How to Integrate Bright Data With Strands Agents

Building an AI startup?

You might be eligible for our Startup Program. Get fully funded access to the infrastructure you’re reading about right now (up to $50K value).

Learn more

Strands Agents is an open-source Python library that provides a unified toolkit for developing autonomous AI agents. It bridges the gap between large language models and practical applications by offering ready-to-use tools for file operations, system execution, API interactions, mathematical operations, and more.

Steps to Get Started

1. Prerequisites

   • Bright Data API Key
   • Python 3.10+
2. Installation

   Set up the strands-agents-tools package by either using the quick pip install or the full development installation with virtual environment and pre-commit hooks.

   Quick Install

   pip install strands-agents-tools
   
3. Set the environment variable

   Set your Bright Data API key and unlocker zone as an environment variables:

   export BRIGHT_DATA_API_KEY="your_api_key_here"
   export BRIGHT_DATA_ZONE="your_unlocker_zone_here"
   
4. Bright Data Usage Examples

   Using bright data tools within an agent

   Sample Code

   from strands import Agent
   from strands.models.litellm import LiteLLMModel
   import strands_tools.bright_data as bright_data
   import os
   from dotenv import load_dotenv
   
   
   load_dotenv()
   
   
   def main():
   load_dotenv()
   print("🔍 Testing Bright Data Tool with OpenAI GPT-4o via LiteLLM")
   print("=" * 50)
   
   # Configure OpenAI model via LiteLLM
   openai_model = LiteLLMModel(
       client_args={
           "api_key": os.getenv("OPENAI_API_KEY"), 
       },
       model_id="openai/gpt-4o",
   )
   
   # Create agent with LiteLLM model and bright_data tool
   agent = Agent(
       model=openai_model,
       tools=[bright_data],
       system_prompt="you are a helpful Web Search assistant, whenever user asks you to search the web you will use avilable tools, always set zone name to 'unlocker'"
   )
   
   # Test the bright_data tool with a relevant query
   print("Testing web scraping...")
   result = agent("Please scrape the content from https://example.com and return it as markdown")
   print(f'\n\nScraping Result:\n{result}')
   
   print("\n" + "=" * 50)
   print("Testing web search...")
   result2 = agent("Please search Google for 'Python programming tutorials")
   print(f'\n\nSearch Result:\n{result2}')
   
   
   if __name__ == "__main__":
   main()
   

   Direct tool invocation

   from strands import Agent
   from strands.models.litellm import LiteLLMModel
   import strands_tools.bright_data as bright_data
   import os
   from dotenv import load_dotenv
   
   
   load_dotenv()
   
   
   def main():
     load_dotenv()
     print("🔍 Testing Bright Data Tool with OpenAI GPT-4o via LiteLLM")
     print("=" * 50)
     
     # Configure OpenAI model via LiteLLM
     openai_model = LiteLLMModel(
         client_args={
             "api_key": os.getenv("OPENAI_API_KEY"), 
         },
         model_id="openai/gpt-4o",
     )
     
     # Create agent with LiteLLM model and bright_data tool
     agent = Agent(
         model=openai_model,
         tools=[bright_data],
         system_prompt="you are a helpful Web Search assistant, whenever user asks you to search the web you will use avilable tools, always set zone name to 'unblocker'"
     )
     
     # Test the bright_data tool with a relevant query
     print("Testing web scraping...")
     result = agent.tool.bright_data(
     action="scrape_as_markdown",
     url="https://example.com",
     zone="unblocker"
   )
     print(f'\n\nScraping Result:\n{result}')
     
     print("\n" + "=" * 50)
     print("Testing web search...")
     result2 = agent.tool.bright_data(
     action="search_engine",
     query="Python programming tutorials",
     engine="google",
     zone="unblocker"
     )
     print(f'\n\nSearch Result:\n{result2}')
   
   
     result5 = agent.tool.bright_data(
         action="web_data_feed",
         source_type="amazon_product",
         url="https://www.amazon.com/dp/B0D2Q9397Y?th=1"
     )
     print(f'\n\nAmazon Product Data:\n{result5}')
   
   
   if __name__ == "__main__":
     main()