This documentation explains how to set up Basic Authentication for the GUI and API key authentication for the API when running the G4F server.
Before proceeding, ensure you have the following installed:
To secure both the GUI and the API, you'll authenticate using an API key. The API key should be injected via an environment variable and passed to both the GUI (via Basic Authentication) and the API.
On Linux/macOS:
export G4F_API_KEY="your-api-key-here"
On Windows (Command Prompt):
set G4F_API_KEY="your-api-key-here"
On Windows (PowerShell):
$env:G4F_API_KEY="your-api-key-here"
Replace your-api-key-here
with your actual API key.
Use the following command to start the G4F server. The API key will be passed to both the GUI and the API:
python -m g4f --debug --port 8080 --g4f-api-key $G4F_API_KEY
--debug
enables debug mode for more verbose logs.--port 8080
specifies the port on which the server will run (you can change this if needed).--g4f-api-key
specifies the API key for both the GUI and the API.export G4F_API_KEY="my-secret-api-key"
python -m g4f --debug --port 8080 --g4f-api-key $G4F_API_KEY
Now, both the GUI and API will require the correct API key for access.
The GUI uses Basic Authentication, where the username can be any value, and the password is your API key.
To access the GUI, open your web browser and navigate to http://localhost:8080/chat/
. You will be prompted for a username and password.
user
or admin
).G4F_API_KEY
environment variable).To interact with the API, you can send requests by including the g4f-api-key
in the headers. Here's an example of how to do this using the requests
library in Python.
import requests
url = "http://localhost:8080/v1/chat/completions"
# Body of the request
body = {
"model": "your-model-name", # Replace with your model name
"provider": "your-provider", # Replace with the provider name
"messages": [
{
"role": "user",
"content": "Hello"
}
]
}
# API Key (can be set as an environment variable)
api_key = "your-api-key-here" # Replace with your actual API key
# Send the POST request
response = requests.post(url, json=body, headers={"g4f-api-key": api_key})
# Check the response
print(response.status_code)
print(response.json())
In this example:
"your-api-key-here"
with your actual API key."model"
and "provider"
should be replaced with the appropriate model and provider you're using.messages
array contains the conversation you want to send to the API.The response will contain the output of the API request, such as the model's completion or other relevant data, which you can then process in your application.
Accessing the GUI: Open a web browser and navigate to http://localhost:8080/chat/
. The GUI will now prompt you for a username and password. You can enter any username (e.g., admin
), and for the password, enter the API key you set up in the environment variable.
Accessing the API: Use the Python code example above to send requests to the API. Ensure the correct API key is included in the g4f-api-key
header.
G4F_API_KEY
environment variable is correctly set and passed to the server. You can also check the server logs for more detailed error messages.By following the steps above, you will have successfully set up Basic Authentication for the G4F GUI (using any username and the API key as the password) and API key authentication for the API. This ensures that only authorized users can access both the interface and make API requests.