-
-
Notifications
You must be signed in to change notification settings - Fork 316
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
docs: update readme and installation guide for litellm backend addition #703
Conversation
README.md
Outdated
```bash | ||
cat << EOF > .env | ||
BACKEND=rdagent.oai.backend.LiteLLMAPIBackend | ||
LITELLM_CHAT_MODEL=gpt-4o |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
remove the prefix
BACKEND=rdagent.oai.backend.LiteLLMAPIBackend | ||
LITELLM_CHAT_MODEL=gpt-4o | ||
LITELLM_EMBEDDING_MODEL=text-embedding-3-small | ||
OPENAI_API_KEY=<replace_with_your_openai_api_key> |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
OPENAI_API_KEY=<replace_with_your_openai_api_key> | |
# The backend api_key and api_base fully follow the convetion of litellm. | |
OPENAI_API_KEY=<replace_with_your_openai_api_key> |
|
||
.. code-block:: Properties | ||
|
||
LITELLM_CHAT_MODEL=deepseek/deepseek-reasoner |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
this parameter will be passed into litellm's completion function. litellm will use its router to decide which backend will be used.
Description
We support using LiteLLM as LLM-Backend to use various model more flexibly.
Motivation and Context
How Has This Been Tested?
Screenshots of Test Results (if appropriate):
Types of changes
📚 Documentation preview 📚: https://RDAgent--703.org.readthedocs.build/en/703/