merge docker_deployement to dev

.dockerignore

@@ -3,10 +3,9 @@ __pycache__/
 *.py[cod]
 
 # Virtual environments
-venv/
+agentic_seek_env/
-.venv/
+.agentic_seek_env/
 
-# Environment variables (secrets)
 .env
 
 # Git metadata

.env.example

@@ -1,4 +1,12 @@
 SEARXNG_BASE_URL="http://127.0.0.1:8080"
+REDIS_BASE_URL="redis://redis:6379/0"
+WORK_DIR="/Users/username/Documents/workspace_with_my_files"
+OLLAMA_PORT="11434"
+LM_STUDIO_PORT="1234"
+CUSTOM_ADDITIONAL_LLM_PORT="11435"
 OPENAI_API_KEY='xxxxx'
 DEEPSEEK_API_KEY='xxxxx'
 OPENROUTER_API_KEY='xxxxx'
+TOGETHER_API_KEY='xxxxx'
+GOOGLE_API_KEY='xxxxx'
+ANTHROPIC_API_KEY='xxxxx'

.gitignore

@@ -21,6 +21,7 @@ agentic_seek_env/*
 .env
 */.env
 dsk/
+chrome136/
 
 ### react ###
 .DS_*

Dockerfile.backend

@@ -1,46 +1,102 @@
-FROM ubuntu:22.04
+
-# Warning: doesn't work yet, backend is run on host machine for now
+FROM --platform=linux/amd64 python:3.11-slim
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Install essential packages and Chrome dependencies
+RUN apt-get update -y && apt-get install -y \
+    wget \
+    gnupg2 \
+    ca-certificates \
+    unzip \
+    xvfb \
+    libxss1 \
+    libappindicator1 \
+    fonts-liberation \
+    libnss3 \
+    libatk1.0-0 \
+    libatk-bridge2.0-0 \
+    libcups2 \
+    libdrm2 \
+    libxcomposite1 \
+    libxdamage1 \
+    libxrandr2 \
+    xdg-utils \
+    dbus \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN apt-get update -y && \
+      apt-get install -y \
+      gcc \
+      g++ \
+      gfortran \
+      libportaudio2 \
+      portaudio19-dev \
+      ffmpeg \
+      libavcodec-dev \
+      libavformat-dev \
+      libavutil-dev \
+      gnupg2 \
+      wget \
+      unzip \
+      python3 \
+      python3-pip \
+      libasound2 \
+      libatk-bridge2.0-0 \
+      libgtk-4-1 \
+      libnss3 \
+      xdg-utils \
+      wget \
+    && rm -rf /var/lib/apt/lists/*
+
+
+RUN apt-get update -y && \
+apt-get install -y \
+  alsa-utils \
+&& rm -rf /var/lib/apt/lists/*
+
+ENV CHROME_TESTING_VERSION=134.0.6998.88
+ENV DISPLAY=:99
 
 WORKDIR /app
 
-RUN apt-get update -qq -y && \
+RUN set -eux; \
-apt-get install -y \
+    wget -qO /tmp/chrome.zip \
-        gcc \
+      "https://storage.googleapis.com/chrome-for-testing-public/${CHROME_TESTING_VERSION}/linux64/chrome-linux64.zip"; \
-        g++ \
+    unzip -q /tmp/chrome.zip -d /opt; \
-        gfortran \
+    rm /tmp/chrome.zip; \
-        libportaudio2 \
+    ln -s /opt/chrome-linux64/chrome /usr/local/bin/google-chrome; \
-        portaudio19-dev \
+    ln -s /opt/chrome-linux64/chrome /usr/local/bin/chrome; \
-        ffmpeg \
+    mkdir -p /opt/chrome; \
-        libavcodec-dev \
+    ln -s /opt/chrome-linux64/chrome /opt/chrome/chrome; \
-        libavformat-dev \
+    google-chrome --version
-        libavutil-dev \
+
-        gnupg2 \
+RUN set -eux; \
-        wget \
+    wget -qO /tmp/chromedriver.zip \
-        unzip \
+      "https://storage.googleapis.com/chrome-for-testing-public/${CHROME_TESTING_VERSION}/linux64/chromedriver-linux64.zip"; \
-        python3 \
+    unzip -q /tmp/chromedriver.zip -d /tmp; \
-        python3-pip \
+    mv /tmp/chromedriver-linux64/chromedriver /usr/local/bin; \
-        libasound2 \
+    rm /tmp/chromedriver.zip; \
-        libatk-bridge2.0-0 \
+    chmod +x /usr/local/bin/chromedriver; \
-        libgtk-4-1 \
+    chromedriver --version
-        libnss3 \
-        xdg-utils \
-        wget && \
 
 RUN chmod +x /opt/chrome/chrome
-# Install dependencies
+
+RUN pip3 install --upgrade pip setuptools wheel
+
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
+RUN mkdir -p /opt/workspace
+RUN mkdir -p /tmp && chmod 1777 /tmp
+
 # Copy application code
 COPY api.py .
 COPY sources/ ./sources/
 COPY prompts/ ./prompts/
 COPY crx/ crx/
 COPY llm_router/ llm_router/
-COPY .env .
 COPY config.ini .
 
-# Expose port
 EXPOSE 8000
 
 # Run the application

README.md

@@ -40,7 +40,7 @@ Disclaimer: This demo, including all the files that appear (e.g: CV_candidates.z
 
 Make sure you have chrome driver, docker and python3.10 installed.
 
-We highly advice you use exactly python3.10 for the setup. Dependencies error might happen otherwise.
+We highly advise you use exactly python3.10 for the setup. Dependencies error might happen otherwise.
 
 For issues related to chrome driver, see the **Chromedriver** section.
 
@@ -64,9 +64,9 @@ source agentic_seek_env/bin/activate
 
 Ensure Python, Docker and docker compose, and Google chrome are installed.
 
-We recommand Python 3.10.0.
+We recommend Python 3.10.0.
 
-**Automatic Installation (Recommanded):**
+**Automatic Installation (recommended):**
 
 For Linux/Macos:
 ```sh
@@ -140,7 +140,7 @@ See below for a list of local supported provider.
 
 **Update the config.ini**
 
-Change the config.ini file to set the provider_name to a supported provider and provider_model to a LLM supported by your provider. We recommand reasoning model such as *Qwen* or *Deepseek*.
+Change the config.ini file to set the provider_name to a supported provider and provider_model to a LLM supported by your provider. We recommend reasoning model such as *Qwen* or *Deepseek*.
 
 See the **FAQ** at the end of the README for required hardware.
 
@@ -159,7 +159,7 @@ work_dir =  /Users/mlg/Documents/workspace # The workspace for AgenticSeek.
 jarvis_personality = False # Whenever to use a more "Jarvis" like personality (experimental)
 languages = en zh # The list of languages, Text to speech will default to the first language on the list
 [BROWSER]
-headless_browser = True # Whenever to use headless browser, recommanded only if you use web interface.
+headless_browser = True # Whenever to use headless browser, recommended only if you use web interface.
 stealth_mode = True # Use undetected selenium to reduce browser detection
 ```
 
@@ -212,9 +212,9 @@ 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.
+*We advise 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.
+Please also note that coding/bash might fail with gemini, it seems 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)
 
@@ -247,7 +247,7 @@ start ./start_services.cmd # Window
 python3 cli.py
 ```
 
-We advice you set `headless_browser` to False in the config.ini for CLI mode.
+We advise you set `headless_browser` to False in the config.ini for CLI mode.
 
 **Options 2:** Run with the Web interface.
 
@@ -541,7 +541,7 @@ Yes with Ollama, lm-studio or server providers, all speech to text, LLM and text
 **Q: Why should I use AgenticSeek when I have Manus?**
 
 This started as Side-Project we did out of interest about AI agents. What’s special about it is that we want to use local model and avoid APIs.
-We draw inspiration from Jarvis and Friday (Iron man movies) to make it "cool" but for functionnality we take more inspiration from Manus, because that's what people want in the first place: a local manus alternative.
+We draw inspiration from Jarvis and Friday (Iron man movies) to make it "cool" but for functionality we take more inspiration from Manus, because that's what people want in the first place: a local manus alternative.
 Unlike Manus, AgenticSeek prioritizes independence from external systems, giving you more control, privacy and avoid api cost.
 
 ## Contribute
@@ -559,3 +559,7 @@ We’re looking for developers to improve AgenticSeek! Check out open issues or
  > [antoineVIVIES](https://github.com/antoineVIVIES) | Taipei Time 
 
  > [steveh8758](https://github.com/steveh8758) | Taipei Time 
+
+## Special Thanks:
+
+ > [tcsenpai](https://github.com/tcsenpai) For dockerization of backend

api.py

@@ -22,6 +22,10 @@ from sources.utility import pretty_print
 from sources.logger import Logger
 from sources.schemas import QueryRequest, QueryResponse
 
+from dotenv import load_dotenv
+
+load_dotenv()
+
 
 from celery import Celery
 
@@ -34,7 +38,7 @@ config.read('config.ini')
 
 api.add_middleware(
     CORSMiddleware,
-    allow_origins=["http://localhost", "http://localhost:3000"],
+    allow_origins=["*"],
     allow_credentials=True,
     allow_methods=["*"],
     allow_headers=["*"],
@@ -247,4 +251,9 @@ async def process_query(request: QueryRequest):
             interaction.save_session()
 
 if __name__ == "__main__":
+    envport = os.getenv("BACKEND_PORT")
+    if envport:
+        port = int(envport)
+    else:
+        port = 8000
     uvicorn.run(api, host="0.0.0.0", port=8000)

config.ini

@@ -1,14 +1,13 @@
 [MAIN]
 is_local = True
 provider_name = ollama
-provider_model = deepseek-r1:14b
+provider_model = deepseek-r1:1.5b
 provider_server_address = 127.0.0.1:11434
-agent_name = Name_of_your_AI
+agent_name = Jarvis
 recover_last_session = False
 save_session = False
 speak = False
 listen = False
-work_dir =  /Users/mlg/Documents/workspace_for_agenticseek
 jarvis_personality = False
 languages = en
 [BROWSER]

docker-compose.yml

@@ -3,6 +3,7 @@ version: '3'
 services:
   redis:
     container_name: redis
+    profiles: ["core", "full"]
     image: docker.io/valkey/valkey:8-alpine
     command: valkey-server --save 30 1 --loglevel warning
     restart: unless-stopped
@@ -24,6 +25,7 @@ services:
 
   searxng:
     container_name: searxng
+    profiles: ["core", "full"]
     image: docker.io/searxng/searxng:latest
     restart: unless-stopped
     ports:
@@ -31,8 +33,8 @@ services:
     volumes:
       - ./searxng:/etc/searxng:rw,z
     environment:
-      - SEARXNG_BASE_URL=http://localhost:8080/
+      - SEARXNG_BASE_URL=${SEARXNG_BASE_URL:-http://localhost:8080/}
-      - SEARXNG_SECRET_KEY=$(openssl rand -hex 32)
+      - SEARXNG_SECRET_KEY=${SEARXNG_SECRET_KEY}
       - UWSGI_WORKERS=4
       - UWSGI_THREADS=4
     cap_add:
@@ -51,6 +53,7 @@ services:
 
   frontend:
     container_name: frontend
+    profiles: ["core", "full"]
     build:
       context: ./frontend
       dockerfile: Dockerfile.frontend
@@ -62,39 +65,38 @@ services:
     environment:
       - NODE_ENV=development
       - CHOKIDAR_USEPOLLING=true
-      - BACKEND_URL=http://backend:8000
+      - REACT_APP_BACKEND_URL=http://0.0.0.0:${BACKEND_PORT:-8000}
     networks:
       - agentic-seek-net
 
-  # NOTE: backend service is not working yet due to issue with chromedriver on docker.
+  backend:
-  # Therefore backend is run on host machine.
+    container_name: backend
-  # Open to pull requests to fix this.
+    profiles: ["backend", "full"]
-
+    build:
-  #backend:
+      context: .
-  #  container_name: backend
+      dockerfile: Dockerfile.backend
-  #  build:
+    ports:
-  #    context: ./
+      - ${BACKEND_PORT:-7777}:${BACKEND_PORT:-7777}
-  #    dockerfile: Dockerfile.backend
+      - ${OLLAMA_PORT:-11434}:${OLLAMA_PORT:-11434}
-  #  stdin_open: true
+      - ${LM_STUDIO_PORT:-1234}:${LM_STUDIO_PORT:-1234}
-  #  tty: true
+      - ${CUSTOM_ADDITIONAL_LLM_PORT:-8000}:${CUSTOM_ADDITIONAL_LLM_PORT:-8000}
-  #  shm_size: 8g
+    volumes:
-  #  ports:
+      - ./:/app
-  #    - "8000:8000"
+      - ${WORK_DIR:-.}:/opt/workspace
-  #  volumes:
+    command: python3 api.py
-  #    - ./:/app
+    environment:
-  #  environment:
+      - SEARXNG_URL=${SEARXNG_BASE_URL:-http://searxng:8080}
-  #    - NODE_ENV=development
+      - REDIS_URL=${REDIS_BASE_URL:-redis://redis:6379/0}
-  #    - REDIS_URL=redis://redis:6379/0
+      - WORK_DIR=/opt/workspace
-  #    - SEARXNG_URL=http://searxng:8080
+      - OPENAI_API_KEY=${OPENAI_API_KEY}
-  #    - OLLAMA_URL=http://localhost:11434
+      - DEEPSEEK_API_KEY=${DEEPSEEK_API_KEY}
-  #    - LM_STUDIO_URL=http://localhost:1234
+      - OPENROUTER_API_KEY=${OPENROUTER_API_KEY}
-  #  extra_hosts:
+      - TOGETHER_API_KEY=${TOGETHER_API_KEY}
-  #    - "host.docker.internal:host-gateway"
+      - GOOGLE_API_KEY=${GOOGLE_API_KEY}
-  #  depends_on:
+      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
-  #    - redis
+      - HUGGINGFACE_API_KEY=${HUGGINGFACE_API_KEY}
-  #    - searxng
+      - DSK_DEEPSEEK_API_KEY=${DSK_DEEPSEEK_API_KEY}
-  #  networks:
+    network_mode: "host"
-  #    - agentic-seek-net
   
 volumes:
   redis-data:

frontend/agentic-seek-front/src/App.js

@@ -4,6 +4,8 @@ import axios from 'axios';
 import './App.css';
 import { colors } from './colors';
 
+const BACKEND_URL = process.env.BACKEND_PORT || 'http://0.0.0.0:8000';
+
 function App() {
     const [query, setQuery] = useState('');
     const [messages, setMessages] = useState([]);
@@ -27,7 +29,7 @@ function App() {
 
     const checkHealth = async () => {
         try {
-            await axios.get('http://127.0.0.1:8000/health');
+            await axios.get(`${BACKEND_URL}/health`);
             setIsOnline(true);
             console.log('System is online');
         } catch {
@@ -39,7 +41,7 @@ function App() {
     const fetchScreenshot = async () => {
         try {
             const timestamp = new Date().getTime();
-            const res = await axios.get(`http://127.0.0.1:8000/screenshots/updated_screen.png?timestamp=${timestamp}`, {
+            const res = await axios.get(`${BACKEND_URL}/screenshots/updated_screen.png?timestamp=${timestamp}`, {
                 responseType: 'blob'
             });
             console.log('Screenshot fetched successfully');
@@ -90,7 +92,7 @@ function App() {
 
     const fetchLatestAnswer = async () => {
         try {
-            const res = await axios.get('http://127.0.0.1:8000/latest_answer');
+            const res = await axios.get(`${BACKEND_URL}/latest_answer`);
             const data = res.data;
 
             updateData(data);
@@ -141,7 +143,7 @@ function App() {
         setIsLoading(false);
         setError(null);
         try {
-            const res = await axios.get('http://127.0.0.1:8000/stop');
+            const res = await axios.get(`${BACKEND_URL}/stop`);
             setStatus("Requesting stop...");
         } catch (err) {
             console.error('Error stopping the agent:', err);
@@ -162,7 +164,7 @@ function App() {
         try {
             console.log('Sending query:', query);
             setQuery('waiting for response...');
-            const res = await axios.post('http://127.0.0.1:8000/query', {
+            const res = await axios.post(`${BACKEND_URL}/query`, {
                 query,
                 tts_enabled: false
             });

requirements.txt

@@ -17,7 +17,6 @@ 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>=1.9.3
 soundfile>=0.13.1
@@ -41,6 +40,7 @@ fake_useragent>=2.1.0
 selenium_stealth>=1.0.6
 undetected-chromedriver>=3.5.5
 sentencepiece>=0.2.0
+together>=1.5.0
 tqdm>4
 openai
 sniffio

sources/agents/browser_agent.py

@@ -41,7 +41,7 @@ class BrowserAgent(Agent):
         self.memory = Memory(self.load_prompt(prompt_path),
                         recover_last_session=False, # session recovery in handled by the interaction class
                         memory_compression=False,
-                        model_provider=provider.get_model_name())
+                        model_provider=provider.get_model_name() if provider else None)
     
     def get_today_date(self) -> str:
         """Get the date"""
@@ -77,14 +77,14 @@ class BrowserAgent(Agent):
     def get_unvisited_links(self) -> List[str]:
         return "\n".join([f"[{i}] {link}" for i, link in enumerate(self.navigable_links) if link not in self.search_history])
 
-    def make_newsearch_prompt(self, user_prompt: str, search_result: dict) -> str:
+    def make_newsearch_prompt(self, prompt: str, search_result: dict) -> str:
         search_choice = self.stringify_search_results(search_result)
         self.logger.info(f"Search results: {search_choice}")
         return f"""
         Based on the search result:
         {search_choice}
         Your goal is to find accurate and complete information to satisfy the user’s request.
-        User request: {user_prompt}
+        User request: {prompt}
         To proceed, choose a relevant link from the search results. Announce your choice by saying: "I will navigate to <link>"
         Do not explain your choice.
         """
@@ -235,13 +235,17 @@ class BrowserAgent(Agent):
         return links
     
     def select_link(self, links: List[str]) -> str | None:
+        """
+        Select the first unvisited link that is not the current page.
+        Preference is given to links not in search_history.
+        """
         for lk in links:
-            if lk == self.current_page:
+            if lk == self.current_page or lk in self.search_history:
-                self.logger.info(f"Already visited {lk}. Skipping.")
+                self.logger.info(f"Skipping already visited or current link: {lk}")
                 continue
             self.logger.info(f"Selected link: {lk}")
             return lk
-        self.logger.warning("No link selected.")
+        self.logger.warning("No suitable link selected.")
         return None
     
     def get_page_text(self, limit_to_model_ctx = False) -> str:
@@ -396,7 +400,10 @@ class BrowserAgent(Agent):
             if (link == None and len(extracted_form) < 3) or Action.GO_BACK.value in answer or link in self.search_history:
                 pretty_print(f"Going back to results. Still {len(unvisited)}", color="status")
                 self.status_message = "Going back to search results..."
-                prompt = self.make_newsearch_prompt(user_prompt, unvisited)
+                request_prompt = user_prompt
+                if link is None:
+                    request_prompt += f"\nYou previously choosen:\n{self.last_answer} but the website is unavailable. Consider other options."
+                prompt = self.make_newsearch_prompt(request_prompt, unvisited)
                 self.search_history.append(link)
                 self.current_page = link
                 continue

sources/browser.py

@@ -19,6 +19,7 @@ import time
 import random
 import os
 import shutil
+import uuid
 import tempfile
 import markdownify
 import sys
@@ -42,7 +43,14 @@ def get_chrome_path() -> str:
         paths = ["/Applications/Google Chrome.app/Contents/MacOS/Google Chrome",
                  "/Applications/Google Chrome Beta.app/Contents/MacOS/Google Chrome Beta"]
     else:  # Linux
-        paths = ["/usr/bin/google-chrome", "/usr/bin/chromium-browser", "/usr/bin/chromium", "/opt/chrome/chrome", "/usr/local/bin/chrome"]
+        paths = ["/usr/bin/google-chrome",
+                 "/opt/chrome/chrome",
+                 "/usr/bin/chromium-browser",
+                 "/usr/bin/chromium",
+                 "/usr/local/bin/chrome",
+                 "/opt/google/chrome/chrome-headless-shell",
+                 #"/app/chrome_bundle/chrome136/chrome-linux64"
+                ]
 
     for path in paths:
         if os.path.exists(path) and os.access(path, os.X_OK):
@@ -75,6 +83,7 @@ def install_chromedriver() -> str:
     chromedriver_path = shutil.which("chromedriver")
     if not chromedriver_path:
         try:
+            print("ChromeDriver not found, attempting to install automatically...")
             chromedriver_path = chromedriver_autoinstaller.install()
         except Exception as e:
             raise FileNotFoundError(
@@ -120,17 +129,28 @@ def create_driver(headless=False, stealth_mode=True, crx_path="./crx/nopecha.crx
     chrome_options.binary_location = chrome_path
     
     if headless:
-        chrome_options.add_argument("--headless")
+        #chrome_options.add_argument("--headless")
+        chrome_options.add_argument("--headless=new")
         chrome_options.add_argument("--disable-gpu")
         chrome_options.add_argument("--disable-webgl")
     user_data_dir = tempfile.mkdtemp()
     user_agent = get_random_user_agent()
     width, height = (1920, 1080)
-    chrome_options.add_argument(f"--user-data-dir={user_data_dir}")
+    user_data_dir = tempfile.mkdtemp(prefix="chrome_profile_")
-    chrome_options.add_argument(f"--accept-lang={lang}-{lang.upper()},{lang};q=0.9")
-    chrome_options.add_argument("--timezone=Europe/Paris")
     chrome_options.add_argument("--no-sandbox")
-    chrome_options.add_argument("--disable-dev-shm-usage")
+    chrome_options.add_argument('--disable-dev-shm-usage')
+    profile_dir = f"/tmp/chrome_profile_{uuid.uuid4().hex[:8]}"
+    chrome_options.add_argument(f'--user-data-dir={profile_dir}')
+    chrome_options.add_argument(f"--accept-lang={lang}-{lang.upper()},{lang};q=0.9")
+    chrome_options.add_argument("--disable-extensions")
+    chrome_options.add_argument("--disable-background-timer-throttling")
+    chrome_options.add_argument("--timezone=Europe/Paris")
+    chrome_options.add_argument('--remote-debugging-port=9222')
+    chrome_options.add_argument('--disable-background-timer-throttling')
+    chrome_options.add_argument('--disable-backgrounding-occluded-windows')
+    chrome_options.add_argument('--disable-renderer-backgrounding')
+    chrome_options.add_argument('--disable-features=TranslateUI')
+    chrome_options.add_argument('--disable-ipc-flooding-protection')
     chrome_options.add_argument("--mute-audio")
     chrome_options.add_argument("--disable-notifications")
     chrome_options.add_argument("--autoplay-policy=user-gesture-required")
@@ -698,8 +718,6 @@ if __name__ == "__main__":
     
     input("press enter to continue")
     print("AntiCaptcha / Form Test")
-    browser.go_to("https://www.google.com/recaptcha/api2/demo")
-    time.sleep(50)
     browser.go_to("https://bot.sannysoft.com")
     time.sleep(5)
     #txt = browser.get_text()

sources/language.py

@@ -1,8 +1,6 @@
 from typing import List, Tuple, Type, Dict
 import re
 import langid
-import nltk
-from nltk.sentiment.vader import SentimentIntensityAnalyzer
 from transformers import MarianMTModel, MarianTokenizer
 
 from sources.utility import pretty_print, animate_thinking
@@ -16,7 +14,6 @@ class LanguageUtility:
         args:
             supported_language: list of languages for translation, determine which Helsinki-NLP model to load
         """
-        self.sid = None 
         self.translators_tokenizer = None 
         self.translators_model = None
         self.logger = Logger("language.log")
@@ -25,11 +22,6 @@ class LanguageUtility:
     
     def load_model(self) -> None:
         animate_thinking("Loading language utility...", color="status")
-        try:
-            nltk.data.find('vader_lexicon')
-        except LookupError:
-            nltk.download('vader_lexicon')
-        self.sid = SentimentIntensityAnalyzer()
         self.translators_tokenizer = {lang: MarianTokenizer.from_pretrained(f"Helsinki-NLP/opus-mt-{lang}-en") for lang in self.supported_language if lang != "en"}
         self.translators_model = {lang: MarianMTModel.from_pretrained(f"Helsinki-NLP/opus-mt-{lang}-en") for lang in self.supported_language if lang != "en"}
     
@@ -65,49 +57,17 @@ class LanguageUtility:
         translation = model.generate(**inputs)
         return tokenizer.decode(translation[0], skip_special_tokens=True)
 
-    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'
-            self.logger.info(f"Emotion: {dominant_emotion} for text: {text}")
-            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
+        Returns: dictionary with language related information
         """
         try:
             language = self.detect_language(text)
-            emotions = self.detect_emotion(text)
             return {
-                "language": language,
+                "language": language
-                "emotions": emotions
             }
         except Exception as e:
             raise e
@@ -125,4 +85,4 @@ if __name__ == "__main__":
         pretty_print(f"Language: {detector.detect_language(text)}", color="status")
         result = detector.analyze(text)
         trans = detector.translate(text, result['language'])
-        pretty_print(f"Translation: {trans} - from: {result['language']} - Emotion: {result['emotions']}")
+        pretty_print(f"Translation: {trans} - from: {result['language']}")

sources/tools/tools.py

@@ -50,19 +50,15 @@ class Tools():
     def set_allow_language_exec_bash(value: bool) -> None:
         self.allow_language_exec_bash = value 
 
-    def check_config_dir_validity(self):
+    def safe_get_work_dir_path(self):
-        """Check if the config directory is valid."""
+        path = None
-        path = self.config['MAIN']['work_dir']
+        path = os.getenv('WORK_DIR', path)
-        if path == "":
+        if path is None or path == "":
-            print("WARNING: Work directory not set in config.ini")
+            path = self.config['MAIN']['work_dir'] if 'MAIN' in self.config and 'work_dir' in self.config['MAIN'] else None
-            return False
+        if path is None or path == "":
-        if path.lower() == "none":
+            print("No work directory specified, using default.")
-            print("WARNING: Work directory set to none in config.ini")
+            path = self.create_work_dir()
-            return False
+        return path
-        if not os.path.exists(path):
-            print(f"WARNING: Work directory {path} does not exist")
-            return False
-        return True
     
     def config_exists(self):
         """Check if the config file exists."""
@@ -73,11 +69,10 @@ class Tools():
         default_path = os.path.dirname(os.getcwd())
         if self.config_exists():
             self.config.read('./config.ini')
-            config_path = self.config['MAIN']['work_dir']
+            workdir_path = self.safe_get_work_dir_path()
-            dir_path = default_path if not self.check_config_dir_validity() else config_path
         else:
-            dir_path = default_path
+            workdir_path = default_path
-        return dir_path
+        return workdir_path
 
     @abstractmethod
     def execute(self, blocks:[str], safety:bool) -> str:

start_services.cmd

@@ -1,10 +1,22 @@
 @echo off
 
-docker-compose up
+if "%1"=="full" (
-if %ERRORLEVEL% neq 0 (
+    echo Starting full deployment...
-    echo Error: Failed to start containers. Check Docker logs with 'docker compose logs'.
+) else (
-    echo Possible fixes: Ensure Docker Desktop is running or check if port 8080 is free.
+    echo Starting partial deployment... (backend run on host), use "full" to run all services in containers
-    exit /b 1
 )
 
-timeout /t 10 /nobreak >nul
+REM Stop all containers
+echo Stopping containers...
+docker stop $(docker ps -aq) >nul 2>&1
+
+REM Generate secret key
+for /f %%i in ('powershell -command "[System.Web.Security.Membership]::GeneratePassword(64,0)"') do set SEARXNG_SECRET_KEY=%%i
+
+if "%1"=="full" (
+    docker compose up -d backend
+    timeout /t 5 /nobreak >nul
+    docker compose --profile full up
+) else (
+    docker compose --profile core up
+)

start_services.sh

@@ -1,12 +1,35 @@
 #!/bin/bash
 
+source .env
+
 command_exists() {
     command -v "$1" &> /dev/null
 }
+if [ -z "$WORK_DIR" ]; then
+    echo "Error: WORK_DIR environment variable is not set. Please set it in your .env file."
+    exit 1
+fi
 
-#
+if [[ "$OSTYPE" == "darwin"* ]]; then
-# Check if Docker is installed é running
+    dir_size_bytes=$(du -s -b "$WORK_DIR" 2>/dev/null | awk '{print $1}')
-#
+else
+    dir_size_bytes=$(du -s --bytes "$WORK_DIR" 2>/dev/null | awk '{print $1}')
+fi
+
+max_size_bytes=$((2 * 1024 * 1024 * 1024))
+
+echo "Mounting $WORK_DIR ($dir_size_bytes bytes) to docker."
+
+if [ "$dir_size_bytes" -gt "$max_size_bytes" ]; then
+    echo "Error: WORK_DIR ($WORK_DIR) contains more than 2GB of data ($(du -sh "$WORK_DIR" 2>/dev/null | awk '{print $1}'))."
+    exit 1
+fi
+
+if [ "$1" = "full" ]; then
+    echo "Starting full deployment with backend and all services..."
+else
+    echo "Starting core deployment with frontend and search services only... use ./start_services.sh full to start backend as well"
+fi
 
 if ! command_exists docker; then
     echo "Error: Docker is not installed. Please install Docker first."
@@ -60,15 +83,47 @@ if [ ! -f "docker-compose.yml" ]; then
     exit 1
 fi
 
-# start docker compose for searxng, redis, frontend services
+# Stop all running containers to ensure a clean state
 echo "Warning: stopping all docker containers (t-4 seconds)..."
 sleep 4
 docker stop $(docker ps -a -q)
 echo "All containers stopped"
 
-if ! $COMPOSE_CMD up; then
+# export searxng secret key
-    echo "Error: Failed to start containers. Check Docker logs with '$COMPOSE_CMD logs'."
+export SEARXNG_SECRET_KEY=$(openssl rand -hex 32)
-    echo "Possible fixes: Run with sudo or ensure port 8080 is free."
+
-    exit 1
+if [ "$1" = "full" ]; then
+    # First start backend and wait for it to be healthy
+    echo "Full docker deployement. Starting backend service..."
+    if ! $COMPOSE_CMD up -d backend; then
+        echo "Error: Failed to start backend container."
+        exit 1
+    fi
+    # Wait for backend to be healthy (check if it's running and not restarting)
+    echo "Waiting for backend to be ready..."
+    for i in {1..30}; do
+        if [ "$(docker inspect -f '{{.State.Running}}' backend)" = "true" ] && \
+           [ "$(docker inspect -f '{{.State.Restarting}}' backend)" = "false" ]; then
+            echo "backend is ready!"
+            break
+        fi
+        if [ $i -eq 30 ]; then
+            echo "Error: backend failed to start properly after 30 seconds"
+            $COMPOSE_CMD logs backend 
+            exit 1
+        fi
+        sleep 1
+    done
+    if ! $COMPOSE_CMD --profile full up; then
+        echo "Error: Failed to start containers. Check Docker logs with '$COMPOSE_CMD logs'."
+        echo "Possible fixes: Run with sudo or ensure port 8080 is free."
+        exit 1
+    fi
+else
+    if ! $COMPOSE_CMD --profile core up; then
+        echo "Error: Failed to start containers. Check Docker logs with '$COMPOSE_CMD logs'."
+        echo "Possible fixes: Run with sudo or ensure port 8080 is free."
+        exit 1
+    fi
 fi
 sleep 10

tests/test_browser_agent_parsing.py

@@ -23,7 +23,7 @@ class TestBrowserAgentParsing(unittest.TestCase):
             "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)