Streaming with Assitants API issue

At a glance

The community member is new to Helicone and is using the OpenAI JavaScript SDK to integrate with Helicone's proxy, but is encountering strange metrics. The comments provide steps to help resolve the issue, including:

- Verifying the correct API key configuration and including the Helicone-Auth header in requests

- Ensuring the base path is correctly set to Helicone's proxy URL

- Addressing common issues like model display and missing api-version parameter

- Suggesting to make a test request to verify the setup

The comments also indicate that the assistant's API is currently not fully supported, but the default streaming request should work fine.

Useful resources

MMuhtasham

Hello,

New to helicone and using proxy integration via OpenAI’s JavaScript SDK but seeing weird metrics

Plain Text

import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: request.env.OPENAI_API_KEY,
  baseURL: "https://oai.helicone.ai/v1",
  defaultHeaders: {
    "Helicone-Auth": `Bearer ${request.env.HELICONE_API_KEY}`,
  },
});

Attachment

4 comments

DDuckie

To help you resolve the strange metrics you're encountering with Helicone's proxy integration, here are some steps and common issues to check:

Verify Your Setup

Ensure Correct API Key Configuration:
- Make sure your HELICONE_API_KEY is set as an environment variable:
  Plain Text
```
export HELICONE_API_KEY=<your API key>
```
- Include the Helicone-Auth header in your requests:
  Plain Text
```
defaultHeaders: {
  "Helicone-Auth": `Bearer ${process.env.HELICONE_API_KEY}`,
}
```
source

Check Base Path Configuration:
- Ensure the base path is correctly set to Helicone's proxy URL:
  Plain Text
```
baseURL: "https://oai.helicone.ai/v1",
```
source

Common Issues and Resolutions

Model Display Issues:
- If the model displays differently than expected, use the Helicone-Model-Override header:
  Plain Text
```
"Helicone-Model-Override": "[MODEL_NAME]"
```
source

Missing api-version Parameter:
- Ensure the api-version parameter is included in your requests:
  Plain Text
```
defaultQuery: { "api-version": "[API_VERSION]" }
```
source

Test Your Setup

Make a Test Request:
- Verify your setup by making a test request:
```javascript
const chatCompletion = await openai.chat.completion.create({
model: "gpt-3.5-turbo",
messages: [{ role: "user", content: "Hello world" }],
});

console.log(chatCompletion.data.choices[0].message);
```
source

DDuckie

By following these steps and checking for common issues, you should be able to resolve the unusual metrics you're seeing. If the problem persists, double-check your environment variables and headers for any typos or misconfigurations.

MMuhtasham

is assitants api supported

sst_bokarev

Hi , We are currently not fully supporting the helper API. The default streaming request should work fine!

Add a reply

Helicone Community Page

Streaming with Assitants API issue

Verify Your Setup

Common Issues and Resolutions

Test Your Setup