phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-13 04:22:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add completion() impl for meta-reference

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-18 20:41:21 -07:00
parent bcaf639dd6
commit 072d1b7205
4 changed files with 137 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/apis/inference/inference.py
View file

@ -88,7 +88,8 @@ class CompletionRequest(BaseModel):
class CompletionResponse(BaseModel):
"""Completion response."""
completion_message: CompletionMessage
content: str
stop_reason: StopReason
logprobs: Optional[List[TokenLogProbs]] = None
@ -113,7 +114,7 @@ class BatchCompletionRequest(BaseModel):
class BatchCompletionResponse(BaseModel):
"""Batch completion response."""
completion_message_batch: List[CompletionMessage]
batch: List[CompletionResponse]
@json_schema_type
@ -165,7 +166,7 @@ class BatchChatCompletionRequest(BaseModel):
@json_schema_type
class BatchChatCompletionResponse(BaseModel):
completion_message_batch: List[CompletionMessage]
batch: List[ChatCompletionResponse]
@json_schema_type