Add LiteLLM support in line with AsyncOpenAI and with reproducible examples #318
+86
−1
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Signed-off-by: Víctor Mayoral Vilches <[email protected]>
Signed-off-by: Víctor Mayoral Vilches <[email protected]>
Signed-off-by: Víctor Mayoral Vilches <[email protected]>
In particular:
Traceback (most recent call last):
File /Users/alias/Alias/research/openai-agents-python/examples/agent_patterns/litellm.py, line 4, in <module>
from agents import OpenAIChatCompletionsModel,Agent,Runner
File /Users/alias/Alias/research/openai-agents-python/src/agents/__init__.py, line 44, in <module>
from .models.openai_chatcompletions import OpenAIChatCompletionsModel
File /Users/alias/Alias/research/openai-agents-python/src/agents/models/openai_chatcompletions.py, line 57, in <module>
from openai.types.responses.response_usage import InputTokensDetails, OutputTokensDetails
ImportError: cannot import name 'InputTokensDetails' from 'openai.types.responses.response_usage' (/Users/alias/Alias/research/openai-agents-python/env/lib/python3.12/site-packages/openai/types/responses/response_usage.py). Did you mean: 'OutputTokensDetails'?
Signed-off-by: Víctor Mayoral Vilches <[email protected]>
Signed-off-by: Víctor Mayoral Vilches <[email protected]>
Signed-off-by: Víctor Mayoral Vilches <[email protected]>
Signed-off-by: Víctor Mayoral Vilches <[email protected]>
mjio
reviewed
Mar 27, 2025
| @@ -7,7 +7,7 @@ requires-python = ">=3.9" | |||
| license = "MIT" | |||
| authors = [{ name = "OpenAI", email = "[email protected]" }] | |||
| dependencies = [ | |||
| "openai>=1.66.5", | |||
| "openai>=1.68.2", | |||
There was a problem hiding this comment.
I think this should not be part of the PR, as it has nothing to do with the added example.
There was a problem hiding this comment.
In my local testing, it was neccessary, otherwise it wouldn't work with 1.66.5.
Happy to change it though if that gets this through.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR is a follow up from #125, which unsuccessfully delivered LiteLLM support. See conversation there for further context.
Given the late architectural updates, there's no real need for any relevant code changes to support LiteLLM. Correspondingly, this PR delivers a working example under the
examples/model_providerssupport to easy adoption for others. In particular, the example leveragesAsyncOpenAIproposed extensions, as well as a default generic configuration demonstrating basic use with SOTA models.Empirical testing of proposed changes: