Azure OpenAI with LangChain

Use LangChain to integrate Azure OpenAI with Helicone to log your Azure OpenAI usage.

1. Create an account and generate an API key

   Log into Helicone or create an account. Once you have an account, you can generate an API key here.
2. Set up your Helicone API key in your .env file

   AZURE_OPENAI_API_KEY=<YOUR_AZURE_OPENAI_API_KEY>
   HELICONE_API_KEY=<YOUR_HELICONE_API_KEY>
   

3. Modify the base URL path and set up authentication

   Make sure to include the api-version in all of your requests.

   javascript

   const model = new ChatOpenAI({
     azureOpenAIApiKey: process.env.AZURE_OPENAI_API_KEY,
     azureOpenAIApiDeploymentName: "[DEPLOYMENT_NAME]", // "gpt-35-turbo"
     azureOpenAIApiVersion: "[API_VERSION]", // "2024-12-15-preview"
     azureOpenAIBasePath: "https://oai.helicone.ai",
     configuration: {
       organization: "[YOUR_ORGANIZATION]", // "my-org"
       baseOptions: {
         headers: {
           "Helicone-Auth": `Bearer ${process.env.HELICONE_API_KEY}`,
           "Helicone-OpenAI-Api-Base":
             "https://[YOUR_AZURE_DOMAIN].openai.azure.com",
           "Helicone-Model-Override": "[MODEL_NAME]",  // "gpt-35-turbo"
           // additional headers
         }
       }
     }
   });
   

   Recomendation: Model Override

   When using Azure, the model displays differently than expected at times. We have implemented logic to parse out the model, but if you want to guarantee your model is consistent, we highly recommend using model override:

   Helicone-Model-Override: [MODEL_NAME]
   
   Click here to learn more about model override
4. Start using Azure OpenAI with Helicone

   javascript

   const response = await model.invoke("What is the meaning of life?");
   console.log(response);
   

5. Verify your requests in Helicone

   With the above setup, any calls to Azure OpenAI will automatically be logged and monitored by Helicone. Review them in your Helicone dashboard.