Merge pull request #66 from Fosowl/dev

Fix : AudioRecorder issue, Improve readme, more flexible requirements + python_requires to 3.9

README.md

@@ -38,8 +38,7 @@
 
 - **Memory**: Remembers what’s useful, your preferences and past sessions conversation.
 
-- **Web Browsing**: Autonomous web navigation is underway.
-
+- **Web Browsing**: Autonomous web navigation.
 
 
 ### Searching the web with agenticSeek :
@@ -52,7 +51,7 @@
 
 ## **Installation**
 
-Make sure you have chrome driver and docker installed.
+Make sure you have chrome driver, docker and python3.10 (or newer) installed.
 
 For issues related to chrome driver, see the **Chromedriver** section.
 
@@ -125,7 +124,7 @@ provider_server_address = 127.0.0.1:11434
 start all services :
 
 ```sh
-./start_services.sh
+sudo ./start_services.sh
 ```
 
 Run the assistant:
@@ -150,7 +149,7 @@ Warning: currently the system that choose the best AI agent routing system will
 Make sure the services are up and running with `./start_services.sh` and run the agenticSeek with `python3 main.py`
 
 ```sh
-./start_services.sh
+sudo ./start_services.sh
 python3 main.py
 ```
 
@@ -247,7 +246,7 @@ provider_server_address = x.x.x.x:5000
 Run the assistant:
 
 ```sh
-./start_services.sh
+sudo ./start_services.sh
 python3 main.py
 ```
 
@@ -268,7 +267,7 @@ provider_server_address = 127.0.0.1:5000 # can be set to anything, not used
 Run the assistant:
 
 ```sh
-./start_services.sh
+sudo ./start_services.sh
 python3 main.py
 ```
 
@@ -278,22 +277,25 @@ 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:
+The speech-to-text functionality is disabled by default. To enable it, set the listen option to True in the config.ini file:
 
 ```
 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:
+When enabled, the speech-to-text feature listens for a trigger keyword, which is the agent's name, before it begins processing your input. You can customize the agent's name by updating the `agent_name` value in the *config.ini* file:
 
 ```
 agent_name = Friday
 ```
 
-It will work better if you use a common english name like John or Emma.
+For optimal recognition, we recommend using a common English name like "John" or "Emma" as the agent name
 
-After hearing it's name agenticSeek will listen until it hear one of the following keyword for confirmation:
+Once you see the transcript start to appear, say the agent's name aloud to wake it up (e.g., "Friday").
 
+Speak your query clearly.
+
+End your request with a confirmation phrase to signal the system to proceed. Examples of confirmation phrases include:
 ```
 "do it", "go ahead", "execute", "run", "start", "thanks", "would ya", "please", "okay?", "proceed", "continue", "go on", "do that", "go it", "do you understand?"
 ```
@@ -321,7 +323,7 @@ provider_server_address = 127.0.0.1:5000
 ```
 `is_local`: should be True for any locally running LLM, otherwise False.
 
-`provider_name`: Select the provider to use by its name, see the provider list above.
+`provider_name`: Select the provider to use by it's name, see the provider list above.
 
 `provider_model`: Set the model to use by the agent.
 
@@ -351,6 +353,7 @@ And download the chromedriver version matching your OS.
 ![alt text](./media/chromedriver_readme.png)
 
 ## FAQ
+
 **Q: What hardware do I need?**  
 
 7B Model: GPU with 8GB VRAM.
@@ -365,10 +368,6 @@ Deepseek R1 excels at reasoning and tool use for its size. We think it’s a sol
 
 Ensure Ollama is running (`ollama serve`), your `config.ini` matches your provider, and dependencies are installed. If none work feel free to raise an issue.
 
-**Q: How to join the discord ?**
-
-Ask in the Community section for an invite.
-
 **Q: Can it really run 100% locally?**  
 
 Yes with Ollama or Server providers, all speech to text, LLM and text to speech model run locally. Non-local options (OpenAI or others API) are optional.

requirements.txt

@@ -1,33 +1,35 @@
-requests==2.31.0
-openai==1.61.1
-colorama==0.4.6
-python-dotenv==1.0.0
-playsound==1.3.0
-soundfile==0.13.1
-transformers==4.48.3
-torch==2.5.1
-ollama==0.4.7
-scipy==1.15.1
-kokoro==0.7.12
-flask==3.1.0
-soundfile==0.13.1
-protobuf==3.20.3
-termcolor==2.5.0
-ipython==8.34.0
-gliclass==0.1.8
-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
+requests>=2.31.0
+colorama>=0.4.6
+python-dotenv>=1.0.0
+playsound>=1.3.0
+soundfile>=0.13.1
+transformers>=4.46.3
+torch>=2.4.1
+python-dotenv>=1.0.0
+ollama>=0.4.7
+scipy>=1.15.1
+kokoro>=0.7.12
+flask>=3.1.0
+soundfile>=0.13.1
+protobuf>=3.20.3
+termcolor>=2.5.0
+ipython>=8.34.0
+gliclass>=0.1.8
+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
 distro>=1.7.0,<2
 jiter>=0.4.0,<1
 sniffio
 tqdm>4
+# for api provider
+openai
 # if use chinese
 ordered_set
 pypinyin

scripts/linux_install.sh

@@ -5,6 +5,8 @@ echo "Starting installation for Linux..."
 # Update package list
 sudo apt-get update
 
+pip install --upgrade pip
+
 # Install Python dependencies from requirements.txt
 pip3 install -r requirements.txt
 

searxng/docker-compose.yml

@@ -1,3 +1,4 @@
+version: '3'
 services:
   redis:
     container_name: redis

setup.py

@@ -8,34 +8,35 @@ setup(
     version="0.1.0",
     author="Fosowl",
     author_email="mlg.fcu@gmail.com",
-    description="A Python project for agentic search and processing",
+    description="The open, local alternative to ManusAI",
     long_description=long_description,
     long_description_content_type="text/markdown",
     url="https://github.com/Fosowl/agenticSeek",
     packages=find_packages(),
     include_package_data=True,
     install_requires=[
-        "requests==2.31.0",
-        "openai==1.61.1",
-        "colorama==0.4.6",
-        "python-dotenv==1.0.0",
-        "playsound==1.3.0",
-        "soundfile==0.13.1",
-        "transformers==4.48.3",
-        "torch==2.5.1",
-        "ollama==0.4.7",
-        "scipy==1.15.1",
-        "kokoro==0.7.12",
-        "flask==3.1.0",
-        "protobuf==3.20.3",
-        "termcolor==2.5.0",
-        "gliclass==0.1.8",
-        "ipython==8.34.0",
-        "librosa==0.10.2.post1",
-        "selenium==4.29.0",
-        "markdownify==1.1.0",
-        "text2emotion==0.0.5",
-        "langid==1.1.6",
+        "requests>=2.31.0",
+        "openai",
+        "colorama>=0.4.6",
+        "python-dotenv>=1.0.0",
+        "playsound>=1.3.0",
+        "soundfile>=0.13.1",
+        "transformers>=4.46.3",
+        "torch>=2.4.1",
+        "ollama>=0.4.7",
+        "scipy>=1.15.1",
+        "kokoro>=0.7.12",
+        "flask>=3.1.0",
+        "protobuf>=3.20.3",
+        "termcolor>=2.5.0",
+        "gliclass>=0.1.8",
+        "ipython>=8.34.0",
+        "librosa>=0.10.2.post1",
+        "selenium>=4.29.0",
+        "markdownify>=1.1.0",
+        "text2emotion>=0.0.5",
+        "python-dotenv>=1.0.0",
+        "langid>=1.1.6",
         "httpx>=0.27,<0.29",
         "anyio>=3.5.0,<5",
         "distro>=1.7.0,<2",
@@ -61,5 +62,5 @@ setup(
         "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
         "Operating System :: OS Independent",
     ],
-    python_requires=">=3.6",
+    python_requires=">=3.9",
 )

sources/llm_provider.py

@@ -33,7 +33,7 @@ class Provider:
         if self.provider_name in self.unsafe_providers:
             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 != "":
+        elif self.server != "ollama":
             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]):
@@ -54,6 +54,7 @@ class Provider:
         Validate if the address is valid IP.
         """
         try:
+            address = address.replace('http://', '')
             ip, port = address.rsplit(":", 1)
             if all(c.lower() in ".:abcdef0123456789" for c in ip):
                 ipaddress.ip_address(ip)
@@ -143,6 +144,7 @@ class Provider:
             if e.status_code == 404:
                 animate_thinking(f"Downloading {self.model}...")
                 ollama.pull(self.model)
+                self.ollama_fn(history, verbose)
             if "refused" in str(e).lower():
                 raise Exception("Ollama connection failed. is the server running ?") from e
             raise e

sources/speech_to_text.py

@@ -6,6 +6,7 @@ import torch
 from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
 import time
 import librosa
+import pyaudio
 
 audio_queue = queue.Queue()
 done = False
@@ -14,7 +15,7 @@ class AudioRecorder:
     """
     AudioRecorder is a class that records audio from the microphone and adds it to the audio queue.
     """
-    def __init__(self, format: int, channels: int = 1, rate: int = 4096, chunk: int = 8192, record_seconds: int = 5, verbose: bool = False):
+    def __init__(self, format: int = pyaudio.paInt16, channels: int = 1, rate: int = 4096, chunk: int = 8192, record_seconds: int = 5, verbose: bool = False):
         import pyaudio
         self.format = format
         self.channels = channels