Skip to content

Updated instructions on how to use AzureOpenAI models. #8250

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.

Sign up for GitHub

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

Merged
merged 1 commit into from
May 21, 2025
Merged

Updated instructions on how to use AzureOpenAI models. #8250

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 5 additions & 2 deletions docs/docs/learn/programming/language_models.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,14 +86,16 @@ dspy.configure(lm=lm)
```

=== "Other providers"
In DSPy, you can use any of the dozens of [LLM providers supported by LiteLLM](https://docs.litellm.ai/docs/providers). Simply follow their instructions for which `{PROVIDER}_API_KEY` to set and how to write pass the `{provider_name}/{model_name}` to the constructor.
In DSPy, you can use any of the dozens of [LLM providers supported by LiteLLM](https://docs.litellm.ai/docs/providers). Simply follow their instructions for which `{PROVIDER}_API_KEY` to set and how to write pass the `{provider_name}/{model_name}` to the constructor.

Some examples:

- `anyscale/mistralai/Mistral-7B-Instruct-v0.1`, with `ANYSCALE_API_KEY`
- `together_ai/togethercomputer/llama-2-70b-chat`, with `TOGETHERAI_API_KEY`
- `sagemaker/<your-endpoint-name>`, with `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, and `AWS_REGION_NAME`
- `azure/<your_deployment_name>`, with `AZURE_API_KEY`, `AZURE_API_BASE`, `AZURE_API_VERSION`, and the optional `AZURE_AD_TOKEN` and `AZURE_API_TYPE`
- `azure/<your_deployment_name>`, with `AZURE_API_KEY`, `AZURE_API_BASE`, `AZURE_API_VERSION`, and the optional `AZURE_AD_TOKEN` and `AZURE_API_TYPE` as environment variables. If you are initiating external models without setting environment variables, use the following:
`lm = dspy.LM('azure/<your_deployment_name>', api_key = 'AZURE_API_KEY' , api_base = 'AZURE_API_BASE', api_version = 'AZURE_API_VERSION')`



If your provider offers an OpenAI-compatible endpoint, just add an `openai/` prefix to your full model name.
Expand All @@ -103,6 +105,7 @@ dspy.configure(lm=lm)
lm = dspy.LM('openai/your-model-name', api_key='PROVIDER_API_KEY', api_base='YOUR_PROVIDER_URL')
dspy.configure(lm=lm)
```
If you run into errors, please refer to the [LiteLLM Docs](https://docs.litellm.ai/docs/providers) to verify if you are using the same variable names/following the right procedure.

## Calling the LM directly.

Expand Down