Is it llamaindex support AzureChatOpenAI llm configurations?

[mraguth]

Some have I am getting error: This my config. I like to have a sample example if possible.

llm = AzureChatOpenAI(
    deployment_name="gpt-4o",
    model_name="gpt-4o",
    azure_endpoint="xxxx",
    api_version="2023-07-01-preview",
    temperature=0.0,
    api_key="xxxxx"
)

[dosubot[bot]]

To configure llamaindex to support AzureChatOpenAI LLM configurations, you need to ensure that all required parameters are correctly set. Here is a sample configuration example:

from llama_index.llms.azure_openai import AzureChatOpenAI

llm = AzureChatOpenAI(
    deployment_name="gpt-4o",
    model_name="gpt-4o",
    azure_endpoint="https://YOUR_RESOURCE_NAME.openai.azure.com/",
    api_version="2023-07-01-preview",
    temperature=0.0,
    api_key="YOUR_AZURE_OPENAI_API_KEY"
)

Make sure to replace the placeholders with your actual Azure OpenAI configurations:

• YOUR_RESOURCE_NAME: The name of your Azure resource.
• YOUR_AZURE_OPENAI_API_KEY: Your Azure OpenAI API key.

Additionally, ensure that the following environment variables are set:

• OPENAI_API_VERSION: Set this to 2023-07-01-preview or newer.
• AZURE_OPENAI_ENDPOINT: Your Azure OpenAI endpoint.
• AZURE_OPENAI_API_KEY: Your Azure OpenAI API key.

If you encounter specific errors, such as missing parameters or incorrect endpoint formats, refer to the common error messages and their solutions:

1. Missing engine parameter:

   if engine is None:
       raise ValueError("You must specify an `engine` parameter.")

2. Missing OPENAI_API_BASE or azure_endpoint:

   if (
       values["api_base"] == "https://api.openai.com/v1"
       and values["azure_endpoint"] is None
   ):
       raise ValueError(
           "You must set OPENAI_API_BASE to your Azure endpoint. "
           "It should look like https://YOUR_RESOURCE_NAME.openai.azure.com/"
       )

3. Missing OPENAI_API_VERSION:

   if values["api_version"] is None:
       raise ValueError("You must set OPENAI_API_VERSION for Azure OpenAI.")

4. Missing api_key:

   if self.api_key is None:
       raise ValueError(
           "You must set an `api_key` parameter. "
           "Alternatively, you can set the AZURE_OPENAI_API_KEY env var OR set `use_azure_ad=True`."
       )

5. Invalid azure_endpoint format:

   azure_endpoint = get_from_param_or_env(
       "azure_endpoint", azure_endpoint, "AZURE_OPENAI_ENDPOINT", ""
   )
   if not azure_endpoint.startswith("https://"):
       raise ValueError("The `azure_endpoint` must start with 'https://'.")

Ensure your configuration adheres to these requirements to avoid common issues ^[1][2].

To continue talking to Dosu, mention @dosu.

[mraguth]

@dosu I am getting this error:

---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
Cell In[9], [line 1](vscode-notebook-cell:?execution_count=9&line=1)
----> [1](vscode-notebook-cell:?execution_count=9&line=1) from llama_index.llms.azure_openai import AzureChatOpenAI

ImportError: cannot import name 'AzureChatOpenAI' from 'llama_index.llms.azure_openai'

[dosubot[bot]]

The AzureChatOpenAI class does not exist in the llama_index.llms.azure_openai module. Instead, you should use AzureOpenAI, SyncAzureOpenAI, or AsyncAzureOpenAI. Here is the correct import statement and example configuration:

from llama_index.llms.azure_openai import AzureOpenAI

llm = AzureOpenAI(
    deployment_name="gpt-4o",
    model_name="gpt-4o",
    azure_endpoint="https://YOUR_RESOURCE_NAME.openai.azure.com/",
    api_version="2023-07-01-preview",
    temperature=0.0,
    api_key="YOUR_AZURE_OPENAI_API_KEY"
)

Make sure to replace the placeholders with your actual Azure OpenAI configurations:

• YOUR_RESOURCE_NAME: The name of your Azure resource.
• YOUR_AZURE_OPENAI_API_KEY: Your Azure OpenAI API key.

This should resolve the import error you are encountering ^[1][2].

To continue talking to Dosu, mention @dosu.