phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-03 02:52:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

pre-commit fixes

Browse source
This commit is contained in:
Chantal D Gama Rose 2025-03-14 13:56:05 -07:00
parent 967dd0aa08
commit 7e211f8553
314 changed files with 5574 additions and 11369 deletions
Download patch file Download diff file Expand all files Collapse all files

21
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -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:
@ -90,11 +90,13 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
self,
model_id: str,
content: InterleavedContent,
sampling_params: Optional[SamplingParams] = SamplingParams(),
sampling_params: Optional[SamplingParams] = None,
response_format: Optional[ResponseFormat] = None,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
if sampling_params is None:
sampling_params = SamplingParams()
model = await self.model_store.get_model(model_id)
request = CompletionRequest(
model=model.provider_resource_id,
@ -145,7 +147,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
self,
model_id: str,
messages: List[Message],
sampling_params: Optional[SamplingParams] = SamplingParams(),
sampling_params: Optional[SamplingParams] = None,
response_format: Optional[ResponseFormat] = None,
tools: Optional[List[ToolDefinition]] = None,
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
@ -154,6 +156,8 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
logprobs: Optional[LogProbConfig] = None,
tool_config: Optional[ToolConfig] = None,
) -> AsyncGenerator:
if sampling_params is None:
sampling_params = SamplingParams()
model = await self.model_store.get_model(model_id)
request = ChatCompletionRequest(
model=model.provider_resource_id,
@ -210,7 +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:
@ -286,7 +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: