admin-valentin/openai-agents-python
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
398 commits 1 branch 0 tags 3.4 MiB
Commit graph

3 commits

Author SHA1 Message Date
Ashok Saravanan
1994f9d4c4
feat: pass extra_body through to LiteLLM acompletion (#638) 
**Purpose**  
Allow arbitrary `extra_body` parameters (e.g. `cached_content`) to be
forwarded into the LiteLLM call. Useful for context caching in Gemini
models
([docs](https://ai.google.dev/gemini-api/docs/caching?lang=python)).

**Example usage**  
```python
import os
from agents import Agent, ModelSettings
from agents.extensions.models.litellm_model import LitellmModel

cache_name = "cachedContents/34jopukfx5di"  # previously stored context

gemini_model = LitellmModel(
    model="gemini/gemini-1.5-flash-002",
    api_key=os.getenv("GOOGLE_API_KEY")
)

agent = Agent(
    name="Cached Gemini Agent",
    model=gemini_model,
    model_settings=ModelSettings(
        extra_body={"cached_content": cache_name}
    )
)
 2025-05-14 12:34:27 -04:00
Daniele Morotti
e11b822d5f
Fix stream error using LiteLLM (#589) 
In response to issue #587 , I implemented a solution to first check if
`refusal` and `usage` attributes exist in the `delta` object.

I added a unit test similar to `test_openai_chatcompletions_stream.py`.

Let me know if I should change something.

---------

Co-authored-by: Rohan Mehta <rm@openai.com>
 2025-04-24 12:53:39 -04:00
Rohan Mehta
942ba9840b
Docs and tests for litellm (#561) 2025-04-21 16:59:01 -04:00