146 lines
4.1 KiB
JSON
Generated
{
|
|
"test_id": "tests/integration/agents/test_agents.py::test_tool_choice_required[ollama/llama3.2:3b-instruct-fp16]",
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"messages": [
|
|
{
|
|
"role": "system",
|
|
"content": "You are a helpful assistant"
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": [
|
|
{
|
|
"type": "text",
|
|
"text": "What is the boiling point of the liquid polyjuice in celsius?"
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"stream": true,
|
|
"stream_options": {
|
|
"include_usage": true
|
|
},
|
|
"tools": [
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"type": "function",
|
|
"name": "get_boiling_point",
|
|
"description": "Returns the boiling point of a liquid in Celcius or Fahrenheit.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"liquid_name": {
|
|
"type": "string",
|
|
"description": "The name of the liquid"
|
|
},
|
|
"celcius": {
|
|
"type": "boolean",
|
|
"description": "Whether to return the boiling point in Celcius"
|
|
}
|
|
},
|
|
"required": [
|
|
"liquid_name"
|
|
]
|
|
},
|
|
"strict": null
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": [
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-9de50d9e432d",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": "call_u7hftvf9",
|
|
"function": {
|
|
"arguments": "{\"celcius\":true,\"liquid_name\":\"polyjuice\"}",
|
|
"name": "get_boiling_point"
|
|
},
|
|
"type": "function"
|
|
}
|
|
]
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-9de50d9e432d",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": "tool_calls",
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": null
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-9de50d9e432d",
|
|
"choices": [],
|
|
"created": 0,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": {
|
|
"completion_tokens": 29,
|
|
"prompt_tokens": 209,
|
|
"total_tokens": 238,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"is_streaming": true
|
|
},
|
|
"id_normalization_mapping": {}
|
|
}
|