Update requirements.txt with curl_cffi

[tosin2013]

Exception in thread Thread-7 ():

Traceback (most recent call last):
  File "/usr/lib/python3.10/threading.py", line 1016, in _bootstrap_inner
    self.run()
  File "/usr/lib/python3.10/threading.py", line 953, in run
    self._target(*self._args, **self._kwargs)
  File "/home/ubuntu/devika/devika.py", line 85, in <lambda>
    thread = Thread(target=lambda: agent.execute(message, project_name))
  File "/home/ubuntu/devika/src/agents/agent.py", line 344, in execute
    search_results = self.search_queries(queries, project_name)
  File "/home/ubuntu/devika/src/agents/agent.py", line 89, in search_queries
    web_search = DuckDuckGoSearch()
  File "/home/ubuntu/devika/src/browser/search.py", line 94, in __init__
    from curl_cffi import requests as curl_requests
ModuleNotFoundError: No module named 'curl_cffi'

Description:

This pull request addresses an issue where the curl_cffi module is not found, causing a ModuleNotFoundError when attempting to initialize a DuckDuckGoSearch instance. The error occurs in the search.py file during the import of curl_cffi.

• [x] Bug: ModuleNotFoundError due to missing curl_cffi module
• [ ] Additional bugs or features to be addressed in future PRs

Problem Solved:

The pull request solves the issue by ensuring that the curl_cffi module is correctly installed and available for use within the project. This is crucial for the proper functioning of the web search functionality implemented in search.py.

Test Plan (required):

1. Installation Check: Verify that curl_cffi is installed in the project environment.
2. Functionality Test: Run the devika.py script and ensure that the web search functionality works without raising a ModuleNotFoundError.
3. Integration Test: Ensure that other functionalities dependent on the web search are also functioning correctly.

Closing Issues (optional):