forked from phoenix-oss/llama-stack-mirror
feat(logging): implement category-based logging (#1362)
# What does this PR do?
This commit introduces a new logging system that allows loggers to be
assigned
a category while retaining the logger name based on the file name. The
log
format includes both the logger name and the category, producing output
like:
```
INFO 2025-03-03 21:44:11,323 llama_stack.distribution.stack:103 [core]: Tool_groups: builtin::websearch served by
tavily-search
```
Key features include:
- Category-based logging: Loggers can be assigned a category (e.g.,
"core", "server") when programming. The logger can be loaded like
this: `logger = get_logger(name=__name__, category="server")`
- Environment variable control: Log levels can be configured
per-category using the
`LLAMA_STACK_LOGGING` environment variable. For example:
`LLAMA_STACK_LOGGING="server=DEBUG;core=debug"` enables DEBUG level for
the "server"
and "core" categories.
- `LLAMA_STACK_LOGGING="all=debug"` sets DEBUG level globally for all
categories and
third-party libraries.
This provides fine-grained control over logging levels while maintaining
a clean and
informative log format.
The formatter uses the rich library which provides nice colors better
stack traces like so:
```
ERROR 2025-03-03 21:49:37,124 asyncio:1758 [uncategorized]: unhandled exception during asyncio.run() shutdown
task: <Task finished name='Task-16' coro=<handle_signal.<locals>.shutdown() done, defined at
/Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/server/server.py:146>
exception=UnboundLocalError("local variable 'loop' referenced before assignment")>
╭────────────────────────────────────── Traceback (most recent call last) ───────────────────────────────────────╮
│ /Users/leseb/Documents/AI/llama-stack/llama_stack/distribution/server/server.py:178 in shutdown │
│ │
│ 175 │ │ except asyncio.CancelledError: │
│ 176 │ │ │ pass │
│ 177 │ │ finally: │
│ ❱ 178 │ │ │ loop.stop() │
│ 179 │ │
│ 180 │ loop = asyncio.get_running_loop() │
│ 181 │ loop.create_task(shutdown()) │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
UnboundLocalError: local variable 'loop' referenced before assignment
```
Co-authored-by: Ashwin Bharambe <@ashwinb>
Signed-off-by: Sébastien Han <seb@redhat.com>
[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])
## Test Plan
```
python -m llama_stack.distribution.server.server --yaml-config ./llama_stack/templates/ollama/run.yaml
INFO 2025-03-03 21:55:35,918 __main__:365 [server]: Using config file: llama_stack/templates/ollama/run.yaml
INFO 2025-03-03 21:55:35,925 __main__:378 [server]: Run configuration:
INFO 2025-03-03 21:55:35,928 __main__:380 [server]: apis:
- agents
```
[//]: # (## Documentation)
---------
Signed-off-by: Sébastien Han <seb@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
This commit is contained in:
Sébastien Han
GitHub
parent
bad12ee21f
commit
7cf1e24c4e
16 changed files with 296 additions and 431 deletions
|
|
@ -17,7 +17,6 @@ from urllib.parse import urlparse
|
|||
|
||||
import httpx
|
||||
|
||||
from llama_stack import logcat
|
||||
from llama_stack.apis.agents import (
|
||||
AgentConfig,
|
||||
AgentToolGroup,
|
||||
|
|
@ -67,6 +66,7 @@ from llama_stack.apis.tools import (
|
|||
ToolRuntime,
|
||||
)
|
||||
from llama_stack.apis.vector_io import VectorIO
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.models.llama.datatypes import (
|
||||
BuiltinTool,
|
||||
ToolCall,
|
||||
|
|
@ -88,6 +88,8 @@ MEMORY_QUERY_TOOL = "knowledge_search"
|
|||
WEB_SEARCH_TOOL = "web_search"
|
||||
RAG_TOOL_GROUP = "builtin::rag"
|
||||
|
||||
logger = get_logger(name=__name__, category="agents")
|
||||
|
||||
|
||||
class ChatAgent(ShieldRunnerMixin):
|
||||
def __init__(
|
||||
|
|
@ -609,7 +611,7 @@ class ChatAgent(ShieldRunnerMixin):
|
|||
)
|
||||
|
||||
if n_iter >= self.agent_config.max_infer_iters:
|
||||
logcat.info("agents", f"done with MAX iterations ({n_iter}), exiting.")
|
||||
logger.info(f"done with MAX iterations ({n_iter}), exiting.")
|
||||
# NOTE: mark end_of_turn to indicate to client that we are done with the turn
|
||||
# Do not continue the tool call loop after this point
|
||||
message.stop_reason = StopReason.end_of_turn
|
||||
|
|
@ -617,7 +619,7 @@ class ChatAgent(ShieldRunnerMixin):
|
|||
break
|
||||
|
||||
if stop_reason == StopReason.out_of_tokens:
|
||||
logcat.info("agents", "out of token budget, exiting.")
|
||||
logger.info("out of token budget, exiting.")
|
||||
yield message
|
||||
break
|
||||
|
||||
|
|
@ -631,16 +633,10 @@ class ChatAgent(ShieldRunnerMixin):
|
|||
message.content = [message.content] + output_attachments
|
||||
yield message
|
||||
else:
|
||||
logcat.debug(
|
||||
"agents",
|
||||
f"completion message with EOM (iter: {n_iter}): {str(message)}",
|
||||
)
|
||||
logger.debug(f"completion message with EOM (iter: {n_iter}): {str(message)}")
|
||||
input_messages = input_messages + [message]
|
||||
else:
|
||||
logcat.debug(
|
||||
"agents",
|
||||
f"completion message (iter: {n_iter}) from the model: {str(message)}",
|
||||
)
|
||||
logger.debug(f"completion message (iter: {n_iter}) from the model: {str(message)}")
|
||||
# 1. Start the tool execution step and progress
|
||||
step_id = str(uuid.uuid4())
|
||||
yield AgentTurnResponseStreamChunk(
|
||||
|
|
@ -983,7 +979,7 @@ async def attachment_message(tempdir: str, urls: List[URL]) -> ToolResponseMessa
|
|||
path = urlparse(uri).path
|
||||
basename = os.path.basename(path)
|
||||
filepath = f"{tempdir}/{make_random_string() + basename}"
|
||||
logcat.info("agents", f"Downloading {url} -> {filepath}")
|
||||
logger.info(f"Downloading {url} -> {filepath}")
|
||||
|
||||
async with httpx.AsyncClient() as client:
|
||||
r = await client.get(uri)
|
||||
|
|
@ -1023,7 +1019,7 @@ async def execute_tool_call_maybe(
|
|||
else:
|
||||
name = name.value
|
||||
|
||||
logcat.info("agents", f"executing tool call: {name} with args: {tool_call.arguments}")
|
||||
logger.info(f"executing tool call: {name} with args: {tool_call.arguments}")
|
||||
result = await tool_runtime_api.invoke_tool(
|
||||
tool_name=name,
|
||||
kwargs={
|
||||
|
|
@ -1033,7 +1029,7 @@ async def execute_tool_call_maybe(
|
|||
**toolgroup_args.get(group_name, {}),
|
||||
},
|
||||
)
|
||||
logcat.debug("agents", f"tool call {name} completed with result: {result}")
|
||||
logger.info(f"tool call {name} completed with result: {result}")
|
||||
return result
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -8,7 +8,6 @@ from typing import AsyncGenerator, List, Optional, Union
|
|||
|
||||
from fireworks.client import Fireworks
|
||||
|
||||
from llama_stack import logcat
|
||||
from llama_stack.apis.common.content_types import (
|
||||
InterleavedContent,
|
||||
InterleavedContentItem,
|
||||
|
|
@ -33,6 +32,7 @@ from llama_stack.apis.inference import (
|
|||
ToolPromptFormat,
|
||||
)
|
||||
from llama_stack.distribution.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.providers.utils.inference.model_registry import (
|
||||
ModelRegistryHelper,
|
||||
)
|
||||
|
|
@ -55,6 +55,8 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
|
|||
from .config import FireworksImplConfig
|
||||
from .models import MODEL_ENTRIES
|
||||
|
||||
logger = get_logger(name=__name__, category="inference")
|
||||
|
||||
|
||||
class FireworksInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProviderData):
|
||||
def __init__(self, config: FireworksImplConfig) -> None:
|
||||
|
|
@ -237,7 +239,8 @@ class FireworksInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProv
|
|||
"stream": request.stream,
|
||||
**self._build_options(request.sampling_params, request.response_format, request.logprobs),
|
||||
}
|
||||
logcat.debug("inference", f"params to fireworks: {params}")
|
||||
logger.debug(f"params to fireworks: {params}")
|
||||
|
||||
return params
|
||||
|
||||
async def embeddings(
|
||||
|
|
|
|||
|
|
@ -4,13 +4,12 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import logging
|
||||
|
||||
from typing import AsyncGenerator, List, Optional, Union
|
||||
|
||||
import httpx
|
||||
from ollama import AsyncClient
|
||||
|
||||
from llama_stack import logcat
|
||||
from llama_stack.apis.common.content_types import (
|
||||
ImageContentItem,
|
||||
InterleavedContent,
|
||||
|
|
@ -35,6 +34,7 @@ from llama_stack.apis.inference import (
|
|||
ToolPromptFormat,
|
||||
)
|
||||
from llama_stack.apis.models import Model, ModelType
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.providers.datatypes import ModelsProtocolPrivate
|
||||
from llama_stack.providers.utils.inference.model_registry import (
|
||||
ModelRegistryHelper,
|
||||
|
|
@ -59,7 +59,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
|
|||
|
||||
from .models import model_entries
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
logger = get_logger(name=__name__, category="inference")
|
||||
|
||||
|
||||
class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
|
||||
|
|
@ -72,7 +72,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
|
|||
return AsyncClient(host=self.url)
|
||||
|
||||
async def initialize(self) -> None:
|
||||
log.info(f"checking connectivity to Ollama at `{self.url}`...")
|
||||
logger.info(f"checking connectivity to Ollama at `{self.url}`...")
|
||||
try:
|
||||
await self.client.ps()
|
||||
except httpx.ConnectError as e:
|
||||
|
|
@ -214,7 +214,8 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
|
|||
"options": sampling_options,
|
||||
"stream": request.stream,
|
||||
}
|
||||
logcat.debug("inference", f"params to ollama: {params}")
|
||||
logger.debug(f"params to ollama: {params}")
|
||||
|
||||
return params
|
||||
|
||||
async def _nonstream_chat_completion(self, request: ChatCompletionRequest) -> ChatCompletionResponse:
|
||||
|
|
@ -290,7 +291,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
|
|||
async def register_model(self, model: Model) -> Model:
|
||||
model = await self.register_helper.register_model(model)
|
||||
if model.model_type == ModelType.embedding:
|
||||
log.info(f"Pulling embedding model `{model.provider_resource_id}` if necessary...")
|
||||
logger.info(f"Pulling embedding model `{model.provider_resource_id}` if necessary...")
|
||||
await self.client.pull(model.provider_resource_id)
|
||||
response = await self.client.list()
|
||||
else:
|
||||
|
|
|
|||
|
|
@ -8,7 +8,6 @@ from typing import AsyncGenerator, List, Optional, Union
|
|||
|
||||
from together import Together
|
||||
|
||||
from llama_stack import logcat
|
||||
from llama_stack.apis.common.content_types import (
|
||||
InterleavedContent,
|
||||
InterleavedContentItem,
|
||||
|
|
@ -32,6 +31,7 @@ from llama_stack.apis.inference import (
|
|||
ToolPromptFormat,
|
||||
)
|
||||
from llama_stack.distribution.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.providers.utils.inference.model_registry import (
|
||||
ModelRegistryHelper,
|
||||
)
|
||||
|
|
@ -54,6 +54,8 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
|
|||
from .config import TogetherImplConfig
|
||||
from .models import MODEL_ENTRIES
|
||||
|
||||
logger = get_logger(name=__name__, category="inference")
|
||||
|
||||
|
||||
class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProviderData):
|
||||
def __init__(self, config: TogetherImplConfig) -> None:
|
||||
|
|
@ -224,8 +226,7 @@ class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProvi
|
|||
"stream": request.stream,
|
||||
**self._build_options(request.sampling_params, request.logprobs, request.response_format),
|
||||
}
|
||||
logcat.debug("inference", f"params to together: {params}")
|
||||
return params
|
||||
logger.debug(f"params to together: {params}")
|
||||
|
||||
async def embeddings(
|
||||
self,
|
||||
|
|
|
|||
|
|
@ -8,7 +8,6 @@ from typing import AsyncGenerator, AsyncIterator, List, Optional, Union
|
|||
|
||||
import litellm
|
||||
|
||||
from llama_stack import logcat
|
||||
from llama_stack.apis.common.content_types import (
|
||||
InterleavedContent,
|
||||
InterleavedContentItem,
|
||||
|
|
@ -33,6 +32,7 @@ from llama_stack.apis.inference import (
|
|||
)
|
||||
from llama_stack.apis.models.models import Model
|
||||
from llama_stack.distribution.request_headers import NeedsRequestProviderData
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.providers.utils.inference.model_registry import (
|
||||
ModelRegistryHelper,
|
||||
)
|
||||
|
|
@ -47,6 +47,8 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
|
|||
interleaved_content_as_str,
|
||||
)
|
||||
|
||||
logger = get_logger(name=__name__, category="inference")
|
||||
|
||||
|
||||
class LiteLLMOpenAIMixin(
|
||||
ModelRegistryHelper,
|
||||
|
|
@ -109,8 +111,7 @@ class LiteLLMOpenAIMixin(
|
|||
)
|
||||
|
||||
params = await self._get_params(request)
|
||||
logcat.debug("inference", f"params to litellm (openai compat): {params}")
|
||||
|
||||
logger.debug(f"params to litellm (openai compat): {params}")
|
||||
# unfortunately, we need to use synchronous litellm.completion here because litellm
|
||||
# caches various httpx.client objects in a non-eventloop aware manner
|
||||
response = litellm.completion(**params)
|
||||
|
|
|
|||
|
|
@ -8,14 +8,12 @@ import asyncio
|
|||
import base64
|
||||
import io
|
||||
import json
|
||||
import logging
|
||||
import re
|
||||
from typing import List, Optional, Tuple, Union
|
||||
|
||||
import httpx
|
||||
from PIL import Image as PIL_Image
|
||||
|
||||
from llama_stack import logcat
|
||||
from llama_stack.apis.common.content_types import (
|
||||
ImageContentItem,
|
||||
InterleavedContent,
|
||||
|
|
@ -34,6 +32,7 @@ from llama_stack.apis.inference import (
|
|||
ToolDefinition,
|
||||
UserMessage,
|
||||
)
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.models.llama.datatypes import (
|
||||
ModelFamily,
|
||||
RawContent,
|
||||
|
|
@ -58,7 +57,7 @@ from llama_stack.models.llama.llama3.tokenizer import Tokenizer
|
|||
from llama_stack.models.llama.sku_list import resolve_model
|
||||
from llama_stack.providers.utils.inference import supported_inference_models
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
log = get_logger(name=__name__, category="inference")
|
||||
|
||||
|
||||
class ChatCompletionRequestWithRawContent(ChatCompletionRequest):
|
||||
|
|
@ -464,7 +463,7 @@ def _get_tool_choice_prompt(tool_choice: ToolChoice | str, tools: List[ToolDefin
|
|||
def get_default_tool_prompt_format(model: str) -> ToolPromptFormat:
|
||||
llama_model = resolve_model(model)
|
||||
if llama_model is None:
|
||||
logcat.warning("inference", f"Could not resolve model {model}, defaulting to json tool prompt format")
|
||||
log.warning(f"Could not resolve model {model}, defaulting to json tool prompt format")
|
||||
return ToolPromptFormat.json
|
||||
|
||||
if llama_model.model_family == ModelFamily.llama3_1 or (
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue