How to pass custom azure_endpoint in AzureChatOpenAI

[arjunjoshi-audviklabs]

[dosubot[bot]]

Hello @arjunjoshi-audviklabs! I'm here to assist you with any bugs, questions, or contributions you may have. Let's work together to resolve the issue you're facing.

To pass a custom Azure endpoint in AzureChatOpenAI and avoid getting an openai.APIConnectionError: Connection error, you need to set the AZURE_OPENAI_ENDPOINT environment variable with your custom endpoint URL. Here is how you can do it:

1. Install the langchain-openai package if you haven't already:

   pip install -U langchain-openai

2. Set the AZURE_OPENAI_API_KEY and AZURE_OPENAI_ENDPOINT environment variables:

   export AZURE_OPENAI_API_KEY="your-api-key"
   export AZURE_OPENAI_ENDPOINT="https://<company-name>.azurewebsites.net/proxy"

3. Instantiate the AzureChatOpenAI class with the necessary parameters:

   from langchain_openai import AzureChatOpenAI
   
   llm = AzureChatOpenAI(
       azure_deployment="<deployment-name>",
       api_version="<api-version>",
       temperature=0,
       max_tokens=None,
       timeout=None,
       max_retries=2,
       # other params...
   )

Additionally, ensure that you have the openai Python package installed. You may also need to set other environment variables such as AZURE_OPENAI_AD_TOKEN and OPENAI_API_VERSION if required. The AzureChatOpenAI class will use these environment variables to configure the connection properly, which should help avoid connection errors ^[1][2][3][4].

To continue talking to Dosu, mention @dosu.

[RollsChris]

Hello @arjunjoshi-audviklabs! I'm here to assist you with any bugs, questions, or contributions you may have. Let's work together to resolve the issue you're facing.

To pass a custom Azure endpoint in AzureChatOpenAI and avoid getting an openai.APIConnectionError: Connection error, you need to set the AZURE_OPENAI_ENDPOINT environment variable with your custom endpoint URL. Here is how you can do it:

1. Install the langchain-openai package if you haven't already:

   pip install -U langchain-openai

2. Set the AZURE_OPENAI_API_KEY and AZURE_OPENAI_ENDPOINT environment variables:

   export AZURE_OPENAI_API_KEY="your-api-key"
   export AZURE_OPENAI_ENDPOINT="https://<company-name>.azurewebsites.net/proxy"

3. Instantiate the AzureChatOpenAI class with the necessary parameters:

   from langchain_openai import AzureChatOpenAI
   
   llm = AzureChatOpenAI(
       azure_deployment="<deployment-name>",
       api_version="<api-version>",
       temperature=0,
       max_tokens=None,
       timeout=None,
       max_retries=2,
       # other params...
   )

Additionally, ensure that you have the openai Python package installed. You may also need to set other environment variables such as AZURE_OPENAI_AD_TOKEN and OPENAI_API_VERSION if required. The AzureChatOpenAI class will use these environment variables to configure the connection properly, which should help avoid connection errors [1][2][3][4].

To continue talking to Dosu, mention @dosu.

@dosu How can i change the azure_deployment after i have created the llm object