mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
chore(apis): unpublish deprecated /v1/inference apis (#3297)
# 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.
This commit is contained in:
parent
60484c5c4e
commit
53b15725b6
23 changed files with 3134 additions and 1347 deletions
92
tests/integration/recordings/responses/38ea441b5f83.json
Normal file
92
tests/integration/recordings/responses/38ea441b5f83.json
Normal file
|
@ -0,0 +1,92 @@
|
|||
{
|
||||
"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": false,
|
||||
"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.ChatCompletion",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-761",
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "tool_calls",
|
||||
"index": 0,
|
||||
"logprobs": null,
|
||||
"message": {
|
||||
"content": "",
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"annotations": null,
|
||||
"audio": null,
|
||||
"function_call": null,
|
||||
"tool_calls": [
|
||||
{
|
||||
"id": "call_cj8ownwc",
|
||||
"function": {
|
||||
"arguments": "{\"location\":\"San Francisco, CA\"}",
|
||||
"name": "get_weather"
|
||||
},
|
||||
"type": "function",
|
||||
"index": 0
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
],
|
||||
"created": 1758975113,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 18,
|
||||
"prompt_tokens": 185,
|
||||
"total_tokens": 203,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
}
|
Loading…
Add table
Add a link
Reference in a new issue