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
47
tests/integration/recordings/responses/c8e196049fe4.json
Normal file
47
tests/integration/recordings/responses/c8e196049fe4.json
Normal file
|
@ -0,0 +1,47 @@
|
|||
{
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "http://0.0.0.0:11434/v1/v1/completions",
|
||||
"headers": {},
|
||||
"body": {
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"prompt": "Return the exact same sentence and don't add additional words): Michael Jordan was born in the year of 1963",
|
||||
"stop": [
|
||||
"blathering",
|
||||
"1963"
|
||||
],
|
||||
"stream": false,
|
||||
"extra_body": {}
|
||||
},
|
||||
"endpoint": "/v1/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": {
|
||||
"__type__": "openai.types.completion.Completion",
|
||||
"__data__": {
|
||||
"id": "cmpl-381",
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null,
|
||||
"text": "Michael Jordan was born in the year of "
|
||||
}
|
||||
],
|
||||
"created": 1758978056,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "text_completion",
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 11,
|
||||
"prompt_tokens": 48,
|
||||
"total_tokens": 59,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
}
|
Loading…
Add table
Add a link
Reference in a new issue