mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-14 10:12:37 +00:00
chore: make OpenAIMixin maintainable, turn OpenAIMixin into a pydantic.BaseModel
- implement get_api_key instead of relying on LiteLLMOpenAIMixin.get_api_key - remove use of LiteLLMOpenAIMixin - add default initialize/shutdown methods to OpenAIMixin - remove __init__s to allow proper pydantic construction - remove dead code from vllm adapter and associated / duplicate unit tests - update vllm adapter to use openaimixin for model registration - remove ModelRegistryHelper from fireworks & together adapters - remove Inference from nvidia adapter - complete type hints on embedding_model_metadata - allow extra fields on OpenAIMixin, for model_store, __provider_id__, etc - new recordings for ollama - enhance the list models error handling w/ new tests - update cerebras (remove cerebras-cloud-sdk) and anthropic (custom model listing) inference adapters - parametrized test_inference_client_caching - remove cerebras, databricks, fireworks, together from blanket mypy exclude
This commit is contained in:
Matthew Farrellee
parent
351c4b98e4
commit
fd06717d87
64 changed files with 12901 additions and 1734 deletions
710
tests/integration/recordings/responses/08f97e548c4b.json
Normal file
710
tests/integration/recordings/responses/08f97e548c4b.json
Normal file
|
|
@ -0,0 +1,710 @@
|
|||
{
|
||||
"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"
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "What is the boiling point of the liquid polyjuice in celsius?"
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "",
|
||||
"tool_calls": [
|
||||
{
|
||||
"id": "call_6ah4hyex",
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point",
|
||||
"arguments": "{\"liquid\":\"polyjuice\",\"unit\":\"celsius\"}"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "tool",
|
||||
"tool_call_id": "call_6ah4hyex",
|
||||
"content": "Error when running tool: get_boiling_point() got an unexpected keyword argument 'liquid'"
|
||||
}
|
||||
],
|
||||
"max_tokens": 512,
|
||||
"stream": true,
|
||||
"temperature": 0.0001,
|
||||
"tool_choice": "auto",
|
||||
"tools": [
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point",
|
||||
"description": "Returns the boiling point of a liquid in Celcius or Fahrenheit."
|
||||
}
|
||||
}
|
||||
],
|
||||
"top_p": 0.9
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": [
|
||||
{
|
||||
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "I",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514971,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " was",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514971,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " unable",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514971,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " to",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514971,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " find",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " the",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " boiling",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " point",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " of",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " poly",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "ju",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "ice",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " in",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " my",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " search",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": ".",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " Can",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " I",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " help",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " you",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " with",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " something",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " else",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "?",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"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-622",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514972,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
}
|
||||
}
|
||||
710
tests/integration/recordings/responses/0d3602bdeb33.json
Normal file
710
tests/integration/recordings/responses/0d3602bdeb33.json
Normal file
|
|
@ -0,0 +1,710 @@
|
|||
{
|
||||
"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"
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "What is the boiling point of the liquid polyjuice in celsius?"
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "",
|
||||
"tool_calls": [
|
||||
{
|
||||
"id": "call_4gduxvhb",
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point",
|
||||
"arguments": "{\"liquid\":\"polyjuice\",\"unit\":\"celsius\"}"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "tool",
|
||||
"tool_call_id": "call_4gduxvhb",
|
||||
"content": "Error when running tool: get_boiling_point() got an unexpected keyword argument 'liquid'"
|
||||
}
|
||||
],
|
||||
"max_tokens": 512,
|
||||
"stream": true,
|
||||
"temperature": 0.0001,
|
||||
"tool_choice": "required",
|
||||
"tools": [
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point",
|
||||
"description": "Returns the boiling point of a liquid in Celcius or Fahrenheit."
|
||||
}
|
||||
}
|
||||
],
|
||||
"top_p": 0.9
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": [
|
||||
{
|
||||
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "I",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " was",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " unable",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " to",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " find",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " the",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " boiling",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " point",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " of",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " poly",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "ju",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "ice",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " in",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " my",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " search",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": ".",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " Can",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " I",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " help",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " you",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " with",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " something",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " else",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "?",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"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-759",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514982,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
}
|
||||
}
|
||||
57
tests/integration/recordings/responses/11675efe359b.json
Normal file
57
tests/integration/recordings/responses/11675efe359b.json
Normal file
|
|
@ -0,0 +1,57 @@
|
|||
{
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
||||
"headers": {},
|
||||
"body": {
|
||||
"model": "llama-guard3:1b",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Task: Check if there is unsafe content in 'Assistant' messages in conversations according our safety policy with the below categories.\n\n<BEGIN UNSAFE CONTENT CATEGORIES>\nS1: Violent Crimes.\nS2: Non-Violent Crimes.\nS3: Sex Crimes.\nS4: Child Exploitation.\nS5: Defamation.\nS6: Specialized Advice.\nS7: Privacy.\nS8: Intellectual Property.\nS9: Indiscriminate Weapons.\nS10: Hate.\nS11: Self-Harm.\nS12: Sexual Content.\nS13: Elections.\nS14: Code Interpreter Abuse.\n<END UNSAFE CONTENT CATEGORIES>\n\n<BEGIN CONVERSATION>\n\nUser: What is the boiling point of the liquid polyjuice in celsius?\n\nAssistant: \n\nTool: Error when running tool: get_boiling_point() got an unexpected keyword argument 'liquid'\n\nAssistant: I was unable to find the boiling point of polyjuice in my search. Can I help you with something else?\n\n<END CONVERSATION>\n\nProvide your safety assessment for ONLY THE LAST Assistant message in the above conversation:\n - First line must read 'safe' or 'unsafe'.\n - If unsafe, a second line must include a comma-separated list of violated categories."
|
||||
}
|
||||
],
|
||||
"stream": false,
|
||||
"temperature": 0.0
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama-guard3:1b"
|
||||
},
|
||||
"response": {
|
||||
"body": {
|
||||
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-774",
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null,
|
||||
"message": {
|
||||
"content": "safe",
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"annotations": null,
|
||||
"audio": null,
|
||||
"function_call": null,
|
||||
"tool_calls": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"created": 1759514987,
|
||||
"model": "llama-guard3:1b",
|
||||
"object": "chat.completion",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 2,
|
||||
"prompt_tokens": 447,
|
||||
"total_tokens": 449,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
}
|
||||
3154
tests/integration/recordings/responses/125f1f43f167.json
Normal file
3154
tests/integration/recordings/responses/125f1f43f167.json
Normal file
File diff suppressed because it is too large
Load diff
103
tests/integration/recordings/responses/1b08c8e14202.json
Normal file
103
tests/integration/recordings/responses/1b08c8e14202.json
Normal file
|
|
@ -0,0 +1,103 @@
|
|||
{
|
||||
"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 Always respond with tool calls no matter what. "
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Get the boiling point of polyjuice with a tool call."
|
||||
}
|
||||
],
|
||||
"max_tokens": 512,
|
||||
"stream": true,
|
||||
"temperature": 0.0001,
|
||||
"tool_choice": "auto",
|
||||
"tools": [
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point",
|
||||
"description": "Returns the boiling point of a liquid in Celcius or Fahrenheit."
|
||||
}
|
||||
}
|
||||
],
|
||||
"top_p": 0.9
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": [
|
||||
{
|
||||
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-707",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": [
|
||||
{
|
||||
"index": 0,
|
||||
"id": "call_laifztfo",
|
||||
"function": {
|
||||
"arguments": "{}",
|
||||
"name": "get_boiling_point"
|
||||
},
|
||||
"type": "function"
|
||||
}
|
||||
]
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514973,
|
||||
"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-707",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "tool_calls",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514973,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
}
|
||||
}
|
||||
1724
tests/integration/recordings/responses/26b3819920f0.json
Normal file
1724
tests/integration/recordings/responses/26b3819920f0.json
Normal file
File diff suppressed because it is too large
Load diff
108
tests/integration/recordings/responses/31a87d74ea98.json
Normal file
108
tests/integration/recordings/responses/31a87d74ea98.json
Normal file
|
|
@ -0,0 +1,108 @@
|
|||
{
|
||||
"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"
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "What is the boiling point of the liquid polyjuice in celsius?"
|
||||
}
|
||||
],
|
||||
"max_tokens": 512,
|
||||
"stream": true,
|
||||
"temperature": 0.0001,
|
||||
"tool_choice": {
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point"
|
||||
}
|
||||
},
|
||||
"tools": [
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point",
|
||||
"description": "Returns the boiling point of a liquid in Celcius or Fahrenheit."
|
||||
}
|
||||
}
|
||||
],
|
||||
"top_p": 0.9
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": [
|
||||
{
|
||||
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-269",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": [
|
||||
{
|
||||
"index": 0,
|
||||
"id": "call_m61820zt",
|
||||
"function": {
|
||||
"arguments": "{\"liquid\":\"polyjuice\",\"unit\":\"celsius\"}",
|
||||
"name": "get_boiling_point"
|
||||
},
|
||||
"type": "function"
|
||||
}
|
||||
]
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514985,
|
||||
"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-269",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "tool_calls",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514985,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
}
|
||||
}
|
||||
170
tests/integration/recordings/responses/3e8248d253fd.json
Normal file
170
tests/integration/recordings/responses/3e8248d253fd.json
Normal file
|
|
@ -0,0 +1,170 @@
|
|||
{
|
||||
"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."
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Say hi to the world. Use tools to do so."
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "",
|
||||
"tool_calls": [
|
||||
{
|
||||
"id": "call_bhtxlmzm",
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "greet_everyone",
|
||||
"arguments": "{\"url\":\"world\"}"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "tool",
|
||||
"tool_call_id": "call_bhtxlmzm",
|
||||
"content": [
|
||||
{
|
||||
"type": "text",
|
||||
"text": "Hello, world!"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "I'm able to \"speak\" to you through this chat platform, hello! Would you like me to repeat anything or provide assistance with something else?"
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "What is the boiling point of polyjuice? Use tools to answer."
|
||||
}
|
||||
],
|
||||
"max_tokens": 0,
|
||||
"stream": true,
|
||||
"tool_choice": "auto",
|
||||
"tools": [
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "greet_everyone",
|
||||
"parameters": {
|
||||
"properties": {
|
||||
"url": {
|
||||
"title": "Url",
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"url"
|
||||
],
|
||||
"title": "greet_everyoneArguments",
|
||||
"type": "object"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point",
|
||||
"description": "\n Returns the boiling point of a liquid in Celsius or Fahrenheit.\n\n :param liquid_name: The name of the liquid\n :param celsius: Whether to return the boiling point in Celsius\n :return: The boiling point of the liquid in Celcius or Fahrenheit\n ",
|
||||
"parameters": {
|
||||
"properties": {
|
||||
"liquid_name": {
|
||||
"title": "Liquid Name",
|
||||
"type": "string"
|
||||
},
|
||||
"celsius": {
|
||||
"default": true,
|
||||
"title": "Celsius",
|
||||
"type": "boolean"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"liquid_name"
|
||||
],
|
||||
"title": "get_boiling_pointArguments",
|
||||
"type": "object"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": [
|
||||
{
|
||||
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-515",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": [
|
||||
{
|
||||
"index": 0,
|
||||
"id": "call_li57r4tl",
|
||||
"function": {
|
||||
"arguments": "{\"celsius\":\"true\",\"liquid_name\":\"polyjuice\"}",
|
||||
"name": "get_boiling_point"
|
||||
},
|
||||
"type": "function"
|
||||
}
|
||||
]
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515074,
|
||||
"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-515",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "tool_calls",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515074,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
}
|
||||
}
|
||||
1828
tests/integration/recordings/responses/41393ddb2491.json
Normal file
1828
tests/integration/recordings/responses/41393ddb2491.json
Normal file
File diff suppressed because it is too large
Load diff
57
tests/integration/recordings/responses/864a270ca97b.json
Normal file
57
tests/integration/recordings/responses/864a270ca97b.json
Normal file
|
|
@ -0,0 +1,57 @@
|
|||
{
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
||||
"headers": {},
|
||||
"body": {
|
||||
"model": "llama-guard3:1b",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Task: Check if there is unsafe content in 'Tool' messages in conversations according our safety policy with the below categories.\n\n<BEGIN UNSAFE CONTENT CATEGORIES>\nS1: Violent Crimes.\nS2: Non-Violent Crimes.\nS3: Sex Crimes.\nS4: Child Exploitation.\nS5: Defamation.\nS6: Specialized Advice.\nS7: Privacy.\nS8: Intellectual Property.\nS9: Indiscriminate Weapons.\nS10: Hate.\nS11: Self-Harm.\nS12: Sexual Content.\nS13: Elections.\nS14: Code Interpreter Abuse.\n<END UNSAFE CONTENT CATEGORIES>\n\n<BEGIN CONVERSATION>\n\nUser: Get the boiling point of polyjuice with a tool call.\n\nAssistant: \n\nTool: Error when running tool: get_boiling_point() missing 1 required positional argument: 'liquid_name'\n\n<END CONVERSATION>\n\nProvide your safety assessment for ONLY THE LAST Tool message in the above conversation:\n - First line must read 'safe' or 'unsafe'.\n - If unsafe, a second line must include a comma-separated list of violated categories."
|
||||
}
|
||||
],
|
||||
"stream": false,
|
||||
"temperature": 0.0
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama-guard3:1b"
|
||||
},
|
||||
"response": {
|
||||
"body": {
|
||||
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-394",
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null,
|
||||
"message": {
|
||||
"content": "safe",
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"annotations": null,
|
||||
"audio": null,
|
||||
"function_call": null,
|
||||
"tool_calls": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"created": 1759514973,
|
||||
"model": "llama-guard3:1b",
|
||||
"object": "chat.completion",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 2,
|
||||
"prompt_tokens": 422,
|
||||
"total_tokens": 424,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
}
|
||||
57
tests/integration/recordings/responses/b63c1324a814.json
Normal file
57
tests/integration/recordings/responses/b63c1324a814.json
Normal file
|
|
@ -0,0 +1,57 @@
|
|||
{
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
||||
"headers": {},
|
||||
"body": {
|
||||
"model": "llama-guard3:1b",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Task: Check if there is unsafe content in 'Assistant' messages in conversations according our safety policy with the below categories.\n\n<BEGIN UNSAFE CONTENT CATEGORIES>\nS1: Violent Crimes.\nS2: Non-Violent Crimes.\nS3: Sex Crimes.\nS4: Child Exploitation.\nS5: Defamation.\nS6: Specialized Advice.\nS7: Privacy.\nS8: Intellectual Property.\nS9: Indiscriminate Weapons.\nS10: Hate.\nS11: Self-Harm.\nS12: Sexual Content.\nS13: Elections.\nS14: Code Interpreter Abuse.\n<END UNSAFE CONTENT CATEGORIES>\n\n<BEGIN CONVERSATION>\n\nUser: Get the boiling point of polyjuice with a tool call.\n\nAssistant: \n\nTool: Error when running tool: get_boiling_point() missing 1 required positional argument: 'liquid_name'\n\nAssistant: I apologize for the error. It seems that the `get_boiling_point` tool requires a liquid name as an argument.\n\nTo provide the boiling point of polyjuice, I'll need to know that polyjuice is not a real substance and its boiling point cannot be found in my database. However, if you meant to ask about Polyjuice Potion from the Harry Potter series, I can tell you that it's a fictional potion.\n\nIf you could provide more context or clarify which polyjuice you are referring to, I'll do my best to assist you with your question.\n\n<END CONVERSATION>\n\nProvide your safety assessment for ONLY THE LAST Assistant message in the above conversation:\n - First line must read 'safe' or 'unsafe'.\n - If unsafe, a second line must include a comma-separated list of violated categories."
|
||||
}
|
||||
],
|
||||
"stream": false,
|
||||
"temperature": 0.0
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama-guard3:1b"
|
||||
},
|
||||
"response": {
|
||||
"body": {
|
||||
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-515",
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null,
|
||||
"message": {
|
||||
"content": "safe",
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"annotations": null,
|
||||
"audio": null,
|
||||
"function_call": null,
|
||||
"tool_calls": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"created": 1759514975,
|
||||
"model": "llama-guard3:1b",
|
||||
"object": "chat.completion",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 2,
|
||||
"prompt_tokens": 542,
|
||||
"total_tokens": 544,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
}
|
||||
57
tests/integration/recordings/responses/c23c11b48503.json
Normal file
57
tests/integration/recordings/responses/c23c11b48503.json
Normal file
|
|
@ -0,0 +1,57 @@
|
|||
{
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
||||
"headers": {},
|
||||
"body": {
|
||||
"model": "llama-guard3:1b",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Task: Check if there is unsafe content in 'Tool' messages in conversations according our safety policy with the below categories.\n\n<BEGIN UNSAFE CONTENT CATEGORIES>\nS1: Violent Crimes.\nS2: Non-Violent Crimes.\nS3: Sex Crimes.\nS4: Child Exploitation.\nS5: Defamation.\nS6: Specialized Advice.\nS7: Privacy.\nS8: Intellectual Property.\nS9: Indiscriminate Weapons.\nS10: Hate.\nS11: Self-Harm.\nS12: Sexual Content.\nS13: Elections.\nS14: Code Interpreter Abuse.\n<END UNSAFE CONTENT CATEGORIES>\n\n<BEGIN CONVERSATION>\n\nUser: What is the boiling point of the liquid polyjuice in celsius?\n\nAssistant: \n\nTool: Error when running tool: get_boiling_point() got an unexpected keyword argument 'liquid'\n\n<END CONVERSATION>\n\nProvide your safety assessment for ONLY THE LAST Tool message in the above conversation:\n - First line must read 'safe' or 'unsafe'.\n - If unsafe, a second line must include a comma-separated list of violated categories."
|
||||
}
|
||||
],
|
||||
"stream": false,
|
||||
"temperature": 0.0
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama-guard3:1b"
|
||||
},
|
||||
"response": {
|
||||
"body": {
|
||||
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-576",
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null,
|
||||
"message": {
|
||||
"content": "safe",
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"annotations": null,
|
||||
"audio": null,
|
||||
"function_call": null,
|
||||
"tool_calls": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"model": "llama-guard3:1b",
|
||||
"object": "chat.completion",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 2,
|
||||
"prompt_tokens": 421,
|
||||
"total_tokens": 423,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
}
|
||||
715
tests/integration/recordings/responses/c315ffba4f17.json
Normal file
715
tests/integration/recordings/responses/c315ffba4f17.json
Normal file
|
|
@ -0,0 +1,715 @@
|
|||
{
|
||||
"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"
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "What is the boiling point of the liquid polyjuice in celsius?"
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "",
|
||||
"tool_calls": [
|
||||
{
|
||||
"id": "call_m61820zt",
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point",
|
||||
"arguments": "{\"liquid\":\"polyjuice\",\"unit\":\"celsius\"}"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "tool",
|
||||
"tool_call_id": "call_m61820zt",
|
||||
"content": "Error when running tool: get_boiling_point() got an unexpected keyword argument 'liquid'"
|
||||
}
|
||||
],
|
||||
"max_tokens": 512,
|
||||
"stream": true,
|
||||
"temperature": 0.0001,
|
||||
"tool_choice": {
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point"
|
||||
}
|
||||
},
|
||||
"tools": [
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point",
|
||||
"description": "Returns the boiling point of a liquid in Celcius or Fahrenheit."
|
||||
}
|
||||
}
|
||||
],
|
||||
"top_p": 0.9
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": [
|
||||
{
|
||||
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "I",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " was",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " unable",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " to",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " find",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " the",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " boiling",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " point",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " of",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " poly",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "ju",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "ice",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " in",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " my",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " search",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": ".",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " Can",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " I",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " help",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " you",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " with",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " something",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " else",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "?",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"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-884",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514986,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
}
|
||||
}
|
||||
103
tests/integration/recordings/responses/c8632717f6b8.json
Normal file
103
tests/integration/recordings/responses/c8632717f6b8.json
Normal file
|
|
@ -0,0 +1,103 @@
|
|||
{
|
||||
"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"
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "What is the boiling point of the liquid polyjuice in celsius?"
|
||||
}
|
||||
],
|
||||
"max_tokens": 512,
|
||||
"stream": true,
|
||||
"temperature": 0.0001,
|
||||
"tool_choice": "auto",
|
||||
"tools": [
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point",
|
||||
"description": "Returns the boiling point of a liquid in Celcius or Fahrenheit."
|
||||
}
|
||||
}
|
||||
],
|
||||
"top_p": 0.9
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": [
|
||||
{
|
||||
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-382",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": [
|
||||
{
|
||||
"index": 0,
|
||||
"id": "call_6ah4hyex",
|
||||
"function": {
|
||||
"arguments": "{\"liquid\":\"polyjuice\",\"unit\":\"celsius\"}",
|
||||
"name": "get_boiling_point"
|
||||
},
|
||||
"type": "function"
|
||||
}
|
||||
]
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514971,
|
||||
"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-382",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "tool_calls",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514971,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
}
|
||||
}
|
||||
103
tests/integration/recordings/responses/ccdce45aab2c.json
Normal file
103
tests/integration/recordings/responses/ccdce45aab2c.json
Normal file
|
|
@ -0,0 +1,103 @@
|
|||
{
|
||||
"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"
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "What is the boiling point of the liquid polyjuice in celsius?"
|
||||
}
|
||||
],
|
||||
"max_tokens": 512,
|
||||
"stream": true,
|
||||
"temperature": 0.0001,
|
||||
"tool_choice": "required",
|
||||
"tools": [
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point",
|
||||
"description": "Returns the boiling point of a liquid in Celcius or Fahrenheit."
|
||||
}
|
||||
}
|
||||
],
|
||||
"top_p": 0.9
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": [
|
||||
{
|
||||
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-421",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": [
|
||||
{
|
||||
"index": 0,
|
||||
"id": "call_4gduxvhb",
|
||||
"function": {
|
||||
"arguments": "{\"liquid\":\"polyjuice\",\"unit\":\"celsius\"}",
|
||||
"name": "get_boiling_point"
|
||||
},
|
||||
"type": "function"
|
||||
}
|
||||
]
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514981,
|
||||
"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-421",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "tool_calls",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514981,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
}
|
||||
}
|
||||
932
tests/integration/recordings/responses/d9c3bf231670.json
Normal file
932
tests/integration/recordings/responses/d9c3bf231670.json
Normal file
|
|
@ -0,0 +1,932 @@
|
|||
{
|
||||
"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."
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Say hi to the world. Use tools to do so."
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "",
|
||||
"tool_calls": [
|
||||
{
|
||||
"id": "call_bhtxlmzm",
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "greet_everyone",
|
||||
"arguments": "{\"url\":\"world\"}"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "tool",
|
||||
"tool_call_id": "call_bhtxlmzm",
|
||||
"content": [
|
||||
{
|
||||
"type": "text",
|
||||
"text": "Hello, world!"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"max_tokens": 0,
|
||||
"stream": true,
|
||||
"tool_choice": "auto",
|
||||
"tools": [
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "greet_everyone",
|
||||
"parameters": {
|
||||
"properties": {
|
||||
"url": {
|
||||
"title": "Url",
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"url"
|
||||
],
|
||||
"title": "greet_everyoneArguments",
|
||||
"type": "object"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point",
|
||||
"description": "\n Returns the boiling point of a liquid in Celsius or Fahrenheit.\n\n :param liquid_name: The name of the liquid\n :param celsius: Whether to return the boiling point in Celsius\n :return: The boiling point of the liquid in Celcius or Fahrenheit\n ",
|
||||
"parameters": {
|
||||
"properties": {
|
||||
"liquid_name": {
|
||||
"title": "Liquid Name",
|
||||
"type": "string"
|
||||
},
|
||||
"celsius": {
|
||||
"default": true,
|
||||
"title": "Celsius",
|
||||
"type": "boolean"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"liquid_name"
|
||||
],
|
||||
"title": "get_boiling_pointArguments",
|
||||
"type": "object"
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": [
|
||||
{
|
||||
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "I",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515073,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "'m",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515073,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " able",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515073,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " to",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515073,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " \"",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515073,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "s",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515073,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "peak",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515073,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "\"",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515073,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " to",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515073,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " you",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515073,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " through",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515073,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " this",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515073,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " chat",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515073,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " platform",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515073,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": ",",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515073,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " hello",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515074,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "!",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515074,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " Would",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515074,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " you",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515074,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " like",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515074,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " me",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515074,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " to",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515074,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " repeat",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515074,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " anything",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515074,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " or",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515074,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " provide",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515074,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " assistance",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515074,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " with",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515074,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " something",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515074,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " else",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515074,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "?",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515074,
|
||||
"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-770",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515074,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
}
|
||||
}
|
||||
103
tests/integration/recordings/responses/db9689e2cf53.json
Normal file
103
tests/integration/recordings/responses/db9689e2cf53.json
Normal file
|
|
@ -0,0 +1,103 @@
|
|||
{
|
||||
"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"
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Call get_boiling_point_with_metadata tool and answer What is the boiling point of polyjuice?"
|
||||
}
|
||||
],
|
||||
"max_tokens": 512,
|
||||
"stream": true,
|
||||
"temperature": 0.0001,
|
||||
"tool_choice": "auto",
|
||||
"tools": [
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point_with_metadata",
|
||||
"description": "Returns the boiling point of a liquid in Celcius or Fahrenheit"
|
||||
}
|
||||
}
|
||||
],
|
||||
"top_p": 0.9
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": [
|
||||
{
|
||||
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-178",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": [
|
||||
{
|
||||
"index": 0,
|
||||
"id": "call_9vy3xwac",
|
||||
"function": {
|
||||
"arguments": "{}",
|
||||
"name": "get_boiling_point_with_metadata"
|
||||
},
|
||||
"type": "function"
|
||||
}
|
||||
]
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515075,
|
||||
"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-178",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "tool_calls",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759515075,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
}
|
||||
}
|
||||
103
tests/integration/recordings/responses/eac12959a803.json
Normal file
103
tests/integration/recordings/responses/eac12959a803.json
Normal file
|
|
@ -0,0 +1,103 @@
|
|||
{
|
||||
"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"
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Call get_boiling_point tool and answer What is the boiling point of polyjuice?"
|
||||
}
|
||||
],
|
||||
"max_tokens": 512,
|
||||
"stream": true,
|
||||
"temperature": 0.0001,
|
||||
"tool_choice": "auto",
|
||||
"tools": [
|
||||
{
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point",
|
||||
"description": "Returns the boiling point of a liquid in Celcius or Fahrenheit."
|
||||
}
|
||||
}
|
||||
],
|
||||
"top_p": 0.9
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": [
|
||||
{
|
||||
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
||||
"__data__": {
|
||||
"id": "chatcmpl-367",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": [
|
||||
{
|
||||
"index": 0,
|
||||
"id": "call_swism1x1",
|
||||
"function": {
|
||||
"arguments": "{}",
|
||||
"name": "get_boiling_point"
|
||||
},
|
||||
"type": "function"
|
||||
}
|
||||
]
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514987,
|
||||
"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-367",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "tool_calls",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 1759514987,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load diff
|
|
@ -131,6 +131,27 @@ SETUP_DEFINITIONS: dict[str, Setup] = {
|
|||
"embedding_model": "fireworks/accounts/fireworks/models/qwen3-embedding-8b",
|
||||
},
|
||||
),
|
||||
"anthropic": Setup(
|
||||
name="anthropic",
|
||||
description="Anthropic Claude models",
|
||||
defaults={
|
||||
"text_model": "anthropic/claude-3-5-haiku-20241022",
|
||||
},
|
||||
),
|
||||
"llama-api": Setup(
|
||||
name="llama-openai-compat",
|
||||
description="Llama models from https://api.llama.com",
|
||||
defaults={
|
||||
"text_model": "llama_openai_compat/Llama-3.3-8B-Instruct",
|
||||
},
|
||||
),
|
||||
"groq": Setup(
|
||||
name="groq",
|
||||
description="Groq models",
|
||||
defaults={
|
||||
"text_model": "groq/llama-3.3-70b-versatile",
|
||||
},
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -7,6 +7,8 @@
|
|||
import json
|
||||
from unittest.mock import MagicMock
|
||||
|
||||
import pytest
|
||||
|
||||
from llama_stack.core.request_headers import request_provider_data_context
|
||||
from llama_stack.providers.remote.inference.groq.config import GroqConfig
|
||||
from llama_stack.providers.remote.inference.groq.groq import GroqInferenceAdapter
|
||||
|
|
@ -18,72 +20,41 @@ from llama_stack.providers.remote.inference.together.config import TogetherImplC
|
|||
from llama_stack.providers.remote.inference.together.together import TogetherInferenceAdapter
|
||||
|
||||
|
||||
def test_groq_provider_openai_client_caching():
|
||||
"""Ensure the Groq provider does not cache api keys across client requests"""
|
||||
|
||||
config = GroqConfig()
|
||||
inference_adapter = GroqInferenceAdapter(config)
|
||||
|
||||
inference_adapter.__provider_spec__ = MagicMock()
|
||||
inference_adapter.__provider_spec__.provider_data_validator = (
|
||||
"llama_stack.providers.remote.inference.groq.config.GroqProviderDataValidator"
|
||||
)
|
||||
|
||||
for api_key in ["test1", "test2"]:
|
||||
with request_provider_data_context(
|
||||
{"x-llamastack-provider-data": json.dumps({inference_adapter.provider_data_api_key_field: api_key})}
|
||||
):
|
||||
assert inference_adapter.client.api_key == api_key
|
||||
|
||||
|
||||
def test_openai_provider_openai_client_caching():
|
||||
@pytest.mark.parametrize(
|
||||
"config_cls,adapter_cls,provider_data_validator",
|
||||
[
|
||||
(
|
||||
GroqConfig,
|
||||
GroqInferenceAdapter,
|
||||
"llama_stack.providers.remote.inference.groq.config.GroqProviderDataValidator",
|
||||
),
|
||||
(
|
||||
OpenAIConfig,
|
||||
OpenAIInferenceAdapter,
|
||||
"llama_stack.providers.remote.inference.openai.config.OpenAIProviderDataValidator",
|
||||
),
|
||||
(
|
||||
TogetherImplConfig,
|
||||
TogetherInferenceAdapter,
|
||||
"llama_stack.providers.remote.inference.together.TogetherProviderDataValidator",
|
||||
),
|
||||
(
|
||||
LlamaCompatConfig,
|
||||
LlamaCompatInferenceAdapter,
|
||||
"llama_stack.providers.remote.inference.llama_openai_compat.config.LlamaProviderDataValidator",
|
||||
),
|
||||
],
|
||||
)
|
||||
def test_openai_provider_data_used(config_cls, adapter_cls, provider_data_validator: str):
|
||||
"""Ensure the OpenAI provider does not cache api keys across client requests"""
|
||||
|
||||
config = OpenAIConfig()
|
||||
inference_adapter = OpenAIInferenceAdapter(config)
|
||||
inference_adapter = adapter_cls(config=config_cls())
|
||||
|
||||
inference_adapter.__provider_spec__ = MagicMock()
|
||||
inference_adapter.__provider_spec__.provider_data_validator = (
|
||||
"llama_stack.providers.remote.inference.openai.config.OpenAIProviderDataValidator"
|
||||
)
|
||||
inference_adapter.__provider_spec__.provider_data_validator = provider_data_validator
|
||||
|
||||
for api_key in ["test1", "test2"]:
|
||||
with request_provider_data_context(
|
||||
{"x-llamastack-provider-data": json.dumps({inference_adapter.provider_data_api_key_field: api_key})}
|
||||
):
|
||||
openai_client = inference_adapter.client
|
||||
assert openai_client.api_key == api_key
|
||||
|
||||
|
||||
def test_together_provider_openai_client_caching():
|
||||
"""Ensure the Together provider does not cache api keys across client requests"""
|
||||
|
||||
config = TogetherImplConfig()
|
||||
inference_adapter = TogetherInferenceAdapter(config)
|
||||
|
||||
inference_adapter.__provider_spec__ = MagicMock()
|
||||
inference_adapter.__provider_spec__.provider_data_validator = (
|
||||
"llama_stack.providers.remote.inference.together.TogetherProviderDataValidator"
|
||||
)
|
||||
|
||||
for api_key in ["test1", "test2"]:
|
||||
with request_provider_data_context({"x-llamastack-provider-data": json.dumps({"together_api_key": api_key})}):
|
||||
together_client = inference_adapter._get_client()
|
||||
assert together_client.client.api_key == api_key
|
||||
openai_client = inference_adapter._get_openai_client()
|
||||
assert openai_client.api_key == api_key
|
||||
|
||||
|
||||
def test_llama_compat_provider_openai_client_caching():
|
||||
"""Ensure the LlamaCompat provider does not cache api keys across client requests"""
|
||||
config = LlamaCompatConfig()
|
||||
inference_adapter = LlamaCompatInferenceAdapter(config)
|
||||
|
||||
inference_adapter.__provider_spec__ = MagicMock()
|
||||
inference_adapter.__provider_spec__.provider_data_validator = (
|
||||
"llama_stack.providers.remote.inference.llama_openai_compat.config.LlamaProviderDataValidator"
|
||||
)
|
||||
|
||||
for api_key in ["test1", "test2"]:
|
||||
with request_provider_data_context({"x-llamastack-provider-data": json.dumps({"llama_api_key": api_key})}):
|
||||
assert inference_adapter.client.api_key == api_key
|
||||
|
|
|
|||
|
|
@ -18,7 +18,7 @@ class TestOpenAIBaseURLConfig:
|
|||
def test_default_base_url_without_env_var(self):
|
||||
"""Test that the adapter uses the default OpenAI base URL when no environment variable is set."""
|
||||
config = OpenAIConfig(api_key="test-key")
|
||||
adapter = OpenAIInferenceAdapter(config)
|
||||
adapter = OpenAIInferenceAdapter(config=config)
|
||||
adapter.provider_data_api_key_field = None # Disable provider data for this test
|
||||
|
||||
assert adapter.get_base_url() == "https://api.openai.com/v1"
|
||||
|
|
@ -27,7 +27,7 @@ class TestOpenAIBaseURLConfig:
|
|||
"""Test that the adapter uses a custom base URL when provided in config."""
|
||||
custom_url = "https://custom.openai.com/v1"
|
||||
config = OpenAIConfig(api_key="test-key", base_url=custom_url)
|
||||
adapter = OpenAIInferenceAdapter(config)
|
||||
adapter = OpenAIInferenceAdapter(config=config)
|
||||
adapter.provider_data_api_key_field = None # Disable provider data for this test
|
||||
|
||||
assert adapter.get_base_url() == custom_url
|
||||
|
|
@ -39,7 +39,7 @@ class TestOpenAIBaseURLConfig:
|
|||
config_data = OpenAIConfig.sample_run_config(api_key="test-key")
|
||||
processed_config = replace_env_vars(config_data)
|
||||
config = OpenAIConfig.model_validate(processed_config)
|
||||
adapter = OpenAIInferenceAdapter(config)
|
||||
adapter = OpenAIInferenceAdapter(config=config)
|
||||
adapter.provider_data_api_key_field = None # Disable provider data for this test
|
||||
|
||||
assert adapter.get_base_url() == "https://env.openai.com/v1"
|
||||
|
|
@ -49,7 +49,7 @@ class TestOpenAIBaseURLConfig:
|
|||
"""Test that explicit config value overrides environment variable."""
|
||||
custom_url = "https://config.openai.com/v1"
|
||||
config = OpenAIConfig(api_key="test-key", base_url=custom_url)
|
||||
adapter = OpenAIInferenceAdapter(config)
|
||||
adapter = OpenAIInferenceAdapter(config=config)
|
||||
adapter.provider_data_api_key_field = None # Disable provider data for this test
|
||||
|
||||
# Config should take precedence over environment variable
|
||||
|
|
@ -60,7 +60,7 @@ class TestOpenAIBaseURLConfig:
|
|||
"""Test that the OpenAI client is initialized with the configured base URL."""
|
||||
custom_url = "https://test.openai.com/v1"
|
||||
config = OpenAIConfig(api_key="test-key", base_url=custom_url)
|
||||
adapter = OpenAIInferenceAdapter(config)
|
||||
adapter = OpenAIInferenceAdapter(config=config)
|
||||
adapter.provider_data_api_key_field = None # Disable provider data for this test
|
||||
|
||||
# Mock the get_api_key method since it's delegated to LiteLLMOpenAIMixin
|
||||
|
|
@ -80,7 +80,7 @@ class TestOpenAIBaseURLConfig:
|
|||
"""Test that check_model_availability uses the configured base URL."""
|
||||
custom_url = "https://test.openai.com/v1"
|
||||
config = OpenAIConfig(api_key="test-key", base_url=custom_url)
|
||||
adapter = OpenAIInferenceAdapter(config)
|
||||
adapter = OpenAIInferenceAdapter(config=config)
|
||||
adapter.provider_data_api_key_field = None # Disable provider data for this test
|
||||
|
||||
# Mock the get_api_key method
|
||||
|
|
@ -122,7 +122,7 @@ class TestOpenAIBaseURLConfig:
|
|||
config_data = OpenAIConfig.sample_run_config(api_key="test-key")
|
||||
processed_config = replace_env_vars(config_data)
|
||||
config = OpenAIConfig.model_validate(processed_config)
|
||||
adapter = OpenAIInferenceAdapter(config)
|
||||
adapter = OpenAIInferenceAdapter(config=config)
|
||||
adapter.provider_data_api_key_field = None # Disable provider data for this test
|
||||
|
||||
# Mock the get_api_key method
|
||||
|
|
|
|||
|
|
@ -5,45 +5,21 @@
|
|||
# the root directory of this source tree.
|
||||
|
||||
import asyncio
|
||||
import json
|
||||
import time
|
||||
from unittest.mock import AsyncMock, MagicMock, PropertyMock, patch
|
||||
|
||||
import pytest
|
||||
from openai.types.chat.chat_completion_chunk import (
|
||||
ChatCompletionChunk as OpenAIChatCompletionChunk,
|
||||
)
|
||||
from openai.types.chat.chat_completion_chunk import (
|
||||
Choice as OpenAIChoiceChunk,
|
||||
)
|
||||
from openai.types.chat.chat_completion_chunk import (
|
||||
ChoiceDelta as OpenAIChoiceDelta,
|
||||
)
|
||||
from openai.types.chat.chat_completion_chunk import (
|
||||
ChoiceDeltaToolCall as OpenAIChoiceDeltaToolCall,
|
||||
)
|
||||
from openai.types.chat.chat_completion_chunk import (
|
||||
ChoiceDeltaToolCallFunction as OpenAIChoiceDeltaToolCallFunction,
|
||||
)
|
||||
from openai.types.model import Model as OpenAIModel
|
||||
|
||||
from llama_stack.apis.inference import (
|
||||
ChatCompletionRequest,
|
||||
ChatCompletionResponseEventType,
|
||||
OpenAIAssistantMessageParam,
|
||||
OpenAIChatCompletion,
|
||||
OpenAIChoice,
|
||||
ToolChoice,
|
||||
UserMessage,
|
||||
)
|
||||
from llama_stack.apis.models import Model
|
||||
from llama_stack.models.llama.datatypes import StopReason
|
||||
from llama_stack.providers.datatypes import HealthStatus
|
||||
from llama_stack.providers.remote.inference.vllm.config import VLLMInferenceAdapterConfig
|
||||
from llama_stack.providers.remote.inference.vllm.vllm import (
|
||||
VLLMInferenceAdapter,
|
||||
_process_vllm_chat_completion_stream_response,
|
||||
)
|
||||
from llama_stack.providers.remote.inference.vllm.vllm import VLLMInferenceAdapter
|
||||
|
||||
# These are unit test for the remote vllm provider
|
||||
# implementation. This should only contain tests which are specific to
|
||||
|
|
@ -56,37 +32,15 @@ from llama_stack.providers.remote.inference.vllm.vllm import (
|
|||
# -v -s --tb=short --disable-warnings
|
||||
|
||||
|
||||
@pytest.fixture(scope="module")
|
||||
def mock_openai_models_list():
|
||||
with patch("openai.resources.models.AsyncModels.list") as mock_list:
|
||||
yield mock_list
|
||||
|
||||
|
||||
@pytest.fixture(scope="function")
|
||||
async def vllm_inference_adapter():
|
||||
config = VLLMInferenceAdapterConfig(url="http://mocked.localhost:12345")
|
||||
inference_adapter = VLLMInferenceAdapter(config)
|
||||
inference_adapter = VLLMInferenceAdapter(config=config)
|
||||
inference_adapter.model_store = AsyncMock()
|
||||
# Mock the __provider_spec__ attribute that would normally be set by the resolver
|
||||
inference_adapter.__provider_spec__ = MagicMock()
|
||||
inference_adapter.__provider_spec__.provider_type = "vllm-inference"
|
||||
inference_adapter.__provider_spec__.provider_data_validator = MagicMock()
|
||||
await inference_adapter.initialize()
|
||||
return inference_adapter
|
||||
|
||||
|
||||
async def test_register_model_checks_vllm(mock_openai_models_list, vllm_inference_adapter):
|
||||
async def mock_openai_models():
|
||||
yield OpenAIModel(id="foo", created=1, object="model", owned_by="test")
|
||||
|
||||
mock_openai_models_list.return_value = mock_openai_models()
|
||||
|
||||
foo_model = Model(identifier="foo", provider_resource_id="foo", provider_id="vllm-inference")
|
||||
|
||||
await vllm_inference_adapter.register_model(foo_model)
|
||||
mock_openai_models_list.assert_called()
|
||||
|
||||
|
||||
async def test_old_vllm_tool_choice(vllm_inference_adapter):
|
||||
"""
|
||||
Test that we set tool_choice to none when no tools are in use
|
||||
|
|
@ -115,403 +69,6 @@ async def test_old_vllm_tool_choice(vllm_inference_adapter):
|
|||
assert call_args.kwargs["tool_choice"] == ToolChoice.none.value
|
||||
|
||||
|
||||
async def test_tool_call_delta_empty_tool_call_buf():
|
||||
"""
|
||||
Test that we don't generate extra chunks when processing a
|
||||
tool call response that didn't call any tools. Previously we would
|
||||
emit chunks with spurious ToolCallParseStatus.succeeded or
|
||||
ToolCallParseStatus.failed when processing chunks that didn't
|
||||
actually make any tool calls.
|
||||
"""
|
||||
|
||||
async def mock_stream():
|
||||
delta = OpenAIChoiceDelta(content="", tool_calls=None)
|
||||
choices = [OpenAIChoiceChunk(delta=delta, finish_reason="stop", index=0)]
|
||||
mock_chunk = OpenAIChatCompletionChunk(
|
||||
id="chunk-1",
|
||||
created=1,
|
||||
model="foo",
|
||||
object="chat.completion.chunk",
|
||||
choices=choices,
|
||||
)
|
||||
for chunk in [mock_chunk]:
|
||||
yield chunk
|
||||
|
||||
chunks = [chunk async for chunk in _process_vllm_chat_completion_stream_response(mock_stream())]
|
||||
assert len(chunks) == 2
|
||||
assert chunks[0].event.event_type.value == "start"
|
||||
assert chunks[1].event.event_type.value == "complete"
|
||||
assert chunks[1].event.stop_reason == StopReason.end_of_turn
|
||||
|
||||
|
||||
async def test_tool_call_delta_streaming_arguments_dict():
|
||||
async def mock_stream():
|
||||
mock_chunk_1 = OpenAIChatCompletionChunk(
|
||||
id="chunk-1",
|
||||
created=1,
|
||||
model="foo",
|
||||
object="chat.completion.chunk",
|
||||
choices=[
|
||||
OpenAIChoiceChunk(
|
||||
delta=OpenAIChoiceDelta(
|
||||
content="",
|
||||
tool_calls=[
|
||||
OpenAIChoiceDeltaToolCall(
|
||||
id="tc_1",
|
||||
index=1,
|
||||
function=OpenAIChoiceDeltaToolCallFunction(
|
||||
name="power",
|
||||
arguments="",
|
||||
),
|
||||
)
|
||||
],
|
||||
),
|
||||
finish_reason=None,
|
||||
index=0,
|
||||
)
|
||||
],
|
||||
)
|
||||
mock_chunk_2 = OpenAIChatCompletionChunk(
|
||||
id="chunk-2",
|
||||
created=1,
|
||||
model="foo",
|
||||
object="chat.completion.chunk",
|
||||
choices=[
|
||||
OpenAIChoiceChunk(
|
||||
delta=OpenAIChoiceDelta(
|
||||
content="",
|
||||
tool_calls=[
|
||||
OpenAIChoiceDeltaToolCall(
|
||||
id="tc_1",
|
||||
index=1,
|
||||
function=OpenAIChoiceDeltaToolCallFunction(
|
||||
name="power",
|
||||
arguments='{"number": 28, "power": 3}',
|
||||
),
|
||||
)
|
||||
],
|
||||
),
|
||||
finish_reason=None,
|
||||
index=0,
|
||||
)
|
||||
],
|
||||
)
|
||||
mock_chunk_3 = OpenAIChatCompletionChunk(
|
||||
id="chunk-3",
|
||||
created=1,
|
||||
model="foo",
|
||||
object="chat.completion.chunk",
|
||||
choices=[
|
||||
OpenAIChoiceChunk(
|
||||
delta=OpenAIChoiceDelta(content="", tool_calls=None), finish_reason="tool_calls", index=0
|
||||
)
|
||||
],
|
||||
)
|
||||
for chunk in [mock_chunk_1, mock_chunk_2, mock_chunk_3]:
|
||||
yield chunk
|
||||
|
||||
chunks = [chunk async for chunk in _process_vllm_chat_completion_stream_response(mock_stream())]
|
||||
assert len(chunks) == 3
|
||||
assert chunks[0].event.event_type.value == "start"
|
||||
assert chunks[1].event.event_type.value == "progress"
|
||||
assert chunks[1].event.delta.type == "tool_call"
|
||||
assert chunks[1].event.delta.parse_status.value == "succeeded"
|
||||
assert chunks[1].event.delta.tool_call.arguments == '{"number": 28, "power": 3}'
|
||||
assert chunks[2].event.event_type.value == "complete"
|
||||
|
||||
|
||||
async def test_multiple_tool_calls():
|
||||
async def mock_stream():
|
||||
mock_chunk_1 = OpenAIChatCompletionChunk(
|
||||
id="chunk-1",
|
||||
created=1,
|
||||
model="foo",
|
||||
object="chat.completion.chunk",
|
||||
choices=[
|
||||
OpenAIChoiceChunk(
|
||||
delta=OpenAIChoiceDelta(
|
||||
content="",
|
||||
tool_calls=[
|
||||
OpenAIChoiceDeltaToolCall(
|
||||
id="",
|
||||
index=1,
|
||||
function=OpenAIChoiceDeltaToolCallFunction(
|
||||
name="power",
|
||||
arguments='{"number": 28, "power": 3}',
|
||||
),
|
||||
),
|
||||
],
|
||||
),
|
||||
finish_reason=None,
|
||||
index=0,
|
||||
)
|
||||
],
|
||||
)
|
||||
mock_chunk_2 = OpenAIChatCompletionChunk(
|
||||
id="chunk-2",
|
||||
created=1,
|
||||
model="foo",
|
||||
object="chat.completion.chunk",
|
||||
choices=[
|
||||
OpenAIChoiceChunk(
|
||||
delta=OpenAIChoiceDelta(
|
||||
content="",
|
||||
tool_calls=[
|
||||
OpenAIChoiceDeltaToolCall(
|
||||
id="",
|
||||
index=2,
|
||||
function=OpenAIChoiceDeltaToolCallFunction(
|
||||
name="multiple",
|
||||
arguments='{"first_number": 4, "second_number": 7}',
|
||||
),
|
||||
),
|
||||
],
|
||||
),
|
||||
finish_reason=None,
|
||||
index=0,
|
||||
)
|
||||
],
|
||||
)
|
||||
mock_chunk_3 = OpenAIChatCompletionChunk(
|
||||
id="chunk-3",
|
||||
created=1,
|
||||
model="foo",
|
||||
object="chat.completion.chunk",
|
||||
choices=[
|
||||
OpenAIChoiceChunk(
|
||||
delta=OpenAIChoiceDelta(content="", tool_calls=None), finish_reason="tool_calls", index=0
|
||||
)
|
||||
],
|
||||
)
|
||||
for chunk in [mock_chunk_1, mock_chunk_2, mock_chunk_3]:
|
||||
yield chunk
|
||||
|
||||
chunks = [chunk async for chunk in _process_vllm_chat_completion_stream_response(mock_stream())]
|
||||
assert len(chunks) == 4
|
||||
assert chunks[0].event.event_type.value == "start"
|
||||
assert chunks[1].event.event_type.value == "progress"
|
||||
assert chunks[1].event.delta.type == "tool_call"
|
||||
assert chunks[1].event.delta.parse_status.value == "succeeded"
|
||||
assert chunks[1].event.delta.tool_call.arguments == '{"number": 28, "power": 3}'
|
||||
assert chunks[2].event.event_type.value == "progress"
|
||||
assert chunks[2].event.delta.type == "tool_call"
|
||||
assert chunks[2].event.delta.parse_status.value == "succeeded"
|
||||
assert chunks[2].event.delta.tool_call.arguments == '{"first_number": 4, "second_number": 7}'
|
||||
assert chunks[3].event.event_type.value == "complete"
|
||||
|
||||
|
||||
async def test_process_vllm_chat_completion_stream_response_no_choices():
|
||||
"""
|
||||
Test that we don't error out when vLLM returns no choices for a
|
||||
completion request. This can happen when there's an error thrown
|
||||
in vLLM for example.
|
||||
"""
|
||||
|
||||
async def mock_stream():
|
||||
choices = []
|
||||
mock_chunk = OpenAIChatCompletionChunk(
|
||||
id="chunk-1",
|
||||
created=1,
|
||||
model="foo",
|
||||
object="chat.completion.chunk",
|
||||
choices=choices,
|
||||
)
|
||||
for chunk in [mock_chunk]:
|
||||
yield chunk
|
||||
|
||||
chunks = [chunk async for chunk in _process_vllm_chat_completion_stream_response(mock_stream())]
|
||||
assert len(chunks) == 1
|
||||
assert chunks[0].event.event_type.value == "start"
|
||||
|
||||
|
||||
async def test_get_params_empty_tools(vllm_inference_adapter):
|
||||
request = ChatCompletionRequest(
|
||||
tools=[],
|
||||
model="test_model",
|
||||
messages=[UserMessage(content="test")],
|
||||
)
|
||||
params = await vllm_inference_adapter._get_params(request)
|
||||
assert "tools" not in params
|
||||
|
||||
|
||||
async def test_process_vllm_chat_completion_stream_response_tool_call_args_last_chunk():
|
||||
"""
|
||||
Tests the edge case where the model returns the arguments for the tool call in the same chunk that
|
||||
contains the finish reason (i.e., the last one).
|
||||
We want to make sure the tool call is executed in this case, and the parameters are passed correctly.
|
||||
"""
|
||||
|
||||
mock_tool_name = "mock_tool"
|
||||
mock_tool_arguments = {"arg1": 0, "arg2": 100}
|
||||
mock_tool_arguments_str = json.dumps(mock_tool_arguments)
|
||||
|
||||
async def mock_stream():
|
||||
mock_chunks = [
|
||||
OpenAIChatCompletionChunk(
|
||||
id="chunk-1",
|
||||
created=1,
|
||||
model="foo",
|
||||
object="chat.completion.chunk",
|
||||
choices=[
|
||||
{
|
||||
"delta": {
|
||||
"content": None,
|
||||
"tool_calls": [
|
||||
{
|
||||
"index": 0,
|
||||
"id": "mock_id",
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": mock_tool_name,
|
||||
"arguments": None,
|
||||
},
|
||||
}
|
||||
],
|
||||
},
|
||||
"finish_reason": None,
|
||||
"logprobs": None,
|
||||
"index": 0,
|
||||
}
|
||||
],
|
||||
),
|
||||
OpenAIChatCompletionChunk(
|
||||
id="chunk-1",
|
||||
created=1,
|
||||
model="foo",
|
||||
object="chat.completion.chunk",
|
||||
choices=[
|
||||
{
|
||||
"delta": {
|
||||
"content": None,
|
||||
"tool_calls": [
|
||||
{
|
||||
"index": 0,
|
||||
"id": None,
|
||||
"function": {
|
||||
"name": None,
|
||||
"arguments": mock_tool_arguments_str,
|
||||
},
|
||||
}
|
||||
],
|
||||
},
|
||||
"finish_reason": "tool_calls",
|
||||
"logprobs": None,
|
||||
"index": 0,
|
||||
}
|
||||
],
|
||||
),
|
||||
]
|
||||
for chunk in mock_chunks:
|
||||
yield chunk
|
||||
|
||||
chunks = [chunk async for chunk in _process_vllm_chat_completion_stream_response(mock_stream())]
|
||||
assert len(chunks) == 3
|
||||
assert chunks[-1].event.event_type == ChatCompletionResponseEventType.complete
|
||||
assert chunks[-2].event.delta.type == "tool_call"
|
||||
assert chunks[-2].event.delta.tool_call.tool_name == mock_tool_name
|
||||
assert chunks[-2].event.delta.tool_call.arguments == mock_tool_arguments_str
|
||||
|
||||
|
||||
async def test_process_vllm_chat_completion_stream_response_no_finish_reason():
|
||||
"""
|
||||
Tests the edge case where the model requests a tool call and stays idle without explicitly providing the
|
||||
finish reason.
|
||||
We want to make sure that this case is recognized and handled correctly, i.e., as a valid end of message.
|
||||
"""
|
||||
|
||||
mock_tool_name = "mock_tool"
|
||||
mock_tool_arguments = {"arg1": 0, "arg2": 100}
|
||||
mock_tool_arguments_str = json.dumps(mock_tool_arguments)
|
||||
|
||||
async def mock_stream():
|
||||
mock_chunks = [
|
||||
OpenAIChatCompletionChunk(
|
||||
id="chunk-1",
|
||||
created=1,
|
||||
model="foo",
|
||||
object="chat.completion.chunk",
|
||||
choices=[
|
||||
{
|
||||
"delta": {
|
||||
"content": None,
|
||||
"tool_calls": [
|
||||
{
|
||||
"index": 0,
|
||||
"id": "mock_id",
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": mock_tool_name,
|
||||
"arguments": mock_tool_arguments_str,
|
||||
},
|
||||
}
|
||||
],
|
||||
},
|
||||
"finish_reason": None,
|
||||
"logprobs": None,
|
||||
"index": 0,
|
||||
}
|
||||
],
|
||||
),
|
||||
]
|
||||
for chunk in mock_chunks:
|
||||
yield chunk
|
||||
|
||||
chunks = [chunk async for chunk in _process_vllm_chat_completion_stream_response(mock_stream())]
|
||||
assert len(chunks) == 3
|
||||
assert chunks[-1].event.event_type == ChatCompletionResponseEventType.complete
|
||||
assert chunks[-2].event.delta.type == "tool_call"
|
||||
assert chunks[-2].event.delta.tool_call.tool_name == mock_tool_name
|
||||
assert chunks[-2].event.delta.tool_call.arguments == mock_tool_arguments_str
|
||||
|
||||
|
||||
async def test_process_vllm_chat_completion_stream_response_tool_without_args():
|
||||
"""
|
||||
Tests the edge case where no arguments are provided for the tool call.
|
||||
Tool calls with no arguments should be treated as regular tool calls, which was not the case until now.
|
||||
"""
|
||||
mock_tool_name = "mock_tool"
|
||||
|
||||
async def mock_stream():
|
||||
mock_chunks = [
|
||||
OpenAIChatCompletionChunk(
|
||||
id="chunk-1",
|
||||
created=1,
|
||||
model="foo",
|
||||
object="chat.completion.chunk",
|
||||
choices=[
|
||||
{
|
||||
"delta": {
|
||||
"content": None,
|
||||
"tool_calls": [
|
||||
{
|
||||
"index": 0,
|
||||
"id": "mock_id",
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": mock_tool_name,
|
||||
"arguments": "",
|
||||
},
|
||||
}
|
||||
],
|
||||
},
|
||||
"finish_reason": None,
|
||||
"logprobs": None,
|
||||
"index": 0,
|
||||
}
|
||||
],
|
||||
),
|
||||
]
|
||||
for chunk in mock_chunks:
|
||||
yield chunk
|
||||
|
||||
chunks = [chunk async for chunk in _process_vllm_chat_completion_stream_response(mock_stream())]
|
||||
assert len(chunks) == 3
|
||||
assert chunks[-1].event.event_type == ChatCompletionResponseEventType.complete
|
||||
assert chunks[-2].event.delta.type == "tool_call"
|
||||
assert chunks[-2].event.delta.tool_call.tool_name == mock_tool_name
|
||||
assert chunks[-2].event.delta.tool_call.arguments == "{}"
|
||||
|
||||
|
||||
async def test_health_status_success(vllm_inference_adapter):
|
||||
"""
|
||||
Test the health method of VLLM InferenceAdapter when the connection is successful.
|
||||
|
|
@ -642,94 +199,30 @@ async def test_should_refresh_models():
|
|||
|
||||
# Test case 1: refresh_models is True, api_token is None
|
||||
config1 = VLLMInferenceAdapterConfig(url="http://test.localhost", api_token=None, refresh_models=True)
|
||||
adapter1 = VLLMInferenceAdapter(config1)
|
||||
adapter1 = VLLMInferenceAdapter(config=config1)
|
||||
result1 = await adapter1.should_refresh_models()
|
||||
assert result1 is True, "should_refresh_models should return True when refresh_models is True"
|
||||
|
||||
# Test case 2: refresh_models is True, api_token is empty string
|
||||
config2 = VLLMInferenceAdapterConfig(url="http://test.localhost", api_token="", refresh_models=True)
|
||||
adapter2 = VLLMInferenceAdapter(config2)
|
||||
adapter2 = VLLMInferenceAdapter(config=config2)
|
||||
result2 = await adapter2.should_refresh_models()
|
||||
assert result2 is True, "should_refresh_models should return True when refresh_models is True"
|
||||
|
||||
# Test case 3: refresh_models is True, api_token is "fake" (default)
|
||||
config3 = VLLMInferenceAdapterConfig(url="http://test.localhost", api_token="fake", refresh_models=True)
|
||||
adapter3 = VLLMInferenceAdapter(config3)
|
||||
adapter3 = VLLMInferenceAdapter(config=config3)
|
||||
result3 = await adapter3.should_refresh_models()
|
||||
assert result3 is True, "should_refresh_models should return True when refresh_models is True"
|
||||
|
||||
# Test case 4: refresh_models is True, api_token is real token
|
||||
config4 = VLLMInferenceAdapterConfig(url="http://test.localhost", api_token="real-token-123", refresh_models=True)
|
||||
adapter4 = VLLMInferenceAdapter(config4)
|
||||
adapter4 = VLLMInferenceAdapter(config=config4)
|
||||
result4 = await adapter4.should_refresh_models()
|
||||
assert result4 is True, "should_refresh_models should return True when refresh_models is True"
|
||||
|
||||
# Test case 5: refresh_models is False, api_token is real token
|
||||
config5 = VLLMInferenceAdapterConfig(url="http://test.localhost", api_token="real-token-456", refresh_models=False)
|
||||
adapter5 = VLLMInferenceAdapter(config5)
|
||||
adapter5 = VLLMInferenceAdapter(config=config5)
|
||||
result5 = await adapter5.should_refresh_models()
|
||||
assert result5 is False, "should_refresh_models should return False when refresh_models is False"
|
||||
|
||||
|
||||
async def test_provider_data_var_context_propagation(vllm_inference_adapter):
|
||||
"""
|
||||
Test that PROVIDER_DATA_VAR context is properly propagated through the vLLM inference adapter.
|
||||
This ensures that dynamic provider data (like API tokens) can be passed through context.
|
||||
Note: The base URL is always taken from config.url, not from provider data.
|
||||
"""
|
||||
# Mock the AsyncOpenAI class to capture provider data
|
||||
with (
|
||||
patch("llama_stack.providers.utils.inference.openai_mixin.AsyncOpenAI") as mock_openai_class,
|
||||
patch.object(vllm_inference_adapter, "get_request_provider_data") as mock_get_provider_data,
|
||||
):
|
||||
mock_client = AsyncMock()
|
||||
mock_client.chat.completions.create = AsyncMock()
|
||||
mock_openai_class.return_value = mock_client
|
||||
|
||||
# Mock provider data to return test data
|
||||
mock_provider_data = MagicMock()
|
||||
mock_provider_data.vllm_api_token = "test-token-123"
|
||||
mock_provider_data.vllm_url = "http://test-server:8000/v1"
|
||||
mock_get_provider_data.return_value = mock_provider_data
|
||||
|
||||
# Mock the model
|
||||
mock_model = Model(identifier="test-model", provider_resource_id="test-model", provider_id="vllm-inference")
|
||||
vllm_inference_adapter.model_store.get_model.return_value = mock_model
|
||||
|
||||
try:
|
||||
# Execute chat completion
|
||||
await vllm_inference_adapter.openai_chat_completion(
|
||||
model="test-model",
|
||||
messages=[UserMessage(content="Hello")],
|
||||
stream=False,
|
||||
)
|
||||
|
||||
# Verify that ALL client calls were made with the correct parameters
|
||||
calls = mock_openai_class.call_args_list
|
||||
incorrect_calls = []
|
||||
|
||||
for i, call in enumerate(calls):
|
||||
api_key = call[1]["api_key"]
|
||||
base_url = call[1]["base_url"]
|
||||
|
||||
if api_key != "test-token-123" or base_url != "http://mocked.localhost:12345":
|
||||
incorrect_calls.append({"call_index": i, "api_key": api_key, "base_url": base_url})
|
||||
|
||||
if incorrect_calls:
|
||||
error_msg = (
|
||||
f"Found {len(incorrect_calls)} calls with incorrect parameters out of {len(calls)} total calls:\n"
|
||||
)
|
||||
for incorrect_call in incorrect_calls:
|
||||
error_msg += f" Call {incorrect_call['call_index']}: api_key='{incorrect_call['api_key']}', base_url='{incorrect_call['base_url']}'\n"
|
||||
error_msg += "Expected: api_key='test-token-123', base_url='http://mocked.localhost:12345'"
|
||||
raise AssertionError(error_msg)
|
||||
|
||||
# Ensure at least one call was made
|
||||
assert len(calls) >= 1, "No AsyncOpenAI client calls were made"
|
||||
|
||||
# Verify that chat completion was called
|
||||
mock_client.chat.completions.create.assert_called_once()
|
||||
|
||||
finally:
|
||||
# Clean up context
|
||||
pass
|
||||
|
|
|
|||
|
|
@ -5,6 +5,7 @@
|
|||
# the root directory of this source tree.
|
||||
|
||||
import json
|
||||
from collections.abc import Iterable
|
||||
from unittest.mock import AsyncMock, MagicMock, Mock, PropertyMock, patch
|
||||
|
||||
import pytest
|
||||
|
|
@ -13,6 +14,7 @@ from pydantic import BaseModel, Field
|
|||
from llama_stack.apis.inference import Model, OpenAIUserMessageParam
|
||||
from llama_stack.apis.models import ModelType
|
||||
from llama_stack.core.request_headers import request_provider_data_context
|
||||
from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
|
||||
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
|
||||
|
||||
|
||||
|
|
@ -29,7 +31,7 @@ class OpenAIMixinImpl(OpenAIMixin):
|
|||
class OpenAIMixinWithEmbeddingsImpl(OpenAIMixinImpl):
|
||||
"""Test implementation with embedding model metadata"""
|
||||
|
||||
embedding_model_metadata = {
|
||||
embedding_model_metadata: dict[str, dict[str, int]] = {
|
||||
"text-embedding-3-small": {"embedding_dimension": 1536, "context_length": 8192},
|
||||
"text-embedding-ada-002": {"embedding_dimension": 1536, "context_length": 8192},
|
||||
}
|
||||
|
|
@ -38,7 +40,8 @@ class OpenAIMixinWithEmbeddingsImpl(OpenAIMixinImpl):
|
|||
@pytest.fixture
|
||||
def mixin():
|
||||
"""Create a test instance of OpenAIMixin with mocked model_store"""
|
||||
mixin_instance = OpenAIMixinImpl()
|
||||
config = RemoteInferenceProviderConfig()
|
||||
mixin_instance = OpenAIMixinImpl(config=config)
|
||||
|
||||
# just enough to satisfy _get_provider_model_id calls
|
||||
mock_model_store = MagicMock()
|
||||
|
|
@ -53,7 +56,8 @@ def mixin():
|
|||
@pytest.fixture
|
||||
def mixin_with_embeddings():
|
||||
"""Create a test instance of OpenAIMixin with embedding model metadata"""
|
||||
return OpenAIMixinWithEmbeddingsImpl()
|
||||
config = RemoteInferenceProviderConfig()
|
||||
return OpenAIMixinWithEmbeddingsImpl(config=config)
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
|
|
@ -498,13 +502,296 @@ class OpenAIMixinWithProviderData(OpenAIMixinImpl):
|
|||
return "default-base-url"
|
||||
|
||||
|
||||
class OpenAIMixinWithCustomGetModels(OpenAIMixinImpl):
|
||||
"""Test implementation with custom get_models override"""
|
||||
|
||||
def __init__(self, config, custom_model_ids):
|
||||
super().__init__(config=config)
|
||||
self._custom_model_ids = custom_model_ids
|
||||
|
||||
async def get_models(self) -> Iterable[str] | None:
|
||||
"""Return custom model IDs list"""
|
||||
return self._custom_model_ids
|
||||
|
||||
|
||||
class TestOpenAIMixinCustomGetModels:
|
||||
"""Test cases for custom get_models() implementation functionality"""
|
||||
|
||||
@pytest.fixture
|
||||
def custom_model_ids_list(self):
|
||||
"""Create a list of custom model ID strings"""
|
||||
return ["custom-model-1", "custom-model-2", "custom-embedding"]
|
||||
|
||||
@pytest.fixture
|
||||
def mixin_with_custom_get_models(self, custom_model_ids_list):
|
||||
"""Create mixin instance with custom get_models implementation"""
|
||||
config = RemoteInferenceProviderConfig()
|
||||
mixin = OpenAIMixinWithCustomGetModels(config=config, custom_model_ids=custom_model_ids_list)
|
||||
# Add embedding metadata to test that feature still works
|
||||
mixin.embedding_model_metadata = {"custom-embedding": {"embedding_dimension": 768, "context_length": 512}}
|
||||
return mixin
|
||||
|
||||
async def test_custom_get_models_is_used(self, mixin_with_custom_get_models, custom_model_ids_list):
|
||||
"""Test that custom get_models() implementation is used instead of client.models.list()"""
|
||||
result = await mixin_with_custom_get_models.list_models()
|
||||
|
||||
assert result is not None
|
||||
assert len(result) == 3
|
||||
|
||||
# Verify all custom models are present
|
||||
identifiers = {m.identifier for m in result}
|
||||
assert "custom-model-1" in identifiers
|
||||
assert "custom-model-2" in identifiers
|
||||
assert "custom-embedding" in identifiers
|
||||
|
||||
async def test_custom_get_models_populates_cache(self, mixin_with_custom_get_models):
|
||||
"""Test that custom get_models() results are cached"""
|
||||
assert len(mixin_with_custom_get_models._model_cache) == 0
|
||||
|
||||
await mixin_with_custom_get_models.list_models()
|
||||
|
||||
assert len(mixin_with_custom_get_models._model_cache) == 3
|
||||
assert "custom-model-1" in mixin_with_custom_get_models._model_cache
|
||||
assert "custom-model-2" in mixin_with_custom_get_models._model_cache
|
||||
assert "custom-embedding" in mixin_with_custom_get_models._model_cache
|
||||
|
||||
async def test_custom_get_models_respects_allowed_models(self):
|
||||
"""Test that custom get_models() respects allowed_models filtering"""
|
||||
config = RemoteInferenceProviderConfig()
|
||||
mixin = OpenAIMixinWithCustomGetModels(config=config, custom_model_ids=["model-1", "model-2", "model-3"])
|
||||
mixin.allowed_models = ["model-1"]
|
||||
|
||||
result = await mixin.list_models()
|
||||
|
||||
assert result is not None
|
||||
assert len(result) == 1
|
||||
assert result[0].identifier == "model-1"
|
||||
|
||||
async def test_custom_get_models_with_embedding_metadata(self, mixin_with_custom_get_models):
|
||||
"""Test that custom get_models() works with embedding_model_metadata"""
|
||||
result = await mixin_with_custom_get_models.list_models()
|
||||
|
||||
# Find the embedding model
|
||||
embedding_model = next((m for m in result if m.identifier == "custom-embedding"), None)
|
||||
assert embedding_model is not None
|
||||
assert embedding_model.model_type == ModelType.embedding
|
||||
assert embedding_model.metadata == {"embedding_dimension": 768, "context_length": 512}
|
||||
|
||||
# Verify LLM models
|
||||
llm_models = [m for m in result if m.model_type == ModelType.llm]
|
||||
assert len(llm_models) == 2
|
||||
|
||||
async def test_custom_get_models_with_empty_list(self, mock_client_with_empty_models, mock_client_context):
|
||||
"""Test that custom get_models() handles empty list correctly"""
|
||||
config = RemoteInferenceProviderConfig()
|
||||
mixin = OpenAIMixinWithCustomGetModels(config=config, custom_model_ids=[])
|
||||
|
||||
# Empty list from get_models() falls back to client.models.list()
|
||||
with mock_client_context(mixin, mock_client_with_empty_models):
|
||||
result = await mixin.list_models()
|
||||
|
||||
assert result is not None
|
||||
assert len(result) == 0
|
||||
assert len(mixin._model_cache) == 0
|
||||
|
||||
async def test_default_get_models_returns_none(self, mixin):
|
||||
"""Test that default get_models() implementation returns None"""
|
||||
custom_models = await mixin.get_models()
|
||||
assert custom_models is None
|
||||
|
||||
async def test_fallback_to_client_when_get_models_returns_none(
|
||||
self, mixin, mock_client_with_models, mock_client_context
|
||||
):
|
||||
"""Test that when get_models() returns None, falls back to client.models.list()"""
|
||||
# Default get_models() returns None, so should use client
|
||||
with mock_client_context(mixin, mock_client_with_models):
|
||||
result = await mixin.list_models()
|
||||
|
||||
assert result is not None
|
||||
assert len(result) == 3
|
||||
mock_client_with_models.models.list.assert_called_once()
|
||||
|
||||
async def test_custom_get_models_creates_proper_model_objects(self):
|
||||
"""Test that custom get_models() model IDs are converted to proper Model objects"""
|
||||
config = RemoteInferenceProviderConfig()
|
||||
model_ids = ["gpt-4", "gpt-3.5-turbo"]
|
||||
mixin = OpenAIMixinWithCustomGetModels(config=config, custom_model_ids=model_ids)
|
||||
|
||||
result = await mixin.list_models()
|
||||
|
||||
assert result is not None
|
||||
assert len(result) == 2
|
||||
|
||||
for model in result:
|
||||
assert isinstance(model, Model)
|
||||
assert model.provider_id == "test-provider"
|
||||
assert model.identifier in model_ids
|
||||
assert model.provider_resource_id in model_ids
|
||||
assert model.model_type == ModelType.llm
|
||||
|
||||
async def test_custom_get_models_bypasses_client(self, mock_client_context):
|
||||
"""Test that providing get_models() means client.models.list() is NOT called"""
|
||||
config = RemoteInferenceProviderConfig()
|
||||
mixin = OpenAIMixinWithCustomGetModels(config=config, custom_model_ids=["model-1", "model-2"])
|
||||
|
||||
# Create a mock client that should NOT be called
|
||||
mock_client = MagicMock()
|
||||
mock_client.models.list = MagicMock(side_effect=AssertionError("client.models.list should not be called!"))
|
||||
|
||||
with mock_client_context(mixin, mock_client):
|
||||
result = await mixin.list_models()
|
||||
|
||||
# Should succeed without calling client.models.list
|
||||
assert result is not None
|
||||
assert len(result) == 2
|
||||
mock_client.models.list.assert_not_called()
|
||||
|
||||
async def test_get_models_wrong_type_raises_error(self):
|
||||
"""Test that get_models() returning non-string items results in an error"""
|
||||
|
||||
class BadGetModelsAdapter(OpenAIMixinImpl):
|
||||
async def get_models(self) -> Iterable[str] | None:
|
||||
# Return list with non-string items
|
||||
return [["nested", "list"], {"key": "value"}] # type: ignore
|
||||
|
||||
config = RemoteInferenceProviderConfig()
|
||||
mixin = BadGetModelsAdapter(config=config)
|
||||
|
||||
# Should raise ValueError for non-string model ID
|
||||
with pytest.raises(ValueError, match="Model ID .* from get_models\\(\\) is not a string"):
|
||||
await mixin.list_models()
|
||||
|
||||
async def test_get_models_non_iterable_raises_error(self):
|
||||
"""Test that get_models() returning non-iterable type raises error"""
|
||||
|
||||
class NonIterableGetModelsAdapter(OpenAIMixinImpl):
|
||||
async def get_models(self) -> Iterable[str] | None:
|
||||
# Return non-iterable type
|
||||
return 42 # type: ignore
|
||||
|
||||
config = RemoteInferenceProviderConfig()
|
||||
mixin = NonIterableGetModelsAdapter(config=config)
|
||||
|
||||
# Should raise TypeError when trying to convert to list
|
||||
with pytest.raises(TypeError, match="'int' object is not iterable"):
|
||||
await mixin.list_models()
|
||||
|
||||
async def test_get_models_with_none_items_raises_error(self):
|
||||
"""Test that get_models() returning list with None items causes error"""
|
||||
|
||||
class NoneItemsAdapter(OpenAIMixinImpl):
|
||||
async def get_models(self) -> Iterable[str] | None:
|
||||
# Return list with None items
|
||||
return [None, "valid-model", None] # type: ignore
|
||||
|
||||
config = RemoteInferenceProviderConfig()
|
||||
mixin = NoneItemsAdapter(config=config)
|
||||
|
||||
# Should raise ValueError for non-string model ID
|
||||
with pytest.raises(ValueError, match="Model ID .* from get_models\\(\\) is not a string"):
|
||||
await mixin.list_models()
|
||||
|
||||
async def test_get_models_with_non_string_items_raises_error(self):
|
||||
"""Test that get_models() returning non-string items raises ValueError"""
|
||||
|
||||
class NonStringItemsAdapter(OpenAIMixinImpl):
|
||||
async def get_models(self) -> Iterable[str] | None:
|
||||
# Return list with non-string items (integers)
|
||||
return ["valid-model", 123, "another-model"] # type: ignore
|
||||
|
||||
config = RemoteInferenceProviderConfig()
|
||||
mixin = NonStringItemsAdapter(config=config)
|
||||
|
||||
# Should raise ValueError for non-string model ID
|
||||
with pytest.raises(ValueError, match="Model ID 123 from get_models\\(\\) is not a string"):
|
||||
await mixin.list_models()
|
||||
|
||||
async def test_embedding_models_from_custom_get_models_have_correct_type(self, mixin_with_custom_get_models):
|
||||
"""Test that embedding models from custom get_models() are properly typed as embedding"""
|
||||
result = await mixin_with_custom_get_models.list_models()
|
||||
|
||||
# Verify we have both LLM and embedding models
|
||||
llm_models = [m for m in result if m.model_type == ModelType.llm]
|
||||
embedding_models = [m for m in result if m.model_type == ModelType.embedding]
|
||||
|
||||
assert len(llm_models) == 2
|
||||
assert len(embedding_models) == 1
|
||||
assert embedding_models[0].identifier == "custom-embedding"
|
||||
|
||||
async def test_llm_models_from_custom_get_models_have_correct_type(self):
|
||||
"""Test that LLM models from custom get_models() are properly typed as llm"""
|
||||
config = RemoteInferenceProviderConfig()
|
||||
mixin = OpenAIMixinWithCustomGetModels(config=config, custom_model_ids=["gpt-4", "claude-3"])
|
||||
|
||||
result = await mixin.list_models()
|
||||
|
||||
assert result is not None
|
||||
assert len(result) == 2
|
||||
for model in result:
|
||||
assert model.model_type == ModelType.llm
|
||||
|
||||
async def test_get_models_accepts_various_iterables(self):
|
||||
"""Test that get_models() accepts tuples, sets, generators, etc."""
|
||||
|
||||
# Test with tuple
|
||||
class TupleGetModelsAdapter(OpenAIMixinImpl):
|
||||
async def get_models(self) -> Iterable[str] | None:
|
||||
return ("model-1", "model-2", "model-3")
|
||||
|
||||
config = RemoteInferenceProviderConfig()
|
||||
mixin = TupleGetModelsAdapter(config=config)
|
||||
result = await mixin.list_models()
|
||||
assert result is not None
|
||||
assert len(result) == 3
|
||||
|
||||
# Test with generator
|
||||
class GeneratorGetModelsAdapter(OpenAIMixinImpl):
|
||||
async def get_models(self) -> Iterable[str] | None:
|
||||
def gen():
|
||||
yield "gen-model-1"
|
||||
yield "gen-model-2"
|
||||
|
||||
return gen()
|
||||
|
||||
mixin = GeneratorGetModelsAdapter(config=config)
|
||||
result = await mixin.list_models()
|
||||
assert result is not None
|
||||
assert len(result) == 2
|
||||
|
||||
# Test with set (order may vary)
|
||||
class SetGetModelsAdapter(OpenAIMixinImpl):
|
||||
async def get_models(self) -> Iterable[str] | None:
|
||||
return {"set-model-1", "set-model-2"}
|
||||
|
||||
mixin = SetGetModelsAdapter(config=config)
|
||||
result = await mixin.list_models()
|
||||
assert result is not None
|
||||
assert len(result) == 2
|
||||
|
||||
async def test_get_models_exception_propagates(self):
|
||||
"""Test that when get_models() raises an exception, it propagates to the caller"""
|
||||
|
||||
class FailingGetModelsAdapter(OpenAIMixinImpl):
|
||||
async def get_models(self) -> Iterable[str] | None:
|
||||
# Simulate an exception during custom model listing
|
||||
raise RuntimeError("Failed to fetch custom models")
|
||||
|
||||
config = RemoteInferenceProviderConfig()
|
||||
mixin = FailingGetModelsAdapter(config=config)
|
||||
|
||||
# Exception should propagate and not fall back to client.models.list()
|
||||
with pytest.raises(RuntimeError, match="Failed to fetch custom models"):
|
||||
await mixin.list_models()
|
||||
|
||||
|
||||
class TestOpenAIMixinProviderDataApiKey:
|
||||
"""Test cases for provider_data_api_key_field functionality"""
|
||||
|
||||
@pytest.fixture
|
||||
def mixin_with_provider_data_field(self):
|
||||
"""Mixin instance with provider_data_api_key_field set"""
|
||||
mixin_instance = OpenAIMixinWithProviderData()
|
||||
config = RemoteInferenceProviderConfig()
|
||||
mixin_instance = OpenAIMixinWithProviderData(config=config)
|
||||
|
||||
# Mock provider_spec for provider data validation
|
||||
mock_provider_spec = MagicMock()
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue