mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
53b15725b6
# What does this PR do? unpublish (make unavailable to users) the following apis - - `/v1/inference/completion`, replaced by `/v1/openai/v1/completions` - `/v1/inference/chat-completion`, replaced by `/v1/openai/v1/chat/completions` - `/v1/inference/embeddings`, replaced by `/v1/openai/v1/embeddings` - `/v1/inference/batch-completion`, replaced by `/v1/openai/v1/batches` - `/v1/inference/batch-chat-completion`, replaced by `/v1/openai/v1/batches` note: the implementations are still available for internal use, e.g. agents uses chat-completion.
112 lines
3 KiB
JSON
112 lines
3 KiB
JSON
{
|
|
"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": "Pretend you are a weather assistant."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "What's the weather like in San Francisco, CA?"
|
|
}
|
|
],
|
|
"stream": true,
|
|
"tool_choice": "auto",
|
|
"tools": [
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "get_weather",
|
|
"description": "Get the current weather",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"location": {
|
|
"type": "string",
|
|
"description": "The city and state (both required), e.g. San Francisco, CA."
|
|
}
|
|
},
|
|
"required": [
|
|
"location"
|
|
]
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "llama3.2:3b-instruct-fp16"
|
|
},
|
|
"response": {
|
|
"body": [
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "chatcmpl-634",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": "call_wubm4yax",
|
|
"function": {
|
|
"arguments": "{\"location\":\"San Francisco, CA\"}",
|
|
"name": "get_weather"
|
|
},
|
|
"type": "function"
|
|
}
|
|
]
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 1758975115,
|
|
"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": "chatcmpl-634",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": "tool_calls",
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 1758975115,
|
|
"model": "llama3.2:3b-instruct-fp16",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": null,
|
|
"system_fingerprint": "fp_ollama",
|
|
"usage": null
|
|
}
|
|
}
|
|
],
|
|
"is_streaming": true
|
|
}
|
|
}
|