With Portkey, you can take advantage of features like fast AI gateway access, observability, prompt management, and more, all while ensuring the secure management of your LLM API keys through a virtual key system.

Provider Slug: deepseek

Portkey SDK Integration with DeepSeek Models

Portkey provides a consistent API to interact with models from various providers. To integrate DeepSeek with Portkey:

1. Install the Portkey SDK

Add the Portkey SDK to your application to interact with DeepSeek AI’s API through Portkey’s gateway.

npm install --save portkey-ai

2. Initialize Portkey with the Virtual Key

To use DeepSeek with Portkey, get your API key from here, then add it to Portkey to create the virtual key.

import Portkey from 'portkey-ai'

const portkey = new Portkey({
    apiKey: "PORTKEY_API_KEY", // defaults to process.env["PORTKEY_API_KEY"]
    virtualKey: "VIRTUAL_KEY" // Your DeepSeek Virtual Key
})

3. Invoke Chat Completions with DeepSeek

Use the Portkey instance to send requests to DeepSeek. You can also override the virtual key directly in the API call if needed.

const chatCompletion = await portkey.chat.completions.create({
    messages: [{ role: 'user', content: 'Say this is a test' }],
    model: 'deepseek-chat',
});

console.log(chatCompletion.choices);

4. Invoke Multi-round Conversation with DeepSeek

const client = new Portkey({
    apiKey: "PORTKEY_API_KEY", // defaults to process.env["PORTKEY_API_KEY"]
    virtualKey: "VIRTUAL_KEY" // Your DeepSeek Virtual Key
})

// Function to send chat messages and get a response
async function sendChatMessages(messages) {
  try {
    const response = await axios.post(baseURL, {
      model: 'deepseek-chat',
      messages: messages
    }, { headers: headers });
    return response.data;
  } catch (error) {
    console.error('Error during the API request:', error.response ? error.response.data : error.message);
    return null;
  }
}

// Round 1
(async () => {
  let messages = [{ role: 'user', content: "What's the highest mountain in the world?" }];

  let response = await sendChatMessages(messages);
  if (response) {
    messages.push(response.choices[0].message);
    console.log(`Messages Round 1: ${JSON.stringify(messages, null, 2)}`);
  }

  // Round 2
  messages.push({ role: 'user', content: 'What is the second?' });
  response = await sendChatMessages(messages);
  if (response) {
    messages.push(response.choices[0].message);
    console.log(`Messages Round 2: ${JSON.stringify(messages, null, 2)}`);
  }
})();

5. JSON Output with DeepSeek

const client = new Portkey({
    apiKey: "PORTKEY_API_KEY", // defaults to process.env["PORTKEY_API_KEY"]
    virtualKey: "VIRTUAL_KEY" // Your DeepSeek Virtual Key
})

const systemPrompt = `
The user will provide some exam text. Please parse the "question" and "answer" and output them in JSON format.

EXAMPLE INPUT:
Which is the highest mountain in the world? Mount Everest.

EXAMPLE JSON OUTPUT:
{
    "question": "Which is the highest mountain in the world?",
    "answer": "Mount Everest"
}
`;

const userPrompt = "Which is the longest river in the world? The Nile River.";

const messages = [
    { role: "system", content: systemPrompt },
    { role: "user", content: userPrompt }
];

client.chat.completions.create({
    model: "deepseek-chat",
    messages: messages,
    responseFormat: {
        type: 'json_object'
    }
}).then(response => {
    console.log(JSON.parse(response.choices[0].message.content));
}).catch(error => {
    console.error('Error:', error);
});

Managing DeepSeek Prompts

You can manage all prompts to DeepSeek in the Prompt Library. All the current models of DeepSeek are supported and you can easily start testing different prompts.

Once you’re ready with your prompt, you can use the portkey.prompts.completions.create interface to use the prompt in your application.

Supported Endpoints

  1. CHAT_COMPLETIONS
  2. STREAM_CHAT_COMPLETIONS

The complete list of features supported in the SDK is available on the link below.

Portkey SDK Client

Learn more about the Portkey SDK Client

You’ll find more information in the relevant sections:

  1. Add metadata to your requests
  2. Add gateway configs to your DeepSeek requests
  3. Tracing DeepSeek requests
  4. Setup a fallback from OpenAI to DeepSeek APIs