Merge pull request #152 from Fosowl/dev

Improve chromedriver install error handling + improved fileFinder

README.md

@@ -159,9 +159,9 @@ Set the desired provider in the `config.ini`. See below for a list of API provid
 ```sh
 [MAIN]
 is_local = False
-provider_name = openai
+provider_name = google
-provider_model = gpt-4o
+provider_model = gemini-2.0-flash
-provider_server_address = 127.0.0.1:5000
+provider_server_address = 127.0.0.1:5000 # doesn't matter
 ```
 Warning: Make sure there is not trailing space in the config.
 
@@ -179,6 +179,10 @@ Example: export `TOGETHER_API_KEY="xxxxx"`
 | togetherAI | No    | Use together AI API (non-private)                         |
 | google | No    | Use google gemini API (non-private)                         |
 
+*We advice against using gpt-4o or other closedAI models*, performance are poor for web browsing and task planning.
+
+Please also note that coding/bash might fail with gemini, it seem to ignore our prompt for format to respect, which are optimized for deepseek r1.
+
 Next step: [Start services and run AgenticSeek](#Start-services-and-Run)
 
 *See the **Known issues** section if you are having issues*

sources/agents/agent.py

@@ -123,6 +123,8 @@ class Agent():
         """
         start_tag = "<think>"
         end_tag = "</think>"
+        if text is None:
+            return None
         start_idx = text.find(start_tag)
         end_idx = text.rfind(end_tag)+8
         return text[start_idx:end_idx]

sources/agents/planner_agent.py

@@ -151,7 +151,7 @@ class PlannerAgent(Agent):
                 return []
             agents_tasks = self.parse_agent_tasks(answer)
             if agents_tasks == []:
-                prompt = f"Failed to parse the tasks. Please make a plan within ```json. Do not ask for clarification.\n"
+                prompt = f"Failed to parse the tasks. Please write down your task followed by a json plan within ```json. Do not ask for clarification.\n"
                 pretty_print("Failed to make plan. Retrying...", color="warning")
                 continue
             self.show_plan(agents_tasks, answer)

sources/browser.py

@@ -65,6 +65,25 @@ def get_random_user_agent() -> str:
     ]
     return random.choice(user_agents)
 
+def install_chromedriver() -> str:
+    """
+    Install the ChromeDriver if not already installed. Return the path.
+    """
+    chromedriver_path = shutil.which("chromedriver")
+    if not chromedriver_path:
+        try:
+            chromedriver_path = chromedriver_autoinstaller.install()
+        except Exception as e:
+            raise FileNotFoundError(
+                "ChromeDriver not found and could not be installed automatically. "
+                "Please install it manually from https://chromedriver.chromium.org/downloads."
+                "and ensure it's in your PATH or specify the path directly."
+                "See know issues in readme if your chrome version is above 115."
+            ) from e
+    if not chromedriver_path:
+        raise FileNotFoundError("ChromeDriver not found. Please install it or add it to your PATH.")
+    return chromedriver_path
+
 def create_driver(headless=False, stealth_mode=True, crx_path="./crx/nopecha.crx") -> webdriver.Chrome:
     """Create a Chrome WebDriver with specified options."""
     chrome_options = Options()
@@ -97,14 +116,9 @@ def create_driver(headless=False, stealth_mode=True, crx_path="./crx/nopecha.crx
             pretty_print(f"Anti-captcha CRX not found at {crx_path}.", color="failure")
         else:
             chrome_options.add_extension(crx_path)
-    
+
-    chromedriver_path = shutil.which("chromedriver")
+    chromedriver_path = install_chromedriver()
-    if not chromedriver_path:
+
-        chromedriver_path = chromedriver_autoinstaller.install()
-    
-    if not chromedriver_path:
-        raise FileNotFoundError("ChromeDriver not found. Please install it or add it to your PATH.")
-    
     service = Service(chromedriver_path)
     if stealth_mode:
         chrome_options.add_argument("--disable-blink-features=AutomationControlled")

sources/llm_provider.py

@@ -72,6 +72,8 @@ class Provider:
         except ModuleNotFoundError as e:
             raise ModuleNotFoundError(f"{str(e)}\nA import related to provider {self.provider_name} was not found. Is it installed ?")
         except Exception as e:
+            if "try again later" in str(e).lower():
+                return f"{self.provider_name} server is overloaded. Please try again later."
             if "refused" in str(e):
                 return f"Server {self.server_ip} seem offline. Unable to answer."
             raise Exception(f"Provider {self.provider_name} failed: {str(e)}") from e
@@ -214,7 +216,7 @@ class Provider:
         """
         base_url = self.server_ip
         if self.is_local:
-            raise Exception("Google Gemini is not available for local use.")
+            raise Exception("Google Gemini is not available for local use. Change config.ini")
 
         client = OpenAI(api_key=self.api_key, base_url="https://generativelanguage.googleapis.com/v1beta/openai/")
         try:
@@ -237,6 +239,8 @@ class Provider:
         """
         from together import Together
         client = Together(api_key=self.api_key)
+        if self.is_local:
+            raise Exception("Together AI is not available for local use. Change config.ini")
 
         try:
             response = client.chat.completions.create(
@@ -257,6 +261,8 @@ class Provider:
         Use deepseek api to generate text.
         """
         client = OpenAI(api_key=self.api_key, base_url="https://api.deepseek.com")
+        if self.is_local:
+            raise Exception("Deepseek (API) is not available for local use. Change config.ini")
         try:
             response = client.chat.completions.create(
                 model="deepseek-chat",

sources/text_to_speech.py

@@ -140,6 +140,7 @@ class Speech():
         return sentence
 
 if __name__ == "__main__":
+    # TODO add info message for cn2an, jieba chinese related import
     sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
     speech = Speech()
     tosay_en = """

sources/tools/BashInterpreter.py

@@ -1,15 +1,14 @@
 
-import sys
+import os, sys
 import re
 from io import StringIO
 import subprocess
 
-if __name__ == "__main__":
+if __name__ == "__main__": # if running as a script for individual testing
-    from tools import Tools
+    sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
-    from safety import is_unsafe
+
-else:
+from sources.tools.tools import Tools
-    from sources.tools.tools import Tools
+from sources.tools.safety import is_unsafe
-    from sources.tools.safety import is_unsafe
 
 class BashInterpreter(Tools):
     """

sources/tools/C_Interpreter.py

@@ -1,12 +1,12 @@
 import subprocess
-import os
+import os, sys
 import tempfile
 import re
 
-if __name__ == "__main__":
+if __name__ == "__main__": # if running as a script for individual testing
-    from tools import Tools
+    sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
-else:
+
-    from sources.tools.tools import Tools
+from sources.tools.tools import Tools
 
 class CInterpreter(Tools):
     """

sources/tools/GoInterpreter.py

@@ -1,12 +1,12 @@
 import subprocess
-import os
+import os, sys
 import tempfile
 import re
 
-if __name__ == "__main__":
+if __name__ == "__main__": # if running as a script for individual testing
-    from tools import Tools
+    sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
-else:
+
-    from sources.tools.tools import Tools
+from sources.tools.tools import Tools
 
 class GoInterpreter(Tools):
     """

sources/tools/JavaInterpreter.py

@@ -1,12 +1,12 @@
 import subprocess
-import os
+import os, sys
 import tempfile
 import re
 
-if __name__ == "__main__":
+if __name__ == "__main__": # if running as a script for individual testing
-    from tools import Tools
+    sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
-else:
+
-    from sources.tools.tools import Tools
+from sources.tools.tools import Tools
 
 class JavaInterpreter(Tools):
     """

sources/tools/PyInterpreter.py

@@ -4,10 +4,10 @@ import os
 import re
 from io import StringIO
 
-if __name__ == "__main__":
+if __name__ == "__main__": # if running as a script for individual testing
-    from tools import Tools
+    sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
-else:
+
-    from sources.tools.tools import Tools
+from sources.tools.tools import Tools
 
 class PyInterpreter(Tools):
     """

sources/tools/fileFinder.py

@@ -1,13 +1,12 @@
-import os
+import os, sys
 import stat
 import mimetypes
 import configparser
 
-if __name__ == "__main__":
+if __name__ == "__main__": # if running as a script for individual testing
-    from tools import Tools
+    sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
-else:
-    from sources.tools.tools import Tools
 
+from sources.tools.tools import Tools
 
 class FileFinder(Tools):
     """
@@ -30,14 +29,46 @@ class FileFinder(Tools):
                 return file.read()
         except Exception as e:
             return f"Error reading file: {e}"
+        
+    def read_arbitrary_file(self, file_path: str, file_type: str) -> str:
+        """
+        Reads the content of a file with arbitrary encoding.
+        Args:
+            file_path (str): The path to the file to read
+        Returns:
+            str: The content of the file in markdown format
+        """
+        mime_type, _ = mimetypes.guess_type(file_path)
+        if mime_type:
+            if mime_type.startswith(('image/', 'video/', 'audio/')):
+                return "can't read file type: image, video, or audio files are not supported."
+        content_raw = self.read_file(file_path)
+        if "text" in file_type:
+            content = content_raw
+        elif "pdf" in file_type:
+            from pypdf import PdfReader
+            reader = PdfReader(file_path)
+            content = '\n'.join([pt.extract_text() for pt in reader.pages])
+        elif "binary" in file_type:
+            content = content_raw.decode('utf-8', errors='replace')
+        else:
+            content = content_raw
+        return content
     
     def get_file_info(self, file_path: str) -> str:
+        """
+        Gets information about a file, including its name, path, type, content, and permissions.
+        Args:
+            file_path (str): The path to the file
+        Returns:
+            str: A dictionary containing the file information
+        """
         if os.path.exists(file_path):
             stats = os.stat(file_path)
             permissions = oct(stat.S_IMODE(stats.st_mode))
             file_type, _ = mimetypes.guess_type(file_path)
             file_type = file_type if file_type else "Unknown"
-            content = self.read_file(file_path)
+            content = self.read_arbitrary_file(file_path, file_type)
             
             result = {
                 "filename": os.path.basename(file_path),

sources/tools/flightSearch.py

@@ -1,13 +1,13 @@
-import os
+import os, sys
 import requests
 import dotenv
 
 dotenv.load_dotenv()
 
-if __name__ == "__main__":
+if __name__ == "__main__": # if running as a script for individual testing
-    from tools import Tools
+    sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
-else:
+
-    from sources.tools.tools import Tools
+from sources.tools.tools import Tools
 
 class FlightSearch(Tools):
     def __init__(self, api_key: str = None):

sources/tools/mcpFinder.py

@@ -1,12 +1,13 @@
-import os
+import os, sys
 import requests
 from urllib.parse import urljoin
 from typing import Dict, Any, Optional
 
-if __name__ == "__main__":
+from sources.tools.tools import Tools
-    from tools import Tools
+
-else:
+if __name__ == "__main__": # if running as a script for individual testing
-    from sources.tools.tools import Tools
+    sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
+
 
 class MCP_finder(Tools):
     """

sources/tools/searxSearch.py

@@ -2,10 +2,10 @@ import requests
 from bs4 import BeautifulSoup
 import os
 
-if __name__ == "__main__":
+if __name__ == "__main__": # if running as a script for individual testing
-    from tools import Tools
+    sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
-else:
+
-    from sources.tools.tools import Tools
+from sources.tools.tools import Tools
 
 class searxSearch(Tools):
     def __init__(self, base_url: str = None):

sources/tools/tools.py

@@ -14,13 +14,17 @@ For example:
 print("Hello world")
 ```
 This is then executed by the tool with its own class implementation of execute().
-A tool is not just for code tool but also API, internet, etc..
+A tool is not just for code tool but also API, internet search, MCP, etc..
 """
 
 import sys
 import os
 import configparser
 from abc import abstractmethod
+
+if __name__ == "__main__": # if running as a script for individual testing
+    sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
 from sources.logger import Logger
 
 class Tools():

sources/tools/webSearch.py

@@ -5,14 +5,8 @@ import dotenv
 
 dotenv.load_dotenv()
 
-if __name__ == "__main__":
+from sources.tools.tools import Tools
-    import sys
+from sources.utility import animate_thinking, pretty_print
-    sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-    from utility import animate_thinking, pretty_print
-    from tools import Tools
-else:
-    from sources.tools.tools import Tools
-    from sources.utility import animate_thinking, pretty_print
 
 """
 WARNING

tests/test_browser_agent_parsing.py

@@ -17,13 +17,13 @@ class TestBrowserAgentParsing(unittest.TestCase):
         # Test various link formats
         test_text = """
         Check this out: https://thriveonai.com/15-ai-startups-in-japan-to-take-note-of, and www.google.com!
-        Also try https://test.org/about?page=1, hey this one as well bro https://weatherstack.com/documentation.
+        Also try https://test.org/about?page=1, hey this one as well bro https://weatherstack.com/documentation/.
         """
         expected = [
             "https://thriveonai.com/15-ai-startups-in-japan-to-take-note-of",
             "www.google.com",
             "https://test.org/about?page=1",
-            "https://weatherstack.com/documentation"
+            "https://weatherstack.com/documentation",
         ]
         result = self.agent.extract_links(test_text)
         self.assertEqual(result, expected)