Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+output.mp3 filter=lfs diff=lfs merge=lfs -text

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,68 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <value>
+          <list size="55">
+            <item index="0" class="java.lang.String" itemvalue="notebook_shim" />
+            <item index="1" class="java.lang.String" itemvalue="jupyterlab_widgets" />
+            <item index="2" class="java.lang.String" itemvalue="greenlet" />
+            <item index="3" class="java.lang.String" itemvalue="arrow" />
+            <item index="4" class="java.lang.String" itemvalue="Babel" />
+            <item index="5" class="java.lang.String" itemvalue="nbclient" />
+            <item index="6" class="java.lang.String" itemvalue="QtPy" />
+            <item index="7" class="java.lang.String" itemvalue="executing" />
+            <item index="8" class="java.lang.String" itemvalue="tinycss2" />
+            <item index="9" class="java.lang.String" itemvalue="pyzmq" />
+            <item index="10" class="java.lang.String" itemvalue="bleach" />
+            <item index="11" class="java.lang.String" itemvalue="jupyter_server_terminals" />
+            <item index="12" class="java.lang.String" itemvalue="lxml" />
+            <item index="13" class="java.lang.String" itemvalue="prometheus_client" />
+            <item index="14" class="java.lang.String" itemvalue="notebook" />
+            <item index="15" class="java.lang.String" itemvalue="qtconsole" />
+            <item index="16" class="java.lang.String" itemvalue="terminado" />
+            <item index="17" class="java.lang.String" itemvalue="comm" />
+            <item index="18" class="java.lang.String" itemvalue="isoduration" />
+            <item index="19" class="java.lang.String" itemvalue="jupyter-lsp" />
+            <item index="20" class="java.lang.String" itemvalue="IMDbPY" />
+            <item index="21" class="java.lang.String" itemvalue="fqdn" />
+            <item index="22" class="java.lang.String" itemvalue="jupyter_client" />
+            <item index="23" class="java.lang.String" itemvalue="JustWatch" />
+            <item index="24" class="java.lang.String" itemvalue="ipykernel" />
+            <item index="25" class="java.lang.String" itemvalue="jupyterlab_server" />
+            <item index="26" class="java.lang.String" itemvalue="nbconvert" />
+            <item index="27" class="java.lang.String" itemvalue="psutil" />
+            <item index="28" class="java.lang.String" itemvalue="jupyterlab_pygments" />
+            <item index="29" class="java.lang.String" itemvalue="asttokens" />
+            <item index="30" class="java.lang.String" itemvalue="widgetsnbextension" />
+            <item index="31" class="java.lang.String" itemvalue="matplotlib-inline" />
+            <item index="32" class="java.lang.String" itemvalue="webcolors" />
+            <item index="33" class="java.lang.String" itemvalue="json5" />
+            <item index="34" class="java.lang.String" itemvalue="SQLAlchemy" />
+            <item index="35" class="java.lang.String" itemvalue="pandocfilters" />
+            <item index="36" class="java.lang.String" itemvalue="wcwidth" />
+            <item index="37" class="java.lang.String" itemvalue="types-python-dateutil" />
+            <item index="38" class="java.lang.String" itemvalue="uri-template" />
+            <item index="39" class="java.lang.String" itemvalue="jupyter" />
+            <item index="40" class="java.lang.String" itemvalue="stack-data" />
+            <item index="41" class="java.lang.String" itemvalue="jupyterlab" />
+            <item index="42" class="java.lang.String" itemvalue="ipywidgets" />
+            <item index="43" class="java.lang.String" itemvalue="prompt_toolkit" />
+            <item index="44" class="java.lang.String" itemvalue="parso" />
+            <item index="45" class="java.lang.String" itemvalue="nbformat" />
+            <item index="46" class="java.lang.String" itemvalue="ipython" />
+            <item index="47" class="java.lang.String" itemvalue="jsonpointer" />
+            <item index="48" class="java.lang.String" itemvalue="Send2Trash" />
+            <item index="49" class="java.lang.String" itemvalue="overrides" />
+            <item index="50" class="java.lang.String" itemvalue="mistune" />
+            <item index="51" class="java.lang.String" itemvalue="pytube" />
+            <item index="52" class="java.lang.String" itemvalue="jupyter-console" />
+            <item index="53" class="java.lang.String" itemvalue="debugpy" />
+            <item index="54" class="java.lang.String" itemvalue="argon2-cffi" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="searchbot-001" />
+  </component>
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/searchbot.iml" filepath="$PROJECT_DIR$/.idea/searchbot.iml" />
+    </modules>
+  </component>
+</project>

.idea/searchbot.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="searchbot-001" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/workspace.xml

@@ -0,0 +1,66 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="AutoImportSettings">
+    <option name="autoReloadType" value="SELECTIVE" />
+  </component>
+  <component name="ChangeListManager">
+    <list default="true" id="0c898110-30f4-4a5c-b755-e3a433ebce38" name="Changes" comment="" />
+    <option name="SHOW_DIALOG" value="false" />
+    <option name="HIGHLIGHT_CONFLICTS" value="true" />
+    <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
+    <option name="LAST_RESOLUTION" value="IGNORE" />
+  </component>
+  <component name="FileTemplateManagerImpl">
+    <option name="RECENT_TEMPLATES">
+      <list>
+        <option value="Python Script" />
+      </list>
+    </option>
+  </component>
+  <component name="ProjectColorInfo"><![CDATA[{
+  "associatedIndex": 3
+}]]></component>
+  <component name="ProjectId" id="2sk4uY24GzIoOyfaI4SvqFInupk" />
+  <component name="ProjectViewState">
+    <option name="hideEmptyMiddlePackages" value="true" />
+    <option name="showLibraryContents" value="true" />
+  </component>
+  <component name="PropertiesComponent"><![CDATA[{
+  "keyToString": {
+    "Python.helper.executor": "Run",
+    "RunOnceActivity.ShowReadmeOnStart": "true",
+    "node.js.detected.package.eslint": "true",
+    "node.js.detected.package.tslint": "true",
+    "node.js.selected.package.eslint": "(autodetect)",
+    "node.js.selected.package.tslint": "(autodetect)",
+    "nodejs_package_manager_path": "npm",
+    "vue.rearranger.settings.migration": "true"
+  }
+}]]></component>
+  <component name="SharedIndexes">
+    <attachedChunks>
+      <set>
+        <option value="bundled-js-predefined-d6986cc7102b-deb605915726-JavaScript-PY-243.22562.220" />
+        <option value="bundled-python-sdk-0fc6c617c4bd-9a18a617cbe4-com.jetbrains.pycharm.pro.sharedIndexes.bundled-PY-243.22562.220" />
+      </set>
+    </attachedChunks>
+  </component>
+  <component name="SpellCheckerSettings" RuntimeDictionaries="0" Folders="0" CustomDictionaries="0" DefaultDictionary="application-level" UseSingleDictionary="true" transferred="true" />
+  <component name="TaskManager">
+    <task active="true" id="Default" summary="Default task">
+      <changelist id="0c898110-30f4-4a5c-b755-e3a433ebce38" name="Changes" comment="" />
+      <created>1738986461767</created>
+      <option name="number" value="Default" />
+      <option name="presentableId" value="Default" />
+      <updated>1738986461767</updated>
+      <workItem from="1738986462803" duration="703000" />
+    </task>
+    <servers />
+  </component>
+  <component name="TypeScriptGeneratedFilesManager">
+    <option name="version" value="3" />
+  </component>
+  <component name="com.intellij.coverage.CoverageDataManagerImpl">
+    <SUITE FILE_PATH="coverage/searchbot$helper.coverage" NAME="helper Coverage Results" MODIFIED="1738987126236" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="false" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
+  </component>
+</project>

app.py

@@ -0,0 +1,216 @@
+import os
+import json
+import asyncio
+from datetime import datetime
+from typing import Dict, List, Any
+
+import streamlit as st
+
+from helper import ChatBot, current_year, save_to_audio, invoke_duckduckgo_news_search
+
+# ============================ FRONT-END SETUP ============================
+
+st.set_page_config(layout="wide")  # Set Streamlit layout to wide mode
+st.title("SearchBot 🤖")  # App title
+
+# ============================ SIDEBAR SETTINGS ============================
+
+with st.sidebar:
+    with st.expander("📖 Instruction Manual"):
+        st.markdown(
+            """
+            ## 🧠 SearchBot 🤖 - Your AI-Powered Research Assistant
+            Welcome to **SearchBot**, an advanced AI assistant that helps you find the latest news, trends, and information 
+            across various sources.
+
+            ### 🔹 How to Use:
+            1. **📌 Choose Search Source**  
+               - Select the type of search (News, Research Papers, Web Articles).
+            2. **📊 Choose Number of Results**  
+               - Decide how many results you want (1 to 10).
+            3. **🌍 Set Location**  
+               - Customize search results based on location.  
+               *(e.g., "us-en" for USA, "in-en" for India)*
+            4. **⏳ Filter by Time**  
+               - Search for the most recent news or past articles:  
+                 - **Past Day** 🕐 (Breaking News)  
+                 - **Past Week** 🗓 (Trending Topics)  
+                 - **Past Month** 📅 (Major Stories)  
+                 - **Past Year** ���� (Deep Research)  
+            5. **💬 Review Search Results & Chat History**  
+               - View results in an interactive table.  
+               - Chatbot provides summarized responses with references.
+
+            ---
+
+            ### 🔹 Live Examples You Can Try:
+            **📰 Find Latest News**
+            - *"What are the latest AI breakthroughs?"*
+            - *"Recent developments in space exploration."*
+
+            **📖 Research Papers & Analysis**
+            - *"Most cited papers on quantum computing."*
+            - *"Deep learning advancements in 2024."*
+
+            **🌍 Location-Based Information**
+            - *"Tech news in Silicon Valley."*
+            - *"Political updates in the UK."*
+
+            **⚡ AI-Powered Chatbot Insights**
+            - *"Summarize recent news on cryptocurrency."*
+            - *"Give me top AI news from last week with analysis."*
+
+            """
+        )
+
+    # User inputs for search customization
+    num: int = st.number_input("📊 Number of results", value=7, step=1, min_value=1, max_value=10)
+    location: str = st.text_input("🌍 Location (e.g., us-en, in-en)", value="us-en")
+    time_filter: str = st.selectbox(
+        "⏳ Time filter",
+        ["Past Day", "Past Week", "Past Month", "Past Year"],
+        index=1
+    )
+
+    # Convert time filter to DuckDuckGo-compatible format
+    time_mapping: Dict[str, str] = {"Past Day": "d", "Past Week": "w", "Past Month": "m", "Past Year": "y"}
+    time_filter = time_mapping[time_filter]
+
+    only_use_chatbot: bool = st.checkbox("💬 Only use chatbot (Disable Search)")
+
+    # Clear chat history button
+    if st.button("🧹 Clear Session"):
+        st.session_state.messages = []
+        st.rerun()
+
+    # Footer with dynamic year
+    st.markdown(f"<h6>📅 Copyright © 2010-{current_year()} Present</h6>", unsafe_allow_html=True)
+
+# ============================ CHAT HISTORY SETUP ============================
+
+# Initialize chat history
+if "messages" not in st.session_state:
+    st.session_state.messages: List[Dict[str, str]] = []
+
+# Ensure messages are always a list of dictionaries
+if not isinstance(st.session_state.messages, list) or not all(isinstance(msg, dict) for msg in st.session_state.messages):
+    st.session_state.messages = []
+
+# Display past chat history in Streamlit chat UI
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+# ============================ CHAT INPUT & PROCESSING ============================
+
+# Process user input in the chatbox
+if prompt := st.chat_input("Ask anything!"):
+    st.chat_message("user").markdown(prompt)
+    st.session_state.messages.append({"role": "user", "content": prompt})
+
+    # **Initialize ref_table_string to hold search results**
+    ref_table_string: str = "**No references found.**"
+
+    try:
+        with st.spinner("Searching..."):  # Show loading spinner
+            if only_use_chatbot:
+                response: str = "<empty>"
+            else:
+                # **Call async search function using `asyncio.run()`**
+                search_results: Dict[str, Any] = asyncio.run(
+                    invoke_duckduckgo_news_search(query=prompt, location=location, num=num, time_filter=time_filter)
+                )
+
+                if search_results["status"] == "success":
+                    md_data: List[Dict[str, Any]] = search_results["results"]
+                    response = f"Here are your search results:\n{md_data}"
+
+                    def clean_title(title: str) -> str:
+                        """
+                        Cleans the title by replacing '|' with '-' to ensure proper formatting.
+
+                        Args:
+                            title (str): The original title.
+
+                        Returns:
+                            str: The cleaned title with '|' replaced by '-'.
+                        """
+                        return title.replace("|", " - ").strip()  # Replace '|' with ' - ' and remove leading/trailing spaces
+
+                    def generate_star_rating(rating: str) -> str:
+                        """
+                        Converts a numeric rating into a star representation (supports half-stars).
+
+                        Args:
+                            rating (str): The rating value as a string.
+
+                        Returns:
+                            str: A string representation of the rating using stars (⭐) and half-stars (⭐½).
+                        """
+                        try:
+                            rating_float: float = float(rating)  # Convert rating to float
+                            full_stars: int = int(rating_float)  # Extract full stars
+                            half_star: str = "⭐½" if (rating_float - full_stars) >= 0.5 else ""  # Add half-star if needed
+                            return "⭐" * full_stars + half_star  # Construct final star rating
+                        except ValueError:
+                            return "N/A"  # Fallback for non-numeric ratings
+
+                    # Start building reference table with proper Markdown formatting
+                    ref_table_string = "| Num | Title | Rating | Context |\n|---|------|--------|---------|\n"
+
+                    for res in md_data:
+                        # **Fix: Clean the title by replacing '|' with '-'**
+                        title_cleaned = clean_title(res['title'])
+
+                        # **Ensure the rating is always numeric before converting to stars**
+                        raw_rating = str(res.get('rating', 'N/A')).strip()  # Get rating and strip whitespace
+
+                        # Fix: Only convert rating if it’s a valid number
+                        if raw_rating.replace('.', '', 1).isdigit():  # Check if it’s a valid float
+                            stars = generate_star_rating(raw_rating)
+                        else:
+                            stars = "N/A"  # If it's text (like "MIT News"), default to "N/A"
+
+                        # **Ensure proper clickable links in the Title column**
+                        if res.get('link', '').startswith("http"):  # Ensure link exists and is valid
+                            title = f"[{title_cleaned}]({res['link']})"
+                        else:
+                            title = title_cleaned  # Fallback to text-only title
+
+                        # **Properly format Context column (limit to 100 chars)**
+                        context_summary = res.get('summary', '').strip()  # Ensure it's a string and strip spaces
+                        summary = context_summary[:100] + "..." if len(context_summary) > 100 else context_summary
+
+                        # **Final row construction**
+                        ref_table_string += f"| {res['num']} | {title} | {stars} | {summary} |\n"
+
+            # **Generate chatbot response based on search results or chat history**
+            bot = ChatBot()
+            bot.history = st.session_state.messages.copy()
+            response = bot.generate_response(
+                f"""
+                User prompt: {prompt}
+                Search results: {response}
+                Context: {[res['summary'] for res in search_results.get("results", [])]}
+                If search results exist, use them for the answer.
+                Otherwise, generate a response based on chat history.
+                """
+            )
+
+    except Exception as e:
+        st.warning(f"Error fetching data: {e}")
+        response = "We encountered an issue. Please try again later."
+
+    # **Convert response to audio**
+    save_to_audio(response)
+
+    # **Display assistant response in chat UI**
+    with st.chat_message("assistant"):
+        st.markdown(response, unsafe_allow_html=True)
+        st.audio("output.mp3", format="audio/mpeg", loop=True)
+        with st.expander("References:", expanded=True):
+            st.markdown(ref_table_string, unsafe_allow_html=True)
+
+    # **Update chat history with final response**
+    final_response: str = f"{response}\n\n{ref_table_string}"
+    st.session_state.messages.append({"role": "assistant", "content": final_response})

helper.py

@@ -0,0 +1,252 @@
+import asyncio
+import json
+import os
+import subprocess
+import urllib
+from datetime import datetime
+from typing import Dict, List, Any, Optional
+import requests
+import re
+from bs4 import BeautifulSoup
+from gtts import gTTS
+from logger.app_logger import app_logger
+
+# ============================ CHATBOT CLASS ============================
+
+class ChatBot:
+    """
+    A chatbot class that interacts with a local Llama model using Ollama.
+    """
+
+    def __init__(self) -> None:
+        """Initialize the ChatBot instance with a conversation history."""
+        self.history: List[Dict[str, str]] = [{"role": "system", "content": "You are a helpful assistant."}]
+        app_logger.log_info("ChatBot instance initialized", level="INFO")
+
+    def generate_response(self, prompt: str) -> str:
+        """
+        Generate a response from the chatbot based on the user's prompt.
+
+        Args:
+            prompt (str): The input message from the user.
+
+        Returns:
+            str: The chatbot's response to the provided prompt.
+        """
+        self.history.append({"role": "user", "content": prompt})
+        # app_logger.log_info(f"User prompt added to history: {prompt}", level="INFO")
+        app_logger.log_info("User prompt added to history", level="INFO")
+
+        # Convert chat history into a string for subprocess input
+        conversation = "\n".join(f"{msg['role']}: {msg['content']}" for msg in self.history)
+
+        try:
+            # Run the Llama model using Ollama
+            completion = subprocess.run(
+                ["ollama", "run", "llama3.2:latest"],
+                input=conversation,
+                capture_output=True,
+                text=True,
+            )
+
+            if completion.returncode != 0:
+                app_logger.log_error(f"Error running subprocess: {completion.stderr}")
+                return "I'm sorry, I encountered an issue processing your request."
+
+            response = completion.stdout.strip()
+            self.history.append({"role": "assistant", "content": response})
+            # app_logger.log_info(f"Assistant response generated: {response}", level="INFO")
+            app_logger.log_info("Assistant response generated", level="INFO")
+
+            return response
+
+        except Exception as e:
+            app_logger.log_error(f"Error sending query to the model: {e}")
+            return "I'm sorry, an error occurred while processing your request."
+
+    async def rate_body_of_article(self, article_title: str, article_content: str) -> str:
+        """
+        Rate the quality of an article's content based on its title.
+
+        Args:
+            article_title (str): The title of the article.
+            article_content (str): The full content of the article.
+
+        Returns:
+            str: A rating between 1 and 5 based on relevance and quality.
+        """
+        prompt = f"""
+        Given the following article title and content, provide a rating between 1 and 5 
+        based on how well the content aligns with the title and its overall quality.
+
+        - **Article Title**: {article_title}
+        - **Article Content**: {article_content[:1000]}  # Limit to first 1000 chars
+
+        **Instructions:**
+        - The rating should be a whole number between 1 and 5.
+        - Base your score on accuracy, clarity, and relevance.
+        - Only return a single numeric value (1-5) with no extra text.
+
+        **Example Output:**
+        `4` or `2` or `3.5` or `1.5`
+        """
+
+        try:
+            # Run the Llama model using Ollama
+            completion = subprocess.run(
+                ["ollama", "run", "llama3.2:latest"],
+                input=prompt,
+                capture_output=True,
+                text=True,
+            )
+
+            if completion.returncode != 0:
+                app_logger.log_error(f"Error running subprocess: {completion.stderr}")
+                return "Error"
+
+            response = completion.stdout.strip()
+
+            # Validate the rating is within the expected range
+            if response.isdigit() and 1 <= int(response) <= 5:
+                self.history.append({"role": "assistant", "content": response})
+                app_logger.log_info(f"Article rated: {response}", level="INFO")
+                return response
+            else:
+                app_logger.log_warning(f"Invalid rating received: {response}")
+                return "Error"
+
+        except Exception as e:
+            app_logger.log_error(f"Error sending query to the model: {e}")
+            return "Error"
+
+
+# ============================ EXTRACT NEWS BODY ============================
+
+def extract_news_body(news_url: str) -> str:
+    """
+    Extract the full article body from a given news URL.
+
+    Args:
+        news_url (str): The URL of the news article.
+
+    Returns:
+        str: Extracted full article content.
+    """
+    try:
+        headers = {
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36"
+        }
+
+        response = requests.get(news_url, headers=headers, timeout=5)
+        if response.status_code != 200:
+            app_logger.log_error(f"Failed to fetch article: {response.status_code}")
+            return "Failed to fetch article."
+
+        soup = BeautifulSoup(response.text, "html.parser")
+        paragraphs = soup.find_all("p")
+
+        # Extract and return cleaned text
+        article_content = "\n".join([p.text.strip() for p in paragraphs if p.text.strip()])
+        app_logger.log_info(f"Article content extracted from {news_url}", level="INFO")
+        return article_content
+
+    except Exception as e:
+        app_logger.log_error(f"Error extracting article content: {e}")
+        return f"Error extracting article content: {e}"
+
+
+# ============================ ASYNC NEWS SCRAPING ============================
+
+async def invoke_duckduckgo_news_search(query: str, num: int = 5, location: str = "us-en", time_filter: str = "w") -> \
+Dict[str, Any]:
+    """
+    Perform a DuckDuckGo News search, extract news headlines, fetch full content,
+    and rate articles using parallel asynchronous processing.
+
+    Args:
+        query (str): The search query string.
+        num (int): Number of search results to retrieve.
+        location (str): The region code for location-based results (e.g., 'us-en', 'in-en').
+        time_filter (str): Time filter for news ('d' = past day, 'w' = past week, 'm' = past month, 'y' = past year).
+
+    Returns:
+        Dict[str, Any]: A dictionary containing extracted news articles.
+    """
+    app_logger.log_info(f"Starting DuckDuckGo news search for query: {query}", level="INFO")
+
+    duckduckgo_news_url = f"https://duckduckgo.com/html/?q={query.replace(' ', '+')}&kl={location}&df={time_filter}&ia=news"
+    headers = {"User-Agent": "Mozilla/5.0"}
+
+    response = requests.get(duckduckgo_news_url, headers=headers)
+    if response.status_code != 200:
+        app_logger.log_error(f"Failed to fetch news search results: {response.status_code}")
+        return {"status": "error", "message": "Failed to fetch news search results"}
+
+    soup = BeautifulSoup(response.text, "html.parser")
+    search_results = soup.find_all("div", class_="result__body")
+
+    async def process_article(result, index: int) -> Optional[Dict[str, Any]]:
+        """Processes a single article: extracts details, fetches content, and rates it."""
+        try:
+            title_tag = result.find("a", class_="result__a")
+            if not title_tag:
+                app_logger.log_warning(f"Title tag not found for result index {index}")
+                return None
+
+            title = title_tag.text.strip()
+            raw_link = title_tag["href"]
+
+            match = re.search(r"uddg=(https?%3A%2F%2F[^&]+)", raw_link)
+            link = urllib.parse.unquote(match.group(1)) if match else "Unknown Link"
+
+            snippet_tag = result.find("a", class_="result__snippet")
+            summary = snippet_tag.text.strip() if snippet_tag else "No summary available."
+
+            article_content = extract_news_body(link)
+
+            bot = ChatBot()
+            rating = await bot.rate_body_of_article(title, article_content)
+
+            app_logger.log_info(f"Processed article: {title}", level="INFO")
+
+            return {
+                "num": index + 1,
+                "link": link,
+                "title": title,
+                "summary": summary,
+                "body": article_content,
+                "rating": rating
+            }
+
+        except Exception as e:
+            app_logger.log_error(f"Error processing article: {e}")
+            return None
+
+    tasks = [process_article(result, index) for index, result in enumerate(search_results[:num])]
+    extracted_results = await asyncio.gather(*tasks)
+
+    extracted_results = [res for res in extracted_results if res is not None]
+
+    if extracted_results:
+        app_logger.log_info(f"News search completed successfully with {len(extracted_results)} results", level="INFO")
+        return {"status": "success", "results": extracted_results}
+    else:
+        app_logger.log_error("No valid news search results found")
+        return {"status": "error", "message": "No valid news search results found"}
+
+
+# ============================ UTILITY FUNCTIONS ============================
+
+def current_year() -> int:
+    """Returns the current year as an integer."""
+    return datetime.now().year
+
+
+def save_to_audio(text: str) -> None:
+    """Converts text to an audio file using Google Text-to-Speech (gTTS)."""
+    try:
+        tts = gTTS(text=text, lang="en")
+        tts.save("output.mp3")
+        app_logger.log_info("Response converted to audio", level="INFO")
+    except Exception as e:
+        app_logger.log_error(f"Error converting response to audio: {e}")

logger/app_logger.py

@@ -0,0 +1,75 @@
+import os
+from loguru import logger as loguru_logger
+from typing import Any, Generator
+from contextlib import contextmanager
+# Define log file path
+LOG_FILE = "logs/app.log"
+
+# Ensure the logs directory exists
+os.makedirs("logs", exist_ok=True)
+
+# Configure Loguru Logger
+loguru_logger.add(
+    LOG_FILE,
+    rotation="1 day",
+    retention="10 days",
+    format="<green>{time:YYYY-MM-DD HH:mm:ss}</green> | "
+           "<level>{level: <8}</level> | "
+           "<cyan>{file}</cyan>:<cyan>{name}</cyan>:<cyan>{line}</cyan> - <level>{message}</level>",
+)
+
+
+class AppLogger:
+    """
+    Logging class using Loguru for structured logging.
+    Provides synchronous and asynchronous logging capabilities.
+    """
+
+    def __init__(self):
+        pass
+
+    def log_info(self, *args: Any, **kwargs: Any) -> None:
+        """Synchronous logging with level selection."""
+        level = kwargs.pop("level", "INFO")
+        message = " ".join(map(str, args))
+        loguru_logger.opt(depth=1).log(level, message, **kwargs)
+
+    async def log_info_async(self, *args: Any, **kwargs: Any) -> None:
+        """Asynchronous logging for async functions."""
+        level = kwargs.pop("level", "INFO")
+        message = " ".join(map(str, args))
+        loguru_logger.opt(depth=1).log(level, message, **kwargs)
+
+    def log_error(self, *args: Any, **kwargs: Any) -> None:
+        """Synchronous error logging."""
+        message = " ".join(map(str, args))
+        loguru_logger.opt(depth=1).error(message, **kwargs)
+
+    async def log_error_async(self, *args: Any, **kwargs: Any) -> None:
+        """Asynchronous error logging."""
+        message = " ".join(map(str, args))
+        loguru_logger.opt(depth=1).error(message, **kwargs)
+
+    def log_debug(self, *args: Any, **kwargs: Any) -> None:
+        """Synchronous debug logging."""
+        message = " ".join(map(str, args))
+        loguru_logger.opt(depth=1).debug(message, **kwargs)
+
+    async def log_debug_async(self, *args: Any, **kwargs: Any) -> None:
+        """Asynchronous debug logging."""
+        message = " ".join(map(str, args))
+        loguru_logger.opt(depth=1).debug(message, **kwargs)
+
+    def log_warning(self, *args: Any, **kwargs: Any) -> None:
+        """Synchronous warning logging."""
+        message = " ".join(map(str, args))
+        loguru_logger.opt(depth=1).warning(message, **kwargs)
+
+    async def log_warning_async(self, *args: Any, **kwargs: Any) -> None:
+        """Asynchronous warning logging."""
+        message = " ".join(map(str, args))
+        loguru_logger.opt(depth=1).warning(message, **kwargs)
+
+
+# Instantiate global logger instance
+app_logger = AppLogger()

output.mp3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:806ab164eee42905afa55bd61329e4ed93074eef9793b844388ad2045b134cef
+size 632064

requirements.txt

@@ -0,0 +1,7 @@
+google-search-results
+openai
+streamlit
+serpapi
+gTTS
+bs4
+loguru