phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Moved ToolPromptFormat and jinja templates to llama_models.llama3.api

Browse source
This commit is contained in:
Hardik Shah 2024-08-23 14:58:52 -07:00
parent ab8193c88c
commit 5655266d58
13 changed files with 21 additions and 388 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_toolchain/inference/api/endpoints.py
View file

@ -7,7 +7,7 @@
from .datatypes import * # noqa: F403
from typing import Optional, Protocol
from llama_models.llama3.api.datatypes import ToolDefinition
from llama_models.llama3.api.datatypes import ToolDefinition, ToolPromptFormat
# this dependency is annoying and we need a forked up version anyway
from llama_models.schema_utils import webmethod
@ -16,7 +16,7 @@ from llama_models.schema_utils import webmethod
@json_schema_type
class CompletionRequest(BaseModel):
model: str
content: InterleavedTextAttachment
content: InterleavedTextMedia
sampling_params: Optional[SamplingParams] = SamplingParams()
stream: Optional[bool] = False
@ -41,7 +41,7 @@ class CompletionResponseStreamChunk(BaseModel):
@json_schema_type
class BatchCompletionRequest(BaseModel):
model: str
content_batch: List[InterleavedTextAttachment]
content_batch: List[InterleavedTextMedia]
sampling_params: Optional[SamplingParams] = SamplingParams()
logprobs: Optional[LogProbConfig] = None