phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-09 11:20:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

rename augment_messages

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-08 13:48:44 -07:00 • committed by Ashwin Bharambe
parent 336cf7a674
commit 640c5c54f7
10 changed files with 34 additions and 33 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/providers/adapters/inference/databricks/databricks.py
View file

@ -15,15 +15,15 @@ from openai import OpenAI
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.providers.utils.inference.augment_messages import (
chat_completion_request_to_prompt,
)
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
from llama_stack.providers.utils.inference.openai_compat import (
get_sampling_options,
process_chat_completion_response,
process_chat_completion_stream_response,
)
from llama_stack.providers.utils.inference.prompt_adapter import (
chat_completion_request_to_prompt,
)
from .config import DatabricksImplConfig

6
llama_stack/providers/adapters/inference/fireworks/fireworks.py
View file

@ -15,15 +15,15 @@ from llama_models.llama3.api.tokenizer import Tokenizer
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.providers.utils.inference.augment_messages import (
chat_completion_request_to_prompt,
)
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
from llama_stack.providers.utils.inference.openai_compat import (
get_sampling_options,
process_chat_completion_response,
process_chat_completion_stream_response,
)
from llama_stack.providers.utils.inference.prompt_adapter import (
chat_completion_request_to_prompt,
)
from .config import FireworksImplConfig

6
llama_stack/providers/adapters/inference/ollama/ollama.py
View file

@ -15,9 +15,6 @@ from llama_models.llama3.api.tokenizer import Tokenizer
from ollama import AsyncClient
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.providers.utils.inference.augment_messages import (
chat_completion_request_to_prompt,
)
from llama_stack.providers.utils.inference.openai_compat import (
get_sampling_options,
OpenAICompatCompletionChoice,
@ -25,6 +22,9 @@ from llama_stack.providers.utils.inference.openai_compat import (
process_chat_completion_response,
process_chat_completion_stream_response,
)
from llama_stack.providers.utils.inference.prompt_adapter import (
chat_completion_request_to_prompt,
)
OLLAMA_SUPPORTED_MODELS = {
"Llama3.1-8B-Instruct": "llama3.1:8b-instruct-fp16",

6
llama_stack/providers/adapters/inference/tgi/tgi.py
View file

@ -14,9 +14,6 @@ from llama_models.llama3.api.tokenizer import Tokenizer
from llama_models.sku_list import resolve_model
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.providers.utils.inference.augment_messages import (
chat_completion_request_to_model_input_info,
)
from llama_stack.providers.utils.inference.openai_compat import (
get_sampling_options,
OpenAICompatCompletionChoice,
@ -24,6 +21,9 @@ from llama_stack.providers.utils.inference.openai_compat import (
process_chat_completion_response,
process_chat_completion_stream_response,
)
from llama_stack.providers.utils.inference.prompt_adapter import (
chat_completion_request_to_model_input_info,
)
from .config import InferenceAPIImplConfig, InferenceEndpointImplConfig, TGIImplConfig

6
llama_stack/providers/adapters/inference/together/together.py
View file

@ -15,15 +15,15 @@ from together import Together
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.distribution.request_headers import NeedsRequestProviderData
from llama_stack.providers.utils.inference.augment_messages import (
chat_completion_request_to_prompt,
)
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
from llama_stack.providers.utils.inference.openai_compat import (
get_sampling_options,
process_chat_completion_response,
process_chat_completion_stream_response,
)
from llama_stack.providers.utils.inference.prompt_adapter import (
chat_completion_request_to_prompt,
)
from .config import TogetherImplConfig