I can't figure out how to get Helicone proxy to work with AzureChatOpenAI from langchain.
This does not work - 404 - Model not found (I've tried every iteration of model I can think of)
const model = new AzureChatOpenAI({
model: "gpt-4o-mini-2024-07-18",
temperature: 0,
maxRetries: 2,
azureOpenAIApiKey: process.env.AZURE_OPENAI_API_KEY,
azureOpenAIApiInstanceName: process.env.AZURE_OPENAI_INSTANCE_NAME,
azureOpenAIApiDeploymentName: process.env.AZURE_OPENAI_DEPLOYMENT_NAME,
azureOpenAIApiVersion: process.env.AZURE_OPENAI_API_VERSION,
azureOpenAIBasePath: "https://oai.helicone.ai",
configuration: {
defaultHeaders: {
"Helicone-Auth": `Bearer ${process.env.HELICONE_API_KEY}`,
"Helicone-OpenAI-Api-Base": process.env.AZURE_OPENAI_ENDPOINT,
},
},
});However if I go straight to Azure with the request it works great.
ie this works
const model = new AzureChatOpenAI({
model: "gpt-4o-mini-2024-07-18",
temperature: 0,
maxRetries: 2,
azureOpenAIApiKey: process.env.AZURE_OPENAI_API_KEY,
azureOpenAIApiInstanceName: process.env.AZURE_OPENAI_INSTANCE_NAME,
azureOpenAIApiDeploymentName: process.env.AZURE_OPENAI_DEPLOYMENT_NAME,
azureOpenAIApiVersion: process.env.AZURE_OPENAI_API_VERSION,
});What am I doing wrong? I feel like I tried every which way to get it working and the docs seem out of date for this.
