AzureOpenAI is missing

[MChorfa]

System Info

Hello,
I noticed that the AzureOpenAI is missing from the latest release. Now we kind of have to create our own custom class. Is this the direction of the project?

Thank you

Who can help?

No response

Information

• The official example notebooks/scripts
• My own modified scripts

Related Components

• LLMs/Chat Models
• Embedding Models
• Prompts / Prompt Templates / Prompt Selectors
• Output Parsers
• Document Loaders
• Vector Stores / Retrievers
• Memory
• Agents / Agent Executors
• Tools / Toolkits
• Chains
• Callbacks/Tracing
• Async

Reproduction

from langchain.llms import AzureOpenAI

no logner availiable

no possibility to add engine or deployment id, nor the possibility to add extra headers

Expected behavior

from langchain.llms import AzureOpenAI

os.environ["OPENAI_API_TYPE"] = "azure"
os.environ["OPENAI_API_BASE"] = "https://<your-endpoint.openai.azure.com/"
os.environ["OPENAI_API_KEY"] = "your AzureOpenAI key"
os.environ["OPENAI_API_VERSION"] = "2023-05-15"

embeddings = OpenAIEmbeddings(deployment="your-embeddings-deployment-name")

[dosubot]

🤖

Hello,

Thank you for bringing this to our attention. The AzureOpenAI class is not missing but has been renamed to AzureChatOpenAI. This class is a wrapper for the Azure OpenAI chat completion API and is used to interact with a deployed model on Azure OpenAI.

Here is how you can use it:

from langchain.llms import AzureChatOpenAI

os.environ["OPENAI_API_TYPE"] = "azure"
os.environ["OPENAI_API_BASE"] = "https://<your-endpoint.openai.azure.com/"
os.environ["OPENAI_API_KEY"] = "your AzureOpenAI key"
os.environ["OPENAI_API_VERSION"] = "2023-05-15"

embeddings = AzureChatOpenAI(deployment="your-embeddings-deployment-name")

Please note that users are not expected to create their own custom classes unless they have specific requirements that are not covered by the AzureChatOpenAI class. The AzureChatOpenAI class provides a comprehensive set of features for interacting with the Azure OpenAI chat completion API, including environment variable validation, default parameter generation, and response handling.

You can find more details about this class in the source code.

I hope this helps! If you have any other questions or issues, feel free to ask.

Best,
Dosu

Sources

• Functions might not be supported through Azure OpenAI
• Azure OpenAI Embeddings failed due to no deployment_id set.
• AzureOpenAI example error (embeddding)
• libs/langchain/langchain/chat_models/azure_openai.py

---

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.

[dosubot]

Hi, @MChorfa,

I'm helping the LangChain team manage their backlog and am marking this issue as stale. From what I understand, the issue you raised about the missing AzureOpenAI class has been resolved. The class has been renamed to AzureChatOpenAI in the latest release, and usage instructions were provided. It was also clarified that users are not expected to create their own custom classes unless they have specific requirements not covered by AzureChatOpenAI.

Could you please confirm if this issue is still relevant to the latest version of the LangChain repository? If it is, please let the LangChain team know by commenting on the issue. Otherwise, feel free to close the issue yourself, or it will be automatically closed in 7 days.

Thank you for your understanding and cooperation.