phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-09 03:19:20 +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

8
llama_stack/providers/utils/inference/augment_messages.py → llama_stack/providers/utils/inference/prompt_adapter.py
View file

@ -26,7 +26,7 @@ from llama_stack.providers.utils.inference import supported_inference_models
def chat_completion_request_to_prompt(
request: ChatCompletionRequest, formatter: ChatFormat
) -> str:
messages = augment_messages_for_tools(request)
messages = chat_completion_request_to_messages(request)
model_input = formatter.encode_dialog_prompt(messages)
return formatter.tokenizer.decode(model_input.tokens)
@ -34,7 +34,7 @@ def chat_completion_request_to_prompt(
def chat_completion_request_to_model_input_info(
request: ChatCompletionRequest, formatter: ChatFormat
) -> Tuple[str, int]:
messages = augment_messages_for_tools(request)
messages = chat_completion_request_to_messages(request)
model_input = formatter.encode_dialog_prompt(messages)
return (
formatter.tokenizer.decode(model_input.tokens),
@ -42,7 +42,9 @@ def chat_completion_request_to_model_input_info(
)
def augment_messages_for_tools(request: ChatCompletionRequest) -> List[Message]:
def chat_completion_request_to_messages(
request: ChatCompletionRequest,
) -> List[Message]:
"""Reads chat completion request and augments the messages to handle tools.
For eg. for llama_3_1, add system message with the appropriate tools or
add user messsage for custom tools, etc.