mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-25 13:28:03 +00:00
feat: add auto-generated CI documentation pre-commit hook (#2890)
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
Mustafa Elbehery
parent
7f834339ba
commit
b381ed6d64
93 changed files with 495 additions and 477 deletions
|
|
@ -65,7 +65,7 @@ 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")
|
||||
log = get_logger(name=__name__, category="inference")
|
||||
|
||||
|
||||
class FireworksInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProviderData):
|
||||
|
|
@ -256,7 +256,7 @@ class FireworksInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProv
|
|||
"stream": bool(request.stream),
|
||||
**self._build_options(request.sampling_params, request.response_format, request.logprobs),
|
||||
}
|
||||
logger.debug(f"params to fireworks: {params}")
|
||||
log.debug(f"params to fireworks: {params}")
|
||||
|
||||
return params
|
||||
|
||||
|
|
|
|||
|
|
@ -3,7 +3,6 @@
|
|||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
import logging
|
||||
|
||||
from llama_stack.providers.remote.inference.llama_openai_compat.config import LlamaCompatConfig
|
||||
from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
|
||||
|
|
@ -11,8 +10,6 @@ from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
|
|||
|
||||
from .models import MODEL_ENTRIES
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class LlamaCompatInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin):
|
||||
"""
|
||||
|
|
|
|||
|
|
@ -4,7 +4,6 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import logging
|
||||
import warnings
|
||||
from collections.abc import AsyncIterator
|
||||
|
||||
|
|
@ -33,6 +32,7 @@ from llama_stack.apis.inference import (
|
|||
ToolChoice,
|
||||
ToolConfig,
|
||||
)
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.models.llama.datatypes import ToolDefinition, ToolPromptFormat
|
||||
from llama_stack.providers.utils.inference.model_registry import (
|
||||
ModelRegistryHelper,
|
||||
|
|
@ -54,7 +54,7 @@ from .openai_utils import (
|
|||
)
|
||||
from .utils import _is_nvidia_hosted
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
log = get_logger(name=__name__, category="inference")
|
||||
|
||||
|
||||
class NVIDIAInferenceAdapter(OpenAIMixin, Inference, ModelRegistryHelper):
|
||||
|
|
@ -75,7 +75,7 @@ class NVIDIAInferenceAdapter(OpenAIMixin, Inference, ModelRegistryHelper):
|
|||
# TODO(mf): filter by available models
|
||||
ModelRegistryHelper.__init__(self, model_entries=MODEL_ENTRIES)
|
||||
|
||||
logger.info(f"Initializing NVIDIAInferenceAdapter({config.url})...")
|
||||
log.info(f"Initializing NVIDIAInferenceAdapter({config.url})...")
|
||||
|
||||
if _is_nvidia_hosted(config):
|
||||
if not config.api_key:
|
||||
|
|
|
|||
|
|
@ -4,13 +4,14 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import logging
|
||||
|
||||
import httpx
|
||||
|
||||
from llama_stack.log import get_logger
|
||||
|
||||
from . import NVIDIAConfig
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
log = get_logger(name=__name__, category="inference")
|
||||
|
||||
|
||||
def _is_nvidia_hosted(config: NVIDIAConfig) -> bool:
|
||||
|
|
@ -44,7 +45,7 @@ async def check_health(config: NVIDIAConfig) -> None:
|
|||
RuntimeError: If the server is not running or ready
|
||||
"""
|
||||
if not _is_nvidia_hosted(config):
|
||||
logger.info("Checking NVIDIA NIM health...")
|
||||
log.info("Checking NVIDIA NIM health...")
|
||||
try:
|
||||
is_live, is_ready = await _get_health(config.url)
|
||||
if not is_live:
|
||||
|
|
|
|||
|
|
@ -85,7 +85,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
|
|||
|
||||
from .models import MODEL_ENTRIES
|
||||
|
||||
logger = get_logger(name=__name__, category="inference")
|
||||
log = get_logger(name=__name__, category="inference")
|
||||
|
||||
|
||||
class OllamaInferenceAdapter(
|
||||
|
|
@ -117,10 +117,10 @@ class OllamaInferenceAdapter(
|
|||
return self._openai_client
|
||||
|
||||
async def initialize(self) -> None:
|
||||
logger.info(f"checking connectivity to Ollama at `{self.config.url}`...")
|
||||
log.info(f"checking connectivity to Ollama at `{self.config.url}`...")
|
||||
health_response = await self.health()
|
||||
if health_response["status"] == HealthStatus.ERROR:
|
||||
logger.warning(
|
||||
log.warning(
|
||||
"Ollama Server is not running, make sure to start it using `ollama serve` in a separate terminal"
|
||||
)
|
||||
|
||||
|
|
@ -339,7 +339,7 @@ class OllamaInferenceAdapter(
|
|||
"options": sampling_options,
|
||||
"stream": request.stream,
|
||||
}
|
||||
logger.debug(f"params to ollama: {params}")
|
||||
log.debug(f"params to ollama: {params}")
|
||||
|
||||
return params
|
||||
|
||||
|
|
@ -437,7 +437,7 @@ class OllamaInferenceAdapter(
|
|||
if provider_resource_id not in available_models:
|
||||
available_models_latest = [m.model.split(":latest")[0] for m in response.models]
|
||||
if provider_resource_id in available_models_latest:
|
||||
logger.warning(
|
||||
log.warning(
|
||||
f"Imprecise provider resource id was used but 'latest' is available in Ollama - using '{model.provider_resource_id}:latest'"
|
||||
)
|
||||
return model
|
||||
|
|
|
|||
|
|
@ -4,7 +4,6 @@
|
|||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
import logging
|
||||
|
||||
from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin
|
||||
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
|
||||
|
|
@ -12,8 +11,6 @@ from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
|
|||
from .config import OpenAIConfig
|
||||
from .models import MODEL_ENTRIES
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
#
|
||||
# This OpenAI adapter implements Inference methods using two mixins -
|
||||
|
|
|
|||
|
|
@ -5,7 +5,6 @@
|
|||
# the root directory of this source tree.
|
||||
|
||||
|
||||
import logging
|
||||
from collections.abc import AsyncGenerator
|
||||
|
||||
from huggingface_hub import AsyncInferenceClient, HfApi
|
||||
|
|
@ -34,6 +33,7 @@ from llama_stack.apis.inference import (
|
|||
ToolPromptFormat,
|
||||
)
|
||||
from llama_stack.apis.models import Model
|
||||
from llama_stack.log import get_logger
|
||||
from llama_stack.models.llama.sku_list import all_registered_models
|
||||
from llama_stack.providers.datatypes import ModelsProtocolPrivate
|
||||
from llama_stack.providers.utils.inference.model_registry import (
|
||||
|
|
@ -58,7 +58,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
|
|||
|
||||
from .config import InferenceAPIImplConfig, InferenceEndpointImplConfig, TGIImplConfig
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
logger = get_logger(__name__, category="core")
|
||||
|
||||
|
||||
def build_hf_repo_model_entries():
|
||||
|
|
@ -307,7 +307,7 @@ class TGIAdapter(_HfAdapter):
|
|||
async def initialize(self, config: TGIImplConfig) -> None:
|
||||
if not config.url:
|
||||
raise ValueError("You must provide a URL in run.yaml (or via the TGI_URL environment variable) to use TGI.")
|
||||
log.info(f"Initializing TGI client with url={config.url}")
|
||||
logger.info(f"Initializing TGI client with url={config.url}")
|
||||
self.client = AsyncInferenceClient(
|
||||
model=config.url,
|
||||
)
|
||||
|
|
|
|||
|
|
@ -61,7 +61,7 @@ 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")
|
||||
log = get_logger(name=__name__, category="inference")
|
||||
|
||||
|
||||
class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProviderData):
|
||||
|
|
@ -232,7 +232,7 @@ class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProvi
|
|||
"stream": request.stream,
|
||||
**self._build_options(request.sampling_params, request.logprobs, request.response_format),
|
||||
}
|
||||
logger.debug(f"params to together: {params}")
|
||||
log.debug(f"params to together: {params}")
|
||||
return params
|
||||
|
||||
async def embeddings(
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue