phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-12 13:57:57 +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

15
llama_stack/providers/inline/eval/meta_reference/eval.py
View file

@ -12,7 +12,14 @@ from llama_stack.apis.agents import Agents, StepType
from llama_stack.apis.benchmarks import Benchmark
from llama_stack.apis.datasetio import DatasetIO
from llama_stack.apis.datasets import Datasets
from llama_stack.apis.inference import Inference, OpenAISystemMessageParam, OpenAIUserMessageParam, UserMessage
from llama_stack.apis.inference import (
Inference,
OpenAIChatCompletionRequest,
OpenAICompletionRequest,
OpenAISystemMessageParam,
OpenAIUserMessageParam,
UserMessage,
)
from llama_stack.apis.scoring import Scoring
from llama_stack.providers.datatypes import BenchmarksProtocolPrivate
from llama_stack.providers.inline.agents.meta_reference.agent_instance import (
@ -168,11 +175,12 @@ class MetaReferenceEvalImpl(
sampling_params["stop"] = candidate.sampling_params.stop
input_content = json.loads(x[ColumnName.completion_input.value])
response = await self.inference_api.openai_completion(
params = OpenAICompletionRequest(
model=candidate.model,
prompt=input_content,
**sampling_params,
)
response = await self.inference_api.openai_completion(params)
generations.append({ColumnName.generated_answer.value: response.choices[0].text})
elif ColumnName.chat_completion_input.value in x:
chat_completion_input_json = json.loads(x[ColumnName.chat_completion_input.value])
@ -187,11 +195,12 @@ class MetaReferenceEvalImpl(
messages += [OpenAISystemMessageParam(**x) for x in chat_completion_input_json if x["role"] == "system"]
messages += input_messages
response = await self.inference_api.openai_chat_completion(
params = OpenAIChatCompletionRequest(
model=candidate.model,
messages=messages,
**sampling_params,
)
response = await self.inference_api.openai_chat_completion(params)
generations.append({ColumnName.generated_answer.value: response.choices[0].message.content})
else:
raise ValueError("Invalid input row")