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 (#3622)

Browse source 
# What does this PR do?

the /inference/completion route is gone. this removes the
implementations.

## Test Plan

ci
This commit is contained in:
Matthew Farrellee 2025-10-01 11:36:53 -04:00 • committed by GitHub
parent ea15f2a270
commit f7c5ef4ec0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
75 changed files with 16141 additions and 17056 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):