Doc: readme; Feat : language utility class, small fix

README.md

@@ -9,7 +9,13 @@
 
 ![alt text](./media/whale_readme.jpg)
 
+> *Do a web search to find tech startup in Japan working on cutting edge AI research*
 
+> *Make a snake game in Python*
+
+> *Scan my network with nmap, find out who is connected?*
+
+> *Hey can you find where is contract.pdf*?
 
 ## Features:
 
@@ -34,6 +40,7 @@
 - **Web Browsing**: Autonomous web navigation is underway.
 
 
+
 ### Searching the web with agenticSeek :
 
 ![alt text](./media/exemples/search_startup.png)
@@ -126,6 +133,77 @@ Run the assistant:
 python3 main.py
 ```
 
+*See the **Usage** section if you don't understand how to use it*
+
+*See the **Config** section for more informations on the config*
+
+---
+
+## Usage
+
+致中文使用者的重要提示：目前根据您的提示选择最佳AI代理的系统（代理路由）在处理中文文本时效果不佳，这是因为我们使用的是基于英文文本训练的一次性分类模型。我们正在努力解决这个问题。请暂时使用英文
+
+Warning: currently the system that choose the best AI agent routing system will work poorly with non-english text. This is because the agent routing currently use a model that was trained on english text. We are working hard to fix this. Please use english for now.
+
+
+Make sure the services are up and running with `./start_services.sh` and run the agenticSeek with `python3 main.py`
+
+```sh
+./start_services.sh
+python3 main.py
+```
+
+You will be prompted with `>>> `
+This indicate agenticSeek await you type for instructions.
+You can also use speech to text by setting `listen = True` in the config.
+
+Here are some example usage:
+
+### Coding/Bash
+
+> *Help me with matrix multiplication in Golang*
+
+> *Scan my network with nmap, find if any suspicious devices is connected*
+
+> *Make a snake game in python*
+
+### Web search
+
+> *Do a web search to find cool tech startup in Japan working on cutting edge AI research*
+
+> *Can you find on the internet who created agenticSeek?*
+
+> *Can you find on which website I can buy a rtx 4090 for cheap*
+
+### File system
+
+> *Hey can you find where is million_dollars_contract.pdf i lost it*
+
+> *Show me how much space I have left on my disk*
+
+> *Find and read the README.md and follow the install instruction*
+
+### Casual
+
+> *Tell me a joke*
+
+> *Where is flight ABC777 ? my mom is on that plane*
+
+> *what is the meaning of life ?*
+
+
+After you type your query, agenticSeek will allocate the best agent for the task.
+
+Because this is an early prototype, the agent routing system might not always allocate the right agent based on your query.
+
+Therefore, you should be very explicit in what you want and how the AI might proceed for example if you want it to conduct a web search, do not say:
+
+`Do you know some good countries for solo-travel?`
+
+Instead, ask:
+
+`Do a web search and find out which are the best country for solo-travel`
+
 ---
 
 ## **Run the LLM on your own server**  
@@ -195,6 +273,30 @@ python3 main.py
 
 ---
 
+
+
+## Speech to Text
+
+The speech to text is disabled by default, you can enable it by setting listen to true in the config.ini:
+
+```
+listen = True
+```
+
+The speech to text will await for a AI name as a trigger keyword before it start listening, you can change the AI name by changing the agent_name in the config.ini:
+
+```
+agent_name = Friday
+```
+
+It will work better if you use a common english name like John or Emma.
+
+After hearing it's name agenticSeek will listen until it hear one of the following keyword for confirmation:
+
+```
+"do it", "go ahead", "execute", "run", "start", "thanks", "would ya", "please", "okay?", "proceed", "continue", "go on", "do that", "go it", "do you understand?"
+```
+
 ## Providers
 
 The table below show the available providers:

requirements.txt

@@ -19,6 +19,8 @@ pyaudio==0.2.14
 librosa==0.10.2.post1
 selenium==4.29.0
 markdownify==1.1.0
+text2emotion==0.0.5
+langid==1.1.6
 chromedriver-autoinstaller==0.6.4
 httpx>=0.27,<0.29
 anyio>=3.5.0,<5

setup.py

@@ -34,6 +34,8 @@ setup(
         "librosa==0.10.2.post1",
         "selenium==4.29.0",
         "markdownify==1.1.0",
+        "text2emotion==0.0.5",
+        "langid==1.1.6",
         "httpx>=0.27,<0.29",
         "anyio>=3.5.0,<5",
         "distro>=1.7.0,<2",

sources/agents/browser_agent.py

@@ -16,7 +16,7 @@ class BrowserAgent(Agent):
         self.tools = {
             "web_search": searxSearch(),
         }
-        self.role = "web search, internet browsing, news"
+        self.role = "Web Research"
         self.browser = Browser()
         self.search_history = []
         self.navigable_links = []
@@ -101,7 +101,7 @@ class BrowserAgent(Agent):
 
         Current date: {self.date}
         Remember, the user asked: {user_prompt}
-        Do not exit until you found information the user seek or accomplished the task.
+        Do not explain your choice.
         """
     
     def llm_decide(self, prompt):
@@ -182,9 +182,10 @@ class BrowserAgent(Agent):
     def process(self, user_prompt, speech_module) -> str:
         complete = False
 
-        animate_thinking(f"Searching...", color="status")
+        animate_thinking(f"Thinking...", color="status")
         self.memory.push('user', self.search_prompt(user_prompt))
         ai_prompt, _ = self.llm_request()
+        animate_thinking(f"Searching...", color="status")
         search_result_raw = self.tools["web_search"].execute([ai_prompt], False)
         search_result = self.jsonify_search_results(search_result_raw)[:7] # until futher improvement
         prompt = self.make_newsearch_prompt(user_prompt, search_result)
@@ -220,4 +221,4 @@ class BrowserAgent(Agent):
         return answer, reasoning
 
 if __name__ == "__main__":
-    browser = Browser()
+    pass

sources/agents/casual_agent.py

@@ -18,7 +18,7 @@ class CasualAgent(Agent):
             "file_finder": FileFinder(),
             "bash": BashInterpreter()
         }
-        self.role = "casual talking"
+        self.role = "Chat and Conversation"
     
     def process(self, prompt, speech_module) -> str:
         complete = False

sources/agents/code_agent.py

@@ -20,7 +20,7 @@ class CoderAgent(Agent):
             "go": GoInterpreter(),
             "file_finder": FileFinder()
         }
-        self.role = "coding and programming"
+        self.role = "Code Assistance"
 
     def process(self, prompt, speech_module) -> str:
         answer = ""

sources/agents/file_agent.py

@@ -14,7 +14,7 @@ class FileAgent(Agent):
             "file_finder": FileFinder(),
             "bash": BashInterpreter()
         }
-        self.role = "find, read, write, edit files"
+        self.role = "find and read files"
     
     def process(self, prompt, speech_module) -> str:
         complete = False

sources/agents/planner_agent.py

@@ -21,7 +21,7 @@ class PlannerAgent(Agent):
             "file": FileAgent(model, name, prompt_path, provider),
             "web": BrowserAgent(model, name, prompt_path, provider)
         }
-        self.role = "Manage complex tasks"
+        self.role = "Research, setup and code"
         self.tag = "json"
 
     def parse_agent_tasks(self, text):

sources/language.py

@@ -0,0 +1,84 @@
+import langid
+import re
+import nltk
+from nltk.sentiment.vader import SentimentIntensityAnalyzer
+
+class LanguageUtility:
+    """LanguageUtility for language, or emotion identification"""
+    def __init__(self):
+        try:
+            nltk.data.find('vader_lexicon')
+        except LookupError:
+            nltk.download('vader_lexicon')
+        self.sid = SentimentIntensityAnalyzer()
+    
+    def detect_language(self, text: str) -> str:
+        """
+        Detect the language of the given text using langdetect
+        Args:
+            text: string to analyze
+        Returns: ISO639-1 language code
+        """
+        langid.set_languages(['fr', 'en', 'zh', 'es'])  # ISO 639-1 codes
+        lang, score = langid.classify(text)
+        return lang
+
+    def detect_emotion(self, text: str) -> str:
+        """
+        Detect the dominant emotion in the given text
+        Args:
+            text: string to analyze
+        Returns: string of the dominant emotion
+        """
+        try:
+            scores = self.sid.polarity_scores(text)
+            emotions = {
+                'Happy': max(scores['pos'], 0),
+                'Angry': 0,
+                'Sad': max(scores['neg'], 0),
+                'Fear': 0,
+                'Surprise': 0
+            }
+            if scores['compound'] < -0.5:
+                emotions['Angry'] = abs(scores['compound']) * 0.5
+                emotions['Fear'] = abs(scores['compound']) * 0.5
+            elif scores['compound'] > 0.5:
+                emotions['Happy'] = scores['compound']
+                emotions['Surprise'] = scores['compound'] * 0.5
+            dominant_emotion = max(emotions, key=emotions.get)
+            if emotions[dominant_emotion] == 0:
+                return 'Neutral'
+            return dominant_emotion
+        except Exception as e:
+            raise e
+    
+    def analyze(self, text):
+        """
+        Combined analysis of language and emotion
+        Args:
+            text: string to analyze
+        Returns: dictionary with language and emotion results
+        """
+        try:
+            language = self.detect_language(text)
+            emotions = self.detect_emotion(text)
+            return {
+                "language": language,
+                "emotions": emotions
+            }
+        except Exception as e:
+            raise e
+
+if __name__ == "__main__":
+    detector = LanguageUtility()
+    
+    test_texts = [
+        "I am so happy today!",
+        "Qué tristeza siento ahora",
+        "我不要去巴黎",
+        "La vie c'est cool"
+    ]
+    for text in test_texts:
+        print(f"\nAnalyzing: {text}")
+        result = detector.analyze(text)
+        print(result)

sources/llm_provider.py

@@ -12,6 +12,8 @@ from huggingface_hub import InferenceClient
 import os
 import httpx
 
+from sources.utility import pretty_print, animate_thinking
+
 class Provider:
     def __init__(self, provider_name, model, server_address = "127.0.0.1:5000"):
         self.provider_name = provider_name.lower()
@@ -29,10 +31,10 @@ class Provider:
         if self.provider_name not in self.available_providers:
             raise ValueError(f"Unknown provider: {provider_name}")
         if self.provider_name in self.unsafe_providers:
-            print("Warning: you are using an API provider. You data will be sent to the cloud.")
+            pretty_print("Warning: you are using an API provider. You data will be sent to the cloud.", color="warning")
             self.api_key = self.get_api_key(self.provider_name)
         elif self.server != "":
-            print("Provider", provider_name, "initialized at", self.server)
+            pretty_print(f"Provider: {provider_name} initialized at {self.server}", color="success")
         self.check_address_format(self.server)
         if not self.is_ip_online(self.server.split(':')[0]):
             raise Exception(f"Server at {self.server} is offline.")
@@ -89,13 +91,11 @@ class Provider:
             if output.returncode == 0:
                 return True
             else:
-                print("errorcode:", output)
                 return False
         except subprocess.TimeoutExpired:
-            print("timeout")
-            return True
+            return False
         except Exception as e:
-            print(f"is_ip_online error:\n{e}")
+            pretty_print(f"Error with ping request {str(e)}", color="failure")
             return False
 
     def server_fn(self, history, verbose = False):
@@ -117,7 +117,7 @@ class Provider:
                 is_complete = bool(response.json()["is_complete"])
                 time.sleep(2)
         except KeyError as e:
-            raise f"{str(e)}\n\nError occured with server route. Are you using the correct address for the config.ini provider?"
+            raise Exception(f"{str(e)}\n\nError occured with server route. Are you using the correct address for the config.ini provider?") from e
         except Exception as e:
             raise e
         return thought
@@ -141,7 +141,7 @@ class Provider:
             raise Exception("\nOllama connection failed. provider should not be set to ollama if server address is not localhost") from e
         except ollama.ResponseError as e:
             if e.status_code == 404:
-                print(f"Downloading {self.model}...")
+                animate_thinking(f"Downloading {self.model}...")
                 ollama.pull(self.model)
             if "refused" in str(e).lower():
                 raise Exception("Ollama connection failed. is the server running ?") from e

sources/router.py

@@ -9,6 +9,7 @@ from sources.agents.agent import Agent
 from sources.agents.code_agent import CoderAgent
 from sources.agents.casual_agent import CasualAgent
 from sources.agents.planner_agent import PlannerAgent
+from sources.agents.browser_agent import BrowserAgent
 from sources.utility import pretty_print
 
 class AgentRouter:
@@ -30,7 +31,7 @@ class AgentRouter:
         else:
             return "cpu"
 
-    def classify_text(self, text: str, threshold: float = 0.5) -> list:
+    def classify_text(self, text: str, threshold: float = 0.4) -> list:
         """
         Classify the text into labels (agent roles).
         Args:
@@ -67,30 +68,50 @@ class AgentRouter:
 
 if __name__ == "__main__":
     agents = [
-        CoderAgent("deepseek-r1:14b", "agent1", "../prompts/coder_agent.txt", "server"),
-        CasualAgent("deepseek-r1:14b", "agent2", "../prompts/casual_agent.txt", "server"),
-        PlannerAgent("deepseek-r1:14b", "agent3", "../prompts/planner_agent.txt", "server")
+        CasualAgent("deepseek-r1:14b", "jarvis", "../prompts/casual_agent.txt", None),
+        BrowserAgent("deepseek-r1:14b", "browser", "../prompts/planner_agent.txt", None),
+        CoderAgent("deepseek-r1:14b", "coder", "../prompts/coder_agent.txt", None)
     ]
     router = AgentRouter(agents)
-    
-    texts = ["""
-    Write a python script to check if the device on my network is connected to the internet
-    """,
-    """
-    Hey could you search the web for the latest news on the stock market ?
-    """,
-    """
-    hey can you give give a list of the files in the current directory ?
-    """,
-    """
-    Make a cool game to illustrate the current relation between USA and europe
-    """
+    texts = [
+        "Write a python script to check if the device on my network is connected to the internet",
+        #"Peut tu écrire un script python qui vérifie si l'appareil sur mon réseau est connecté à internet?",
+        #"写一个Python脚本，检查我网络上的设备是否连接到互联网",
+        "Hey could you search the web for the latest news on the tesla stock market ?",
+        #"嘿，你能搜索网页上关于股票市场的最新新闻吗？",
+        #"Yo, cherche sur internet comment va tesla en bourse.",
+        "I would like you to search for weather api and then make an app using this API",
+        #"我想让你搜索天气API，然后用这个API做一个应用程序",
+        #"J'aimerais que tu cherche une api météo et que l'utilise pour faire une application",
+        "Plan a 3-day trip to New York, including flights and hotels.",
+        #"计划一次为期3天的纽约之旅，包括机票和酒店。",
+        #"Planifie un trip de 3 jours à Paris, y compris les vols et hotels.",
+        "Find me the latest research papers on AI.",
+        #"给我找最新的AI研究论文。",
+        #"Trouve moi les derniers papiers de recherche en IA",
+        "Help me write a C++ program to sort an array",
+        #"帮我写一个C++程序来排序数组",
+        #"Aide moi à faire un programme c++ pour trier une array.",
+        "What’s the weather like today? Oh, and can you find a good weather app?",
+        #"今天天气怎么样？哦，你还能找到一个好的天气应用程序吗？",
+        #"La météo est comment aujourd'hui ? oh et trouve moi une bonne appli météo tant que tu y est.",
+        "Can you debug this Java code? It’s not working.",
+        #"你能调试这段Java代码吗？它不起作用。",
+        #"Peut tu m'aider à debugger ce code java, ça marche pas",
+        "What's the latest brainrot on the internet ?",
+        #"互联网上最新的“脑残”是什么？",
+        #"Quel est la dernière connerie sur internet ?",
+        "i would like to setup a new AI project, index as mark2",
+        #"我想建立一个新的 AI 项目，索引为 Mark2",
+        #"Je voudrais configurer un nouveau projet d'IA, index Mark2",
+        "Hey, can you find the old_project.zip file somewhere on my drive?",
+        #"嘿，你能在我驱动器上找到old_project.zip文件吗？",
+        #"Hé trouve moi le old_project.zip, il est quelque part sur mon disque.",
+        "Tell me a funny story",
+        #"给我讲一个有趣的故事",
+        #"Raconte moi une histoire drole"
     ]
-
     for text in texts:
-        print(text)
-        results = router.classify_text(text)
-        for result in results:
-            print(result["label"], "=>", result["score"])
+        print("Input text:", text)
         agent = router.select_agent(text)
-        print("Selected agent role:", agent.role)
+        print()

sources/tools/searxSearch.py

@@ -50,7 +50,6 @@ class searxSearch(Tools):
         """Check all links, one by one."""
         # TODO Make it asyncromous or smth
         statuses = []
-        print("Web scrawl to verify links accessibilty...")
         for i, link in enumerate(links):
             status = self.link_valid(link)
             statuses.append(status)

sources/tools/tools.py

@@ -118,10 +118,8 @@ class Tools():
         save_path_file = os.path.basename(save_path)
         directory = os.path.join(self.current_dir, save_path_dir)
         if directory and not os.path.exists(directory):
-            print(f"Creating directory: {directory}")
             os.makedirs(directory)
         for block in blocks:
-            print(f"Saving code block to: {save_path}")
             with open(os.path.join(directory, save_path_file), 'w') as f:
                 f.write(block)
     

sources/tools/webSearch.py

@@ -58,7 +58,6 @@ class webSearch(Tools):
         """Check all links, one by one."""
         # TODO Make it asyncromous or smth
         statuses = []
-        print("Workers started, scrawling the web...")
         for i, link in enumerate(links):
             status = self.link_valid(link)
             statuses.append(status)