How to access DeepSeekapi - DeepSeekapi access call tutorial

Detailed explanation of DeepSeek API access and call: Quick guide

This article will provide you with detailed instructions on how to access and call the DeepSeek API, helping you easily use powerful AI models.

Step 1: Obtain the API key

1. Visit the DeepSeek official website and click on the "Open Platform" in the upper right corner.

2. You will get a certain number of free tokens (for metering API usage). In the menu on the left, click "API Keys" and then click "Create API key".

3. Name your API key (for example, "test") and copy the generated key immediately. Be sure to save this key properly as it will only be displayed once.

Step 2: Get base_url and chat_model

1. In the Quick Start section of the DeepSeek API documentation, find base_url and chat_model parameters. The acquisition methods of other platforms are similar.

Step 3: Configure model parameters

For security reasons, it is recommended to store the API key in environment variables rather than writing directly into the code. The following two methods are provided:

Method 1: The terminal temporarily sets environment variables (only valid in the current terminal session)

Enter the following command in the terminal to add your API key to the environment variable (replace YOUR_API_KEY with your actual key):

 export API_KEY="YOUR_API_KEY"

Method 2: Create .env file (recommended)

1. Create a file named .env .
2. Add the following in the .env file, replacing YOUR_API_KEY with your actual key:

 <code>API_KEY="YOUR_API_KEY"</code>

In Python code, use the python-dotenv library to read environment variables:

 from dotenv import load_dotenv
import os

load_dotenv() # Load the .env file api_key = os.getenv("API_KEY")

Step 4: Create a client

Create a DeepSeek client using base_url and api_key . (The specific client creation method depends on the library you are using)

Step 5: Test API calls

Here is a simple Python code example for testing API connections:

 # ... (Previous code, including client creation) ...

response = client.chat(model=chat_model, messages=[{"role": "user", "content": "Hello"}])
print(response)

If everything is configured correctly, you will receive a reply from the model. If an error occurs, check that your API key and configuration are correct.

For more details, please refer to the official DeepSeek document. Original link (please replace it with the actual link)

The above is the detailed content of How to access DeepSeekapi - DeepSeekapi access call tutorial. For more information, please follow other related articles on the PHP Chinese website!