Skip to main content

​
1. Get an API Key

Open the Anyfast console and sign up (or log in if you already have an account). After signing up, go to API Keys, create a new API Key, and copy it for later use.

​
2. Deploy MindSearch

Clone MindSearch and install dependencies (see the MindSearch README). Edit /path/to/MindSearch/mindsearch/models.py and add the Anyfast API configuration: 
anyfast_config = dict(
    type=GPTAPI,
    model_type='gpt-4o',
    key=os.environ.get('ANYFAST_API_KEY', 'YOUR ANYFAST API KEY'),
    openai_api_base='https://www.anyfast.ai/v1/chat/completions',
    meta_template=[
        dict(role='system', api_role='system'),
        dict(role='user', api_role='user'),
        dict(role='assistant', api_role='assistant'),
        dict(role='environment', api_role='system')
    ],
    top_p=0.8,
    top_k=1,
    temperature=0,
    max_new_tokens=8192,
    repetition_penalty=1.02,
    stop_words=['<|im_end|>']
)
Start the backend: 
# Set your Anyfast API Key
export ANYFAST_API_KEY=<your-api-key>

# Start MindSearch
python -m mindsearch.app --lang en --model_format anyfast_config --search_engine DuckDuckGoSearch
Start the frontend (Gradio example): 
python frontend/mindsearch_gradio.py

​
3. Deploy to HuggingFace Space

You can also deploy to HuggingFace Spaces:
  • Create a new Space at huggingface.co/new-space with Gradio template and Blank configuration.
  • Go to Settings and add your Anyfast API Key as a secret.
  • Upload the MindSearch directory, requirements.txt, and an app.py file.
For a complete example, refer to the MindSearch + Anyfast HuggingFace Space.