phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: remove /v1/inference/completion and implementations

Browse source
This commit is contained in:
Matthew Farrellee 2025-09-30 03:46:07 -04:00
parent 606f4cf281
commit 4b641d7127
78 changed files with 16143 additions and 17755 deletions
Download patch file Download diff file Expand all files Collapse all files

22
llama_stack/providers/utils/inference/prompt_adapter.py
View file

@ -229,28 +229,6 @@ async def convert_image_content_to_url(
return base64.b64encode(content).decode("utf-8")
async def completion_request_to_prompt(request: CompletionRequest) -> str:
content = augment_content_with_response_format_prompt(request.response_format, request.content)
request.content = content
request = await convert_request_to_raw(request)
formatter = ChatFormat(tokenizer=Tokenizer.get_instance())
model_input = formatter.encode_content(request.content)
return formatter.tokenizer.decode(model_input.tokens)
async def completion_request_to_prompt_model_input_info(
request: CompletionRequest,
) -> tuple[str, int]:
content = augment_content_with_response_format_prompt(request.response_format, request.content)
request.content = content
request = await convert_request_to_raw(request)
formatter = ChatFormat(tokenizer=Tokenizer.get_instance())
model_input = formatter.encode_content(request.content)
return (formatter.tokenizer.decode(model_input.tokens), len(model_input.tokens))
def augment_content_with_response_format_prompt(response_format, content):
if fmt_prompt := response_format_prompt(response_format):
if isinstance(content, list):