mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-13 19:32:37 +00:00
Merge remote-tracking branch 'origin/main' into stack-config-default-embed
This commit is contained in:
Ashwin Bharambe
commit
31249a1a75
237 changed files with 30895 additions and 15441 deletions
18
tests/external/run-byoa.yaml
vendored
18
tests/external/run-byoa.yaml
vendored
|
|
@ -7,6 +7,24 @@ providers:
|
|||
- provider_id: kaze
|
||||
provider_type: remote::kaze
|
||||
config: {}
|
||||
storage:
|
||||
backends:
|
||||
kv_default:
|
||||
type: kv_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/external}/kvstore.db
|
||||
sql_default:
|
||||
type: sql_sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/external}/sql_store.db
|
||||
stores:
|
||||
metadata:
|
||||
namespace: registry
|
||||
backend: kv_default
|
||||
inference:
|
||||
table_name: inference_store
|
||||
backend: sql_default
|
||||
conversations:
|
||||
table_name: openai_conversations
|
||||
backend: sql_default
|
||||
external_apis_dir: ~/.llama/apis.d
|
||||
external_providers_dir: ~/.llama/providers.d
|
||||
server:
|
||||
|
|
|
|||
|
|
@ -548,5 +548,6 @@
|
|||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -0,0 +1,447 @@
|
|||
{
|
||||
"test_id": "tests/integration/agents/test_agents.py::test_tool_choice_get_boiling_point[ollama/llama3.2:3b-instruct-fp16]",
|
||||
"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_5qverjg6",
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point",
|
||||
"arguments": "{\"celcius\":true,\"liquid_name\":\"polyjuice\"}"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "tool",
|
||||
"tool_call_id": "call_5qverjg6",
|
||||
"content": "-100"
|
||||
}
|
||||
],
|
||||
"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.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"liquid_name": {
|
||||
"type": "string",
|
||||
"description": "The name of the liquid"
|
||||
},
|
||||
"celcius": {
|
||||
"type": "boolean",
|
||||
"description": "Whether to return the boiling point in Celcius"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"liquid_name"
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"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": "rec-0940d1521204",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "The",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0940d1521204",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " boiling",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0940d1521204",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " point",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0940d1521204",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " of",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0940d1521204",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " liquid",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0940d1521204",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " poly",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0940d1521204",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "ju",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0940d1521204",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "ice",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0940d1521204",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " is",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0940d1521204",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " -",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0940d1521204",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "100",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0940d1521204",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "\u00b0C",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0940d1521204",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": ".",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0940d1521204",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
@ -0,0 +1,888 @@
|
|||
{
|
||||
"test_id": "tests/integration/agents/test_openai_responses.py::test_response_with_instructions[txt=ollama/llama3.2:3b-instruct-fp16]",
|
||||
"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 and speak in pirate language."
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "What is the capital of France?"
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "The capital of France is Paris."
|
||||
}
|
||||
],
|
||||
"stream": true,
|
||||
"stream_options": {
|
||||
"include_usage": true
|
||||
}
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": [
|
||||
{
|
||||
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
||||
"__data__": {
|
||||
"id": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " Yer",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " look",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "in",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "'",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " fer",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " a",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " port",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " o",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "'",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " call",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": ",",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " eh",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "?",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " That",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " be",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " the",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " one",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "!",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " Yer",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " won",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "'t",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " go",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " astr",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "ay",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " with",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " that",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " answer",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": ",",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " mate",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "y",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": ".",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-0f5443c07d15",
|
||||
"choices": [],
|
||||
"created": 0,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 32,
|
||||
"prompt_tokens": 50,
|
||||
"total_tokens": 82,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
@ -54,5 +54,6 @@
|
|||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -0,0 +1,256 @@
|
|||
{
|
||||
"test_id": "tests/integration/agents/test_openai_responses.py::test_response_with_instructions[txt=ollama/llama3.2:3b-instruct-fp16]",
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
||||
"headers": {},
|
||||
"body": {
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "What is the capital of France?"
|
||||
}
|
||||
],
|
||||
"stream": true,
|
||||
"stream_options": {
|
||||
"include_usage": true
|
||||
}
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": [
|
||||
{
|
||||
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
||||
"__data__": {
|
||||
"id": "rec-15b23045b5cd",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "The",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-15b23045b5cd",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " capital",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-15b23045b5cd",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " of",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-15b23045b5cd",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " France",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-15b23045b5cd",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " is",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-15b23045b5cd",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " Paris",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-15b23045b5cd",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": ".",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-15b23045b5cd",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-15b23045b5cd",
|
||||
"choices": [],
|
||||
"created": 0,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 8,
|
||||
"prompt_tokens": 32,
|
||||
"total_tokens": 40,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
@ -54,5 +54,6 @@
|
|||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load diff
|
|
@ -0,0 +1,442 @@
|
|||
{
|
||||
"test_id": "tests/integration/agents/test_agents.py::test_create_turn_response[ollama/llama3.2:3b-instruct-fp16-client_tools1]",
|
||||
"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?"
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "",
|
||||
"tool_calls": [
|
||||
{
|
||||
"id": "call_klhbln13",
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point_with_metadata",
|
||||
"arguments": "{\"celcius\":false,\"liquid_name\":\"polyjuice\"}"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "tool",
|
||||
"tool_call_id": "call_klhbln13",
|
||||
"content": "-212"
|
||||
}
|
||||
],
|
||||
"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",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"liquid_name": {
|
||||
"type": "string",
|
||||
"description": "The name of the liquid"
|
||||
},
|
||||
"celcius": {
|
||||
"type": "boolean",
|
||||
"description": "Whether to return the boiling point in Celcius"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"liquid_name"
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"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": "rec-1f0aef747544",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "The",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-1f0aef747544",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " boiling",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-1f0aef747544",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " point",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-1f0aef747544",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " of",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-1f0aef747544",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " poly",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-1f0aef747544",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "ju",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-1f0aef747544",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "ice",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-1f0aef747544",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " is",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-1f0aef747544",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " -",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-1f0aef747544",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "212",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-1f0aef747544",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " degrees",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-1f0aef747544",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " Celsius",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-1f0aef747544",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": ".",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-1f0aef747544",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
@ -56,7 +56,7 @@
|
|||
"tool_calls": [
|
||||
{
|
||||
"index": 0,
|
||||
"id": "call_os3xa9go",
|
||||
"id": "call_6nqo069h",
|
||||
"function": {
|
||||
"arguments": "{\"city\":\"Tokyo\"}",
|
||||
"name": "get_weather"
|
||||
|
|
@ -115,9 +115,9 @@
|
|||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 15,
|
||||
"completion_tokens": 18,
|
||||
"prompt_tokens": 179,
|
||||
"total_tokens": 194,
|
||||
"total_tokens": 197,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
|
|
|
|||
|
|
@ -0,0 +1,416 @@
|
|||
{
|
||||
"test_id": "tests/integration/agents/test_agents.py::test_custom_tool_infinite_loop[ollama/llama3.2:3b-instruct-fp16]",
|
||||
"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."
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "",
|
||||
"tool_calls": [
|
||||
{
|
||||
"id": "call_9x4z21g1",
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point",
|
||||
"arguments": "{\"celcius\":\"true\",\"liquid_name\":\"polyjuice\"}"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "tool",
|
||||
"tool_call_id": "call_9x4z21g1",
|
||||
"content": "-100"
|
||||
}
|
||||
],
|
||||
"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.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"liquid_name": {
|
||||
"type": "string",
|
||||
"description": "The name of the liquid"
|
||||
},
|
||||
"celcius": {
|
||||
"type": "boolean",
|
||||
"description": "Whether to return the boiling point in Celcius"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"liquid_name"
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"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": "rec-256d85719096",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "The",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-256d85719096",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " boiling",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-256d85719096",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " point",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-256d85719096",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " of",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-256d85719096",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " Poly",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-256d85719096",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "ju",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-256d85719096",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "ice",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-256d85719096",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " is",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-256d85719096",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " -",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-256d85719096",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "100",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-256d85719096",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "\u00b0C",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-256d85719096",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": ".",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-256d85719096",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
@ -54,5 +54,6 @@
|
|||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -66,7 +66,7 @@
|
|||
"tool_calls": [
|
||||
{
|
||||
"index": 0,
|
||||
"id": "call_ixvkq8fh",
|
||||
"id": "call_icfpgg5q",
|
||||
"function": {
|
||||
"arguments": "{\"celcius\":true,\"liquid_name\":\"polyjuice\"}",
|
||||
"name": "get_boiling_point"
|
||||
|
|
@ -116,5 +116,6 @@
|
|||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -54,5 +54,6 @@
|
|||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -0,0 +1,442 @@
|
|||
{
|
||||
"test_id": "tests/integration/agents/test_agents.py::test_custom_tool[ollama/llama3.2:3b-instruct-fp16]",
|
||||
"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_icfpgg5q",
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point",
|
||||
"arguments": "{\"celcius\":true,\"liquid_name\":\"polyjuice\"}"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "tool",
|
||||
"tool_call_id": "call_icfpgg5q",
|
||||
"content": "-100"
|
||||
}
|
||||
],
|
||||
"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.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"liquid_name": {
|
||||
"type": "string",
|
||||
"description": "The name of the liquid"
|
||||
},
|
||||
"celcius": {
|
||||
"type": "boolean",
|
||||
"description": "Whether to return the boiling point in Celcius"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"liquid_name"
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"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": "rec-45d0aabc5023",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "The",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-45d0aabc5023",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " boiling",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-45d0aabc5023",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " point",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-45d0aabc5023",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " of",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-45d0aabc5023",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " liquid",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-45d0aabc5023",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " poly",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-45d0aabc5023",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "ju",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-45d0aabc5023",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "ice",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-45d0aabc5023",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " is",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-45d0aabc5023",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " -",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-45d0aabc5023",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "100",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-45d0aabc5023",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "\u00b0C",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-45d0aabc5023",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": ".",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-45d0aabc5023",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
File diff suppressed because it is too large
Load diff
|
|
@ -48,7 +48,7 @@
|
|||
"tool_calls": [
|
||||
{
|
||||
"index": 0,
|
||||
"id": "call_lqrdy0rt",
|
||||
"id": "call_x427af31",
|
||||
"function": {
|
||||
"arguments": "{}",
|
||||
"name": "get_current_time"
|
||||
|
|
@ -107,9 +107,9 @@
|
|||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 14,
|
||||
"completion_tokens": 12,
|
||||
"prompt_tokens": 161,
|
||||
"total_tokens": 175,
|
||||
"total_tokens": 173,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
|
|
|
|||
|
|
@ -56,7 +56,7 @@
|
|||
"tool_calls": [
|
||||
{
|
||||
"index": 0,
|
||||
"id": "call_4ibtjudr",
|
||||
"id": "call_wkjhgmpf",
|
||||
"function": {
|
||||
"arguments": "{\"city\":\"Tokyo\"}",
|
||||
"name": "get_weather"
|
||||
|
|
|
|||
|
|
@ -66,7 +66,7 @@
|
|||
"tool_calls": [
|
||||
{
|
||||
"index": 0,
|
||||
"id": "call_pojpzwm8",
|
||||
"id": "call_klhbln13",
|
||||
"function": {
|
||||
"arguments": "{\"celcius\":false,\"liquid_name\":\"polyjuice\"}",
|
||||
"name": "get_boiling_point_with_metadata"
|
||||
|
|
@ -116,5 +116,6 @@
|
|||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load diff
|
|
@ -54,5 +54,6 @@
|
|||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -54,5 +54,6 @@
|
|||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -54,5 +54,6 @@
|
|||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -66,7 +66,7 @@
|
|||
"tool_calls": [
|
||||
{
|
||||
"index": 0,
|
||||
"id": "call_rwasjr3y",
|
||||
"id": "call_zqu5i0ti",
|
||||
"function": {
|
||||
"arguments": "{\"celcius\":null,\"liquid_name\":\"polyjuice\"}",
|
||||
"name": "get_boiling_point"
|
||||
|
|
@ -116,5 +116,6 @@
|
|||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -0,0 +1,59 @@
|
|||
{
|
||||
"test_id": "tests/integration/agents/test_agents.py::test_tool_choice_required[ollama/llama3.2:3b-instruct-fp16]",
|
||||
"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: -100\n\nAssistant: The boiling point of liquid polyjuice is -100\u00b0C.\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": "rec-7e794c73bf79",
|
||||
"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": 0,
|
||||
"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
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
@ -54,5 +54,6 @@
|
|||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -54,5 +54,6 @@
|
|||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -0,0 +1,442 @@
|
|||
{
|
||||
"test_id": "tests/integration/agents/test_agents.py::test_create_turn_response[ollama/llama3.2:3b-instruct-fp16-client_tools0]",
|
||||
"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?"
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "",
|
||||
"tool_calls": [
|
||||
{
|
||||
"id": "call_zqu5i0ti",
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point",
|
||||
"arguments": "{\"celcius\":null,\"liquid_name\":\"polyjuice\"}"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "tool",
|
||||
"tool_call_id": "call_zqu5i0ti",
|
||||
"content": "-212"
|
||||
}
|
||||
],
|
||||
"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.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"liquid_name": {
|
||||
"type": "string",
|
||||
"description": "The name of the liquid"
|
||||
},
|
||||
"celcius": {
|
||||
"type": "boolean",
|
||||
"description": "Whether to return the boiling point in Celcius"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"liquid_name"
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"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": "rec-8c4ec4715269",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "The",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-8c4ec4715269",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " boiling",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-8c4ec4715269",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " point",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-8c4ec4715269",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " of",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-8c4ec4715269",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " poly",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-8c4ec4715269",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "ju",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-8c4ec4715269",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "ice",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-8c4ec4715269",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " is",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-8c4ec4715269",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " -",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-8c4ec4715269",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "212",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-8c4ec4715269",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " degrees",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-8c4ec4715269",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " Celsius",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-8c4ec4715269",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": ".",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-8c4ec4715269",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
@ -54,5 +54,6 @@
|
|||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -0,0 +1,59 @@
|
|||
{
|
||||
"test_id": "tests/integration/agents/test_agents.py::test_tool_choice_get_boiling_point[ollama/llama3.2:3b-instruct-fp16]",
|
||||
"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: -100\n\nAssistant: The boiling point of liquid polyjuice is -100\u00b0C.\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": "rec-8fc418c02b8b",
|
||||
"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": 0,
|
||||
"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
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
@ -54,5 +54,6 @@
|
|||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1510,5 +1510,6 @@
|
|||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -54,5 +54,6 @@
|
|||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -54,5 +54,6 @@
|
|||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -54,5 +54,6 @@
|
|||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -0,0 +1,260 @@
|
|||
{
|
||||
"test_id": "tests/integration/agents/test_openai_responses.py::test_response_with_instructions[txt=ollama/llama3.2:3b-instruct-fp16]",
|
||||
"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 capital of France?"
|
||||
}
|
||||
],
|
||||
"stream": true,
|
||||
"stream_options": {
|
||||
"include_usage": true
|
||||
}
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": [
|
||||
{
|
||||
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
||||
"__data__": {
|
||||
"id": "rec-b3c24a0ab429",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "The",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b3c24a0ab429",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " capital",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b3c24a0ab429",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " of",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b3c24a0ab429",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " France",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b3c24a0ab429",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " is",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b3c24a0ab429",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " Paris",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b3c24a0ab429",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": ".",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b3c24a0ab429",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b3c24a0ab429",
|
||||
"choices": [],
|
||||
"created": 0,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 8,
|
||||
"prompt_tokens": 38,
|
||||
"total_tokens": 46,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
@ -0,0 +1,442 @@
|
|||
{
|
||||
"test_id": "tests/integration/agents/test_agents.py::test_tool_choice_required[ollama/llama3.2:3b-instruct-fp16]",
|
||||
"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_z1rt0qb1",
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "get_boiling_point",
|
||||
"arguments": "{\"celcius\":true,\"liquid_name\":\"polyjuice\"}"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"role": "tool",
|
||||
"tool_call_id": "call_z1rt0qb1",
|
||||
"content": "-100"
|
||||
}
|
||||
],
|
||||
"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.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"liquid_name": {
|
||||
"type": "string",
|
||||
"description": "The name of the liquid"
|
||||
},
|
||||
"celcius": {
|
||||
"type": "boolean",
|
||||
"description": "Whether to return the boiling point in Celcius"
|
||||
}
|
||||
},
|
||||
"required": [
|
||||
"liquid_name"
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"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": "rec-b4a47451a2af",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "The",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b4a47451a2af",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " boiling",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b4a47451a2af",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " point",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b4a47451a2af",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " of",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b4a47451a2af",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " liquid",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b4a47451a2af",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " poly",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b4a47451a2af",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "ju",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b4a47451a2af",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "ice",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b4a47451a2af",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " is",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b4a47451a2af",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " -",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b4a47451a2af",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "100",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b4a47451a2af",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "\u00b0C",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b4a47451a2af",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": ".",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-b4a47451a2af",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
@ -66,7 +66,7 @@
|
|||
"tool_calls": [
|
||||
{
|
||||
"index": 0,
|
||||
"id": "call_qryqpevz",
|
||||
"id": "call_9x4z21g1",
|
||||
"function": {
|
||||
"arguments": "{\"celcius\":\"true\",\"liquid_name\":\"polyjuice\"}",
|
||||
"name": "get_boiling_point"
|
||||
|
|
@ -116,5 +116,6 @@
|
|||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -54,5 +54,6 @@
|
|||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -54,5 +54,6 @@
|
|||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -54,5 +54,6 @@
|
|||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -0,0 +1,59 @@
|
|||
{
|
||||
"test_id": "tests/integration/agents/test_agents.py::test_custom_tool[ollama/llama3.2:3b-instruct-fp16]",
|
||||
"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: -100\n\nAssistant: The boiling point of liquid polyjuice is -100\u00b0C.\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": "rec-da6fc54bb65d",
|
||||
"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": 0,
|
||||
"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
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
@ -71,7 +71,7 @@
|
|||
"tool_calls": [
|
||||
{
|
||||
"index": 0,
|
||||
"id": "call_ur5tbdbt",
|
||||
"id": "call_5qverjg6",
|
||||
"function": {
|
||||
"arguments": "{\"celcius\":true,\"liquid_name\":\"polyjuice\"}",
|
||||
"name": "get_boiling_point"
|
||||
|
|
@ -121,5 +121,6 @@
|
|||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -54,5 +54,6 @@
|
|||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -66,7 +66,7 @@
|
|||
"tool_calls": [
|
||||
{
|
||||
"index": 0,
|
||||
"id": "call_rq1pcgq7",
|
||||
"id": "call_z1rt0qb1",
|
||||
"function": {
|
||||
"arguments": "{\"celcius\":true,\"liquid_name\":\"polyjuice\"}",
|
||||
"name": "get_boiling_point"
|
||||
|
|
@ -116,5 +116,6 @@
|
|||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
}
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -466,3 +466,53 @@ def test_guardrails_with_tools(compat_client, text_model_id):
|
|||
# Response should be either a function call or a message
|
||||
output_type = response.output[0].type
|
||||
assert output_type in ["function_call", "message"]
|
||||
|
||||
|
||||
def test_response_with_instructions(openai_client, client_with_models, text_model_id):
|
||||
"""Test instructions parameter in the responses object."""
|
||||
if isinstance(client_with_models, LlamaStackAsLibraryClient):
|
||||
pytest.skip("OpenAI responses are not supported when testing with library client yet.")
|
||||
|
||||
client = openai_client
|
||||
|
||||
messages = [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "What is the capital of France?",
|
||||
}
|
||||
]
|
||||
|
||||
# First create a response without instructions parameter
|
||||
response_w_o_instructions = client.responses.create(
|
||||
model=text_model_id,
|
||||
input=messages,
|
||||
stream=False,
|
||||
)
|
||||
|
||||
# Verify we have None in the instructions field
|
||||
assert response_w_o_instructions.instructions is None
|
||||
|
||||
# Next create a response and pass instructions parameter
|
||||
instructions = "You are a helpful assistant."
|
||||
response_with_instructions = client.responses.create(
|
||||
model=text_model_id,
|
||||
instructions=instructions,
|
||||
input=messages,
|
||||
stream=False,
|
||||
)
|
||||
|
||||
# Verify we have a valid instructions field
|
||||
assert response_with_instructions.instructions == instructions
|
||||
|
||||
# Finally test instructions parameter with a previous response id
|
||||
instructions2 = "You are a helpful assistant and speak in pirate language."
|
||||
response_with_instructions2 = client.responses.create(
|
||||
model=text_model_id,
|
||||
instructions=instructions2,
|
||||
input=messages,
|
||||
previous_response_id=response_with_instructions.id,
|
||||
stream=False,
|
||||
)
|
||||
|
||||
# Verify instructions from previous response was not carried over to the next response
|
||||
assert response_with_instructions2.instructions == instructions2
|
||||
|
|
|
|||
|
|
@ -70,10 +70,15 @@ class BatchHelper:
|
|||
):
|
||||
"""Wait for a batch to reach a terminal status.
|
||||
|
||||
Uses exponential backoff polling strategy for efficient waiting:
|
||||
- Starts with short intervals (0.1s) for fast batches (e.g., replay mode)
|
||||
- Doubles interval each iteration up to a maximum
|
||||
- Adapts automatically to both fast and slow batch processing
|
||||
|
||||
Args:
|
||||
batch_id: The batch ID to monitor
|
||||
max_wait_time: Maximum time to wait in seconds (default: 60 seconds)
|
||||
sleep_interval: Time to sleep between checks in seconds (default: 1/10th of max_wait_time, min 1s, max 15s)
|
||||
sleep_interval: If provided, uses fixed interval instead of exponential backoff
|
||||
expected_statuses: Set of expected terminal statuses (default: {"completed"})
|
||||
timeout_action: Action on timeout - "fail" (pytest.fail) or "skip" (pytest.skip)
|
||||
|
||||
|
|
@ -84,10 +89,6 @@ class BatchHelper:
|
|||
pytest.Failed: If batch reaches an unexpected status or timeout_action is "fail"
|
||||
pytest.Skipped: If timeout_action is "skip" on timeout or unexpected status
|
||||
"""
|
||||
if sleep_interval is None:
|
||||
# Default to 1/10th of max_wait_time, with min 1s and max 15s
|
||||
sleep_interval = max(1, min(15, max_wait_time // 10))
|
||||
|
||||
if expected_statuses is None:
|
||||
expected_statuses = {"completed"}
|
||||
|
||||
|
|
@ -95,6 +96,15 @@ class BatchHelper:
|
|||
unexpected_statuses = terminal_statuses - expected_statuses
|
||||
|
||||
start_time = time.time()
|
||||
|
||||
# Use exponential backoff if no explicit sleep_interval provided
|
||||
if sleep_interval is None:
|
||||
current_interval = 0.1 # Start with 100ms
|
||||
max_interval = 10.0 # Cap at 10 seconds
|
||||
else:
|
||||
current_interval = sleep_interval
|
||||
max_interval = sleep_interval
|
||||
|
||||
while time.time() - start_time < max_wait_time:
|
||||
current_batch = self.client.batches.retrieve(batch_id)
|
||||
|
||||
|
|
@ -107,7 +117,11 @@ class BatchHelper:
|
|||
else:
|
||||
pytest.fail(error_msg)
|
||||
|
||||
time.sleep(sleep_interval)
|
||||
time.sleep(current_interval)
|
||||
|
||||
# Exponential backoff: double the interval each time, up to max
|
||||
if sleep_interval is None:
|
||||
current_interval = min(current_interval * 2, max_interval)
|
||||
|
||||
timeout_msg = f"Batch did not reach expected status {expected_statuses} within {max_wait_time} seconds"
|
||||
if timeout_action == "skip":
|
||||
|
|
|
|||
|
|
@ -0,0 +1,506 @@
|
|||
{
|
||||
"test_id": null,
|
||||
"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 2 + 2?"
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"content": "The answer to the equation 2 + 2 is 4."
|
||||
},
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Tell me a short joke"
|
||||
}
|
||||
],
|
||||
"max_tokens": 0,
|
||||
"stream": true
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": [
|
||||
{
|
||||
"__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
|
||||
"__data__": {
|
||||
"id": "rec-ab1a32474062",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "Why",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-ab1a32474062",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " did",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-ab1a32474062",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " the",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-ab1a32474062",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " scare",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-ab1a32474062",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "crow",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-ab1a32474062",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " win",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-ab1a32474062",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " an",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-ab1a32474062",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " award",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-ab1a32474062",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "?\n\n",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-ab1a32474062",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "Because",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-ab1a32474062",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " he",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-ab1a32474062",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " was",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-ab1a32474062",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " outstanding",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-ab1a32474062",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " in",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-ab1a32474062",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " his",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-ab1a32474062",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": " field",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-ab1a32474062",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "!",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": null,
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"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": "rec-ab1a32474062",
|
||||
"choices": [
|
||||
{
|
||||
"delta": {
|
||||
"content": "",
|
||||
"function_call": null,
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"tool_calls": null
|
||||
},
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion.chunk",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": true
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,88 @@
|
|||
{
|
||||
"test_id": null,
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "http://0.0.0.0:11434/v1/v1/models",
|
||||
"headers": {},
|
||||
"body": {},
|
||||
"endpoint": "/v1/models",
|
||||
"model": ""
|
||||
},
|
||||
"response": {
|
||||
"body": [
|
||||
{
|
||||
"__type__": "openai.types.model.Model",
|
||||
"__data__": {
|
||||
"id": "llama3.2:3b-instruct-fp16",
|
||||
"created": 1760453641,
|
||||
"object": "model",
|
||||
"owned_by": "library"
|
||||
}
|
||||
},
|
||||
{
|
||||
"__type__": "openai.types.model.Model",
|
||||
"__data__": {
|
||||
"id": "qwen3:4b",
|
||||
"created": 1757615302,
|
||||
"object": "model",
|
||||
"owned_by": "library"
|
||||
}
|
||||
},
|
||||
{
|
||||
"__type__": "openai.types.model.Model",
|
||||
"__data__": {
|
||||
"id": "gpt-oss:latest",
|
||||
"created": 1756395223,
|
||||
"object": "model",
|
||||
"owned_by": "library"
|
||||
}
|
||||
},
|
||||
{
|
||||
"__type__": "openai.types.model.Model",
|
||||
"__data__": {
|
||||
"id": "nomic-embed-text:latest",
|
||||
"created": 1756318548,
|
||||
"object": "model",
|
||||
"owned_by": "library"
|
||||
}
|
||||
},
|
||||
{
|
||||
"__type__": "openai.types.model.Model",
|
||||
"__data__": {
|
||||
"id": "llama3.2:3b",
|
||||
"created": 1755191039,
|
||||
"object": "model",
|
||||
"owned_by": "library"
|
||||
}
|
||||
},
|
||||
{
|
||||
"__type__": "openai.types.model.Model",
|
||||
"__data__": {
|
||||
"id": "all-minilm:l6-v2",
|
||||
"created": 1753968177,
|
||||
"object": "model",
|
||||
"owned_by": "library"
|
||||
}
|
||||
},
|
||||
{
|
||||
"__type__": "openai.types.model.Model",
|
||||
"__data__": {
|
||||
"id": "llama3.2:1b",
|
||||
"created": 1746124735,
|
||||
"object": "model",
|
||||
"owned_by": "library"
|
||||
}
|
||||
},
|
||||
{
|
||||
"__type__": "openai.types.model.Model",
|
||||
"__data__": {
|
||||
"id": "llama3.2:latest",
|
||||
"created": 1746044170,
|
||||
"object": "model",
|
||||
"owned_by": "library"
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": false
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,44 @@
|
|||
{
|
||||
"test_id": null,
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "http://0.0.0.0:11434/v1/v1/models",
|
||||
"headers": {},
|
||||
"body": {},
|
||||
"endpoint": "/v1/models",
|
||||
"model": ""
|
||||
},
|
||||
"response": {
|
||||
"body": [
|
||||
{
|
||||
"__type__": "openai.types.model.Model",
|
||||
"__data__": {
|
||||
"id": "llama-guard3:1b",
|
||||
"created": 1753937098,
|
||||
"object": "model",
|
||||
"owned_by": "library"
|
||||
}
|
||||
},
|
||||
{
|
||||
"__type__": "openai.types.model.Model",
|
||||
"__data__": {
|
||||
"id": "all-minilm:l6-v2",
|
||||
"created": 1753936935,
|
||||
"object": "model",
|
||||
"owned_by": "library"
|
||||
}
|
||||
},
|
||||
{
|
||||
"__type__": "openai.types.model.Model",
|
||||
"__data__": {
|
||||
"id": "llama3.2:3b-instruct-fp16",
|
||||
"created": 1753936925,
|
||||
"object": "model",
|
||||
"owned_by": "library"
|
||||
}
|
||||
}
|
||||
],
|
||||
"is_streaming": false
|
||||
},
|
||||
"id_normalization_mapping": {}
|
||||
}
|
||||
|
|
@ -246,7 +246,7 @@ def instantiate_llama_stack_client(session):
|
|||
|
||||
run_config_file = tempfile.NamedTemporaryFile(delete=False, suffix=".yaml")
|
||||
with open(run_config_file.name, "w") as f:
|
||||
yaml.dump(run_config.model_dump(), f)
|
||||
yaml.dump(run_config.model_dump(mode="json"), f)
|
||||
config = run_config_file.name
|
||||
|
||||
client = LlamaStackAsLibraryClient(
|
||||
|
|
|
|||
|
|
@ -12,9 +12,15 @@ import pytest
|
|||
|
||||
from llama_stack.core.access_control.access_control import default_policy
|
||||
from llama_stack.core.datatypes import User
|
||||
from llama_stack.core.storage.datatypes import SqlStoreReference
|
||||
from llama_stack.providers.utils.sqlstore.api import ColumnType
|
||||
from llama_stack.providers.utils.sqlstore.authorized_sqlstore import AuthorizedSqlStore
|
||||
from llama_stack.providers.utils.sqlstore.sqlstore import PostgresSqlStoreConfig, SqliteSqlStoreConfig, sqlstore_impl
|
||||
from llama_stack.providers.utils.sqlstore.sqlstore import (
|
||||
PostgresSqlStoreConfig,
|
||||
SqliteSqlStoreConfig,
|
||||
register_sqlstore_backends,
|
||||
sqlstore_impl,
|
||||
)
|
||||
|
||||
|
||||
def get_postgres_config():
|
||||
|
|
@ -55,8 +61,9 @@ def authorized_store(backend_config):
|
|||
config_func = backend_config
|
||||
|
||||
config = config_func()
|
||||
|
||||
base_sqlstore = sqlstore_impl(config)
|
||||
backend_name = f"sql_{type(config).__name__.lower()}"
|
||||
register_sqlstore_backends({backend_name: config})
|
||||
base_sqlstore = sqlstore_impl(SqlStoreReference(backend=backend_name, table_name="authorized_store"))
|
||||
authorized_store = AuthorizedSqlStore(base_sqlstore, default_policy())
|
||||
|
||||
yield authorized_store
|
||||
|
|
|
|||
95
tests/integration/telemetry/conftest.py
Normal file
95
tests/integration/telemetry/conftest.py
Normal file
|
|
@ -0,0 +1,95 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
"""Telemetry test configuration using OpenTelemetry SDK exporters.
|
||||
|
||||
This conftest provides in-memory telemetry collection for library_client mode only.
|
||||
Tests using these fixtures should skip in server mode since the in-memory collector
|
||||
cannot access spans from a separate server process.
|
||||
"""
|
||||
|
||||
from typing import Any
|
||||
|
||||
import opentelemetry.metrics as otel_metrics
|
||||
import opentelemetry.trace as otel_trace
|
||||
import pytest
|
||||
from opentelemetry import metrics, trace
|
||||
from opentelemetry.sdk.metrics import MeterProvider
|
||||
from opentelemetry.sdk.metrics.export import InMemoryMetricReader
|
||||
from opentelemetry.sdk.trace import ReadableSpan, TracerProvider
|
||||
from opentelemetry.sdk.trace.export import SimpleSpanProcessor
|
||||
from opentelemetry.sdk.trace.export.in_memory_span_exporter import InMemorySpanExporter
|
||||
|
||||
import llama_stack.providers.inline.telemetry.meta_reference.telemetry as telemetry_module
|
||||
from llama_stack.testing.api_recorder import patch_httpx_for_test_id
|
||||
from tests.integration.fixtures.common import instantiate_llama_stack_client
|
||||
|
||||
|
||||
class TestCollector:
|
||||
def __init__(self, span_exp, metric_read):
|
||||
assert span_exp and metric_read
|
||||
self.span_exporter = span_exp
|
||||
self.metric_reader = metric_read
|
||||
|
||||
def get_spans(self) -> tuple[ReadableSpan, ...]:
|
||||
return self.span_exporter.get_finished_spans()
|
||||
|
||||
def get_metrics(self) -> Any | None:
|
||||
metrics = self.metric_reader.get_metrics_data()
|
||||
if metrics and metrics.resource_metrics:
|
||||
return metrics.resource_metrics[0].scope_metrics[0].metrics
|
||||
return None
|
||||
|
||||
def clear(self) -> None:
|
||||
self.span_exporter.clear()
|
||||
self.metric_reader.get_metrics_data()
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def _telemetry_providers():
|
||||
"""Set up in-memory OTEL providers before llama_stack_client initializes."""
|
||||
# Reset set-once flags to allow re-initialization
|
||||
if hasattr(otel_trace, "_TRACER_PROVIDER_SET_ONCE"):
|
||||
otel_trace._TRACER_PROVIDER_SET_ONCE._done = False # type: ignore
|
||||
if hasattr(otel_metrics, "_METER_PROVIDER_SET_ONCE"):
|
||||
otel_metrics._METER_PROVIDER_SET_ONCE._done = False # type: ignore
|
||||
|
||||
# Create in-memory exporters/readers
|
||||
span_exporter = InMemorySpanExporter()
|
||||
tracer_provider = TracerProvider()
|
||||
tracer_provider.add_span_processor(SimpleSpanProcessor(span_exporter))
|
||||
trace.set_tracer_provider(tracer_provider)
|
||||
|
||||
metric_reader = InMemoryMetricReader()
|
||||
meter_provider = MeterProvider(metric_readers=[metric_reader])
|
||||
metrics.set_meter_provider(meter_provider)
|
||||
|
||||
# Set module-level provider so TelemetryAdapter uses our in-memory providers
|
||||
telemetry_module._TRACER_PROVIDER = tracer_provider
|
||||
|
||||
yield (span_exporter, metric_reader, tracer_provider, meter_provider)
|
||||
|
||||
telemetry_module._TRACER_PROVIDER = None
|
||||
tracer_provider.shutdown()
|
||||
meter_provider.shutdown()
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def llama_stack_client(_telemetry_providers, request):
|
||||
"""Override llama_stack_client to ensure in-memory telemetry providers are used."""
|
||||
patch_httpx_for_test_id()
|
||||
client = instantiate_llama_stack_client(request.session)
|
||||
|
||||
return client
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_otlp_collector(_telemetry_providers):
|
||||
"""Provides access to telemetry data and clears between tests."""
|
||||
span_exporter, metric_reader, _, _ = _telemetry_providers
|
||||
collector = TestCollector(span_exporter, metric_reader)
|
||||
yield collector
|
||||
collector.clear()
|
||||
|
|
@ -0,0 +1,57 @@
|
|||
{
|
||||
"test_id": "tests/integration/telemetry/test_openai_telemetry.py::test_openai_completion_creates_telemetry[txt=ollama/llama3.2:3b-instruct-fp16]",
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
||||
"headers": {},
|
||||
"body": {
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Test OpenAI telemetry creation"
|
||||
}
|
||||
],
|
||||
"stream": false
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": {
|
||||
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
||||
"__data__": {
|
||||
"id": "rec-0de60cd6a6ec",
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "stop",
|
||||
"index": 0,
|
||||
"logprobs": null,
|
||||
"message": {
|
||||
"content": "I'm happy to help you with setting up and testing OpenAI's telemetry creation.\n\nOpenAI provides a feature called \"Telemetry\" which allows developers to collect data about their users' interactions with the model. To test this feature, we need to create a simple application that uses the OpenAI API and sends telemetry data to their servers.\n\nHere's an example code in Python that demonstrates how to create a simple telemetry creator:\n\n```python\nimport os\nfrom openai.api import API\n\n# Initialize the OpenAI API client\napi = API(os.environ['OPENAI_API_KEY'])\n\ndef create_user():\n # Create a new user entity\n user_entity = {\n 'id': 'user-123',\n 'name': 'John Doe',\n 'email': 'john.doe@example.com'\n }\n \n # Send the user creation request to OpenAI\n response = api.users.create(user_entity)\n print(f\"User created: {response}\")\n\ndef create_transaction():\n # Create a new transaction entity\n transaction_entity = {\n 'id': 'tran-123',\n 'user_id': 'user-123',\n 'transaction_type': 'query'\n }\n \n # Send the transaction creation request to OpenAI\n response = api.transactions.create(transaction_entity)\n print(f\"Transaction created: {response}\")\n\ndef send_telemetry_data():\n # Create a new telemetry event entity\n telemetry_event_entity = {\n 'id': 'telem-123',\n 'transaction_id': 'tran-123',\n 'data': '{ \"event\": \"test\", \"user_id\": 1 }'\n }\n \n # Send the telemetry data to OpenAI\n response = api.telemetry.create(telemetry_event_entity)\n print(f\"Telemetry event sent: {response}\")\n\n# Test the telemetry creation\ncreate_user()\ncreate_transaction()\nsend_telemetry_data()\n```\n\nMake sure you replace `OPENAI_API_KEY` with your actual API key. Also, ensure that you have the OpenAI API client library installed by running `pip install openai`.\n\nOnce you've created the test code, run it and observe the behavior of the telemetry creation process.\n\nPlease let me know if you need further modifications or assistance!",
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"annotations": null,
|
||||
"audio": null,
|
||||
"function_call": null,
|
||||
"tool_calls": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 460,
|
||||
"prompt_tokens": 30,
|
||||
"total_tokens": 490,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,59 @@
|
|||
{
|
||||
"test_id": "tests/integration/telemetry/test_completions.py::test_telemetry_format_completeness[txt=ollama/llama3.2:3b-instruct-fp16]",
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "http://0.0.0.0:11434/v1/v1/chat/completions",
|
||||
"headers": {},
|
||||
"body": {
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Test trace openai with temperature 0.7"
|
||||
}
|
||||
],
|
||||
"max_tokens": 100,
|
||||
"stream": false,
|
||||
"temperature": 0.7
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": {
|
||||
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
||||
"__data__": {
|
||||
"id": "rec-1fcfd86d8111",
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "length",
|
||||
"index": 0,
|
||||
"logprobs": null,
|
||||
"message": {
|
||||
"content": "import torch\nfrom transformers import AutoModelForCausalLM, AutoTokenizer\n\n# Load the pre-trained model and tokenizer\nmodel_name = \"CompVis/transformers-base-uncased\"\nmodel = AutoModelForCausalLM.from_pretrained(model_name)\ntokenizer = AutoTokenizer.from_pretrained(model_name)\n\n# Set the temperature to 0.7\ntemperature = 0.7\n\n# Define a function to generate text\ndef generate_text(prompt, max_length=100):\n input",
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"annotations": null,
|
||||
"audio": null,
|
||||
"function_call": null,
|
||||
"tool_calls": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 100,
|
||||
"prompt_tokens": 35,
|
||||
"total_tokens": 135,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
}
|
||||
4211
tests/integration/telemetry/recordings/d45c9a9229e7e3f50a6eac139508babe21988649eb321b562f74061f58593c25.json
generated
Normal file
4211
tests/integration/telemetry/recordings/d45c9a9229e7e3f50a6eac139508babe21988649eb321b562f74061f58593c25.json
generated
Normal file
File diff suppressed because it is too large
Load diff
4263
tests/integration/telemetry/recordings/db8ffad4840512348c215005128557807ffbed0cf6bf11a52c1d1009878886ef.json
generated
Normal file
4263
tests/integration/telemetry/recordings/db8ffad4840512348c215005128557807ffbed0cf6bf11a52c1d1009878886ef.json
generated
Normal file
File diff suppressed because it is too large
Load diff
|
|
@ -0,0 +1,59 @@
|
|||
{
|
||||
"test_id": "tests/integration/telemetry/test_completions.py::test_telemetry_format_completeness[txt=llama3.2:3b-instruct-fp16]",
|
||||
"request": {
|
||||
"method": "POST",
|
||||
"url": "http://localhost:11434/v1/v1/chat/completions",
|
||||
"headers": {},
|
||||
"body": {
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
"content": "Test trace openai with temperature 0.7"
|
||||
}
|
||||
],
|
||||
"max_tokens": 100,
|
||||
"stream": false,
|
||||
"temperature": 0.7
|
||||
},
|
||||
"endpoint": "/v1/chat/completions",
|
||||
"model": "llama3.2:3b-instruct-fp16"
|
||||
},
|
||||
"response": {
|
||||
"body": {
|
||||
"__type__": "openai.types.chat.chat_completion.ChatCompletion",
|
||||
"__data__": {
|
||||
"id": "rec-dba5042d6691",
|
||||
"choices": [
|
||||
{
|
||||
"finish_reason": "length",
|
||||
"index": 0,
|
||||
"logprobs": null,
|
||||
"message": {
|
||||
"content": "To test the \"trace\" functionality of OpenAI's GPT-4 model at a temperature of 0.7, you can follow these steps:\n\n1. First, make sure you have an account with OpenAI and have been granted access to their API.\n\n2. You will need to install the `transformers` library, which is the official library for working with Transformers models like GPT-4:\n\n ```bash\npip install transformers\n```\n\n3. Next, import the necessary",
|
||||
"refusal": null,
|
||||
"role": "assistant",
|
||||
"annotations": null,
|
||||
"audio": null,
|
||||
"function_call": null,
|
||||
"tool_calls": null
|
||||
}
|
||||
}
|
||||
],
|
||||
"created": 0,
|
||||
"model": "llama3.2:3b-instruct-fp16",
|
||||
"object": "chat.completion",
|
||||
"service_tier": null,
|
||||
"system_fingerprint": "fp_ollama",
|
||||
"usage": {
|
||||
"completion_tokens": 100,
|
||||
"prompt_tokens": 35,
|
||||
"total_tokens": 135,
|
||||
"completion_tokens_details": null,
|
||||
"prompt_tokens_details": null
|
||||
}
|
||||
}
|
||||
},
|
||||
"is_streaming": false
|
||||
}
|
||||
}
|
||||
112
tests/integration/telemetry/test_completions.py
Normal file
112
tests/integration/telemetry/test_completions.py
Normal file
|
|
@ -0,0 +1,112 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
"""Telemetry tests verifying @trace_protocol decorator format using in-memory exporter."""
|
||||
|
||||
import json
|
||||
import os
|
||||
|
||||
import pytest
|
||||
|
||||
pytestmark = pytest.mark.skipif(
|
||||
os.environ.get("LLAMA_STACK_TEST_STACK_CONFIG_TYPE") == "server",
|
||||
reason="In-memory telemetry tests only work in library_client mode (server mode runs in separate process)",
|
||||
)
|
||||
|
||||
|
||||
def test_streaming_chunk_count(mock_otlp_collector, llama_stack_client, text_model_id):
|
||||
"""Verify streaming adds chunk_count and __type__=async_generator."""
|
||||
|
||||
stream = llama_stack_client.chat.completions.create(
|
||||
model=text_model_id,
|
||||
messages=[{"role": "user", "content": "Test trace openai 1"}],
|
||||
stream=True,
|
||||
)
|
||||
|
||||
chunks = list(stream)
|
||||
assert len(chunks) > 0
|
||||
|
||||
spans = mock_otlp_collector.get_spans()
|
||||
assert len(spans) > 0
|
||||
|
||||
chunk_count = None
|
||||
for span in spans:
|
||||
if span.attributes.get("__type__") == "async_generator":
|
||||
chunk_count = span.attributes.get("chunk_count")
|
||||
if chunk_count:
|
||||
chunk_count = int(chunk_count)
|
||||
break
|
||||
|
||||
assert chunk_count is not None
|
||||
assert chunk_count == len(chunks)
|
||||
|
||||
|
||||
def test_telemetry_format_completeness(mock_otlp_collector, llama_stack_client, text_model_id):
|
||||
"""Comprehensive validation of telemetry data format including spans and metrics."""
|
||||
response = llama_stack_client.chat.completions.create(
|
||||
model=text_model_id,
|
||||
messages=[{"role": "user", "content": "Test trace openai with temperature 0.7"}],
|
||||
temperature=0.7,
|
||||
max_tokens=100,
|
||||
stream=False,
|
||||
)
|
||||
|
||||
# Handle both dict and Pydantic model for usage
|
||||
# This occurs due to the replay system returning a dict for usage, but the client returning a Pydantic model
|
||||
# TODO: Fix this by making the replay system return a Pydantic model for usage
|
||||
usage = response.usage if isinstance(response.usage, dict) else response.usage.model_dump()
|
||||
assert usage.get("prompt_tokens") and usage["prompt_tokens"] > 0
|
||||
assert usage.get("completion_tokens") and usage["completion_tokens"] > 0
|
||||
assert usage.get("total_tokens") and usage["total_tokens"] > 0
|
||||
|
||||
# Verify spans
|
||||
spans = mock_otlp_collector.get_spans()
|
||||
assert len(spans) == 5
|
||||
|
||||
# we only need this captured one time
|
||||
logged_model_id = None
|
||||
|
||||
for span in spans:
|
||||
attrs = span.attributes
|
||||
assert attrs is not None
|
||||
|
||||
# Root span is created manually by tracing middleware, not by @trace_protocol decorator
|
||||
is_root_span = attrs.get("__root__") is True
|
||||
|
||||
if is_root_span:
|
||||
# Root spans have different attributes
|
||||
assert attrs.get("__location__") in ["library_client", "server"]
|
||||
else:
|
||||
# Non-root spans are created by @trace_protocol decorator
|
||||
assert attrs.get("__autotraced__")
|
||||
assert attrs.get("__class__") and attrs.get("__method__")
|
||||
assert attrs.get("__type__") in ["async", "sync", "async_generator"]
|
||||
|
||||
args = json.loads(attrs["__args__"])
|
||||
if "model_id" in args:
|
||||
logged_model_id = args["model_id"]
|
||||
|
||||
assert logged_model_id is not None
|
||||
assert logged_model_id == text_model_id
|
||||
|
||||
# TODO: re-enable this once metrics get fixed
|
||||
"""
|
||||
# Verify token usage metrics in response
|
||||
metrics = mock_otlp_collector.get_metrics()
|
||||
|
||||
assert metrics
|
||||
for metric in metrics:
|
||||
assert metric.name in ["completion_tokens", "total_tokens", "prompt_tokens"]
|
||||
assert metric.unit == "tokens"
|
||||
assert metric.data.data_points and len(metric.data.data_points) == 1
|
||||
match metric.name:
|
||||
case "completion_tokens":
|
||||
assert metric.data.data_points[0].value == usage["completion_tokens"]
|
||||
case "total_tokens":
|
||||
assert metric.data.data_points[0].value == usage["total_tokens"]
|
||||
case "prompt_tokens":
|
||||
assert metric.data.data_points[0].value == usage["prompt_tokens"
|
||||
"""
|
||||
71
tests/integration/test_persistence_integration.py
Normal file
71
tests/integration/test_persistence_integration.py
Normal file
|
|
@ -0,0 +1,71 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import yaml
|
||||
|
||||
from llama_stack.core.datatypes import StackRunConfig
|
||||
from llama_stack.core.storage.datatypes import (
|
||||
PostgresKVStoreConfig,
|
||||
PostgresSqlStoreConfig,
|
||||
SqliteKVStoreConfig,
|
||||
SqliteSqlStoreConfig,
|
||||
)
|
||||
|
||||
|
||||
def test_starter_distribution_config_loads_and_resolves():
|
||||
"""Integration: Actual starter config should parse and have correct storage structure."""
|
||||
with open("llama_stack/distributions/starter/run.yaml") as f:
|
||||
config_dict = yaml.safe_load(f)
|
||||
|
||||
config = StackRunConfig(**config_dict)
|
||||
|
||||
# Config should have named backends and explicit store references
|
||||
assert config.storage is not None
|
||||
assert "kv_default" in config.storage.backends
|
||||
assert "sql_default" in config.storage.backends
|
||||
assert isinstance(config.storage.backends["kv_default"], SqliteKVStoreConfig)
|
||||
assert isinstance(config.storage.backends["sql_default"], SqliteSqlStoreConfig)
|
||||
|
||||
stores = config.storage.stores
|
||||
assert stores.metadata is not None
|
||||
assert stores.metadata.backend == "kv_default"
|
||||
assert stores.metadata.namespace == "registry"
|
||||
|
||||
assert stores.inference is not None
|
||||
assert stores.inference.backend == "sql_default"
|
||||
assert stores.inference.table_name == "inference_store"
|
||||
assert stores.inference.max_write_queue_size > 0
|
||||
assert stores.inference.num_writers > 0
|
||||
|
||||
assert stores.conversations is not None
|
||||
assert stores.conversations.backend == "sql_default"
|
||||
assert stores.conversations.table_name == "openai_conversations"
|
||||
|
||||
|
||||
def test_postgres_demo_distribution_config_loads():
|
||||
"""Integration: Postgres demo should use Postgres backend for all stores."""
|
||||
with open("llama_stack/distributions/postgres-demo/run.yaml") as f:
|
||||
config_dict = yaml.safe_load(f)
|
||||
|
||||
config = StackRunConfig(**config_dict)
|
||||
|
||||
# Should have postgres backend
|
||||
assert config.storage is not None
|
||||
assert "kv_default" in config.storage.backends
|
||||
assert "sql_default" in config.storage.backends
|
||||
postgres_backend = config.storage.backends["sql_default"]
|
||||
assert isinstance(postgres_backend, PostgresSqlStoreConfig)
|
||||
assert postgres_backend.host == "${env.POSTGRES_HOST:=localhost}"
|
||||
|
||||
kv_backend = config.storage.backends["kv_default"]
|
||||
assert isinstance(kv_backend, PostgresKVStoreConfig)
|
||||
|
||||
stores = config.storage.stores
|
||||
# Stores target the Postgres backends explicitly
|
||||
assert stores.metadata is not None
|
||||
assert stores.metadata.backend == "kv_default"
|
||||
assert stores.inference is not None
|
||||
assert stores.inference.backend == "sql_default"
|
||||
|
|
@ -23,6 +23,27 @@ def config_with_image_name_int():
|
|||
image_name: 1234
|
||||
apis_to_serve: []
|
||||
built_at: {datetime.now().isoformat()}
|
||||
storage:
|
||||
backends:
|
||||
kv_default:
|
||||
type: kv_sqlite
|
||||
db_path: /tmp/test_kv.db
|
||||
sql_default:
|
||||
type: sql_sqlite
|
||||
db_path: /tmp/test_sql.db
|
||||
stores:
|
||||
metadata:
|
||||
backend: kv_default
|
||||
namespace: metadata
|
||||
inference:
|
||||
backend: sql_default
|
||||
table_name: inference
|
||||
conversations:
|
||||
backend: sql_default
|
||||
table_name: conversations
|
||||
responses:
|
||||
backend: sql_default
|
||||
table_name: responses
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: provider1
|
||||
|
|
@ -54,6 +75,27 @@ def up_to_date_config():
|
|||
image_name: foo
|
||||
apis_to_serve: []
|
||||
built_at: {datetime.now().isoformat()}
|
||||
storage:
|
||||
backends:
|
||||
kv_default:
|
||||
type: kv_sqlite
|
||||
db_path: /tmp/test_kv.db
|
||||
sql_default:
|
||||
type: sql_sqlite
|
||||
db_path: /tmp/test_sql.db
|
||||
stores:
|
||||
metadata:
|
||||
backend: kv_default
|
||||
namespace: metadata
|
||||
inference:
|
||||
backend: sql_default
|
||||
table_name: inference
|
||||
conversations:
|
||||
backend: sql_default
|
||||
table_name: conversations
|
||||
responses:
|
||||
backend: sql_default
|
||||
table_name: responses
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: provider1
|
||||
|
|
|
|||
|
|
@ -20,7 +20,14 @@ from llama_stack.core.conversations.conversations import (
|
|||
ConversationServiceConfig,
|
||||
ConversationServiceImpl,
|
||||
)
|
||||
from llama_stack.providers.utils.sqlstore.sqlstore import SqliteSqlStoreConfig
|
||||
from llama_stack.core.datatypes import StackRunConfig
|
||||
from llama_stack.core.storage.datatypes import (
|
||||
ServerStoresConfig,
|
||||
SqliteSqlStoreConfig,
|
||||
SqlStoreReference,
|
||||
StorageConfig,
|
||||
)
|
||||
from llama_stack.providers.utils.sqlstore.sqlstore import register_sqlstore_backends
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
|
|
@ -28,7 +35,18 @@ async def service():
|
|||
with tempfile.TemporaryDirectory() as tmpdir:
|
||||
db_path = Path(tmpdir) / "test_conversations.db"
|
||||
|
||||
config = ConversationServiceConfig(conversations_store=SqliteSqlStoreConfig(db_path=str(db_path)), policy=[])
|
||||
storage = StorageConfig(
|
||||
backends={
|
||||
"sql_test": SqliteSqlStoreConfig(db_path=str(db_path)),
|
||||
},
|
||||
stores=ServerStoresConfig(
|
||||
conversations=SqlStoreReference(backend="sql_test", table_name="openai_conversations"),
|
||||
),
|
||||
)
|
||||
register_sqlstore_backends({"sql_test": storage.backends["sql_test"]})
|
||||
run_config = StackRunConfig(image_name="test", apis=[], providers={}, storage=storage)
|
||||
|
||||
config = ConversationServiceConfig(run_config=run_config, policy=[])
|
||||
service = ConversationServiceImpl(config, {})
|
||||
await service.initialize()
|
||||
yield service
|
||||
|
|
@ -121,9 +139,18 @@ async def test_policy_configuration():
|
|||
AccessRule(forbid=Scope(principal="test_user", actions=[Action.CREATE, Action.READ], resource="*"))
|
||||
]
|
||||
|
||||
config = ConversationServiceConfig(
|
||||
conversations_store=SqliteSqlStoreConfig(db_path=str(db_path)), policy=restrictive_policy
|
||||
storage = StorageConfig(
|
||||
backends={
|
||||
"sql_test": SqliteSqlStoreConfig(db_path=str(db_path)),
|
||||
},
|
||||
stores=ServerStoresConfig(
|
||||
conversations=SqlStoreReference(backend="sql_test", table_name="openai_conversations"),
|
||||
),
|
||||
)
|
||||
register_sqlstore_backends({"sql_test": storage.backends["sql_test"]})
|
||||
run_config = StackRunConfig(image_name="test", apis=[], providers={}, storage=storage)
|
||||
|
||||
config = ConversationServiceConfig(run_config=run_config, policy=restrictive_policy)
|
||||
service = ConversationServiceImpl(config, {})
|
||||
await service.initialize()
|
||||
|
||||
|
|
|
|||
84
tests/unit/core/test_storage_references.py
Normal file
84
tests/unit/core/test_storage_references.py
Normal file
|
|
@ -0,0 +1,84 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
"""Unit tests for storage backend/reference validation."""
|
||||
|
||||
import pytest
|
||||
from pydantic import ValidationError
|
||||
|
||||
from llama_stack.core.datatypes import (
|
||||
LLAMA_STACK_RUN_CONFIG_VERSION,
|
||||
StackRunConfig,
|
||||
)
|
||||
from llama_stack.core.storage.datatypes import (
|
||||
InferenceStoreReference,
|
||||
KVStoreReference,
|
||||
ServerStoresConfig,
|
||||
SqliteKVStoreConfig,
|
||||
SqliteSqlStoreConfig,
|
||||
SqlStoreReference,
|
||||
StorageConfig,
|
||||
)
|
||||
|
||||
|
||||
def _base_run_config(**overrides):
|
||||
metadata_reference = overrides.pop(
|
||||
"metadata_reference",
|
||||
KVStoreReference(backend="kv_default", namespace="registry"),
|
||||
)
|
||||
inference_reference = overrides.pop(
|
||||
"inference_reference",
|
||||
InferenceStoreReference(backend="sql_default", table_name="inference"),
|
||||
)
|
||||
conversations_reference = overrides.pop(
|
||||
"conversations_reference",
|
||||
SqlStoreReference(backend="sql_default", table_name="conversations"),
|
||||
)
|
||||
storage = overrides.pop(
|
||||
"storage",
|
||||
StorageConfig(
|
||||
backends={
|
||||
"kv_default": SqliteKVStoreConfig(db_path="/tmp/kv.db"),
|
||||
"sql_default": SqliteSqlStoreConfig(db_path="/tmp/sql.db"),
|
||||
},
|
||||
stores=ServerStoresConfig(
|
||||
metadata=metadata_reference,
|
||||
inference=inference_reference,
|
||||
conversations=conversations_reference,
|
||||
),
|
||||
),
|
||||
)
|
||||
return StackRunConfig(
|
||||
version=LLAMA_STACK_RUN_CONFIG_VERSION,
|
||||
image_name="test-distro",
|
||||
apis=[],
|
||||
providers={},
|
||||
storage=storage,
|
||||
**overrides,
|
||||
)
|
||||
|
||||
|
||||
def test_references_require_known_backend():
|
||||
with pytest.raises(ValidationError, match="unknown backend 'missing'"):
|
||||
_base_run_config(metadata_reference=KVStoreReference(backend="missing", namespace="registry"))
|
||||
|
||||
|
||||
def test_references_must_match_backend_family():
|
||||
with pytest.raises(ValidationError, match="kv_.* is required"):
|
||||
_base_run_config(metadata_reference=KVStoreReference(backend="sql_default", namespace="registry"))
|
||||
|
||||
with pytest.raises(ValidationError, match="sql_.* is required"):
|
||||
_base_run_config(
|
||||
inference_reference=InferenceStoreReference(backend="kv_default", table_name="inference"),
|
||||
)
|
||||
|
||||
|
||||
def test_valid_configuration_passes_validation():
|
||||
config = _base_run_config()
|
||||
stores = config.storage.stores
|
||||
assert stores.metadata is not None and stores.metadata.backend == "kv_default"
|
||||
assert stores.inference is not None and stores.inference.backend == "sql_default"
|
||||
assert stores.conversations is not None and stores.conversations.backend == "sql_default"
|
||||
|
|
@ -13,6 +13,15 @@ from pydantic import BaseModel, Field, ValidationError
|
|||
|
||||
from llama_stack.core.datatypes import Api, Provider, StackRunConfig
|
||||
from llama_stack.core.distribution import INTERNAL_APIS, get_provider_registry, providable_apis
|
||||
from llama_stack.core.storage.datatypes import (
|
||||
InferenceStoreReference,
|
||||
KVStoreReference,
|
||||
ServerStoresConfig,
|
||||
SqliteKVStoreConfig,
|
||||
SqliteSqlStoreConfig,
|
||||
SqlStoreReference,
|
||||
StorageConfig,
|
||||
)
|
||||
from llama_stack.providers.datatypes import ProviderSpec
|
||||
|
||||
|
||||
|
|
@ -29,6 +38,32 @@ class SampleConfig(BaseModel):
|
|||
}
|
||||
|
||||
|
||||
def _default_storage() -> StorageConfig:
|
||||
return StorageConfig(
|
||||
backends={
|
||||
"kv_default": SqliteKVStoreConfig(db_path=":memory:"),
|
||||
"sql_default": SqliteSqlStoreConfig(db_path=":memory:"),
|
||||
},
|
||||
stores=ServerStoresConfig(
|
||||
metadata=KVStoreReference(backend="kv_default", namespace="registry"),
|
||||
inference=InferenceStoreReference(backend="sql_default", table_name="inference_store"),
|
||||
conversations=SqlStoreReference(backend="sql_default", table_name="conversations"),
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
def make_stack_config(**overrides) -> StackRunConfig:
|
||||
storage = overrides.pop("storage", _default_storage())
|
||||
defaults = dict(
|
||||
image_name="test_image",
|
||||
apis=[],
|
||||
providers={},
|
||||
storage=storage,
|
||||
)
|
||||
defaults.update(overrides)
|
||||
return StackRunConfig(**defaults)
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_providers():
|
||||
"""Mock the available_providers function to return test providers."""
|
||||
|
|
@ -47,8 +82,8 @@ def mock_providers():
|
|||
@pytest.fixture
|
||||
def base_config(tmp_path):
|
||||
"""Create a base StackRunConfig with common settings."""
|
||||
return StackRunConfig(
|
||||
image_name="test_image",
|
||||
return make_stack_config(
|
||||
apis=["inference"],
|
||||
providers={
|
||||
"inference": [
|
||||
Provider(
|
||||
|
|
@ -222,8 +257,8 @@ class TestProviderRegistry:
|
|||
|
||||
def test_missing_directory(self, mock_providers):
|
||||
"""Test handling of missing external providers directory."""
|
||||
config = StackRunConfig(
|
||||
image_name="test_image",
|
||||
config = make_stack_config(
|
||||
apis=["inference"],
|
||||
providers={
|
||||
"inference": [
|
||||
Provider(
|
||||
|
|
@ -278,7 +313,6 @@ pip_packages:
|
|||
"""Test loading an external provider from a module (success path)."""
|
||||
from types import SimpleNamespace
|
||||
|
||||
from llama_stack.core.datatypes import Provider, StackRunConfig
|
||||
from llama_stack.providers.datatypes import Api, ProviderSpec
|
||||
|
||||
# Simulate a provider module with get_provider_spec
|
||||
|
|
@ -293,7 +327,7 @@ pip_packages:
|
|||
import_module_side_effect = make_import_module_side_effect(external_module=fake_module)
|
||||
|
||||
with patch("importlib.import_module", side_effect=import_module_side_effect) as mock_import:
|
||||
config = StackRunConfig(
|
||||
config = make_stack_config(
|
||||
image_name="test_image",
|
||||
providers={
|
||||
"inference": [
|
||||
|
|
@ -317,12 +351,11 @@ pip_packages:
|
|||
|
||||
def test_external_provider_from_module_not_found(self, mock_providers):
|
||||
"""Test handling ModuleNotFoundError for missing provider module."""
|
||||
from llama_stack.core.datatypes import Provider, StackRunConfig
|
||||
|
||||
import_module_side_effect = make_import_module_side_effect(raise_for_external=True)
|
||||
|
||||
with patch("importlib.import_module", side_effect=import_module_side_effect):
|
||||
config = StackRunConfig(
|
||||
config = make_stack_config(
|
||||
image_name="test_image",
|
||||
providers={
|
||||
"inference": [
|
||||
|
|
@ -341,12 +374,11 @@ pip_packages:
|
|||
|
||||
def test_external_provider_from_module_missing_get_provider_spec(self, mock_providers):
|
||||
"""Test handling missing get_provider_spec in provider module (should raise ValueError)."""
|
||||
from llama_stack.core.datatypes import Provider, StackRunConfig
|
||||
|
||||
import_module_side_effect = make_import_module_side_effect(missing_get_provider_spec=True)
|
||||
|
||||
with patch("importlib.import_module", side_effect=import_module_side_effect):
|
||||
config = StackRunConfig(
|
||||
config = make_stack_config(
|
||||
image_name="test_image",
|
||||
providers={
|
||||
"inference": [
|
||||
|
|
@ -399,13 +431,12 @@ class TestGetExternalProvidersFromModule:
|
|||
|
||||
def test_stackrunconfig_provider_without_module(self, mock_providers):
|
||||
"""Test that providers without module attribute are skipped."""
|
||||
from llama_stack.core.datatypes import Provider, StackRunConfig
|
||||
from llama_stack.core.distribution import get_external_providers_from_module
|
||||
|
||||
import_module_side_effect = make_import_module_side_effect()
|
||||
|
||||
with patch("importlib.import_module", side_effect=import_module_side_effect):
|
||||
config = StackRunConfig(
|
||||
config = make_stack_config(
|
||||
image_name="test_image",
|
||||
providers={
|
||||
"inference": [
|
||||
|
|
@ -426,7 +457,6 @@ class TestGetExternalProvidersFromModule:
|
|||
"""Test provider with module containing version spec (e.g., package==1.0.0)."""
|
||||
from types import SimpleNamespace
|
||||
|
||||
from llama_stack.core.datatypes import Provider, StackRunConfig
|
||||
from llama_stack.core.distribution import get_external_providers_from_module
|
||||
from llama_stack.providers.datatypes import ProviderSpec
|
||||
|
||||
|
|
@ -444,7 +474,7 @@ class TestGetExternalProvidersFromModule:
|
|||
raise ModuleNotFoundError(name)
|
||||
|
||||
with patch("importlib.import_module", side_effect=import_side_effect):
|
||||
config = StackRunConfig(
|
||||
config = make_stack_config(
|
||||
image_name="test_image",
|
||||
providers={
|
||||
"inference": [
|
||||
|
|
@ -564,7 +594,6 @@ class TestGetExternalProvidersFromModule:
|
|||
"""Test when get_provider_spec returns a list of specs."""
|
||||
from types import SimpleNamespace
|
||||
|
||||
from llama_stack.core.datatypes import Provider, StackRunConfig
|
||||
from llama_stack.core.distribution import get_external_providers_from_module
|
||||
from llama_stack.providers.datatypes import ProviderSpec
|
||||
|
||||
|
|
@ -589,7 +618,7 @@ class TestGetExternalProvidersFromModule:
|
|||
raise ModuleNotFoundError(name)
|
||||
|
||||
with patch("importlib.import_module", side_effect=import_side_effect):
|
||||
config = StackRunConfig(
|
||||
config = make_stack_config(
|
||||
image_name="test_image",
|
||||
providers={
|
||||
"inference": [
|
||||
|
|
@ -613,7 +642,6 @@ class TestGetExternalProvidersFromModule:
|
|||
"""Test that list return filters specs by provider_type."""
|
||||
from types import SimpleNamespace
|
||||
|
||||
from llama_stack.core.datatypes import Provider, StackRunConfig
|
||||
from llama_stack.core.distribution import get_external_providers_from_module
|
||||
from llama_stack.providers.datatypes import ProviderSpec
|
||||
|
||||
|
|
@ -638,7 +666,7 @@ class TestGetExternalProvidersFromModule:
|
|||
raise ModuleNotFoundError(name)
|
||||
|
||||
with patch("importlib.import_module", side_effect=import_side_effect):
|
||||
config = StackRunConfig(
|
||||
config = make_stack_config(
|
||||
image_name="test_image",
|
||||
providers={
|
||||
"inference": [
|
||||
|
|
@ -662,7 +690,6 @@ class TestGetExternalProvidersFromModule:
|
|||
"""Test that list return adds multiple different provider_types when config requests them."""
|
||||
from types import SimpleNamespace
|
||||
|
||||
from llama_stack.core.datatypes import Provider, StackRunConfig
|
||||
from llama_stack.core.distribution import get_external_providers_from_module
|
||||
from llama_stack.providers.datatypes import ProviderSpec
|
||||
|
||||
|
|
@ -688,7 +715,7 @@ class TestGetExternalProvidersFromModule:
|
|||
raise ModuleNotFoundError(name)
|
||||
|
||||
with patch("importlib.import_module", side_effect=import_side_effect):
|
||||
config = StackRunConfig(
|
||||
config = make_stack_config(
|
||||
image_name="test_image",
|
||||
providers={
|
||||
"inference": [
|
||||
|
|
@ -718,7 +745,6 @@ class TestGetExternalProvidersFromModule:
|
|||
|
||||
def test_module_not_found_raises_value_error(self, mock_providers):
|
||||
"""Test that ModuleNotFoundError raises ValueError with helpful message."""
|
||||
from llama_stack.core.datatypes import Provider, StackRunConfig
|
||||
from llama_stack.core.distribution import get_external_providers_from_module
|
||||
|
||||
def import_side_effect(name):
|
||||
|
|
@ -727,7 +753,7 @@ class TestGetExternalProvidersFromModule:
|
|||
raise ModuleNotFoundError(name)
|
||||
|
||||
with patch("importlib.import_module", side_effect=import_side_effect):
|
||||
config = StackRunConfig(
|
||||
config = make_stack_config(
|
||||
image_name="test_image",
|
||||
providers={
|
||||
"inference": [
|
||||
|
|
@ -751,7 +777,6 @@ class TestGetExternalProvidersFromModule:
|
|||
"""Test that generic exceptions are properly raised."""
|
||||
from types import SimpleNamespace
|
||||
|
||||
from llama_stack.core.datatypes import Provider, StackRunConfig
|
||||
from llama_stack.core.distribution import get_external_providers_from_module
|
||||
|
||||
def bad_spec():
|
||||
|
|
@ -765,7 +790,7 @@ class TestGetExternalProvidersFromModule:
|
|||
raise ModuleNotFoundError(name)
|
||||
|
||||
with patch("importlib.import_module", side_effect=import_side_effect):
|
||||
config = StackRunConfig(
|
||||
config = make_stack_config(
|
||||
image_name="test_image",
|
||||
providers={
|
||||
"inference": [
|
||||
|
|
@ -787,10 +812,9 @@ class TestGetExternalProvidersFromModule:
|
|||
|
||||
def test_empty_provider_list(self, mock_providers):
|
||||
"""Test with empty provider list."""
|
||||
from llama_stack.core.datatypes import StackRunConfig
|
||||
from llama_stack.core.distribution import get_external_providers_from_module
|
||||
|
||||
config = StackRunConfig(
|
||||
config = make_stack_config(
|
||||
image_name="test_image",
|
||||
providers={},
|
||||
)
|
||||
|
|
@ -805,7 +829,6 @@ class TestGetExternalProvidersFromModule:
|
|||
"""Test multiple APIs with providers."""
|
||||
from types import SimpleNamespace
|
||||
|
||||
from llama_stack.core.datatypes import Provider, StackRunConfig
|
||||
from llama_stack.core.distribution import get_external_providers_from_module
|
||||
from llama_stack.providers.datatypes import ProviderSpec
|
||||
|
||||
|
|
@ -830,7 +853,7 @@ class TestGetExternalProvidersFromModule:
|
|||
raise ModuleNotFoundError(name)
|
||||
|
||||
with patch("importlib.import_module", side_effect=import_side_effect):
|
||||
config = StackRunConfig(
|
||||
config = make_stack_config(
|
||||
image_name="test_image",
|
||||
providers={
|
||||
"inference": [
|
||||
|
|
|
|||
50
tests/unit/distribution/test_stack_list_deps.py
Normal file
50
tests/unit/distribution/test_stack_list_deps.py
Normal file
|
|
@ -0,0 +1,50 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import argparse
|
||||
from io import StringIO
|
||||
from unittest.mock import patch
|
||||
|
||||
from llama_stack.cli.stack._list_deps import (
|
||||
run_stack_list_deps_command,
|
||||
)
|
||||
|
||||
|
||||
def test_stack_list_deps_basic():
|
||||
args = argparse.Namespace(
|
||||
config=None,
|
||||
env_name="test-env",
|
||||
providers="inference=remote::ollama",
|
||||
format="deps-only",
|
||||
)
|
||||
|
||||
with patch("sys.stdout", new_callable=StringIO) as mock_stdout:
|
||||
run_stack_list_deps_command(args)
|
||||
output = mock_stdout.getvalue()
|
||||
|
||||
# deps-only format should NOT include "uv pip install" or "Dependencies for"
|
||||
assert "uv pip install" not in output
|
||||
assert "Dependencies for" not in output
|
||||
|
||||
# Check that expected dependencies are present
|
||||
assert "ollama" in output
|
||||
assert "aiohttp" in output
|
||||
assert "fastapi" in output
|
||||
|
||||
|
||||
def test_stack_list_deps_with_distro_uv():
|
||||
args = argparse.Namespace(
|
||||
config="starter",
|
||||
env_name=None,
|
||||
providers=None,
|
||||
format="uv",
|
||||
)
|
||||
|
||||
with patch("sys.stdout", new_callable=StringIO) as mock_stdout:
|
||||
run_stack_list_deps_command(args)
|
||||
output = mock_stdout.getvalue()
|
||||
|
||||
assert "uv pip install" in output
|
||||
|
|
@ -11,11 +11,12 @@ from llama_stack.apis.common.errors import ResourceNotFoundError
|
|||
from llama_stack.apis.common.responses import Order
|
||||
from llama_stack.apis.files import OpenAIFilePurpose
|
||||
from llama_stack.core.access_control.access_control import default_policy
|
||||
from llama_stack.core.storage.datatypes import SqliteSqlStoreConfig, SqlStoreReference
|
||||
from llama_stack.providers.inline.files.localfs import (
|
||||
LocalfsFilesImpl,
|
||||
LocalfsFilesImplConfig,
|
||||
)
|
||||
from llama_stack.providers.utils.sqlstore.sqlstore import SqliteSqlStoreConfig
|
||||
from llama_stack.providers.utils.sqlstore.sqlstore import register_sqlstore_backends
|
||||
|
||||
|
||||
class MockUploadFile:
|
||||
|
|
@ -36,8 +37,11 @@ async def files_provider(tmp_path):
|
|||
storage_dir = tmp_path / "files"
|
||||
db_path = tmp_path / "files_metadata.db"
|
||||
|
||||
backend_name = "sql_localfs_test"
|
||||
register_sqlstore_backends({backend_name: SqliteSqlStoreConfig(db_path=db_path.as_posix())})
|
||||
config = LocalfsFilesImplConfig(
|
||||
storage_dir=storage_dir.as_posix(), metadata_store=SqliteSqlStoreConfig(db_path=db_path.as_posix())
|
||||
storage_dir=storage_dir.as_posix(),
|
||||
metadata_store=SqlStoreReference(backend=backend_name, table_name="files_metadata"),
|
||||
)
|
||||
|
||||
provider = LocalfsFilesImpl(config, default_policy())
|
||||
|
|
|
|||
|
|
@ -9,7 +9,16 @@ import random
|
|||
import pytest
|
||||
|
||||
from llama_stack.core.prompts.prompts import PromptServiceConfig, PromptServiceImpl
|
||||
from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
|
||||
from llama_stack.core.storage.datatypes import (
|
||||
InferenceStoreReference,
|
||||
KVStoreReference,
|
||||
ServerStoresConfig,
|
||||
SqliteKVStoreConfig,
|
||||
SqliteSqlStoreConfig,
|
||||
SqlStoreReference,
|
||||
StorageConfig,
|
||||
)
|
||||
from llama_stack.providers.utils.kvstore import kvstore_impl, register_kvstore_backends
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
|
|
@ -19,12 +28,28 @@ async def temp_prompt_store(tmp_path_factory):
|
|||
db_path = str(temp_dir / f"{unique_id}.db")
|
||||
|
||||
from llama_stack.core.datatypes import StackRunConfig
|
||||
from llama_stack.providers.utils.kvstore import kvstore_impl
|
||||
|
||||
mock_run_config = StackRunConfig(image_name="test-distribution", apis=[], providers={})
|
||||
storage = StorageConfig(
|
||||
backends={
|
||||
"kv_test": SqliteKVStoreConfig(db_path=db_path),
|
||||
"sql_test": SqliteSqlStoreConfig(db_path=str(temp_dir / f"{unique_id}_sql.db")),
|
||||
},
|
||||
stores=ServerStoresConfig(
|
||||
metadata=KVStoreReference(backend="kv_test", namespace="registry"),
|
||||
inference=InferenceStoreReference(backend="sql_test", table_name="inference"),
|
||||
conversations=SqlStoreReference(backend="sql_test", table_name="conversations"),
|
||||
),
|
||||
)
|
||||
mock_run_config = StackRunConfig(
|
||||
image_name="test-distribution",
|
||||
apis=[],
|
||||
providers={},
|
||||
storage=storage,
|
||||
)
|
||||
config = PromptServiceConfig(run_config=mock_run_config)
|
||||
store = PromptServiceImpl(config, deps={})
|
||||
|
||||
store.kvstore = await kvstore_impl(SqliteKVStoreConfig(db_path=db_path))
|
||||
register_kvstore_backends({"kv_test": storage.backends["kv_test"]})
|
||||
store.kvstore = await kvstore_impl(KVStoreReference(backend="kv_test", namespace="prompts"))
|
||||
|
||||
yield store
|
||||
|
|
|
|||
|
|
@ -26,6 +26,20 @@ from llama_stack.providers.inline.agents.meta_reference.config import MetaRefere
|
|||
from llama_stack.providers.inline.agents.meta_reference.persistence import AgentInfo
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def setup_backends(tmp_path):
|
||||
"""Register KV and SQL store backends for testing."""
|
||||
from llama_stack.core.storage.datatypes import SqliteKVStoreConfig, SqliteSqlStoreConfig
|
||||
from llama_stack.providers.utils.kvstore.kvstore import register_kvstore_backends
|
||||
from llama_stack.providers.utils.sqlstore.sqlstore import register_sqlstore_backends
|
||||
|
||||
kv_path = str(tmp_path / "test_kv.db")
|
||||
sql_path = str(tmp_path / "test_sql.db")
|
||||
|
||||
register_kvstore_backends({"kv_default": SqliteKVStoreConfig(db_path=kv_path)})
|
||||
register_sqlstore_backends({"sql_default": SqliteSqlStoreConfig(db_path=sql_path)})
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_apis():
|
||||
return {
|
||||
|
|
@ -40,15 +54,20 @@ def mock_apis():
|
|||
|
||||
@pytest.fixture
|
||||
def config(tmp_path):
|
||||
from llama_stack.core.storage.datatypes import KVStoreReference, ResponsesStoreReference
|
||||
from llama_stack.providers.inline.agents.meta_reference.config import AgentPersistenceConfig
|
||||
|
||||
return MetaReferenceAgentsImplConfig(
|
||||
persistence_store={
|
||||
"type": "sqlite",
|
||||
"db_path": str(tmp_path / "test.db"),
|
||||
},
|
||||
responses_store={
|
||||
"type": "sqlite",
|
||||
"db_path": str(tmp_path / "test.db"),
|
||||
},
|
||||
persistence=AgentPersistenceConfig(
|
||||
agent_state=KVStoreReference(
|
||||
backend="kv_default",
|
||||
namespace="agents",
|
||||
),
|
||||
responses=ResponsesStoreReference(
|
||||
backend="sql_default",
|
||||
table_name="responses",
|
||||
),
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -42,7 +42,7 @@ from llama_stack.apis.inference import (
|
|||
)
|
||||
from llama_stack.apis.tools.tools import ListToolDefsResponse, ToolDef, ToolGroups, ToolInvocationResult, ToolRuntime
|
||||
from llama_stack.core.access_control.access_control import default_policy
|
||||
from llama_stack.core.datatypes import ResponsesStoreConfig
|
||||
from llama_stack.core.storage.datatypes import ResponsesStoreReference, SqliteSqlStoreConfig
|
||||
from llama_stack.providers.inline.agents.meta_reference.responses.openai_responses import (
|
||||
OpenAIResponsesImpl,
|
||||
)
|
||||
|
|
@ -50,7 +50,7 @@ from llama_stack.providers.utils.responses.responses_store import (
|
|||
ResponsesStore,
|
||||
_OpenAIResponseObjectWithInputAndMessages,
|
||||
)
|
||||
from llama_stack.providers.utils.sqlstore.sqlstore import SqliteSqlStoreConfig
|
||||
from llama_stack.providers.utils.sqlstore.sqlstore import register_sqlstore_backends
|
||||
from tests.unit.providers.agents.meta_reference.fixtures import load_chat_completion_fixture
|
||||
|
||||
|
||||
|
|
@ -814,6 +814,69 @@ async def test_create_openai_response_with_instructions_and_previous_response(
|
|||
assert sent_messages[3].content == "Which is the largest?"
|
||||
|
||||
|
||||
async def test_create_openai_response_with_previous_response_instructions(
|
||||
openai_responses_impl, mock_responses_store, mock_inference_api
|
||||
):
|
||||
"""Test prepending instructions and previous response with instructions."""
|
||||
|
||||
input_item_message = OpenAIResponseMessage(
|
||||
id="123",
|
||||
content="Name some towns in Ireland",
|
||||
role="user",
|
||||
)
|
||||
response_output_message = OpenAIResponseMessage(
|
||||
id="123",
|
||||
content="Galway, Longford, Sligo",
|
||||
status="completed",
|
||||
role="assistant",
|
||||
)
|
||||
response = _OpenAIResponseObjectWithInputAndMessages(
|
||||
created_at=1,
|
||||
id="resp_123",
|
||||
model="fake_model",
|
||||
output=[response_output_message],
|
||||
status="completed",
|
||||
text=OpenAIResponseText(format=OpenAIResponseTextFormat(type="text")),
|
||||
input=[input_item_message],
|
||||
messages=[
|
||||
OpenAIUserMessageParam(content="Name some towns in Ireland"),
|
||||
OpenAIAssistantMessageParam(content="Galway, Longford, Sligo"),
|
||||
],
|
||||
instructions="You are a helpful assistant.",
|
||||
)
|
||||
mock_responses_store.get_response_object.return_value = response
|
||||
|
||||
model = "meta-llama/Llama-3.1-8B-Instruct"
|
||||
instructions = "You are a geography expert. Provide concise answers."
|
||||
|
||||
mock_inference_api.openai_chat_completion.return_value = fake_stream()
|
||||
|
||||
# Execute
|
||||
await openai_responses_impl.create_openai_response(
|
||||
input="Which is the largest?", model=model, instructions=instructions, previous_response_id="123"
|
||||
)
|
||||
|
||||
# Verify
|
||||
mock_inference_api.openai_chat_completion.assert_called_once()
|
||||
call_args = mock_inference_api.openai_chat_completion.call_args
|
||||
params = call_args.args[0]
|
||||
sent_messages = params.messages
|
||||
|
||||
# Check that instructions were prepended as a system message
|
||||
# and that the previous response instructions were not carried over
|
||||
assert len(sent_messages) == 4, sent_messages
|
||||
assert sent_messages[0].role == "system"
|
||||
assert sent_messages[0].content == instructions
|
||||
|
||||
# Check the rest of the messages were converted correctly
|
||||
assert sent_messages[1].role == "user"
|
||||
assert sent_messages[1].content == "Name some towns in Ireland"
|
||||
assert sent_messages[2].role == "assistant"
|
||||
assert sent_messages[2].content == "Galway, Longford, Sligo"
|
||||
assert sent_messages[3].role == "user"
|
||||
assert sent_messages[3].content == "Which is the largest?"
|
||||
|
||||
|
||||
async def test_list_openai_response_input_items_delegation(openai_responses_impl, mock_responses_store):
|
||||
"""Test that list_openai_response_input_items properly delegates to responses_store with correct parameters."""
|
||||
# Setup
|
||||
|
|
@ -854,8 +917,10 @@ async def test_responses_store_list_input_items_logic():
|
|||
|
||||
# Create mock store and response store
|
||||
mock_sql_store = AsyncMock()
|
||||
backend_name = "sql_responses_test"
|
||||
register_sqlstore_backends({backend_name: SqliteSqlStoreConfig(db_path="mock_db_path")})
|
||||
responses_store = ResponsesStore(
|
||||
ResponsesStoreConfig(sql_store_config=SqliteSqlStoreConfig(db_path="mock_db_path")), policy=default_policy()
|
||||
ResponsesStoreReference(backend=backend_name, table_name="responses"), policy=default_policy()
|
||||
)
|
||||
responses_store.sql_store = mock_sql_store
|
||||
|
||||
|
|
|
|||
|
|
@ -12,10 +12,10 @@ from unittest.mock import AsyncMock
|
|||
|
||||
import pytest
|
||||
|
||||
from llama_stack.core.storage.datatypes import KVStoreReference, SqliteKVStoreConfig
|
||||
from llama_stack.providers.inline.batches.reference.batches import ReferenceBatchesImpl
|
||||
from llama_stack.providers.inline.batches.reference.config import ReferenceBatchesImplConfig
|
||||
from llama_stack.providers.utils.kvstore import kvstore_impl
|
||||
from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
|
||||
from llama_stack.providers.utils.kvstore import kvstore_impl, register_kvstore_backends
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
|
|
@ -23,8 +23,10 @@ async def provider():
|
|||
"""Create a test provider instance with temporary database."""
|
||||
with tempfile.TemporaryDirectory() as tmpdir:
|
||||
db_path = Path(tmpdir) / "test_batches.db"
|
||||
backend_name = "kv_batches_test"
|
||||
kvstore_config = SqliteKVStoreConfig(db_path=str(db_path))
|
||||
config = ReferenceBatchesImplConfig(kvstore=kvstore_config)
|
||||
register_kvstore_backends({backend_name: kvstore_config})
|
||||
config = ReferenceBatchesImplConfig(kvstore=KVStoreReference(backend=backend_name, namespace="batches"))
|
||||
|
||||
# Create kvstore and mock APIs
|
||||
kvstore = await kvstore_impl(config.kvstore)
|
||||
|
|
|
|||
|
|
@ -8,8 +8,9 @@ import boto3
|
|||
import pytest
|
||||
from moto import mock_aws
|
||||
|
||||
from llama_stack.core.storage.datatypes import SqliteSqlStoreConfig, SqlStoreReference
|
||||
from llama_stack.providers.remote.files.s3 import S3FilesImplConfig, get_adapter_impl
|
||||
from llama_stack.providers.utils.sqlstore.sqlstore import SqliteSqlStoreConfig
|
||||
from llama_stack.providers.utils.sqlstore.sqlstore import register_sqlstore_backends
|
||||
|
||||
|
||||
class MockUploadFile:
|
||||
|
|
@ -38,11 +39,13 @@ def sample_text_file2():
|
|||
def s3_config(tmp_path):
|
||||
db_path = tmp_path / "s3_files_metadata.db"
|
||||
|
||||
backend_name = f"sql_s3_{tmp_path.name}"
|
||||
register_sqlstore_backends({backend_name: SqliteSqlStoreConfig(db_path=db_path.as_posix())})
|
||||
return S3FilesImplConfig(
|
||||
bucket_name=f"test-bucket-{tmp_path.name}",
|
||||
region="not-a-region",
|
||||
auto_create_bucket=True,
|
||||
metadata_store=SqliteSqlStoreConfig(db_path=db_path.as_posix()),
|
||||
metadata_store=SqlStoreReference(backend=backend_name, table_name="s3_files_metadata"),
|
||||
)
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -12,13 +12,14 @@ import pytest
|
|||
|
||||
from llama_stack.apis.vector_dbs import VectorDB
|
||||
from llama_stack.apis.vector_io import Chunk, ChunkMetadata, QueryChunksResponse
|
||||
from llama_stack.core.storage.datatypes import KVStoreReference, SqliteKVStoreConfig
|
||||
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
|
||||
from llama_stack.providers.inline.vector_io.faiss.faiss import FaissIndex, FaissVectorIOAdapter
|
||||
from llama_stack.providers.inline.vector_io.sqlite_vec import SQLiteVectorIOConfig
|
||||
from llama_stack.providers.inline.vector_io.sqlite_vec.sqlite_vec import SQLiteVecIndex, SQLiteVecVectorIOAdapter
|
||||
from llama_stack.providers.remote.vector_io.pgvector.config import PGVectorVectorIOConfig
|
||||
from llama_stack.providers.remote.vector_io.pgvector.pgvector import PGVectorIndex, PGVectorVectorIOAdapter
|
||||
from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
|
||||
from llama_stack.providers.utils.kvstore import register_kvstore_backends
|
||||
|
||||
EMBEDDING_DIMENSION = 768
|
||||
COLLECTION_PREFIX = "test_collection"
|
||||
|
|
@ -112,8 +113,9 @@ async def unique_kvstore_config(tmp_path_factory):
|
|||
unique_id = f"test_kv_{np.random.randint(1e6)}"
|
||||
temp_dir = tmp_path_factory.getbasetemp()
|
||||
db_path = str(temp_dir / f"{unique_id}.db")
|
||||
|
||||
return SqliteKVStoreConfig(db_path=db_path)
|
||||
backend_name = f"kv_vector_{unique_id}"
|
||||
register_kvstore_backends({backend_name: SqliteKVStoreConfig(db_path=db_path)})
|
||||
return KVStoreReference(backend=backend_name, namespace=f"vector_io::{unique_id}")
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
|
|
@ -138,7 +140,7 @@ async def sqlite_vec_vec_index(embedding_dimension, tmp_path_factory):
|
|||
async def sqlite_vec_adapter(sqlite_vec_db_path, unique_kvstore_config, mock_inference_api, embedding_dimension):
|
||||
config = SQLiteVectorIOConfig(
|
||||
db_path=sqlite_vec_db_path,
|
||||
kvstore=unique_kvstore_config,
|
||||
persistence=unique_kvstore_config,
|
||||
)
|
||||
adapter = SQLiteVecVectorIOAdapter(
|
||||
config=config,
|
||||
|
|
@ -176,7 +178,7 @@ async def faiss_vec_index(embedding_dimension):
|
|||
@pytest.fixture
|
||||
async def faiss_vec_adapter(unique_kvstore_config, mock_inference_api, embedding_dimension):
|
||||
config = FaissVectorIOConfig(
|
||||
kvstore=unique_kvstore_config,
|
||||
persistence=unique_kvstore_config,
|
||||
)
|
||||
adapter = FaissVectorIOAdapter(
|
||||
config=config,
|
||||
|
|
@ -251,7 +253,7 @@ async def pgvector_vec_adapter(unique_kvstore_config, mock_inference_api, embedd
|
|||
db="test_db",
|
||||
user="test_user",
|
||||
password="test_password",
|
||||
kvstore=unique_kvstore_config,
|
||||
persistence=unique_kvstore_config,
|
||||
)
|
||||
|
||||
adapter = PGVectorVectorIOAdapter(config, mock_inference_api, None)
|
||||
|
|
|
|||
|
|
@ -10,13 +10,13 @@ import pytest
|
|||
from llama_stack.apis.inference import Model
|
||||
from llama_stack.apis.vector_dbs import VectorDB
|
||||
from llama_stack.core.datatypes import VectorDBWithOwner
|
||||
from llama_stack.core.storage.datatypes import KVStoreReference, SqliteKVStoreConfig
|
||||
from llama_stack.core.store.registry import (
|
||||
KEY_FORMAT,
|
||||
CachedDiskDistributionRegistry,
|
||||
DiskDistributionRegistry,
|
||||
)
|
||||
from llama_stack.providers.utils.kvstore import kvstore_impl
|
||||
from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
|
||||
from llama_stack.providers.utils.kvstore import kvstore_impl, register_kvstore_backends
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
|
|
@ -72,7 +72,11 @@ async def test_cached_registry_initialization(sqlite_kvstore, sample_vector_db,
|
|||
|
||||
# Test cached version loads from disk
|
||||
db_path = sqlite_kvstore.db_path
|
||||
cached_registry = CachedDiskDistributionRegistry(await kvstore_impl(SqliteKVStoreConfig(db_path=db_path)))
|
||||
backend_name = "kv_cached_test"
|
||||
register_kvstore_backends({backend_name: SqliteKVStoreConfig(db_path=db_path)})
|
||||
cached_registry = CachedDiskDistributionRegistry(
|
||||
await kvstore_impl(KVStoreReference(backend=backend_name, namespace="registry"))
|
||||
)
|
||||
await cached_registry.initialize()
|
||||
|
||||
result_vector_db = await cached_registry.get("vector_db", "test_vector_db")
|
||||
|
|
@ -101,7 +105,11 @@ async def test_cached_registry_updates(cached_disk_dist_registry):
|
|||
|
||||
# Verify persisted to disk
|
||||
db_path = cached_disk_dist_registry.kvstore.db_path
|
||||
new_registry = DiskDistributionRegistry(await kvstore_impl(SqliteKVStoreConfig(db_path=db_path)))
|
||||
backend_name = "kv_cached_new"
|
||||
register_kvstore_backends({backend_name: SqliteKVStoreConfig(db_path=db_path)})
|
||||
new_registry = DiskDistributionRegistry(
|
||||
await kvstore_impl(KVStoreReference(backend=backend_name, namespace="registry"))
|
||||
)
|
||||
await new_registry.initialize()
|
||||
result_vector_db = await new_registry.get("vector_db", "test_vector_db_2")
|
||||
assert result_vector_db is not None
|
||||
|
|
|
|||
|
|
@ -516,6 +516,82 @@ def test_get_attributes_from_claims():
|
|||
assert set(attributes["teams"]) == {"my-team", "group1", "group2"}
|
||||
assert attributes["namespaces"] == ["my-tenant"]
|
||||
|
||||
# Test nested claims with dot notation (e.g., Keycloak resource_access structure)
|
||||
claims = {
|
||||
"sub": "user123",
|
||||
"resource_access": {"llamastack": {"roles": ["inference_max", "admin"]}, "other-client": {"roles": ["viewer"]}},
|
||||
"realm_access": {"roles": ["offline_access", "uma_authorization"]},
|
||||
}
|
||||
attributes = get_attributes_from_claims(
|
||||
claims, {"resource_access.llamastack.roles": "roles", "realm_access.roles": "realm_roles"}
|
||||
)
|
||||
assert set(attributes["roles"]) == {"inference_max", "admin"}
|
||||
assert set(attributes["realm_roles"]) == {"offline_access", "uma_authorization"}
|
||||
|
||||
# Test that dot notation takes precedence over literal keys with dots
|
||||
claims = {
|
||||
"my.dotted.key": "literal-value",
|
||||
"my": {"dotted": {"key": "nested-value"}},
|
||||
}
|
||||
attributes = get_attributes_from_claims(claims, {"my.dotted.key": "test"})
|
||||
assert attributes["test"] == ["nested-value"]
|
||||
|
||||
# Test that literal key works when nested traversal doesn't exist
|
||||
claims = {
|
||||
"my.dotted.key": "literal-value",
|
||||
}
|
||||
attributes = get_attributes_from_claims(claims, {"my.dotted.key": "test"})
|
||||
assert attributes["test"] == ["literal-value"]
|
||||
|
||||
# Test missing nested paths are handled gracefully
|
||||
claims = {
|
||||
"sub": "user123",
|
||||
"resource_access": {"other-client": {"roles": ["viewer"]}},
|
||||
}
|
||||
attributes = get_attributes_from_claims(
|
||||
claims,
|
||||
{
|
||||
"resource_access.llamastack.roles": "roles", # Missing nested path
|
||||
"resource_access.missing.key": "missing_attr", # Missing nested path
|
||||
"completely.missing.path": "another_missing", # Completely missing
|
||||
"sub": "username", # Existing path
|
||||
},
|
||||
)
|
||||
# Only the existing claim should be in attributes
|
||||
assert attributes["username"] == ["user123"]
|
||||
assert "roles" not in attributes
|
||||
assert "missing_attr" not in attributes
|
||||
assert "another_missing" not in attributes
|
||||
|
||||
# Test mixture of flat and nested claims paths
|
||||
claims = {
|
||||
"sub": "user456",
|
||||
"flat_key": "flat-value",
|
||||
"scope": "read write admin",
|
||||
"resource_access": {"app1": {"roles": ["role1", "role2"]}, "app2": {"roles": ["role3"]}},
|
||||
"groups": ["group1", "group2"],
|
||||
"metadata": {"tenant": "tenant1", "region": "us-west"},
|
||||
}
|
||||
attributes = get_attributes_from_claims(
|
||||
claims,
|
||||
{
|
||||
"sub": "user_id", # Flat string
|
||||
"scope": "permissions", # Flat string with spaces
|
||||
"groups": "teams", # Flat list
|
||||
"resource_access.app1.roles": "app1_roles", # Nested list
|
||||
"resource_access.app2.roles": "app2_roles", # Nested list
|
||||
"metadata.tenant": "tenant", # Nested string
|
||||
"metadata.region": "region", # Nested string
|
||||
},
|
||||
)
|
||||
assert attributes["user_id"] == ["user456"]
|
||||
assert set(attributes["permissions"]) == {"read", "write", "admin"}
|
||||
assert set(attributes["teams"]) == {"group1", "group2"}
|
||||
assert set(attributes["app1_roles"]) == {"role1", "role2"}
|
||||
assert attributes["app2_roles"] == ["role3"]
|
||||
assert attributes["tenant"] == ["tenant1"]
|
||||
assert attributes["region"] == ["us-west"]
|
||||
|
||||
|
||||
# TODO: add more tests for oauth2 token provider
|
||||
|
||||
|
|
|
|||
|
|
@ -4,6 +4,8 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from uuid import uuid4
|
||||
|
||||
import pytest
|
||||
from fastapi import FastAPI, Request
|
||||
from fastapi.testclient import TestClient
|
||||
|
|
@ -11,7 +13,8 @@ from starlette.middleware.base import BaseHTTPMiddleware
|
|||
|
||||
from llama_stack.core.datatypes import QuotaConfig, QuotaPeriod
|
||||
from llama_stack.core.server.quota import QuotaMiddleware
|
||||
from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig
|
||||
from llama_stack.core.storage.datatypes import KVStoreReference, SqliteKVStoreConfig
|
||||
from llama_stack.providers.utils.kvstore import register_kvstore_backends
|
||||
|
||||
|
||||
class InjectClientIDMiddleware(BaseHTTPMiddleware):
|
||||
|
|
@ -29,8 +32,10 @@ class InjectClientIDMiddleware(BaseHTTPMiddleware):
|
|||
|
||||
|
||||
def build_quota_config(db_path) -> QuotaConfig:
|
||||
backend_name = f"kv_quota_{uuid4().hex}"
|
||||
register_kvstore_backends({backend_name: SqliteKVStoreConfig(db_path=str(db_path))})
|
||||
return QuotaConfig(
|
||||
kvstore=SqliteKVStoreConfig(db_path=str(db_path)),
|
||||
kvstore=KVStoreReference(backend=backend_name, namespace="quota"),
|
||||
anonymous_max_requests=1,
|
||||
authenticated_max_requests=2,
|
||||
period=QuotaPeriod.DAY,
|
||||
|
|
|
|||
|
|
@ -12,15 +12,22 @@ from unittest.mock import AsyncMock, MagicMock
|
|||
from pydantic import BaseModel, Field
|
||||
|
||||
from llama_stack.apis.inference import Inference
|
||||
from llama_stack.core.datatypes import (
|
||||
Api,
|
||||
Provider,
|
||||
StackRunConfig,
|
||||
)
|
||||
from llama_stack.core.datatypes import Api, Provider, StackRunConfig
|
||||
from llama_stack.core.resolver import resolve_impls
|
||||
from llama_stack.core.routers.inference import InferenceRouter
|
||||
from llama_stack.core.routing_tables.models import ModelsRoutingTable
|
||||
from llama_stack.core.storage.datatypes import (
|
||||
InferenceStoreReference,
|
||||
KVStoreReference,
|
||||
ServerStoresConfig,
|
||||
SqliteKVStoreConfig,
|
||||
SqliteSqlStoreConfig,
|
||||
SqlStoreReference,
|
||||
StorageConfig,
|
||||
)
|
||||
from llama_stack.providers.datatypes import InlineProviderSpec, ProviderSpec
|
||||
from llama_stack.providers.utils.kvstore import register_kvstore_backends
|
||||
from llama_stack.providers.utils.sqlstore.sqlstore import register_sqlstore_backends
|
||||
|
||||
|
||||
def add_protocol_methods(cls: type, protocol: type[Protocol]) -> None:
|
||||
|
|
@ -65,6 +72,35 @@ class SampleImpl:
|
|||
pass
|
||||
|
||||
|
||||
def make_run_config(**overrides) -> StackRunConfig:
|
||||
storage = overrides.pop(
|
||||
"storage",
|
||||
StorageConfig(
|
||||
backends={
|
||||
"kv_default": SqliteKVStoreConfig(db_path=":memory:"),
|
||||
"sql_default": SqliteSqlStoreConfig(db_path=":memory:"),
|
||||
},
|
||||
stores=ServerStoresConfig(
|
||||
metadata=KVStoreReference(backend="kv_default", namespace="registry"),
|
||||
inference=InferenceStoreReference(backend="sql_default", table_name="inference_store"),
|
||||
conversations=SqlStoreReference(backend="sql_default", table_name="conversations"),
|
||||
),
|
||||
),
|
||||
)
|
||||
register_kvstore_backends({name: cfg for name, cfg in storage.backends.items() if cfg.type.value.startswith("kv_")})
|
||||
register_sqlstore_backends(
|
||||
{name: cfg for name, cfg in storage.backends.items() if cfg.type.value.startswith("sql_")}
|
||||
)
|
||||
defaults = dict(
|
||||
image_name="test_image",
|
||||
apis=[],
|
||||
providers={},
|
||||
storage=storage,
|
||||
)
|
||||
defaults.update(overrides)
|
||||
return StackRunConfig(**defaults)
|
||||
|
||||
|
||||
async def test_resolve_impls_basic():
|
||||
# Create a real provider spec
|
||||
provider_spec = InlineProviderSpec(
|
||||
|
|
@ -78,7 +114,7 @@ async def test_resolve_impls_basic():
|
|||
# Create provider registry with our provider
|
||||
provider_registry = {Api.inference: {provider_spec.provider_type: provider_spec}}
|
||||
|
||||
run_config = StackRunConfig(
|
||||
run_config = make_run_config(
|
||||
image_name="test_image",
|
||||
providers={
|
||||
"inference": [
|
||||
|
|
|
|||
|
|
@ -5,7 +5,6 @@
|
|||
# the root directory of this source tree.
|
||||
|
||||
import time
|
||||
from tempfile import TemporaryDirectory
|
||||
|
||||
import pytest
|
||||
|
||||
|
|
@ -16,8 +15,16 @@ from llama_stack.apis.inference import (
|
|||
OpenAIUserMessageParam,
|
||||
Order,
|
||||
)
|
||||
from llama_stack.core.storage.datatypes import InferenceStoreReference, SqliteSqlStoreConfig
|
||||
from llama_stack.providers.utils.inference.inference_store import InferenceStore
|
||||
from llama_stack.providers.utils.sqlstore.sqlstore import SqliteSqlStoreConfig
|
||||
from llama_stack.providers.utils.sqlstore.sqlstore import register_sqlstore_backends
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def setup_backends(tmp_path):
|
||||
"""Register SQL store backends for testing."""
|
||||
db_path = str(tmp_path / "test.db")
|
||||
register_sqlstore_backends({"sql_default": SqliteSqlStoreConfig(db_path=db_path)})
|
||||
|
||||
|
||||
def create_test_chat_completion(
|
||||
|
|
@ -44,167 +51,162 @@ def create_test_chat_completion(
|
|||
|
||||
async def test_inference_store_pagination_basic():
|
||||
"""Test basic pagination functionality."""
|
||||
with TemporaryDirectory() as tmp_dir:
|
||||
db_path = tmp_dir + "/test.db"
|
||||
store = InferenceStore(SqliteSqlStoreConfig(db_path=db_path), policy=[])
|
||||
await store.initialize()
|
||||
reference = InferenceStoreReference(backend="sql_default", table_name="chat_completions")
|
||||
store = InferenceStore(reference, policy=[])
|
||||
await store.initialize()
|
||||
|
||||
# Create test data with different timestamps
|
||||
base_time = int(time.time())
|
||||
test_data = [
|
||||
("zebra-task", base_time + 1),
|
||||
("apple-job", base_time + 2),
|
||||
("moon-work", base_time + 3),
|
||||
("banana-run", base_time + 4),
|
||||
("car-exec", base_time + 5),
|
||||
]
|
||||
# Create test data with different timestamps
|
||||
base_time = int(time.time())
|
||||
test_data = [
|
||||
("zebra-task", base_time + 1),
|
||||
("apple-job", base_time + 2),
|
||||
("moon-work", base_time + 3),
|
||||
("banana-run", base_time + 4),
|
||||
("car-exec", base_time + 5),
|
||||
]
|
||||
|
||||
# Store test chat completions
|
||||
for completion_id, timestamp in test_data:
|
||||
completion = create_test_chat_completion(completion_id, timestamp)
|
||||
input_messages = [OpenAIUserMessageParam(role="user", content=f"Test message for {completion_id}")]
|
||||
await store.store_chat_completion(completion, input_messages)
|
||||
# Store test chat completions
|
||||
for completion_id, timestamp in test_data:
|
||||
completion = create_test_chat_completion(completion_id, timestamp)
|
||||
input_messages = [OpenAIUserMessageParam(role="user", content=f"Test message for {completion_id}")]
|
||||
await store.store_chat_completion(completion, input_messages)
|
||||
|
||||
# Wait for all queued writes to complete
|
||||
await store.flush()
|
||||
# Wait for all queued writes to complete
|
||||
await store.flush()
|
||||
|
||||
# Test 1: First page with limit=2, descending order (default)
|
||||
result = await store.list_chat_completions(limit=2, order=Order.desc)
|
||||
assert len(result.data) == 2
|
||||
assert result.data[0].id == "car-exec" # Most recent first
|
||||
assert result.data[1].id == "banana-run"
|
||||
assert result.has_more is True
|
||||
assert result.last_id == "banana-run"
|
||||
# Test 1: First page with limit=2, descending order (default)
|
||||
result = await store.list_chat_completions(limit=2, order=Order.desc)
|
||||
assert len(result.data) == 2
|
||||
assert result.data[0].id == "car-exec" # Most recent first
|
||||
assert result.data[1].id == "banana-run"
|
||||
assert result.has_more is True
|
||||
assert result.last_id == "banana-run"
|
||||
|
||||
# Test 2: Second page using 'after' parameter
|
||||
result2 = await store.list_chat_completions(after="banana-run", limit=2, order=Order.desc)
|
||||
assert len(result2.data) == 2
|
||||
assert result2.data[0].id == "moon-work"
|
||||
assert result2.data[1].id == "apple-job"
|
||||
assert result2.has_more is True
|
||||
# Test 2: Second page using 'after' parameter
|
||||
result2 = await store.list_chat_completions(after="banana-run", limit=2, order=Order.desc)
|
||||
assert len(result2.data) == 2
|
||||
assert result2.data[0].id == "moon-work"
|
||||
assert result2.data[1].id == "apple-job"
|
||||
assert result2.has_more is True
|
||||
|
||||
# Test 3: Final page
|
||||
result3 = await store.list_chat_completions(after="apple-job", limit=2, order=Order.desc)
|
||||
assert len(result3.data) == 1
|
||||
assert result3.data[0].id == "zebra-task"
|
||||
assert result3.has_more is False
|
||||
# Test 3: Final page
|
||||
result3 = await store.list_chat_completions(after="apple-job", limit=2, order=Order.desc)
|
||||
assert len(result3.data) == 1
|
||||
assert result3.data[0].id == "zebra-task"
|
||||
assert result3.has_more is False
|
||||
|
||||
|
||||
async def test_inference_store_pagination_ascending():
|
||||
"""Test pagination with ascending order."""
|
||||
with TemporaryDirectory() as tmp_dir:
|
||||
db_path = tmp_dir + "/test.db"
|
||||
store = InferenceStore(SqliteSqlStoreConfig(db_path=db_path), policy=[])
|
||||
await store.initialize()
|
||||
reference = InferenceStoreReference(backend="sql_default", table_name="chat_completions")
|
||||
store = InferenceStore(reference, policy=[])
|
||||
await store.initialize()
|
||||
|
||||
# Create test data
|
||||
base_time = int(time.time())
|
||||
test_data = [
|
||||
("delta-item", base_time + 1),
|
||||
("charlie-task", base_time + 2),
|
||||
("alpha-work", base_time + 3),
|
||||
]
|
||||
# Create test data
|
||||
base_time = int(time.time())
|
||||
test_data = [
|
||||
("delta-item", base_time + 1),
|
||||
("charlie-task", base_time + 2),
|
||||
("alpha-work", base_time + 3),
|
||||
]
|
||||
|
||||
# Store test chat completions
|
||||
for completion_id, timestamp in test_data:
|
||||
completion = create_test_chat_completion(completion_id, timestamp)
|
||||
input_messages = [OpenAIUserMessageParam(role="user", content=f"Test message for {completion_id}")]
|
||||
await store.store_chat_completion(completion, input_messages)
|
||||
# Store test chat completions
|
||||
for completion_id, timestamp in test_data:
|
||||
completion = create_test_chat_completion(completion_id, timestamp)
|
||||
input_messages = [OpenAIUserMessageParam(role="user", content=f"Test message for {completion_id}")]
|
||||
await store.store_chat_completion(completion, input_messages)
|
||||
|
||||
# Wait for all queued writes to complete
|
||||
await store.flush()
|
||||
# Wait for all queued writes to complete
|
||||
await store.flush()
|
||||
|
||||
# Test ascending order pagination
|
||||
result = await store.list_chat_completions(limit=1, order=Order.asc)
|
||||
assert len(result.data) == 1
|
||||
assert result.data[0].id == "delta-item" # Oldest first
|
||||
assert result.has_more is True
|
||||
# Test ascending order pagination
|
||||
result = await store.list_chat_completions(limit=1, order=Order.asc)
|
||||
assert len(result.data) == 1
|
||||
assert result.data[0].id == "delta-item" # Oldest first
|
||||
assert result.has_more is True
|
||||
|
||||
# Second page with ascending order
|
||||
result2 = await store.list_chat_completions(after="delta-item", limit=1, order=Order.asc)
|
||||
assert len(result2.data) == 1
|
||||
assert result2.data[0].id == "charlie-task"
|
||||
assert result2.has_more is True
|
||||
# Second page with ascending order
|
||||
result2 = await store.list_chat_completions(after="delta-item", limit=1, order=Order.asc)
|
||||
assert len(result2.data) == 1
|
||||
assert result2.data[0].id == "charlie-task"
|
||||
assert result2.has_more is True
|
||||
|
||||
|
||||
async def test_inference_store_pagination_with_model_filter():
|
||||
"""Test pagination combined with model filtering."""
|
||||
with TemporaryDirectory() as tmp_dir:
|
||||
db_path = tmp_dir + "/test.db"
|
||||
store = InferenceStore(SqliteSqlStoreConfig(db_path=db_path), policy=[])
|
||||
await store.initialize()
|
||||
reference = InferenceStoreReference(backend="sql_default", table_name="chat_completions")
|
||||
store = InferenceStore(reference, policy=[])
|
||||
await store.initialize()
|
||||
|
||||
# Create test data with different models
|
||||
base_time = int(time.time())
|
||||
test_data = [
|
||||
("xyz-task", base_time + 1, "model-a"),
|
||||
("def-work", base_time + 2, "model-b"),
|
||||
("pqr-job", base_time + 3, "model-a"),
|
||||
("abc-run", base_time + 4, "model-b"),
|
||||
]
|
||||
# Create test data with different models
|
||||
base_time = int(time.time())
|
||||
test_data = [
|
||||
("xyz-task", base_time + 1, "model-a"),
|
||||
("def-work", base_time + 2, "model-b"),
|
||||
("pqr-job", base_time + 3, "model-a"),
|
||||
("abc-run", base_time + 4, "model-b"),
|
||||
]
|
||||
|
||||
# Store test chat completions
|
||||
for completion_id, timestamp, model in test_data:
|
||||
completion = create_test_chat_completion(completion_id, timestamp, model)
|
||||
input_messages = [OpenAIUserMessageParam(role="user", content=f"Test message for {completion_id}")]
|
||||
await store.store_chat_completion(completion, input_messages)
|
||||
# Store test chat completions
|
||||
for completion_id, timestamp, model in test_data:
|
||||
completion = create_test_chat_completion(completion_id, timestamp, model)
|
||||
input_messages = [OpenAIUserMessageParam(role="user", content=f"Test message for {completion_id}")]
|
||||
await store.store_chat_completion(completion, input_messages)
|
||||
|
||||
# Wait for all queued writes to complete
|
||||
await store.flush()
|
||||
# Wait for all queued writes to complete
|
||||
await store.flush()
|
||||
|
||||
# Test pagination with model filter
|
||||
result = await store.list_chat_completions(limit=1, model="model-a", order=Order.desc)
|
||||
assert len(result.data) == 1
|
||||
assert result.data[0].id == "pqr-job" # Most recent model-a
|
||||
assert result.data[0].model == "model-a"
|
||||
assert result.has_more is True
|
||||
# Test pagination with model filter
|
||||
result = await store.list_chat_completions(limit=1, model="model-a", order=Order.desc)
|
||||
assert len(result.data) == 1
|
||||
assert result.data[0].id == "pqr-job" # Most recent model-a
|
||||
assert result.data[0].model == "model-a"
|
||||
assert result.has_more is True
|
||||
|
||||
# Second page with model filter
|
||||
result2 = await store.list_chat_completions(after="pqr-job", limit=1, model="model-a", order=Order.desc)
|
||||
assert len(result2.data) == 1
|
||||
assert result2.data[0].id == "xyz-task"
|
||||
assert result2.data[0].model == "model-a"
|
||||
assert result2.has_more is False
|
||||
# Second page with model filter
|
||||
result2 = await store.list_chat_completions(after="pqr-job", limit=1, model="model-a", order=Order.desc)
|
||||
assert len(result2.data) == 1
|
||||
assert result2.data[0].id == "xyz-task"
|
||||
assert result2.data[0].model == "model-a"
|
||||
assert result2.has_more is False
|
||||
|
||||
|
||||
async def test_inference_store_pagination_invalid_after():
|
||||
"""Test error handling for invalid 'after' parameter."""
|
||||
with TemporaryDirectory() as tmp_dir:
|
||||
db_path = tmp_dir + "/test.db"
|
||||
store = InferenceStore(SqliteSqlStoreConfig(db_path=db_path), policy=[])
|
||||
await store.initialize()
|
||||
reference = InferenceStoreReference(backend="sql_default", table_name="chat_completions")
|
||||
store = InferenceStore(reference, policy=[])
|
||||
await store.initialize()
|
||||
|
||||
# Try to paginate with non-existent ID
|
||||
with pytest.raises(ValueError, match="Record with id='non-existent' not found in table 'chat_completions'"):
|
||||
await store.list_chat_completions(after="non-existent", limit=2)
|
||||
# Try to paginate with non-existent ID
|
||||
with pytest.raises(ValueError, match="Record with id='non-existent' not found in table 'chat_completions'"):
|
||||
await store.list_chat_completions(after="non-existent", limit=2)
|
||||
|
||||
|
||||
async def test_inference_store_pagination_no_limit():
|
||||
"""Test pagination behavior when no limit is specified."""
|
||||
with TemporaryDirectory() as tmp_dir:
|
||||
db_path = tmp_dir + "/test.db"
|
||||
store = InferenceStore(SqliteSqlStoreConfig(db_path=db_path), policy=[])
|
||||
await store.initialize()
|
||||
reference = InferenceStoreReference(backend="sql_default", table_name="chat_completions")
|
||||
store = InferenceStore(reference, policy=[])
|
||||
await store.initialize()
|
||||
|
||||
# Create test data
|
||||
base_time = int(time.time())
|
||||
test_data = [
|
||||
("omega-first", base_time + 1),
|
||||
("beta-second", base_time + 2),
|
||||
]
|
||||
# Create test data
|
||||
base_time = int(time.time())
|
||||
test_data = [
|
||||
("omega-first", base_time + 1),
|
||||
("beta-second", base_time + 2),
|
||||
]
|
||||
|
||||
# Store test chat completions
|
||||
for completion_id, timestamp in test_data:
|
||||
completion = create_test_chat_completion(completion_id, timestamp)
|
||||
input_messages = [OpenAIUserMessageParam(role="user", content=f"Test message for {completion_id}")]
|
||||
await store.store_chat_completion(completion, input_messages)
|
||||
# Store test chat completions
|
||||
for completion_id, timestamp in test_data:
|
||||
completion = create_test_chat_completion(completion_id, timestamp)
|
||||
input_messages = [OpenAIUserMessageParam(role="user", content=f"Test message for {completion_id}")]
|
||||
await store.store_chat_completion(completion, input_messages)
|
||||
|
||||
# Wait for all queued writes to complete
|
||||
await store.flush()
|
||||
# Wait for all queued writes to complete
|
||||
await store.flush()
|
||||
|
||||
# Test without limit
|
||||
result = await store.list_chat_completions(order=Order.desc)
|
||||
assert len(result.data) == 2
|
||||
assert result.data[0].id == "beta-second" # Most recent first
|
||||
assert result.data[1].id == "omega-first"
|
||||
assert result.has_more is False
|
||||
# Test without limit
|
||||
result = await store.list_chat_completions(order=Order.desc)
|
||||
assert len(result.data) == 2
|
||||
assert result.data[0].id == "beta-second" # Most recent first
|
||||
assert result.data[1].id == "omega-first"
|
||||
assert result.has_more is False
|
||||
|
|
|
|||
|
|
@ -6,6 +6,7 @@
|
|||
|
||||
import time
|
||||
from tempfile import TemporaryDirectory
|
||||
from uuid import uuid4
|
||||
|
||||
import pytest
|
||||
|
||||
|
|
@ -15,8 +16,18 @@ from llama_stack.apis.agents.openai_responses import (
|
|||
OpenAIResponseObject,
|
||||
)
|
||||
from llama_stack.apis.inference import OpenAIMessageParam, OpenAIUserMessageParam
|
||||
from llama_stack.core.storage.datatypes import ResponsesStoreReference, SqliteSqlStoreConfig
|
||||
from llama_stack.providers.utils.responses.responses_store import ResponsesStore
|
||||
from llama_stack.providers.utils.sqlstore.sqlstore import SqliteSqlStoreConfig
|
||||
from llama_stack.providers.utils.sqlstore.sqlstore import register_sqlstore_backends
|
||||
|
||||
|
||||
def build_store(db_path: str, policy: list | None = None) -> ResponsesStore:
|
||||
backend_name = f"sql_responses_{uuid4().hex}"
|
||||
register_sqlstore_backends({backend_name: SqliteSqlStoreConfig(db_path=db_path)})
|
||||
return ResponsesStore(
|
||||
ResponsesStoreReference(backend=backend_name, table_name="responses"),
|
||||
policy=policy or [],
|
||||
)
|
||||
|
||||
|
||||
def create_test_response_object(
|
||||
|
|
@ -54,7 +65,7 @@ async def test_responses_store_pagination_basic():
|
|||
"""Test basic pagination functionality for responses store."""
|
||||
with TemporaryDirectory() as tmp_dir:
|
||||
db_path = tmp_dir + "/test.db"
|
||||
store = ResponsesStore(SqliteSqlStoreConfig(db_path=db_path), policy=[])
|
||||
store = build_store(db_path)
|
||||
await store.initialize()
|
||||
|
||||
# Create test data with different timestamps
|
||||
|
|
@ -103,7 +114,7 @@ async def test_responses_store_pagination_ascending():
|
|||
"""Test pagination with ascending order."""
|
||||
with TemporaryDirectory() as tmp_dir:
|
||||
db_path = tmp_dir + "/test.db"
|
||||
store = ResponsesStore(SqliteSqlStoreConfig(db_path=db_path), policy=[])
|
||||
store = build_store(db_path)
|
||||
await store.initialize()
|
||||
|
||||
# Create test data
|
||||
|
|
@ -141,7 +152,7 @@ async def test_responses_store_pagination_with_model_filter():
|
|||
"""Test pagination combined with model filtering."""
|
||||
with TemporaryDirectory() as tmp_dir:
|
||||
db_path = tmp_dir + "/test.db"
|
||||
store = ResponsesStore(SqliteSqlStoreConfig(db_path=db_path), policy=[])
|
||||
store = build_store(db_path)
|
||||
await store.initialize()
|
||||
|
||||
# Create test data with different models
|
||||
|
|
@ -182,7 +193,7 @@ async def test_responses_store_pagination_invalid_after():
|
|||
"""Test error handling for invalid 'after' parameter."""
|
||||
with TemporaryDirectory() as tmp_dir:
|
||||
db_path = tmp_dir + "/test.db"
|
||||
store = ResponsesStore(SqliteSqlStoreConfig(db_path=db_path), policy=[])
|
||||
store = build_store(db_path)
|
||||
await store.initialize()
|
||||
|
||||
# Try to paginate with non-existent ID
|
||||
|
|
@ -194,7 +205,7 @@ async def test_responses_store_pagination_no_limit():
|
|||
"""Test pagination behavior when no limit is specified."""
|
||||
with TemporaryDirectory() as tmp_dir:
|
||||
db_path = tmp_dir + "/test.db"
|
||||
store = ResponsesStore(SqliteSqlStoreConfig(db_path=db_path), policy=[])
|
||||
store = build_store(db_path)
|
||||
await store.initialize()
|
||||
|
||||
# Create test data
|
||||
|
|
@ -226,7 +237,7 @@ async def test_responses_store_get_response_object():
|
|||
"""Test retrieving a single response object."""
|
||||
with TemporaryDirectory() as tmp_dir:
|
||||
db_path = tmp_dir + "/test.db"
|
||||
store = ResponsesStore(SqliteSqlStoreConfig(db_path=db_path), policy=[])
|
||||
store = build_store(db_path)
|
||||
await store.initialize()
|
||||
|
||||
# Store a test response
|
||||
|
|
@ -254,7 +265,7 @@ async def test_responses_store_input_items_pagination():
|
|||
"""Test pagination functionality for input items."""
|
||||
with TemporaryDirectory() as tmp_dir:
|
||||
db_path = tmp_dir + "/test.db"
|
||||
store = ResponsesStore(SqliteSqlStoreConfig(db_path=db_path), policy=[])
|
||||
store = build_store(db_path)
|
||||
await store.initialize()
|
||||
|
||||
# Store a test response with many inputs with explicit IDs
|
||||
|
|
@ -335,7 +346,7 @@ async def test_responses_store_input_items_before_pagination():
|
|||
"""Test before pagination functionality for input items."""
|
||||
with TemporaryDirectory() as tmp_dir:
|
||||
db_path = tmp_dir + "/test.db"
|
||||
store = ResponsesStore(SqliteSqlStoreConfig(db_path=db_path), policy=[])
|
||||
store = build_store(db_path)
|
||||
await store.initialize()
|
||||
|
||||
# Store a test response with many inputs with explicit IDs
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue