Merge branch 'main' of https://github.com/Fosowl/agenticSeek

.github/FUNDING.yml

@@ -0,0 +1,4 @@
+# These are supported funding model platforms
+
+github: [Fosowl ]# Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
+

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_model = gpt-4o
-provider_server_address = 127.0.0.1:5000
+provider_name = google
+provider_model = gemini-2.0-flash
+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*

config.ini

@@ -1,9 +1,9 @@
 [MAIN]
 is_local = True
-provider_name = openai
-provider_model = gpt-4o
-provider_server_address = 192.168.1.6:11434/v1
-agent_name = Joey
+provider_name = ollama
+provider_model = deepseek-r1:14b
+provider_server_address = 127.0.0.1:11434
+agent_name = Friday
 recover_last_session = False
 save_session = False
 speak = False

requirements.txt

@@ -1,3 +1,5 @@
+kokoro==0.9.4
+certifi==2025.4.26
 fastapi>=0.115.12
 flask>=3.1.0
 celery>=5.5.1
@@ -18,10 +20,10 @@ torch>=2.4.1
 python-dotenv>=1.0.0
 ollama>=0.4.7
 scipy>=1.9.3
-kokoro>=0.7.12
 soundfile>=0.13.1
 protobuf>=3.20.3
 termcolor>=2.4.0
+pypdf>=5.4.0
 ipython>=8.13.0
 pyaudio>=0.2.14
 librosa>=0.10.2.post1
@@ -39,6 +41,7 @@ fake_useragent>=2.1.0
 selenium_stealth>=1.0.6
 undetected-chromedriver>=3.5.5
 sentencepiece>=0.2.0
+tqdm>4
 openai
 sniffio
 tqdm>4
@@ -46,5 +49,3 @@ python-dotenv>=1.0.0
 # if use chinese
 ordered_set
 pypinyin
-cn2an
-jieba

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

@@ -13,6 +13,8 @@ from fake_useragent import UserAgent
 from selenium_stealth import stealth
 import undetected_chromedriver as uc
 import chromedriver_autoinstaller
+import certifi
+import ssl
 import time
 import random
 import os
@@ -28,6 +30,7 @@ from sources.utility import pretty_print, animate_thinking
 from sources.logger import Logger
 
 
+
 def get_chrome_path() -> str:
     """Get the path to the Chrome executable."""
     if sys.platform.startswith("win"):

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

@@ -9,7 +9,10 @@ from kokoro import KPipeline
 from IPython.display import display, Audio
 import soundfile as sf
 
-from sources.utility import pretty_print, animate_thinking
+if __name__ == "__main__":
+    from utility import pretty_print, animate_thinking
+else:
+    from sources.utility import pretty_print, animate_thinking
 
 class Speech():
     """
@@ -140,6 +143,7 @@ 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__":
-    from tools import Tools
-    from safety import is_unsafe
-else:
-    from sources.tools.tools import Tools
-    from sources.tools.safety import is_unsafe
+if __name__ == "__main__": # if running as a script for individual testing
+    sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
+
+from sources.tools.tools import Tools
+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__":
-    from tools import Tools
-else:
-    from sources.tools.tools import Tools
+if __name__ == "__main__": # if running as a script for individual testing
+    sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
+
+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__":
-    from tools import Tools
-else:
-    from sources.tools.tools import Tools
+if __name__ == "__main__": # if running as a script for individual testing
+    sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
+
+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__":
-    from tools import Tools
-else:
-    from sources.tools.tools import Tools
+if __name__ == "__main__": # if running as a script for individual testing
+    sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
+
+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__":
-    from tools import Tools
-else:
-    from sources.tools.tools import Tools
+if __name__ == "__main__": # if running as a script for individual testing
+    sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
+
+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__":
-    from tools import Tools
-else:
-    from sources.tools.tools import Tools
+if __name__ == "__main__": # if running as a script for individual testing
+    sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
 
+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__":
-    from tools import Tools
-else:
-    from sources.tools.tools import Tools
+if __name__ == "__main__": # if running as a script for individual testing
+    sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
+
+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 tools import Tools
-else:
-    from sources.tools.tools import Tools
+from sources.tools.tools import Tools
+
+if __name__ == "__main__": # if running as a script for individual testing
+    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__":
-    from tools import Tools
-else:
-    from sources.tools.tools import Tools
+if __name__ == "__main__": # if running as a script for individual testing
+    sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
+
+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__":
-    import sys
-    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
+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)