phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-05 20:27:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

bugfixes

Browse source
This commit is contained in:
Ashwin Bharambe 2024-09-28 15:21:32 -07:00
parent 37ca22cda6
commit 23028e26ff
7 changed files with 83 additions and 47 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/providers/utils/inference/augment_messages.py
View file

@ -16,6 +16,8 @@ from llama_models.llama3.prompt_templates import (
)
from llama_models.sku_list import resolve_model
from llama_stack.providers.utils.inference import supported_inference_models
def augment_messages_for_tools(request: ChatCompletionRequest) -> List[Message]:
"""Reads chat completion request and augments the messages to handle tools.
@ -27,8 +29,8 @@ def augment_messages_for_tools(request: ChatCompletionRequest) -> List[Message]:
cprint(f"Could not resolve model {request.model}", color="red")
return request.messages
if model.model_family not in [ModelFamily.llama3_1, ModelFamily.llama3_2]:
cprint(f"Model family {model.model_family} not llama 3_1 or 3_2", color="red")
if model.descriptor() not in supported_inference_models():
cprint(f"Unsupported inference model? {model.descriptor()}", color="red")
return request.messages
if model.model_family == ModelFamily.llama3_1 or (