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:
Matthew Farrellee 2025-09-27 14:20:06 -04:00 committed by GitHub
parent 60484c5c4e
commit 53b15725b6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
23 changed files with 3134 additions and 1347 deletions

View file

@ -0,0 +1,89 @@
{
"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": "You are a helpful assistant. Michael Jordan was born in 1963. He played basketball for the Chicago Bulls for 15 seasons."
},
{
"role": "user",
"content": "Please give me information about Michael Jordan."
}
],
"response_format": {
"type": "json_schema",
"json_schema": {
"name": "AnswerFormat",
"schema": {
"properties": {
"first_name": {
"title": "First Name",
"type": "string"
},
"last_name": {
"title": "Last Name",
"type": "string"
},
"year_of_birth": {
"title": "Year Of Birth",
"type": "integer"
}
},
"required": [
"first_name",
"last_name",
"year_of_birth"
],
"title": "AnswerFormat",
"type": "object"
}
}
},
"stream": false
},
"endpoint": "/v1/chat/completions",
"model": "llama3.2:3b-instruct-fp16"
},
"response": {
"body": {
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
"__data__": {
"id": "chatcmpl-433",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"message": {
"content": "{\"first_name\": \"Michael\", \"last_name\": \"Jordan\", \"year_of_birth\": 1963}\n\n \t\t\t\t\t\t\t\t\t\t\t \t\t ",
"refusal": null,
"role": "assistant",
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": null
}
}
],
"created": 1758979490,
"model": "llama3.2:3b-instruct-fp16",
"object": "chat.completion",
"service_tier": null,
"system_fingerprint": "fp_ollama",
"usage": {
"completion_tokens": 31,
"prompt_tokens": 60,
"total_tokens": 91,
"completion_tokens_details": null,
"prompt_tokens_details": null
}
}
},
"is_streaming": false
}
}

View file

@ -0,0 +1,44 @@
{
"request": {
"method": "POST",
"url": "http://0.0.0.0:11434/v1/v1/completions",
"headers": {},
"body": {
"model": "llama3.2:3b-instruct-fp16",
"prompt": "Hello, world!",
"logprobs": false,
"stream": false,
"extra_body": {}
},
"endpoint": "/v1/completions",
"model": "llama3.2:3b-instruct-fp16"
},
"response": {
"body": {
"__type__": "openai.types.completion.Completion",
"__data__": {
"id": "cmpl-74",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"text": "Hello! How can I assist you today?"
}
],
"created": 1758975636,
"model": "llama3.2:3b-instruct-fp16",
"object": "text_completion",
"system_fingerprint": "fp_ollama",
"usage": {
"completion_tokens": 10,
"prompt_tokens": 29,
"total_tokens": 39,
"completion_tokens_details": null,
"prompt_tokens_details": null
}
}
},
"is_streaming": false
}
}

File diff suppressed because one or more lines are too long

View 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
}
}

View file

@ -0,0 +1,44 @@
{
"request": {
"method": "POST",
"url": "http://0.0.0.0:11434/v1/v1/completions",
"headers": {},
"body": {
"model": "llama3.2:3b-instruct-fp16",
"prompt": "Hello, world!",
"logprobs": true,
"stream": false,
"extra_body": {}
},
"endpoint": "/v1/completions",
"model": "llama3.2:3b-instruct-fp16"
},
"response": {
"body": {
"__type__": "openai.types.completion.Completion",
"__data__": {
"id": "cmpl-809",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"text": "Hello! It's nice to meet you. Is there anything I can help you with or would you like to chat?"
}
],
"created": 1758975633,
"model": "llama3.2:3b-instruct-fp16",
"object": "text_completion",
"system_fingerprint": "fp_ollama",
"usage": {
"completion_tokens": 25,
"prompt_tokens": 29,
"total_tokens": 54,
"completion_tokens_details": null,
"prompt_tokens_details": null
}
}
},
"is_streaming": false
}
}

View file

@ -0,0 +1,60 @@
{
"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
},
"endpoint": "/v1/chat/completions",
"model": "llama3.2:3b-instruct-fp16"
},
"response": {
"body": {
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
"__data__": {
"id": "chatcmpl-123",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"message": {
"content": "Hello! As of my knowledge cutoff on December 15th, I have the latest information for you. However, please note that my data may not be entirely up-to-date.\n\nCurrently, and based on historical climate patterns, it appears to be a partly cloudy day with mild temperatures in San Francisco, CA. Expect a temperature range of around 48\u00b0F (9\u00b0C) to 54\u00b0F (12\u00b0C). It's likely to be a breezy day, with winds blowing at about 13 mph (21 km/h).\n\nHowever, if I were to look into more recent weather patterns or forecasts, I would recommend checking the latest conditions directly from reliable sources such as the National Weather Service or local news outlets for more accurate and up-to-date information.\n\nPlease let me know how I can further assist you.",
"refusal": null,
"role": "assistant",
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": null
}
}
],
"created": 1758978071,
"model": "llama3.2:3b-instruct-fp16",
"object": "chat.completion",
"service_tier": null,
"system_fingerprint": "fp_ollama",
"usage": {
"completion_tokens": 163,
"prompt_tokens": 45,
"total_tokens": 208,
"completion_tokens_details": null,
"prompt_tokens_details": null
}
}
},
"is_streaming": false
}
}

View file

@ -0,0 +1,55 @@
{
"request": {
"method": "POST",
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
"headers": {},
"body": {
"model": "llama3.2:3b-instruct-fp16",
"messages": [
{
"role": "user",
"content": "Test trace 0"
}
]
},
"endpoint": "/v1/chat/completions",
"model": "llama3.2:3b-instruct-fp16"
},
"response": {
"body": {
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
"__data__": {
"id": "chatcmpl-272",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"message": {
"content": "I'm happy to help you with a test. Since we are in the middle of a text-based conversation, I'll do my best to simulate a simple test tracing process.\n\n**Trace Test Results**\n\nTo perform this test, please follow these steps:\n\n1. Type \"test\" on command mode.\n2. Press Enter.\n\nNow, let's start tracing...\n\nTest Tracing Results:\nTest Case: General Functions\nTest Case Result: PASS\n\nSystem Response:\n\n```\n# System Boot Time: 2023-10-13T14:30:00\n# CPU Temperature: 35\u00b0C\n# Disk Space Available: 80%\n```\n\nNext Steps?\n\nType 'done' to exit the test, or 'run' for more tests.",
"refusal": null,
"role": "assistant",
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": null
}
}
],
"created": 1758978134,
"model": "llama3.2:3b-instruct-fp16",
"object": "chat.completion",
"service_tier": null,
"system_fingerprint": "fp_ollama",
"usage": {
"completion_tokens": 152,
"prompt_tokens": 29,
"total_tokens": 181,
"completion_tokens_details": null,
"prompt_tokens_details": null
}
}
},
"is_streaming": false
}
}

View file

@ -0,0 +1,44 @@
{
"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": "1963",
"stream": false,
"extra_body": {}
},
"endpoint": "/v1/completions",
"model": "llama3.2:3b-instruct-fp16"
},
"response": {
"body": {
"__type__": "openai.types.completion.Completion",
"__data__": {
"id": "cmpl-183",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"text": "Michael Jordan was born in the year of "
}
],
"created": 1758978053,
"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
}
}

View file

@ -0,0 +1,112 @@
{
"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
}
}

View 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
}
}

View file

@ -0,0 +1,55 @@
{
"request": {
"method": "POST",
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
"headers": {},
"body": {
"model": "llama3.2:3b-instruct-fp16",
"messages": [
{
"role": "user",
"content": "Test trace 1"
}
]
},
"endpoint": "/v1/chat/completions",
"model": "llama3.2:3b-instruct-fp16"
},
"response": {
"body": {
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
"__data__": {
"id": "chatcmpl-122",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"message": {
"content": "It appears you're trying to initiate a conversation or test the functionality of this AI system. I'm happy to chat with you!\n\nWould you like to:\nA) Ask me a question on a specific topic\nB) Engage in a conversational dialogue on a topic of your choice\nC) Play a text-based game\nD) Test my language understanding capabilities\n\nPlease respond with the letter of your preferred activity.",
"refusal": null,
"role": "assistant",
"annotations": null,
"audio": null,
"function_call": null,
"tool_calls": null
}
}
],
"created": 1758978142,
"model": "llama3.2:3b-instruct-fp16",
"object": "chat.completion",
"service_tier": null,
"system_fingerprint": "fp_ollama",
"usage": {
"completion_tokens": 85,
"prompt_tokens": 29,
"total_tokens": 114,
"completion_tokens_details": null,
"prompt_tokens_details": null
}
}
},
"is_streaming": false
}
}

View file

@ -11,26 +11,7 @@
"body": {
"__type__": "ollama._types.ProcessResponse",
"__data__": {
"models": [
{
"model": "llama3.2-vision:11b",
"name": "llama3.2-vision:11b",
"digest": "6f2f9757ae97e8a3f8ea33d6adb2b11d93d9a35bef277cd2c0b1b5af8e8d0b1e",
"expires_at": "2025-09-03T11:51:35.966409-07:00",
"size": 12401209008,
"size_vram": 12401209008,
"details": {
"parent_model": "",
"format": "gguf",
"family": "mllama",
"families": [
"mllama"
],
"parameter_size": "10.7B",
"quantization_level": "Q4_K_M"
}
}
]
"models": []
}
},
"is_streaming": false

View file

@ -31,14 +31,14 @@
"body": {
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
"__data__": {
"id": "chatcmpl-489",
"id": "chatcmpl-51",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"message": {
"content": "The image is a photograph of a young golden retriever puppy from the chest up. The puppy faces the camera and its tongue is out of its mouth, as if to say hello. It appears to be between 1 and 3 months of age. It is a fluffy little golden retriever puppy with very little fat. Its fur is light blond and very fluffy. It has a small, round black nose. It is in front of a blurry background of warm yellows and greys.",
"content": "The image features a close-up of a golden retriever puppy with its mouth agape. The puppy has cream-color fur with golden patches on its big ears, which are held slightly out to the sides. Its dark eyes appear black from across a great distance, while the black nose is surrounded by white fur. The puppy's mouth is wide open, revealing a healthy pink tongue and what appears to be a green leaf (likely a blade of grass) stuck in its mouth. The puppy is facing the camera directly, with its paws pressed up tight against its body. The puppy is sitting in an open field with a golden brown grass carpet. The puppy appears happy. The image is well-compressed with great digital sharpness.",
"refusal": null,
"role": "assistant",
"annotations": null,
@ -48,15 +48,15 @@
}
}
],
"created": 1758461767,
"created": 1756724768,
"model": "llama3.2-vision:11b",
"object": "chat.completion",
"service_tier": null,
"system_fingerprint": "fp_ollama",
"usage": {
"completion_tokens": 100,
"completion_tokens": 147,
"prompt_tokens": 18,
"total_tokens": 118,
"total_tokens": 165,
"completion_tokens_details": null,
"prompt_tokens_details": null
}