phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Use new definitions of Model / SKU

Browse source
This commit is contained in:
Ashwin Bharambe 2024-07-31 11:36:16 -07:00
parent 156bfa0e15
commit 09cf3fe78b
8 changed files with 63 additions and 65 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_toolchain/inference/api/endpoints.py
View file

@ -13,7 +13,7 @@ from pyopenapi import webmethod
@json_schema_type
class CompletionRequest(BaseModel):
model: PretrainedModel
model: str
content: InterleavedTextAttachment
sampling_params: Optional[SamplingParams] = SamplingParams()
@ -39,7 +39,7 @@ class CompletionResponseStreamChunk(BaseModel):
@json_schema_type
class BatchCompletionRequest(BaseModel):
model: PretrainedModel
model: str
content_batch: List[InterleavedTextAttachment]
sampling_params: Optional[SamplingParams] = SamplingParams()
logprobs: Optional[LogProbConfig] = None
@ -53,7 +53,7 @@ class BatchCompletionResponse(BaseModel):
@json_schema_type
class ChatCompletionRequest(BaseModel):
model: InstructModel
model: str
messages: List[Message]
sampling_params: Optional[SamplingParams] = SamplingParams()
@ -80,7 +80,7 @@ class ChatCompletionResponse(BaseModel):
@json_schema_type
class BatchChatCompletionRequest(BaseModel):
model: InstructModel
model: str
messages_batch: List[List[Message]]
sampling_params: Optional[SamplingParams] = SamplingParams()