files

.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
+ai_assistant.db filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.9
+
+   WORKDIR /code
+
+   COPY ./requirements.txt /code/requirements.txt
+   RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+   COPY . /code
+
+   # Ensure the templates folder is copied
+   COPY ./templates /code/templates
+
+   CMD ["python", "app.py"]

ai_assistant.db

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f886ff11abcf7f9b7c22c0c3bc5b657334a06e82607ef2103b3778c46f82f5eb
+size 3715072

app.py

@@ -0,0 +1,472 @@
+import os
+import google.generativeai as genai
+from flask import Flask, request, jsonify, render_template
+from flask_cors import CORS
+from werkzeug.utils import secure_filename
+import PyPDF2
+import docx
+import pandas as pd
+import sqlite3
+import base64
+import json
+import numpy as np
+import logging
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_google_genai.llms import GoogleGenerativeAI  # Updated import statement
+from langchain_experimental.agents import create_csv_agent  # Updated import statement
+from langchain_google_genai import GoogleGenerativeAIEmbeddings
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain.chains.question_answering import load_qa_chain
+from langchain.prompts import PromptTemplate
+from langchain.docstore.document import Document
+from sklearn.metrics.pairwise import cosine_similarity
+import plotly.express as px  # For interactive charts
+import plotly
+from newsapi import NewsApiClient
+import certifi
+import requests
+
+app = Flask(__name__)
+CORS(app)
+
+# Set up logging
+logging.basicConfig(level=logging.INFO)
+
+# Set your Google API key securely using an environment variable
+os.environ['GOOGLE_API_KEY'] = 'AIzaSyD7KJK0GDMh_R9GbE0j7FFyCZIl1BGrpgg'
+genai.configure(api_key=os.environ['GOOGLE_API_KEY'])
+
+NEWSAPI_KEY = 'dd9befe361ba4df8bbbf84283db7a373'
+session = requests.Session()
+session.verify = certifi.where()
+newsapi = NewsApiClient(api_key=NEWSAPI_KEY)
+newsapi.session = session
+
+# Initialize the model
+model = genai.GenerativeModel('gemini-pro')
+
+UPLOAD_FOLDER = 'uploads'
+ALLOWED_EXTENSIONS = {'txt', 'pdf', 'docx', 'xlsx', 'csv'}
+
+if not os.path.exists(UPLOAD_FOLDER):
+    os.makedirs(UPLOAD_FOLDER)
+
+app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
+
+# Database setup
+DATABASE = 'ai_assistant.db'
+
+def get_db():
+    db = sqlite3.connect(DATABASE)
+    db.row_factory = sqlite3.Row
+    return db
+
+def init_db():
+    logging.info("Initializing database...")
+    with app.app_context():
+        db = get_db()
+        db.execute('''CREATE TABLE IF NOT EXISTS files (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            filename TEXT NOT NULL,
+            file_data TEXT NOT NULL,
+            analysis TEXT,
+            timestamp DATETIME DEFAULT CURRENT_TIMESTAMP
+        )''')
+        db.execute('''CREATE TABLE IF NOT EXISTS chunks (
+            id INTEGER PRIMARY KEY AUTOINCREMENT,
+            file_id INTEGER,
+            content TEXT NOT NULL,
+            embedding TEXT NOT NULL,
+            FOREIGN KEY (file_id) REFERENCES files (id)
+        )''')
+        db.commit()
+    logging.info("Database initialized successfully.")
+
+def allowed_file(filename):
+    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
+
+def convert_excel_to_csv(file_path):
+    logging.info(f"Converting Excel to CSV: {file_path}")
+    df = pd.read_excel(file_path)
+    csv_path = file_path.rsplit('.', 1)[0] + '.csv'
+    df.to_csv(csv_path, index=False)
+    return csv_path
+
+def process_document(file_path):
+    logging.info(f"Processing document: {file_path}")
+    if file_path.endswith('.pdf'):
+        return extract_text_from_pdf(file_path)
+    elif file_path.endswith('.docx'):
+        return extract_text_from_docx(file_path)
+    elif file_path.endswith('.xlsx'):
+        csv_path = convert_excel_to_csv(file_path)
+        return extract_text_from_csv(csv_path)
+    elif file_path.endswith('.csv'):
+        return extract_text_from_csv(file_path)
+    else:
+        with open(file_path, 'r') as f:
+            return f.read()
+
+def extract_text_from_pdf(file_path):
+    logging.info(f"Extracting text from PDF: {file_path}")
+    text = ""
+    with open(file_path, 'rb') as file:
+        reader = PyPDF2.PdfReader(file)
+        for page in reader.pages:
+            text += page.extract_text() + "\n"
+    return text
+
+def extract_text_from_docx(file_path):
+    logging.info(f"Extracting text from DOCX: {file_path}")
+    doc = docx.Document(file_path)
+    return "\n".join([para.text for para in doc.paragraphs])
+
+def extract_text_from_csv(file_path):
+    logging.info(f"Extracting text from CSV: {file_path}")
+    df = pd.read_csv(file_path)
+    return df.to_string()
+
+def get_text_chunks(text):
+    logging.info("Chunking text for vector store...")
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    chunks = text_splitter.split_text(text)
+    return chunks
+
+def create_vector_store(text_chunks, file_id):
+    logging.info("Creating vector store in SQLite...")
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+    db = get_db()
+    cursor = db.cursor()
+    
+    for chunk in text_chunks:
+        embedding = embeddings.embed_query(chunk)
+        cursor.execute('INSERT INTO chunks (file_id, content, embedding) VALUES (?, ?, ?)',
+                       (file_id, chunk, json.dumps(embedding)))
+    
+    db.commit()
+    logging.info("Vector store created in SQLite.")
+
+def get_conversational_chain():
+    prompt_template = """
+    Answer the question as detailed as possible from the provided context. If the answer is not directly
+    available in the provided context, use your knowledge to infer a reasonable answer based on the given information.
+    If you're unsure or the question is completely unrelated to the context, state that you don't have enough information to answer accurately.
+
+    Context:\n{context}\n
+    Question:\n{question}\n
+    Answer:
+    """
+    model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.3)
+    prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
+    chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
+    return chain
+
+def answer_query_from_document(user_question, file_id):
+    logging.info("Answering query from SQLite...")
+    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+    query_embedding = np.array(embeddings.embed_query(user_question))
+    
+    db = get_db()
+    cursor = db.cursor()
+    
+    cursor.execute('SELECT id, content, embedding FROM chunks WHERE file_id = ?', (file_id,))
+    chunks = cursor.fetchall()
+    
+    # Calculate cosine similarity
+    chunk_embeddings = [np.array(json.loads(chunk['embedding'])) for chunk in chunks]
+    similarities = cosine_similarity([query_embedding], chunk_embeddings)[0]
+    
+    # Sort chunks by similarity
+    sorted_chunks = sorted(zip(chunks, similarities), key=lambda x: x[1], reverse=True)
+    
+    # Get top 5 most similar chunks
+    top_chunks = sorted_chunks[:5]
+    
+    context = ' '.join([chunk[0]['content'] for chunk in top_chunks])
+    
+    chain = get_conversational_chain()
+    response = chain.invoke({"input_documents": [Document(page_content=context)], "question": user_question})
+    return response["output_text"]
+
+def analyze_document(text):
+    logging.info(f"Analyzing document with text: {text[:200]}...")  # Log first 200 chars
+    prompt = f"Analyze the following document and provide a summary of its key points and any important insights:\n\n{text[:4000]}"
+    response = model.generate_content(prompt)
+    logging.info("Document analysis completed.")
+    return response.text
+
+def process_query(query, role=None, file_id=None):
+    logging.info(f"Processing query: {query}, role: {role}, file_id: {file_id}")
+    if file_id:
+        return answer_query_from_document(query, file_id)
+    else:
+        system_prompt = f"You are an AI assistant specializing in {role}." if role else "You are a helpful AI assistant."
+        
+        prompt = f'''
+        {system_prompt}
+        
+        Query: "{query}"
+        
+        Requirements:
+        - Use a friendly yet professional tone.
+        - Ensure the response is accurate and directly addresses the question.
+        - Include relevant examples, definitions, or comparisons to enhance clarity.
+        - Format the response in well-structured paragraphs or bullet points with bold headings when appropriate.
+        - Use markdown formatting for code snippets, emphasis, and structure.
+        - Aim for a comprehensive response that fully addresses the query.
+        '''
+        
+        logging.info("Generating content...")
+        response = model.generate_content(prompt)
+        generated_text = response.text
+        logging.info("Content generated successfully.")
+
+        return generated_text
+    
+def get_energy_news(query):
+    try:
+        articles = newsapi.get_everything(q=query, language='en', sort_by='publishedAt', page_size=10)
+        return articles['articles']
+    except Exception as e:
+        logging.error(f"Error fetching news: {e}")
+        return []
+    
+def summarize_article(article):
+    title = article.get('title', 'No title')
+    content = article.get('description', '') or article.get('content', '') or ''
+    prompt = f"""
+    Summarize the following news article in 3-4 lines:
+    
+    Title: {title}
+    Content: {content}
+    """
+    try:
+        response = model.generate_content(prompt)
+        return response.text.strip()
+    except Exception as e:
+        logging.error(f"Error summarizing article: {e}")
+        return "Unable to generate summary."
+
+def filter_and_analyze_news(query, articles):
+    filtered_and_analyzed_news = []
+    
+    for article in articles:
+        title = article.get('title', 'No title')
+        content = article.get('description', '') or article.get('content', '') or ''
+        
+        prompt = f"""
+        Analyze the following news article in the context of the energy market:
+        
+        Query: {query}
+        Title: {title}
+        Content: {content}
+        
+        Is this article directly relevant to "{query}" in the context of the energy market? 
+        Answer ONLY 'YES' or 'NO', followed by a brief explanation.
+        
+        If YES, provide:
+        1. A concise 2-3 sentence summary of the news.
+        2. Key points (up to 3 bullet points).
+        3. Specific impact on the energy market related to {query} (1-2 sentences).
+        """
+        
+        try:
+            response = model.generate_content(prompt)
+            analysis = response.text.strip()
+            
+            if analysis.startswith("YES"):
+                filtered_and_analyzed_news.append({
+                    'title': title,
+                    'link': article.get('url', '#'),
+                    'analysis': analysis.split("YES", 1)[1].strip()
+                })
+            
+            if len(filtered_and_analyzed_news) >= 10:
+                break
+        except Exception as e:
+            logging.error(f"Error analyzing article: {e}")
+    
+    return filtered_and_analyzed_news
+
+def generate_market_summary(query, filtered_news):
+    if not filtered_news:
+        return f"No relevant news found for '{query}' in the energy market context."
+
+    summaries = [item.get('analysis', '') for item in filtered_news]
+    combined_summary = "\n\n".join(summaries)
+
+    prompt = f"""
+    Based on the following summaries of recent news articles related to '{query}' in the energy market:
+
+    {combined_summary}
+
+    Provide a concise market summary that:
+    1. Highlights the current trends and developments related to {query} in the energy market.
+    2. Identifies any significant impacts or potential changes in the market.
+    3. Mentions any notable events or decisions affecting this area.
+
+    Keep the summary focused on factual information derived from the news articles, without adding speculation or personal opinions.
+    """
+
+    try:
+        response = model.generate_content(prompt)
+        return response.text.strip()
+    except Exception as e:
+        logging.error(f"Error generating market summary: {e}")
+        return f"Unable to generate market summary for '{query}' due to an error."
+
+@app.route('/')
+def index():
+    return render_template('index.html')
+
+@app.route('/query', methods=['POST'])
+def query():
+    data = request.json
+    query = data.get('query')
+    role = data.get('role')
+    file_id = data.get('file_id')
+    news_context = data.get('newsContext')
+    try:
+        logging.info(f"Received query: {query}, role: {role}, file_id: {file_id}")
+        
+        if role == 'AI News Analyst' and news_context:
+            # Handle news-related queries with context
+            prompt = f"""
+            As an AI News Analyst specializing in the energy market, answer the following question based on the provided news context:
+
+            News Context:
+            {json.dumps(news_context, indent=2)}
+
+            Question: {query}
+
+            Provide a concise and informative response, using the provided news context to support your answer.
+            """
+            response = model.generate_content(prompt)
+            return jsonify({'response': response.text})
+        else:
+            # Handle regular queries as before
+            response = process_query(query, role, file_id)
+            return jsonify({'response': response})
+    except Exception as e:
+        logging.error(f"Error in /query route: {str(e)}", exc_info=True)
+        return jsonify({'error': str(e)}), 500
+
+@app.route('/upload', methods=['POST'])
+def upload_file():
+    if 'file' not in request.files:
+        return jsonify({'error': 'No file part'}), 400
+    file = request.files['file']
+    if file.filename == '':
+        return jsonify({'error': 'No selected file'}), 400
+    if file and allowed_file(file.filename):
+        filename = secure_filename(file.filename)
+        file_path = os.path.join(app.config['UPLOAD_FOLDER'], filename)
+        file.save(file_path)
+        
+        try:
+            logging.info(f"File uploaded successfully: {filename}")
+            extracted_text = process_document(file_path)
+            text_chunks = get_text_chunks(extracted_text)
+            analysis = analyze_document(extracted_text)
+            
+            db = get_db()
+            with open(file_path, 'rb') as f:
+                file_data = f.read()
+            file_data_base64 = base64.b64encode(file_data).decode('utf-8')
+            cursor = db.execute('INSERT INTO files (filename, file_data, analysis) VALUES (?, ?, ?)',
+                       (filename, file_data_base64, analysis))
+            file_id = cursor.lastrowid
+            db.commit()
+            
+            create_vector_store(text_chunks, file_id)
+            
+            os.remove(file_path)  # Remove the file after processing
+            logging.info(f"File processing completed and saved to database with ID: {file_id}")
+            
+            return jsonify({'file_id': file_id, 'analysis': analysis})
+        except Exception as e:
+            logging.error(f'Error processing file: {str(e)}', exc_info=True)
+            return jsonify({'error': str(e)}), 500
+    
+    return jsonify({'error': 'Invalid file type'}), 400
+
+@app.route('/plot', methods=['POST'])
+def plot():
+    data = request.json
+    file_id = data.get('file_id')
+    try:
+        db = get_db()
+        cursor = db.execute('SELECT file_data FROM files WHERE id = ?', (file_id,))
+        file_data_base64 = cursor.fetchone()['file_data']
+        file_data = base64.b64decode(file_data_base64)
+        
+        df = pd.read_excel(pd.io.common.BytesIO(file_data))
+        
+        fig = px.line(df, x=df.columns[0], y=df.columns[1:])
+        graph_json = json.dumps(fig, cls=plotly.utils.PlotlyJSONEncoder)
+        
+        return jsonify({'graph': graph_json})
+    except Exception as e:
+        logging.error(f'Error generating plot: {str(e)}', exc_info=True)
+        return jsonify({'error': str(e)}), 500
+
+@app.route('/process_csv_query', methods=['POST'])
+def process_csv_query():
+    data = request.json
+    file_id = data.get('file_id')
+    query = data.get('query')
+    
+    try:
+        db = get_db()
+        cursor = db.execute('SELECT file_data FROM files WHERE id = ?', (file_id,))
+        file_data_base64 = cursor.fetchone()['file_data']
+        file_data = base64.b64decode(file_data_base64)
+        
+        # Save the CSV data to a temporary file
+        temp_csv_path = f'/tmp/{file_id}.csv'
+        with open(temp_csv_path, 'wb') as temp_csv:
+            temp_csv.write(file_data)
+        
+        # Create a langchain agent using the gemini-pro model
+        agent = create_csv_agent(GoogleGenerativeAI(model="gemini-pro"), temp_csv_path, verbose=True)
+        
+        # Run the query using the agent
+        response = agent.run(query)
+        
+        return jsonify({'response': response})
+    except Exception as e:
+        logging.error(f'Error processing CSV query: {str(e)}', exc_info=True)
+        return jsonify({'error': str(e)}), 500
+
+@app.route('/fetch_news', methods=['POST'])
+def fetch_news():
+    data = request.json
+    query = data.get('query')
+    try:
+        all_articles = get_energy_news(query)
+        filtered_news = filter_and_analyze_news(query, all_articles)
+        market_summary = generate_market_summary(query, filtered_news)
+
+        # Prepare the top 10 articles with summaries
+        top_articles = []
+        for article in filtered_news[:10]:
+            summary = article.get('analysis', '').split('\n\n')[0]  # Get the first paragraph of the analysis as summary
+            top_articles.append({
+                'title': article.get('title', 'No title'),
+                'url': article.get('link', '#'),
+                'summary': summary
+            })
+
+        return jsonify({
+            'top_articles': top_articles,
+            'market_summary': market_summary,
+            'full_analysis': filtered_news
+        })
+    except Exception as e:
+        logging.error(f"Error in fetch_news route: {str(e)}", exc_info=True)
+        return jsonify({'error': str(e)}), 500
+
+if __name__ == '__main__':
+    init_db()
+    port = int(os.environ.get('PORT', 7860))
+    app.run(host='0.0.0.0', port=port, debug=False)

requirements.txt

@@ -0,0 +1,17 @@
+Flask==2.1.0
+flask-cors==3.0.10
+google-generativeai==0.3.2
+Werkzeug==2.2.3
+PyPDF2==3.0.1
+python-docx==0.8.11
+pandas==1.5.3
+openpyxl==3.1.2
+numpy==1.24.3
+scikit-learn==1.2.2
+plotly==5.15.0
+newsapi-python==0.2.7
+requests==2.31.0
+certifi==2023.5.7
+langchain==0.0.350
+langchain-google-genai==0.0.5
+langchain-experimental==0.0.42

schema.sql

@@ -0,0 +1,15 @@
+CREATE TABLE IF NOT EXISTS documents (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    content TEXT NOT NULL,
+    embedding BLOB NOT NULL
+);
+
+CREATE TABLE IF NOT EXISTS chunks (
+    id INTEGER PRIMARY KEY AUTOINCREMENT,
+    document_id INTEGER,
+    content TEXT NOT NULL,
+    embedding BLOB NOT NULL,
+    FOREIGN KEY (document_id) REFERENCES documents(id)
+);
+
+CREATE INDEX idx_chunks_embedding ON chunks(embedding);

templates/index.html

@@ -0,0 +1,594 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Finder - Find Your Answers Here</title>
+    <style>
+        @import url('https://fonts.googleapis.com/css2?family=Poppins:wght@300;400;600&display=swap');
+
+        body, html {
+            font-family: 'Poppins', Arial, sans-serif;
+            margin: 0;
+            padding: 0;
+            height: 100%;
+            background-color: #f0f2f5;
+            color: #333;
+        }
+        .landing-page {
+            display: flex;
+            flex-direction: column;
+            align-items: center;
+            justify-content: center;
+            height: 100vh;
+            background: linear-gradient(135deg, #e0f7fa, #fce4ec);
+            text-align: center;
+            position: relative;
+            overflow: hidden;
+        }
+        .landing-page img.logo {
+            width: 300px;
+            height: auto;
+            margin-bottom: 10px;
+        }
+        .landing-page h1 {
+            font-size: 3em;
+            margin: 10px 0;
+            background: linear-gradient(45deg, #2196f3, #e91e63);
+            background-clip: text;
+            -webkit-background-clip: text;
+            color: transparent;
+            -webkit-text-fill-color: transparent;
+        }
+        .landing-page .im-text {
+            font-size: 1.5em;
+            margin: 0 0 -10px;
+            background: linear-gradient(45deg, #2196f3, #e91e63);
+            background-clip: text;
+            -webkit-background-clip: text;
+            color: transparent;
+            -webkit-text-fill-color: transparent;
+        }
+        .landing-page p {
+            font-size: 1.2em;
+            max-width: 600px;
+            margin: 10px 0 30px;
+            color: #0277bd;
+        }
+        .start-chat-btn {
+            padding: 12px 24px;
+            font-size: 1.2em;
+            background: linear-gradient(45deg, #2196f3, #e91e63);
+            color: white;
+            border: none;
+            border-radius: 25px;
+            cursor: pointer;
+            transition: transform 0.3s, box-shadow 0.3s;
+        }
+        .start-chat-btn:hover {
+            transform: translateY(-3px);
+            box-shadow: 0 4px 15px rgba(0, 0, 0, 0.2);
+        }
+        .ai-image {
+            position: absolute;
+            width: 150px;
+            height: auto;
+            opacity: 0.6;
+        }
+        .ai-image-left {
+            left: 60px;
+            top: 50%;
+            transform: translateY(-50%);
+        }
+        .ai-image-right {
+            right: 60px;
+            top: 50%;
+            transform: translateY(-50%);
+        }
+        .chat-interface {
+            display: none;
+            height: 100vh;
+        }
+        .sidebar {
+            position: fixed;
+            left: -300px;
+            top: 0;
+            width: 300px;
+            height: 100%;
+            background-color: #ffffff;
+            padding: 60px 20px 20px;
+            box-shadow: 2px 0 5px rgba(0,0,0,0.1);
+            transition: left 0.3s ease-in-out, visibility 0.3s ease-in-out;
+            z-index: 1000;
+            visibility: hidden;
+        }
+        .sidebar.open {
+            left: 0;
+            visibility: visible;
+        }
+        .main-content {
+            margin-left: 0;
+            transition: margin-left 0.3s ease-in-out;
+            flex-grow: 1;
+            display: flex;
+            flex-direction: column;
+            overflow-y: auto;
+            padding: 20px;
+        }
+        .main-content.sidebar-open {
+            margin-left: 300px;
+        }
+        .chat-container {
+            flex-grow: 1;
+            overflow-y: auto;
+            padding: 20px;
+            background-color: #ffffff;
+            border-radius: 10px 10px 0 0;
+            box-shadow: 0 1px 3px rgba(0,0,0,0.1);
+            margin-bottom: 0;
+        }
+        .message {
+            max-width: 80%;
+            margin-bottom: 20px;
+            line-height: 1.5;
+            padding: 15px 20px;
+            border-radius: 18px;
+            position: relative;
+            display: inline-block;
+        }
+        .user-message {
+            background-color: #e3f2fd;
+            float: right;
+            clear: both;
+        }
+        .assistant-message {
+            background-color: #fce4ec;
+            float: left;
+            clear: both;
+        }
+        .input-area {
+            display: flex;
+            padding: 20px;
+            background-color: #ffffff;
+            border-top: 1px solid #e1e4e8;
+            border-radius: 0 0 10px 10px;
+            box-shadow: 0 -1px 3px rgba(0,0,0,0.1);
+        }
+        #query {
+            flex-grow: 1;
+            padding: 10px;
+            border: 1px solid #d1d5da;
+            border-radius: 20px;
+            font-size: 16px;
+        }
+        .send-button, .file-upload-button {
+            background: linear-gradient(45deg, #2196f3, #e91e63);
+            color: white;
+            border: none;
+            padding: 10px 20px;
+            margin-left: 10px;
+            border-radius: 20px;
+            cursor: pointer;
+        }
+        .file-input {
+            display: none;
+        }
+        .new-chat {
+            background: linear-gradient(45deg, #2196f3, #e91e63);
+            color: white;
+            padding: 10px;
+            border: none;
+            border-radius: 5px;
+            cursor: pointer;
+            margin-bottom: 20px;
+            font-weight: bold;
+        }
+        .shortcuts {
+            display: grid;
+            grid-template-columns: repeat(2, 1fr);
+            gap: 10px;
+        }
+        .shortcut {
+            background-color: #e3f2fd;
+            border: none;
+            padding: 10px;
+            border-radius: 5px;
+            cursor: pointer;
+            font-size: 14px;
+            transition: background-color 0.3s;
+        }
+        .shortcut:hover {
+            background-color: #bbdefb;
+        }
+        .context-info {
+            background-color: #e3f2fd;
+            padding: 10px;
+            margin-bottom: 10px;
+            border-radius: 5px;
+            font-size: 14px;
+        }
+        .loading {
+            display: none;
+            text-align: center;
+            padding: 20px;
+        }
+        .menu-button {
+            position: fixed;
+            top: 20px;
+            left: 20px;
+            z-index: 1001;
+            background: none;
+            border: none;
+            font-size: 24px;
+            cursor: pointer;
+        }
+        .news-container {
+            display: none;
+            flex-direction: column;
+            height: 100%;
+            padding: 20px;
+            overflow-y: auto;
+        }
+        .news-form {
+            display: flex;
+            margin-bottom: 20px;
+        }
+        .news-form input {
+            flex-grow: 1;
+            padding: 10px;
+            border: 1px solid #d1d5da;
+            border-radius: 20px;
+            font-size: 16px;
+            margin-right: 10px;
+        }
+        .news-form button {
+            background: linear-gradient(45deg, #2196f3, #e91e63);
+            color: white;
+            border: none;
+            padding: 10px 20px;
+            border-radius: 20px;
+            cursor: pointer;
+        }
+        .market-summary {
+            background-color: #e3f2fd;
+            padding: 15px;
+            border-radius: 10px;
+            margin-bottom: 20px;
+        }
+        .news-item {
+            background-color: #ffffff;
+            padding: 15px;
+            border-radius: 10px;
+            margin-bottom: 15px;
+            box-shadow: 0 1px 3px rgba(0,0,0,0.1);
+        }
+        .news-item h3 {
+            margin-top: 0;
+        }
+        .news-item a {
+            color: #2196f3;
+            text-decoration: none;
+        }
+        .news-item a:hover {
+            text-decoration: underline;
+        }
+        .initial-articles {
+            margin-bottom: 20px;
+        }
+        .initial-article {
+            background-color: #f0f8ff;
+            padding: 10px;
+            margin-bottom: 10px;
+            border-radius: 5px;
+        }
+        .top-articles {
+            margin-bottom: 20px;
+        }
+        .article-item {
+            background-color: #f0f8ff;
+            padding: 15px;
+            margin-bottom: 15px;
+            border-radius: 10px;
+            box-shadow: 0 1px 3px rgba(0,0,0,0.1);
+        }
+        .article-item h3 {
+            margin-top: 0;
+        }
+        .article-item a {
+            color: #2196f3;
+            text-decoration: none;
+        }
+        .article-item a:hover {
+            text-decoration: underline;
+        }
+    </style>
+</head>
+<body>
+    <div class="landing-page" id="landing-page">
+        <img src=" static/images/app_icon.png" alt="Finder Logo" class="logo">
+        <p class="im-text">I'm</p>
+        <h1>Finder</h1>
+        <p>Unlock the power of knowledge - Find Your Answers Here</p>
+        <button class="start-chat-btn" onclick="startChat()">Start Exploring</button>
+        <img src="static/images/AI-PNG-L.png" alt="AI Image Left" class="ai-image ai-image-left">
+        <img src="static/images/AI-PNG-R.png" alt="AI Image Right" class="ai-image ai-image-right">
+    </div>
+
+    <div class="chat-interface" id="chat-interface">
+        <button class="menu-button" onclick="toggleSidebar()">☰</button>
+        <div class="sidebar" id="sidebar">
+            <button class="new-chat" onclick="startNewChat()">New chat</button>
+            <div class="shortcuts">
+                <button class="shortcut" onclick="setRole('Python Teacher')">Python Teacher</button>
+                <button class="shortcut" onclick="setRole('Data Analyst')">Data Analyst</button>
+                <button class="shortcut" onclick="setRole('AI Expert')">AI Expert</button>
+                <button class="shortcut" onclick="setRole('Machine Learning Engineer')">ML Engineer</button>
+                <button class="shortcut" onclick="setRole('GenAI Specialist')">GenAI Specialist</button>
+                <button class="shortcut" onclick="setRole('Data Scientist')">Data Scientist</button>
+                <button class="shortcut" onclick="showNewsInterface()">AI News</button>
+            </div>
+        </div>
+        <div class="main-content" id="main-content">
+            <div class="context-info" id="context-info"></div>
+            <div class="chat-container" id="chat-container">
+                <!-- Chat messages will be dynamically inserted here -->
+            </div>
+            <div class="news-container" id="news-container">
+                <form class="news-form" id="news-form" onsubmit="fetchNews(event)">
+                    <input type="text" id="news-query" placeholder="Enter energy market topic..." required>
+                    <button type="submit">Search News</button>
+                </form>
+                <div id="market-summary" class="market-summary"></div>
+                <div id="news-results"></div>
+            </div>
+            <div class="loading" id="loading">Processing...</div>
+            <div class="input-area">
+                <input type="text" id="query" placeholder="Send a message..." />
+                <button class="send-button" onclick="sendMessage()">Send</button>
+                <input type="file" id="file-input" class="file-input" accept=".pdf,.txt,.docx,.xlsx,.csv" onchange="uploadFile()" />
+                <button class="file-upload-button" onclick="document.getElementById('file-input').click()">Upload File</button>
+            </div>
+        </div>
+    </div>
+    <div id="news-display" class="news-display" style="display: none;"></div>
+
+    <script src="https://cdnjs.cloudflare.com/ajax/libs/marked/2.0.3/marked.min.js"></script>
+    <script>
+        let currentRole = null;
+        let currentFileId = null;
+        let newsData = null;
+
+        function startChat() {
+            document.getElementById('landing-page').style.display = 'none';
+            document.getElementById('chat-interface').style.display = 'flex';
+        }
+
+        function toggleSidebar() {
+            const sidebar = document.getElementById('sidebar');
+            const mainContent = document.getElementById('main-content');
+            sidebar.classList.toggle('open');
+            mainContent.classList.toggle('sidebar-open');
+        }
+
+        function updateContextInfo() {
+            const contextInfo = document.getElementById('context-info');
+            let infoText = '';
+            if (currentRole) {
+                infoText += `Current Role: ${currentRole}`;
+            }
+            if (currentFileId) {
+                infoText += infoText ? ' | ' : '';
+                infoText += `File ID: ${currentFileId}`;
+            }
+            contextInfo.textContent = infoText;
+            contextInfo.style.display = infoText ? 'block' : 'none';
+        }
+
+        function setRole(role) {
+            currentRole = role;
+            updateContextInfo();
+            const chatContainer = document.getElementById('chat-container');
+            const roleMessage = document.createElement('div');
+            roleMessage.classList.add('message', 'assistant-message');
+            roleMessage.innerHTML = `Role set to: <strong>${role}</strong>. How can I assist you today?`;
+            chatContainer.appendChild(roleMessage);
+            chatContainer.scrollTop = chatContainer.scrollHeight;
+        }
+
+        function showNewsInterface() {
+            document.getElementById('chat-container').style.display = 'none';
+            document.getElementById('news-container').style.display = 'flex';
+            currentRole = 'AI News Analyst';
+            updateContextInfo();
+        }
+
+        function fetchNews(event) {
+            event.preventDefault();
+            const query = document.getElementById('news-query').value;
+            document.getElementById('loading').style.display = 'block';
+            
+            fetch('/fetch_news', {
+                method: 'POST',
+                headers: {
+                    'Content-Type': 'application/json',
+                },
+                body: JSON.stringify({ query: query }),
+            })
+            .then(response => response.json())
+            .then(data => {
+                newsData = data; // Store the fetched news data
+                const marketSummary = document.getElementById('market-summary');
+                const newsResults = document.getElementById('news-results');
+                
+                // Display market summary
+                marketSummary.innerHTML = `<h2>Market Summary</h2>${marked.parse(data.market_summary)}`;
+                
+                // Display top 10 articles with summaries and links
+                newsResults.innerHTML = '<h2>Top News Articles</h2>';
+                data.top_articles.forEach(article => {
+                    const articleElement = document.createElement('div');
+                    articleElement.classList.add('article-item');
+                    articleElement.innerHTML = `
+                        <h3><a href="${article.url}" target="_blank">${article.title}</a></h3>
+                        <p>${article.summary}</p>
+                    `;
+                    newsResults.appendChild(articleElement);
+                });
+
+                // Switch to chat interface after fetching news
+                document.getElementById('chat-container').style.display = 'block';
+                document.getElementById('news-container').style.display = 'none';
+
+                // Add a system message to indicate that news has been fetched
+                const chatContainer = document.getElementById('chat-container');
+                const systemMessage = document.createElement('div');
+                systemMessage.classList.add('message', 'assistant-message');
+                systemMessage.innerHTML = `News articles related to "${query}" have been fetched and analyzed. You can now ask questions about them.`;
+                chatContainer.appendChild(systemMessage);
+                chatContainer.scrollTop = chatContainer.scrollHeight;
+            })
+            .catch(err => {
+                console.error(err);
+                document.getElementById('news-results').innerHTML = 'Error fetching news.';
+            })
+            .finally(() => {
+                document.getElementById('loading').style.display = 'none';
+            });
+        }
+
+        function sendMessage() {
+            const queryInput = document.getElementById('query');
+            const messageText = queryInput.value.trim();
+            if (messageText === '') {
+                return;
+            }
+
+            const chatContainer = document.getElementById('chat-container');
+
+            const userMessage = document.createElement('div');
+            userMessage.classList.add('message', 'user-message');
+            userMessage.innerText = messageText;
+            chatContainer.appendChild(userMessage);
+
+            queryInput.value = '';
+
+            const assistantMessage = document.createElement('div');
+            assistantMessage.classList.add('message', 'assistant-message');
+            chatContainer.appendChild(assistantMessage);
+
+            chatContainer.scrollTop = chatContainer.scrollHeight;
+
+            document.getElementById('loading').style.display = 'block';
+
+            let requestBody = {
+                query: messageText,
+                role: currentRole,
+                file_id: currentFileId
+            };
+
+            if (currentRole === 'AI News Analyst' && newsData) {
+                requestBody.newsContext = newsData;
+            }
+
+            fetch('/query', {
+                method: 'POST',
+                headers: {
+                    'Content-Type': 'application/json',
+                },
+                body: JSON.stringify(requestBody),
+            })
+            .then(response => response.json())
+            .then(data => {
+                const formattedResponse = marked.parse(data.response);
+                assistantMessage.innerHTML = formattedResponse;
+                chatContainer.scrollTop = chatContainer.scrollHeight;
+            })
+            .catch(err => {
+                assistantMessage.innerText = 'Error: Unable to fetch response.';
+                console.error(err);
+            })
+            .finally(() => {
+                document.getElementById('loading').style.display = 'none';
+            });
+        }
+
+        function startNewChat() {
+            currentRole = null;
+            currentFileId = null;
+            updateContextInfo();
+            const chatContainer = document.getElementById('chat-container');
+            chatContainer.innerHTML = '';
+        }
+
+        function uploadFile() {
+            const fileInput = document.getElementById('file-input');
+            const file = fileInput.files[0];
+            if (file) {
+                const formData = new FormData();
+                formData.append('file', file);
+
+                const chatContainer = document.getElementById('chat-container');
+                const userMessage = document.createElement('div');
+                userMessage.classList.add('message', 'user-message');
+                userMessage.innerText = `Uploaded file: ${file.name}`;
+                chatContainer.appendChild(userMessage);
+
+                const assistantMessage = document.createElement('div');
+                assistantMessage.classList.add('message', 'assistant-message');
+                assistantMessage.innerHTML = 'Processing file...';
+                chatContainer.appendChild(assistantMessage);
+
+                chatContainer.scrollTop = chatContainer.scrollHeight;
+
+                document.getElementById('loading').style.display = 'block';
+
+                fetch('/upload', {
+                    method: 'POST',
+                    body: formData
+                })
+                .then(response => response.json())
+                .then(data => {
+                    if (data.error) {
+                        throw new Error(data.error);
+                    }
+                    currentFileId = data.file_id;
+                    updateContextInfo();
+                    const formattedAnalysis = marked.parse(data.analysis);
+                    assistantMessage.innerHTML = formattedAnalysis;
+                    chatContainer.scrollTop = chatContainer.scrollHeight;
+                })
+                .catch(err => {
+                    assistantMessage.innerText = 'Error: Unable to process file.';
+                    console.error(err);
+                })
+                .finally(() => {
+                    document.getElementById('loading').style.display = 'none';
+                });
+            }
+        }
+        function startNewChat() {
+            currentRole = null;
+            currentFileId = null;
+            newsData = null;
+            updateContextInfo();
+            const chatContainer = document.getElementById('chat-container');
+            chatContainer.innerHTML = '';
+            document.getElementById('chat-container').style.display = 'block';
+            document.getElementById('news-container').style.display = 'none';
+            document.getElementById('news-query').value = '';
+            document.getElementById('market-summary').innerHTML = '';
+            document.getElementById('news-results').innerHTML = '';
+        }
+
+        // Add event listener for Enter key in the input field
+        document.getElementById('query').addEventListener('keypress', function(e) {
+            if (e.key === 'Enter') {
+                sendMessage();
+            }
+        });
+
+        // Initialize the UI
+        updateContextInfo();
+    </script>
+</body>
+</html>

uploads/Check_Survey_Name_11.csv

@@ -0,0 +1,14 @@
+Country,ES_ID,Surveys,ADM_Survey Name,ADM_Alternate Name,Dummy,Year
+United States,1000000000838,US_Seismic_2D,US-Seismic-2D,,N,2005
+United States,1000000000839,US_Seismic_2D,US-Seismic-2D,,N,2006
+United States,1000000000840,US_Seismic_2D,US-Seismic-2D,,N,2007
+United States,1000000000841,US_Seismic_2D,US-Seismic-2D,,N,2005
+United States,1000000000842,US_Seismic_2D,US-Seismic-2D,,N,2009
+United States,1000000000843,US_Seismic_2D,US-Seismic-2D,,N,2010
+United States,1000000000844,US_Seismic_2D,US-Seismic-2D,,N,2011
+United States,1000000000845,US_Seismic_2D,US-Seismic-2D,,N,2010
+United States,1000000000846,US_Seismic_2D,US-Seismic-2D,,N,2010
+United States,1000000000847,US_Seismic_2D,US-Seismic-2D,,N,2014
+United States,1000000000848,US_Seismic_2D,US-Seismic-2D,,N,2015
+United States,1000000000849,US_Seismic_2D,US-Seismic-2D,,N,2019
+United States,1000000000850,US_Seismic_2D,US-Seismic-2D,,N,2020