phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-03 17:29:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

ollama import remove

Browse source
This commit is contained in:
Xi Yan 2024-12-26 18:07:18 -08:00
parent 165777a181
commit f97638a323
3 changed files with 43 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

28
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -5,7 +5,7 @@
# the root directory of this source tree. # the root directory of this source tree.
import logging import logging
from typing import AsyncGenerator from typing import AsyncGenerator, List, Optional, Union
import httpx import httpx
from llama_models.datatypes import CoreModelId from llama_models.datatypes import CoreModelId
@ -14,15 +14,33 @@ from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.tokenizer import Tokenizer from llama_models.llama3.api.tokenizer import Tokenizer
from ollama import AsyncClient from ollama import AsyncClient
from llama_stack.apis.common.content_types import (
ImageContentItem,
InterleavedContent,
TextContentItem,
)
from llama_stack.apis.inference import (
ChatCompletionRequest,
ChatCompletionResponse,
CompletionRequest,
EmbeddingsResponse,
Inference,
LogProbConfig,
Message,
ResponseFormat,
SamplingParams,
ToolChoice,
ToolDefinition,
ToolPromptFormat,
)
from llama_stack.apis.models import Model, ModelType
from llama_stack.providers.datatypes import ModelsProtocolPrivate
from llama_stack.providers.utils.inference.model_registry import ( from llama_stack.providers.utils.inference.model_registry import (
build_model_alias, build_model_alias,
build_model_alias_with_just_provider_model_id, build_model_alias_with_just_provider_model_id,
ModelRegistryHelper, ModelRegistryHelper,
) )
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.apis.common.content_types import ImageContentItem, TextContentItem
from llama_stack.providers.datatypes import ModelsProtocolPrivate
from llama_stack.providers.utils.inference.openai_compat import ( from llama_stack.providers.utils.inference.openai_compat import (
get_sampling_options, get_sampling_options,
OpenAICompatCompletionChoice, OpenAICompatCompletionChoice,

5
llama_stack/providers/remote/inference/sample/sample.py
View file

@ -4,12 +4,11 @@
# This source code is licensed under the terms described in the LICENSE file in # This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree. # the root directory of this source tree.
from llama_stack.apis.inference import Inference
from llama_stack.apis.models import Model
from .config import SampleConfig from .config import SampleConfig
from llama_stack.apis.inference import * # noqa: F403
class SampleInferenceImpl(Inference): class SampleInferenceImpl(Inference):
def __init__(self, config: SampleConfig): def __init__(self, config: SampleConfig):
self.config = config self.config = config

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

@ -13,10 +13,25 @@ from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.tokenizer import Tokenizer from llama_models.llama3.api.tokenizer import Tokenizer
from llama_models.sku_list import all_registered_models from llama_models.sku_list import all_registered_models
from llama_stack.apis.inference import * # noqa: F403 from llama_stack.apis.common.content_types import InterleavedContent
from llama_stack.apis.models import * # noqa: F403 from llama_stack.apis.inference import (
ChatCompletionRequest,
ChatCompletionResponse,
CompletionRequest,
EmbeddingsResponse,
Inference,
LogProbConfig,
Message,
ResponseFormat,
ResponseFormatType,
SamplingParams,
ToolChoice,
ToolDefinition,
ToolPromptFormat,
)
from llama_stack.apis.models import Model
from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate from llama_stack.providers.datatypes import ModelsProtocolPrivate
from llama_stack.providers.utils.inference.model_registry import ( from llama_stack.providers.utils.inference.model_registry import (
build_model_alias, build_model_alias,
ModelRegistryHelper, ModelRegistryHelper,