mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-27 19:50:26 +00:00
62005dc1a9
# What does this PR do?
- Enables users to configure prompts used throughout the File Search /
Vector Retrieval
- Configuration is defined in the Vector Stores Config so they can be
modified at runtime
- Backwards compatible, which means the fields are optional and default
to the previously used values
This is the summary of the new options in the `run.yaml`
```yaml
vector_stores:
file_search_params:
header_template: 'knowledge_search tool found {num_chunks} chunks:\nBEGIN of knowledge_search tool results.\n'
footer_template: 'END of knowledge_search tool results.\n'
context_prompt_params:
chunk_annotation_template: 'Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n'
context_template: 'The above results were retrieved to help answer the user\'s query: "{query}". Use them as supporting information only in answering this query.{annotation_instruction}\n'
annotation_prompt_params:
enable_annotations: true
annotation_instruction_template: 'Cite sources immediately at the end of sentences before punctuation, using `<|file-id|>` format like \'This is a fact <|file-Cn3MSNn72ENTiiq11Qda4A|>.\'. Do not add
extra punctuation. Use only the file IDs provided, do not invent new ones.'
chunk_annotation_template: '[{index}] {metadata_text} cite as <|{file_id}|>\n{chunk_text}\n'
```
<!-- If resolving an issue, uncomment and update the line below -->
<!-- Closes #[issue-number] -->
## Test Plan
Added tests.
---------
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
668 lines
20 KiB
JSON
Generated
668 lines
20 KiB
JSON
Generated
{
|
|
"test_id": "tests/integration/responses/test_tool_responses.py::test_response_sequential_file_search[openai_client-txt=openai/gpt-4o:emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5:dim=768]",
|
|
"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_4ac6gxccWFxDvEl8BizY3BJw",
|
|
"type": "function",
|
|
"function": {
|
|
"name": "knowledge_search",
|
|
"arguments": "{\"query\":\"Llama 4 Maverick model number of experts\"}"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"role": "tool",
|
|
"tool_call_id": "call_4ac6gxccWFxDvEl8BizY3BJw",
|
|
"content": [
|
|
{
|
|
"type": "text",
|
|
"text": "knowledge_search tool found 1 chunks:\nBEGIN of knowledge_search tool results.\n"
|
|
},
|
|
{
|
|
"type": "text",
|
|
"text": "[1] document_id: file-528246887823, score: 0.019272319661840426, attributes: {'filename': 'test_sequential_file_search.txt', 'chunk_id': '3907d885-d8e7-a72d-1113-f7080454d97c', 'document_id': 'file-528246887823', 'token_count': 19.0, 'metadata_token_count': 11.0} cite as <|file-528246887823|>\nThe Llama 4 Maverick model has 128 experts in its mixture of experts architecture.\n"
|
|
},
|
|
{
|
|
"type": "text",
|
|
"text": "END of knowledge_search tool results.\n"
|
|
},
|
|
{
|
|
"type": "text",
|
|
"text": "The above results were retrieved to help answer the user's query: \"Llama 4 Maverick model number of experts\". Use them as supporting information only in answering this query. Cite sources immediately at the end of sentences before punctuation, using `<|file-id|>` format like 'This is a fact <|file-Cn3MSNn72ENTiiq11Qda4A|>.'. Do not add extra punctuation. Use only the file IDs provided, do not invent new ones.\n"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"role": "assistant",
|
|
"content": "The Llama 4 Maverick model has 128 experts in its mixture of experts architecture <|file-528246887823|>."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "Can you tell me more about the architecture?"
|
|
}
|
|
],
|
|
"stream": true,
|
|
"stream_options": {
|
|
"include_usage": true
|
|
},
|
|
"tools": [
|
|
{
|
|
"type": "function",
|
|
"function": {
|
|
"name": "knowledge_search",
|
|
"description": "Search for information in a database.",
|
|
"parameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"query": {
|
|
"type": "string",
|
|
"description": "The query to search for. Can be a natural language sentence or keywords."
|
|
}
|
|
},
|
|
"required": [
|
|
"query"
|
|
]
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
"endpoint": "/v1/chat/completions",
|
|
"model": "gpt-4o"
|
|
},
|
|
"response": {
|
|
"body": [
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-29ab0b407d3d",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": "assistant",
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": "call_de3mxedMBHueFpm2b61KzC57",
|
|
"function": {
|
|
"arguments": "",
|
|
"name": "knowledge_search"
|
|
},
|
|
"type": "function"
|
|
}
|
|
]
|
|
},
|
|
"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_a4d13246c5",
|
|
"usage": null,
|
|
"obfuscation": "WnRz"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-29ab0b407d3d",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": null,
|
|
"function": {
|
|
"arguments": "{\"",
|
|
"name": null
|
|
},
|
|
"type": 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_a4d13246c5",
|
|
"usage": null,
|
|
"obfuscation": "Tdk"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-29ab0b407d3d",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": null,
|
|
"function": {
|
|
"arguments": "query",
|
|
"name": null
|
|
},
|
|
"type": 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_a4d13246c5",
|
|
"usage": null,
|
|
"obfuscation": "b"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-29ab0b407d3d",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": null,
|
|
"function": {
|
|
"arguments": "\":\"",
|
|
"name": null
|
|
},
|
|
"type": 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_a4d13246c5",
|
|
"usage": null,
|
|
"obfuscation": "5"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-29ab0b407d3d",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": null,
|
|
"function": {
|
|
"arguments": "L",
|
|
"name": null
|
|
},
|
|
"type": 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_a4d13246c5",
|
|
"usage": null,
|
|
"obfuscation": "ixufu"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-29ab0b407d3d",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": null,
|
|
"function": {
|
|
"arguments": "lama",
|
|
"name": null
|
|
},
|
|
"type": 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_a4d13246c5",
|
|
"usage": null,
|
|
"obfuscation": "JP"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-29ab0b407d3d",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": null,
|
|
"function": {
|
|
"arguments": " ",
|
|
"name": null
|
|
},
|
|
"type": 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_a4d13246c5",
|
|
"usage": null,
|
|
"obfuscation": "vJSE0"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-29ab0b407d3d",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": null,
|
|
"function": {
|
|
"arguments": "4",
|
|
"name": null
|
|
},
|
|
"type": 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_a4d13246c5",
|
|
"usage": null,
|
|
"obfuscation": "1ps8E"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-29ab0b407d3d",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": null,
|
|
"function": {
|
|
"arguments": " Maver",
|
|
"name": null
|
|
},
|
|
"type": 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_a4d13246c5",
|
|
"usage": null,
|
|
"obfuscation": ""
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-29ab0b407d3d",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": null,
|
|
"function": {
|
|
"arguments": "ick",
|
|
"name": null
|
|
},
|
|
"type": 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_a4d13246c5",
|
|
"usage": null,
|
|
"obfuscation": "YB0"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-29ab0b407d3d",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": null,
|
|
"function": {
|
|
"arguments": " model",
|
|
"name": null
|
|
},
|
|
"type": 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_a4d13246c5",
|
|
"usage": null,
|
|
"obfuscation": ""
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-29ab0b407d3d",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": null,
|
|
"function": {
|
|
"arguments": " architecture",
|
|
"name": null
|
|
},
|
|
"type": 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_a4d13246c5",
|
|
"usage": null,
|
|
"obfuscation": "DgrymXGGS"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-29ab0b407d3d",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": null,
|
|
"function": {
|
|
"arguments": " details",
|
|
"name": null
|
|
},
|
|
"type": 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_a4d13246c5",
|
|
"usage": null,
|
|
"obfuscation": "rcnLxZVgmKPeIW"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-29ab0b407d3d",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": [
|
|
{
|
|
"index": 0,
|
|
"id": null,
|
|
"function": {
|
|
"arguments": "\"}",
|
|
"name": null
|
|
},
|
|
"type": 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_a4d13246c5",
|
|
"usage": null,
|
|
"obfuscation": "uu6"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-29ab0b407d3d",
|
|
"choices": [
|
|
{
|
|
"delta": {
|
|
"content": null,
|
|
"function_call": null,
|
|
"refusal": null,
|
|
"role": null,
|
|
"tool_calls": null
|
|
},
|
|
"finish_reason": "tool_calls",
|
|
"index": 0,
|
|
"logprobs": null
|
|
}
|
|
],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_a4d13246c5",
|
|
"usage": null,
|
|
"obfuscation": "Loyb"
|
|
}
|
|
},
|
|
{
|
|
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
|
"__data__": {
|
|
"id": "rec-29ab0b407d3d",
|
|
"choices": [],
|
|
"created": 0,
|
|
"model": "gpt-4o-2024-08-06",
|
|
"object": "chat.completion.chunk",
|
|
"service_tier": "default",
|
|
"system_fingerprint": "fp_a4d13246c5",
|
|
"usage": {
|
|
"completion_tokens": 23,
|
|
"prompt_tokens": 400,
|
|
"total_tokens": 423,
|
|
"completion_tokens_details": {
|
|
"accepted_prediction_tokens": 0,
|
|
"audio_tokens": 0,
|
|
"reasoning_tokens": 0,
|
|
"rejected_prediction_tokens": 0
|
|
},
|
|
"prompt_tokens_details": {
|
|
"audio_tokens": 0,
|
|
"cached_tokens": 0
|
|
}
|
|
},
|
|
"obfuscation": "3H5M4ak9Z9li3"
|
|
}
|
|
}
|
|
],
|
|
"is_streaming": true
|
|
},
|
|
"id_normalization_mapping": {}
|
|
}
|