mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
ea396a54cd
# What does this PR do? update Ollama inference provider to use OpenAIMixin for openai-compat endpoints ## Test Plan ci
43 lines
1.1 KiB
JSON
43 lines
1.1 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://0.0.0.0:11434/v1/v1/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"prompt": "Say completions",
|
|
"max_tokens": 20,
|
|
"extra_body": {}
|
|
},
|
|
"endpoint": "/v1/completions",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-406",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "length",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": "Sure, I'd be happy to provide some definitions and examples of related words or phrases.\n\nTo better"
|
|
}
|
|
],
|
|
"created": 1757857133,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "text_completion",
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": {
|
|
"completion_tokens": 20,
|
|
"prompt_tokens": 28,
|
|
"total_tokens": 48,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
}
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|