phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-12 05:54:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: refactor (chat)completions endpoints to use shared params struct (#3761)

Browse source 
# What does this PR do?

Converts openai(_chat)_completions params to pydantic BaseModel to
reduce code duplication across all providers.

## Test Plan
CI









---
[//]: # (BEGIN SAPLING FOOTER)
Stack created with [Sapling](https://sapling-scm.com). Best reviewed
with
[ReviewStack](https://reviewstack.dev/llamastack/llama-stack/pull/3761).
* #3777
* __->__ #3761
This commit is contained in:
ehhuang 2025-10-10 15:46:34 -07:00 • committed by GitHub
parent 6954fe2274
commit 80d58ab519
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
33 changed files with 599 additions and 890 deletions
Download patch file Download diff file Expand all files Collapse all files

22
llama_stack/providers/inline/safety/llama_guard/llama_guard.py
View file

@ -10,7 +10,13 @@ from string import Template
from typing import Any
from llama_stack.apis.common.content_types import ImageContentItem, TextContentItem
from llama_stack.apis.inference import Inference, Message, UserMessage
from llama_stack.apis.inference import (
Inference,
Message,
OpenAIChatCompletionRequest,
OpenAIUserMessageParam,
UserMessage,
)
from llama_stack.apis.safety import (
RunShieldResponse,
Safety,
@ -290,20 +296,21 @@ class LlamaGuardShield:
else:
shield_input_message = self.build_text_shield_input(messages)
response = await self.inference_api.openai_chat_completion(
params = OpenAIChatCompletionRequest(
model=self.model,
messages=[shield_input_message],
stream=False,
temperature=0.0, # default is 1, which is too high for safety
)
response = await self.inference_api.openai_chat_completion(params)
content = response.choices[0].message.content
content = content.strip()
return self.get_shield_response(content)
def build_text_shield_input(self, messages: list[Message]) -> UserMessage:
return UserMessage(content=self.build_prompt(messages))
def build_text_shield_input(self, messages: list[Message]) -> OpenAIUserMessageParam:
return OpenAIUserMessageParam(role="user", content=self.build_prompt(messages))
def build_vision_shield_input(self, messages: list[Message]) -> UserMessage:
def build_vision_shield_input(self, messages: list[Message]) -> OpenAIUserMessageParam:
conversation = []
most_recent_img = None
@ -335,7 +342,7 @@ class LlamaGuardShield:
prompt.append(most_recent_img)
prompt.append(self.build_prompt(conversation[::-1]))
return UserMessage(content=prompt)
return OpenAIUserMessageParam(role="user", content=prompt)
def build_prompt(self, messages: list[Message]) -> str:
categories = self.get_safety_categories()
@ -377,11 +384,12 @@ class LlamaGuardShield:
# TODO: Add Image based support for OpenAI Moderations
shield_input_message = self.build_text_shield_input(messages)
response = await self.inference_api.openai_chat_completion(
params = OpenAIChatCompletionRequest(
model=self.model,
messages=[shield_input_message],
stream=False,
)
response = await self.inference_api.openai_chat_completion(params)
content = response.choices[0].message.content
content = content.strip()
return self.get_moderation_object(content)