mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
1f7e87c647
- update Cerebras to use OpenAIMixin - enable openai completions tests - enable openai chat completions tests - disable with n > 1 tests - add recording for --setup cerebras --subdirs inference --pattern openai test with: `./scripts/integration-tests.sh --stack-config server:ci-tests --setup cerebras --subdirs inference --pattern openai`
93 lines
2.5 KiB
JSON
93 lines
2.5 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "https://api.cerebras.ai/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama-3.3-70b",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "What's the weather in Tokyo? Use the get_weather function to get the weather."
|
|
}
|
|
],
|
|
"stream": false,
|
|
"tools": [
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "get_weather",
|
|
"description": "Get the weather in a given city",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"city": {
|
|
"type": "string",
|
|
"description": "The city to get the weather for"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama-3.3-70b"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
|
"__data__": {
|
|
"id": "chatcmpl-6228def9-c13d-4d7a-9029-e2c638a16f1b",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "tool_calls",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"message": {
|
|
"content": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"annotations": null,
|
|
"audio": null,
|
|
"function_call": null,
|
|
"tool_calls": [
|
|
{
|
|
"id": "1c40cbc30",
|
|
"function": {
|
|
"arguments": "{\"city\": \"Tokyo\"}",
|
|
"name": "get_weather"
|
|
},
|
|
"type": "function"
|
|
}
|
|
]
|
|
}
|
|
}
|
|
],
|
|
"created": 1758191364,
|
|
"model": "llama-3.3-70b",
|
|
"object": "chat.completion",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_c5ec625e72d41732d8fd",
|
|
"usage": {
|
|
"completion_tokens": 12,
|
|
"prompt_tokens": 248,
|
|
"total_tokens": 260,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": {
|
|
"audio_tokens": null,
|
|
"cached_tokens": 0
|
|
}
|
|
},
|
|
"time_info": {
|
|
"queue_time": 0.00041449,
|
|
"prompt_time": 0.007237483,
|
|
"completion_time": 0.003803105,
|
|
"total_time": 0.013348102569580078,
|
|
"created": 1758191364
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|