OpenAI

Learn to integrate OpenAI with Portkey, enabling seamless completions, prompt management, and advanced functionalities like streaming, function calling and fine-tuning.

Portkey has native integrations with OpenAI SDKs for Node.js, Python, and its REST APIs. For OpenAI integration using other frameworks, explore our partnerships, including Langchain, LlamaIndex, among others.

Using the Portkey Gateway

To integrate the Portkey gateway with OpenAI,

• Set the baseURL to the Portkey Gateway URL

• Include Portkey-specific headers such as provider, apiKeyand others.

Here's how to apply it to a chat completion request:

OpenAI NodeJS

1. Install the Portkey SDK in your application

npm i --save portkey-ai

2. Next, insert the Portkey-specific code as shown in the highlighted lines to your OpenAI completion calls. PORTKEY_GATEWAY_URL is portkey's gateway URL to route your requests and createHeaders is a convenience function that generates the headers object. (All supported params/headers)

import OpenAI from 'openai'; // We're using the v4 SDK
import { PORTKEY_GATEWAY_URL, createHeaders } from 'portkey-ai'

const openai = new OpenAI({
  apiKey: 'OPENAI_API_KEY', // defaults to process.env["OPENAI_API_KEY"],
  baseURL: PORTKEY_GATEWAY_URL,
  defaultHeaders: createHeaders({
    provider: "openai",
    apiKey: "PORTKEY_API_KEY" // defaults to process.env["PORTKEY_API_KEY"]
  })
});

async function main() {
  const chatCompletion = await openai.chat.completions.create({
    messages: [{ role: 'user', content: 'Say this is a test' }],
    model: 'gpt-4-turbo',
  });

  console.log(chatCompletion.choices);
}

main();

OpenAI Python

1. Install the Portkey SDK in your application

pip install portkey-ai

2. Next, insert the Portkey-specific code as shown in the highlighted lines to your OpenAI function calls. PORTKEY_GATEWAY_URL is portkey's gateway URL to route your requests and createHeaders is a convenience function that generates the headers object. (All supported params/headers)

from openai import OpenAI
from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

client = OpenAI(
    api_key="OPENAI_API_KEY", # defaults to os.environ.get("OPENAI_API_KEY")
    base_url=PORTKEY_GATEWAY_URL,
    default_headers=createHeaders(
        provider="openai",
        api_key="PORTKEY_API_KEY" # defaults to os.environ.get("PORTKEY_API_KEY")
    )
)

chat_complete = client.chat.completions.create(
    model="gpt-4-turbo",
    messages=[{"role": "user", "content": "Say this is a test"}],
)

print(chat_complete.choices[0].message.content)

REST API

curl https://api.portkey.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "x-portkey-provider: openai" \ 
  -d '{
    "model": "gpt-4-turbo",
    "messages": [{
        "role": "system",
        "content": "You are a helpful assistant."
      },{
        "role": "user",
        "content": "Hello!"
      }]
  }'

List of all possible headers

This request will be automatically logged by Portkey. You can view this in your logs dashboard. Portkey logs the tokens utilized, execution time, and cost for each request. Additionally, you can delve into the details to review the precise request and response data.

The same integration approach applies to APIs for completions, embeddings, vision, moderation, transcription, translation, speech and files .

If you are looking for a way to add your Org ID & Project ID to the requests, head over to this section.

Using the Prompts API

Portkey also supports creating and managing prompt templates in the prompt library. This enables the collaborative development of prompts directly through the user interface.

1. Create a prompt template with variables and set the hyperparameters.

2. Use this prompt in your codebase using the Portkey SDK.

Node

import Portkey from 'portkey-ai'

const portkey = new Portkey({
    apiKey: "PORTKEY_API_KEY",
})

// Make the prompt creation call with the variables
const promptCompletion = await portkey.prompts.completions.create({
    promptID: "Your Prompt ID",
    variables: {
       // The variables specified in the prompt
    }
})

// We can also override the hyperparameters
const promptCompletion = await portkey.prompts.completions.create({
    promptID: "Your Prompt ID",
    variables: {
       // The variables specified in the prompt
    },
    max_tokens: 250,
    presence_penalty: 0.2
})

Python

from portkey_ai import Portkey

client = Portkey(
    api_key="PORTKEY_API_KEY",  # defaults to os.environ.get("PORTKEY_API_KEY")
)

prompt_completion = client.prompts.completions.create(
    prompt_id="Your Prompt ID",
    variables={
       # The variables specified in the prompt
    }
)

print(prompt_completion)

# We can also override the hyperparameters
prompt_completion = client.prompts.completions.create(
    prompt_id="Your Prompt ID",
    variables={
       # The variables specified in the prompt
    },
    max_tokens=250,
    presence_penalty=0.2
)
print(prompt_completion)

REST API

curl -X POST "https://api.portkey.ai/v1/prompts/:PROMPT_ID/completions" \
-H "Content-Type: application/json" \
-H "x-portkey-api-key: $PORTKEY_API_KEY" \
-d '{
    "variables": {
        # The variables to use
    },
    "max_tokens": 250, # Optional
    "presence_penalty": 0.2 # Optional
}'

Observe how this streamlines your code readability and simplifies prompt updates via the UI without altering the codebase.

Advanced Use Cases

Streaming Responses

Portkey supports streaming responses using Server Sent Events (SSE).

OpenAI NodeJS

import OpenAI from 'openai';
import { PORTKEY_GATEWAY_URL, createHeaders } from 'portkey-ai'

const openai = new OpenAI({
  baseURL: PORTKEY_GATEWAY_URL,
  defaultHeaders: createHeaders({
    provider: "openai",
    apiKey: "PORTKEY_API_KEY" // defaults to process.env["PORTKEY_API_KEY"]
  })
});

async function main() {
  const stream = await openai.chat.completions.create({
    model: 'gpt-4',
    messages: [{ role: 'user', content: 'Say this is a test' }],
    stream: true,
  });
  for await (const chunk of stream) {
    process.stdout.write(chunk.choices[0]?.delta?.content || '');
  }
}

main();

OpenAI Python

from openai import OpenAI
from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

client = OpenAI(
    api_key="OPENAI_API_KEY",  # defaults to os.environ.get("OPENAI_API_KEY")
    base_url=PORTKEY_GATEWAY_URL,
    default_headers=createHeaders(
        provider="openai",
        api_key="PORTKEY_API_KEY" # defaults to os.environ.get("PORTKEY_API_KEY")
    )
)

chat_complete = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Say this is a test"}],
    stream=True
)

for chunk in chat_complete:
    print(chunk.choices[0].delta.content, end="", flush=True)

Using Vision Models

Portkey's multimodal Gateway fully supports OpenAI vision models as well. See this guide for more info:

pageVision

Function Calling

Function calls within your OpenAI or Portkey SDK operations remain standard. These logs will appear in Portkey, highlighting the utilized functions and their outputs.

Additionally, you can define functions within your prompts and invoke the portkey.prompts.completions.create method as above.

Fine-Tuning

Please refer to our fine-tuning guides to take advantage of Portkey's advanced continuous fine-tuning capabilities.

Image Generation

Portkey supports multiple modalities for OpenAI and you can make image generation requests through Portkey's AI Gateway the same way as making completion calls.

OpenAI NodeJS

// Define the OpenAI client as shown above

const image = await openai.images.generate({
  model:"dall-e-3",
  prompt:"Lucy in the sky with diamonds",
  size:"1024x1024"
})

OpenAI Python

# Define the OpenAI client as shown above

image = openai.images.generate(
  model="dall-e-3",
  prompt="Lucy in the sky with diamonds",
  size="1024x1024"
)

Portkey's fast AI gateway captures the information about the request on your Portkey Dashboard. On your logs screen, you'd be able to see this request with the request and response.

Log view for an image generation request on OpenAI

More information on image generation is available in the API Reference.

Audio - Transcription, Translation, and Text-to-Speech

Portkey's multimodal Gateway also supports the audio methods on OpenAI API. tts-1 , tts-1-hd, and whisper-1 models are supported.

Check out the below guides for more info:

pageText-to-SpeechpageSpeech-to-Text

---

Managing OpenAI Projects & Organizations in Portkey

When integrating OpenAI with Portkey, you can specify your OpenAI organization and project IDs along with your API key. This is particularly useful if you belong to multiple organizations or are accessing projects through a legacy user API key.

Specifying the organization and project IDs helps you maintain better control over your access rules, usage, and costs.

In Portkey, you can add your Org & Project details by,

1. Creating your Virtual Key

2. Defining a Gateway Config

3. Passing Details in a Request

Let's explore each method in more detail.

Using Virtual Keys

When selecting OpenAI from the dropdown menu while creating a virtual key, Portkey automatically displays optional fields for the organization ID and project ID alongside the API key field. You can add all the details in one place and obtain a virtual key that can be used throughout Portkey.

pageVirtual Keys

Portkey takes budget management a step further than OpenAI. While OpenAI allows setting budget limits per project, Portkey enables you to set budget limits for each virtual key you create. For more information on budget limits, refer to this documentation:

pageBudget Limits

Using The Gateway Config

You can also specify the organization and project details in the gateway config, either at the root level or within a specific target.

{
	"provider": "openai",
	"api_key": "OPENAI_API_KEY"
	"openai_organization": "org-xxxxxx",
	"openai_project": "proj_xxxxxxxx"
}

While Making a Request

You can also pass your organization and project details directly when making a request using curl, the OpenAI SDK, or the Portkey SDK.

OpenAI Python SDK

from openai import OpenAI
from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

client = OpenAI(
    api_key="OPENAI_API_KEY",
    organization="org-xxxxxxxxxx",
    project="proj_xxxxxxxxx",
    base_url=PORTKEY_GATEWAY_URL,
    default_headers=createHeaders(
        provider="openai",
        api_key="PORTKEY_API_KEY"
    )
)

chat_complete = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Say this is a test"}],
)

print(chat_complete.choices[0].message.content)

OpenAI TS SDK

import OpenAI from "openai";
import { PORTKEY_GATEWAY_URL, createHeaders } from "portkey-ai";

const openai = new OpenAI({
  apiKey: "OPENAI_API_KEY",
  organization: "org-xxxxxx",
  project: "proj_xxxxxxx",
  baseURL: PORTKEY_GATEWAY_URL,
  defaultHeaders: createHeaders({
    provider: "openai",
    apiKey: "PORTKEY_API_KEY",
  }),
});

async function main() {
  const chatCompletion = await openai.chat.completions.create({
    messages: [{ role: "user", content: "Say this is a test" }],
    model: "gpt-4o",
  });

  console.log(chatCompletion.choices);
}

main();

REST API

curl https://api.portkey.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "OpenAI-Organization: org-xxxxxxx" \
  -H "OpenAI-Project: proj_xxxxxxx" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "x-portkey-provider: openai" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user","content": "Hello!"}]
  }'

Portkey Python SDK

from portkey_ai import Portkey

portkey = Portkey(
    api_key="PORTKEY_API_KEY",
    provider="openai",
    authorization="Bearer OPENAI_API_KEY",
    openai_organization="org-xxxxxxxxx",
    openai_project="proj_xxxxxxxxx",
)

chat_complete = portkey.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Say this is a test"}],
)

print(chat_complete.choices[0].message.content)

Portkey Node SDK

import Portkey from "portkey-ai";

const portkey = new Portkey({
  apiKey: "PORTKEY_API_KEY",
  provider: "openai",
  Authorization: "Bearer OPENAI_API_KEY",
  openaiOrganization: "org-xxxxxxxxxxx",
  openaiProject: "proj_xxxxxxxxxxxxx",
});

async function main() {
  const chatCompletion = await portkey.chat.completions.create({
    messages: [{ role: "user", content: "Say this is a test" }],
    model: "gpt-4o",
  });

  console.log(chatCompletion.choices);
}

main();

---

Portkey Features

Portkey supports the complete host of it's functionality via the OpenAI SDK so you don't need to migrate away from it.

Please find more information in the relevant sections:

1. Add metadata to your requests

2. Add gateway configs to the OpenAI client or a single request

3. Tracing OpenAI requests

4. Setup a fallback to Azure OpenAI