mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-15 06:37:58 +00:00
f50ce11a3b
Renames `inference_recorder.py` to `api_recorder.py` and extends it to support recording/replaying tool invocations in addition to inference calls. This allows us to record web-search, etc. tool calls and thereafter apply recordings for `tests/integration/responses` ## Test Plan ``` export OPENAI_API_KEY=... export TAVILY_SEARCH_API_KEY=... ./scripts/integration-tests.sh --stack-config ci-tests \ --suite responses --inference-mode record-if-missing ```
472 lines
17 KiB
JSON
472 lines
17 KiB
JSON
{
|
|
"test_id": "tests/integration/responses/test_tool_responses.py::test_response_non_streaming_web_search[client_with_models-txt=openai/gpt-4o-llama_experts]",
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "https://api.openai.com/v1/v1/chat/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "gpt-4o",
|
|
"messages": [
|
|
{
|
|
"role": "user",
|
|
"content": "How many experts does the Llama 4 Maverick model have?"
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "",
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": "call_L3lGnODCsLUEKEGSGeVI0Zyo",
|
|
"type": "function",
|
|
"function": {
|
|
"name": "web_search",
|
|
"arguments": "{\"query\":\"Llama 4 Maverick model number of experts\"}"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"tool_call_id": "call_L3lGnODCsLUEKEGSGeVI0Zyo",
|
|
"content": "{\"query\": \"Llama 4 Maverick model number of experts\", \"top_k\": [{\"url\": \"https://console.groq.com/docs/model/meta-llama/llama-4-maverick-17b-128e-instruct\", \"title\": \"Llama 4 Maverick 17B 128E\", \"content\": \"Llama 4 Maverick is Meta's natively multimodal model that enables text and image understanding. With a 17 billion parameter mixture-of-experts architecture (128 experts), this model offers industry-leading performance for multimodal tasks like natural assistant-like chat, image recognition, and coding tasks. Llama 4 Maverick features an auto-regressive language model that uses a mixture-of-experts (MoE) architecture with 17B activated parameters (400B total) and incorporates early fusion for native multimodality. The model uses 128 experts to efficiently handle both text and image inputs while maintaining high performance across chat, knowledge, and code generation tasks, with a knowledge cutoff of August 2024. * For multimodal applications, this model supports up to 5 image inputs create( model =\\\"meta-llama/llama-4-maverick-17b-128e-instruct\\\", messages =[ { \\\"role\\\": \\\"user\\\", \\\"content\\\": \\\"Explain why fast inference is critical for reasoning models\\\" } ] ) print(completion.\", \"score\": 0.9287263, \"raw_content\": null}, {\"url\": \"https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E\", \"title\": \"meta-llama/Llama-4-Maverick-17B-128E\", \"content\": \"... model with 16 experts, and Llama 4 Maverick, a 17 billion parameter model with 128 experts. Model developer: Meta. Model Architecture: The\", \"score\": 0.9183121, \"raw_content\": null}, {\"url\": \"https://build.nvidia.com/meta/llama-4-maverick-17b-128e-instruct/modelcard\", \"title\": \"llama-4-maverick-17b-128e-instruct Model by Meta\", \"content\": \"... model with 16 experts, and Llama 4 Maverick, a 17 billion parameter model with 128 experts. Third-Party Community Consideration. This model\", \"score\": 0.91399205, \"raw_content\": null}, {\"url\": \"https://replicate.com/meta/llama-4-maverick-instruct\", \"title\": \"meta/llama-4-maverick-instruct | Run with an API on ...\", \"content\": \"... model with 16 experts, and Llama 4 Maverick, a 17 billion parameter model with 128 experts. All services are online \\u00b7 Home \\u00b7 About \\u00b7 Changelog\", \"score\": 0.9073207, \"raw_content\": null}, {\"url\": \"https://openrouter.ai/meta-llama/llama-4-maverick\", \"title\": \"Llama 4 Maverick - API, Providers, Stats\", \"content\": \"# Meta: Llama 4 Maverick ### meta-llama/llama-4-maverick Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput. Llama 4 Maverick - API, Providers, Stats | OpenRouter ## Providers for Llama 4 Maverick ## Performance for Llama 4 Maverick ## Apps using Llama 4 Maverick ## Recent activity on Llama 4 Maverick ## Uptime stats for Llama 4 Maverick ## Sample code and API for Llama 4 Maverick\", \"score\": 0.8958969, \"raw_content\": null}]}"
|
|
}
|
|
],
|
|
"stream": true,
|
|
"tools": [
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "web_search",
|
|
"description": "Search the web for information",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"query": {
|
|
"type": "string",
|
|
"description": "The query to search for"
|
|
}
|
|
},
|
|
"required": [
|
|
"query"
|
|
]
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "gpt-4o"
|
|
},
|
|
"response": {
|
|
"body": [
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-541baeb2a555",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": "I58TEoLACNP"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-541baeb2a555",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "The",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": "XchQ5FwMFA"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-541baeb2a555",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " L",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": "aORUeCNu9ms"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-541baeb2a555",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "lama",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": "i1qoe9iPv"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-541baeb2a555",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " ",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": "Jb0TK5InFHcB"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-541baeb2a555",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "4",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": "12yNtgPCgRhM"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-541baeb2a555",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " Maver",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": "OC5sjL3"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-541baeb2a555",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "ick",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": "6qKOYT6XoO"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-541baeb2a555",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " model",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": "fwnf2If"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-541baeb2a555",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " has",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": "vLbjoKRWV"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-541baeb2a555",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " ",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": "U56UFb0MWyN2"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-541baeb2a555",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": "128",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": "pY4LZVSGaA"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-541baeb2a555",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": " experts",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": "1DKT2"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-541baeb2a555",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": ".",
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": null,
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": "e4FTInmy0p04"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-541baeb2a555",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": "stop",
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_cbf1785567",
|
|
"usage": null,
|
|
"obfuscation": "J0gDN2J"
|
|
}
|
|
}
|
|
],
|
|
"is_streaming": true
|
|
},
|
|
"id_normalization_mapping": {}
|
|
}
|