phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-09 05:08:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into vector-store-chunks

Browse source
This commit is contained in:
Francisco Arceo 2025-08-01 23:22:23 -04:00 • committed by GitHub
commit 469413a90d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
72 changed files with 10143 additions and 1784 deletions
Download patch file Download diff file Expand all files Collapse all files

12
llama_stack/providers/utils/inference/litellm_openai_mixin.py
View file

@ -72,6 +72,8 @@ class LiteLLMOpenAIMixin(
api_key_from_config: str | None,
provider_data_api_key_field: str,
openai_compat_api_base: str | None = None,
download_images: bool = False,
json_schema_strict: bool = True,
):
"""
Initialize the LiteLLMOpenAIMixin.
@ -81,6 +83,8 @@ class LiteLLMOpenAIMixin(
:param provider_data_api_key_field: The field in the provider data that contains the API key.
:param litellm_provider_name: The name of the provider, used for model lookups.
:param openai_compat_api_base: The base URL for OpenAI compatibility, or None if not using OpenAI compatibility.
:param download_images: Whether to download images and convert to base64 for message conversion.
:param json_schema_strict: Whether to use strict mode for JSON schema validation.
"""
ModelRegistryHelper.__init__(self, model_entries)
@ -88,6 +92,8 @@ class LiteLLMOpenAIMixin(
self.api_key_from_config = api_key_from_config
self.provider_data_api_key_field = provider_data_api_key_field
self.api_base = openai_compat_api_base
self.download_images = download_images
self.json_schema_strict = json_schema_strict
if openai_compat_api_base:
self.is_openai_compat = True
@ -206,7 +212,9 @@ class LiteLLMOpenAIMixin(
async def _get_params(self, request: ChatCompletionRequest) -> dict:
input_dict = {}
input_dict["messages"] = [await convert_message_to_openai_dict_new(m) for m in request.messages]
input_dict["messages"] = [
await convert_message_to_openai_dict_new(m, download_images=self.download_images) for m in request.messages
]
if fmt := request.response_format:
if not isinstance(fmt, JsonSchemaResponseFormat):
raise ValueError(
@ -226,7 +234,7 @@ class LiteLLMOpenAIMixin(
"json_schema": {
"name": name,
"schema": fmt,
"strict": True,
"strict": self.json_schema_strict,
},
}
if request.tools:

5
llama_stack/providers/utils/inference/openai_compat.py
View file

@ -564,6 +564,7 @@ class UnparseableToolCall(BaseModel):
async def convert_message_to_openai_dict_new(
message: Message | dict,
download_images: bool = False,
) -> OpenAIChatCompletionMessage:
"""
Convert a Message to an OpenAI API-compatible dictionary.
@ -607,7 +608,9 @@ async def convert_message_to_openai_dict_new(
elif isinstance(content_, ImageContentItem):
return OpenAIChatCompletionContentPartImageParam(
type="image_url",
image_url=OpenAIImageURL(url=await convert_image_content_to_url(content_)),
image_url=OpenAIImageURL(
url=await convert_image_content_to_url(content_, download=download_images)
),
)
elif isinstance(content_, list):
return [await impl(item) for item in content_]