phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-25 04:58:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: add auto-generated CI documentation pre-commit hook (#2890)

Browse source 
Our CI is entirely undocumented, this commit adds a README.md file with
a table of the current CI and what is does

---------

Signed-off-by: Nathan Weinberg <nweinber@redhat.com>
This commit is contained in:
Nathan Weinberg 2025-07-25 11:57:01 -04:00 • committed by Mustafa Elbehery
parent 7f834339ba
commit b381ed6d64
93 changed files with 495 additions and 477 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -5,7 +5,6 @@
# the root directory of this source tree.
import base64
import logging
import struct
from typing import TYPE_CHECKING
@ -27,7 +26,9 @@ from llama_stack.providers.utils.inference.prompt_adapter import interleaved_con
EMBEDDING_MODELS = {}
log = logging.getLogger(__name__)
from llama_stack.log import get_logger
log = get_logger(name=__name__, category="inference")
class SentenceTransformerEmbeddingMixin:

6
llama_stack/providers/utils/inference/litellm_openai_mixin.py
View file

@ -54,7 +54,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
interleaved_content_as_str,
)
logger = get_logger(name=__name__, category="inference")
log = get_logger(name=__name__, category="inference")
class LiteLLMOpenAIMixin(
@ -157,7 +157,7 @@ class LiteLLMOpenAIMixin(
params = await self._get_params(request)
params["model"] = self.get_litellm_model_name(params["model"])
logger.debug(f"params to litellm (openai compat): {params}")
log.debug(f"params to litellm (openai compat): {params}")
# see https://docs.litellm.ai/docs/completion/stream#async-completion
response = await litellm.acompletion(**params)
if stream:
@ -460,7 +460,7 @@ class LiteLLMOpenAIMixin(
:return: True if the model is available dynamically, False otherwise.
"""
if self.litellm_provider_name not in litellm.models_by_provider:
logger.error(f"Provider {self.litellm_provider_name} is not registered in litellm.")
log.error(f"Provider {self.litellm_provider_name} is not registered in litellm.")
return False
return model in litellm.models_by_provider[self.litellm_provider_name]

4
llama_stack/providers/utils/inference/model_registry.py
View file

@ -17,7 +17,7 @@ from llama_stack.providers.utils.inference import (
ALL_HUGGINGFACE_REPOS_TO_MODEL_DESCRIPTOR,
)
logger = get_logger(name=__name__, category="core")
log = get_logger(name=__name__, category="core")
class RemoteInferenceProviderConfig(BaseModel):
@ -135,7 +135,7 @@ class ModelRegistryHelper(ModelsProtocolPrivate):
:param model: The model identifier to check.
:return: True if the model is available dynamically, False otherwise.
"""
logger.info(
log.info(
f"check_model_availability is not implemented for {self.__class__.__name__}. Returning False by default."
)
return False

10
llama_stack/providers/utils/inference/openai_compat.py
View file

@ -5,7 +5,6 @@
# the root directory of this source tree.
import base64
import json
import logging
import struct
import time
import uuid
@ -116,6 +115,7 @@ from llama_stack.apis.inference import (
from llama_stack.apis.inference import (
OpenAIChoice as OpenAIChatCompletionChoice,
)
from llama_stack.log import get_logger
from llama_stack.models.llama.datatypes import (
BuiltinTool,
StopReason,
@ -128,7 +128,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
decode_assistant_message,
)
logger = logging.getLogger(__name__)
log = get_logger(name=__name__, category="inference")
class OpenAICompatCompletionChoiceDelta(BaseModel):
@ -316,7 +316,7 @@ def process_chat_completion_response(
if t.tool_name in request_tools:
new_tool_calls.append(t)
else:
logger.warning(f"Tool {t.tool_name} not found in request tools")
log.warning(f"Tool {t.tool_name} not found in request tools")
if len(new_tool_calls) < len(raw_message.tool_calls):
raw_message.tool_calls = new_tool_calls
@ -477,7 +477,7 @@ async def process_chat_completion_stream_response(
)
)
else:
logger.warning(f"Tool {tool_call.tool_name} not found in request tools")
log.warning(f"Tool {tool_call.tool_name} not found in request tools")
yield ChatCompletionResponseStreamChunk(
event=ChatCompletionResponseEvent(
event_type=ChatCompletionResponseEventType.progress,
@ -1198,7 +1198,7 @@ async def convert_openai_chat_completion_stream(
)
for idx, buffer in tool_call_idx_to_buffer.items():
logger.debug(f"toolcall_buffer[{idx}]: {buffer}")
log.debug(f"toolcall_buffer[{idx}]: {buffer}")
if buffer["name"]:
delta = ")"
buffer["content"] += delta

8
llama_stack/providers/utils/inference/openai_mixin.py
View file

@ -25,7 +25,7 @@ from llama_stack.apis.inference import (
from llama_stack.log import get_logger
from llama_stack.providers.utils.inference.openai_compat import prepare_openai_completion_params
logger = get_logger(name=__name__, category="core")
log = get_logger(name=__name__, category="core")
class OpenAIMixin(ABC):
@ -125,9 +125,9 @@ class OpenAIMixin(ABC):
Direct OpenAI completion API call.
"""
if guided_choice is not None:
logger.warning("guided_choice is not supported by the OpenAI API. Ignoring.")
log.warning("guided_choice is not supported by the OpenAI API. Ignoring.")
if prompt_logprobs is not None:
logger.warning("prompt_logprobs is not supported by the OpenAI API. Ignoring.")
log.warning("prompt_logprobs is not supported by the OpenAI API. Ignoring.")
# TODO: fix openai_completion to return type compatible with OpenAI's API response
return await self.client.completions.create( # type: ignore[no-any-return]
@ -267,6 +267,6 @@ class OpenAIMixin(ABC):
pass
except Exception as e:
# All other errors (auth, rate limit, network, etc.)
logger.warning(f"Failed to check model availability for {model}: {e}")
log.warning(f"Failed to check model availability for {model}: {e}")
return False