Update app.py

app.py

@@ -77,17 +77,17 @@ def display_projects():
 
     # Define tab titles
     tab_titles = [
-        "Squat Easy", 
-        "ASL Translator", 
-        "Face Recognition", 
-        "Stock Market Chatbot", 
-        "Twitter Trend Analysis", 
-        "Restaurant Recommendation System", 
-        "Bitcoin Lightning Path Optimization",
-        "National Infrastructure Monitoring",
+        "Resume & CV Crafter",
+        "Multi-Agent Job Search",
+        "Resume Easz",
         "Job Easz",
-        "Prompt Easz",
-        "Resume_Easz"
+        "Bitcoin Lightning Optimization",
+        "National Infrastructure Monitoring",
+        "Stock Market Analysis",
+        "Twitter Trend Analysis",
+        "Restaurant Recommendation",
+        "ASL Translator",
+        "Squat Easy"
     ]
 
     # Create tabs
@@ -95,145 +95,185 @@ def display_projects():
 
     # Add content to each tab
     with tabs[0]:
-        st.header("Squat Easy")
+        st.header("LLM-powered Resume & CV Crafter")
         st.markdown("""
-        - **Description**: Engineered a custom BiLSTM architecture in PyTorch with extensive hyperparameter tuning, achieving 81% training and 75% test accuracy in classifying six types of squatting errors from video data. Optimized through data augmentation and CUDA-based GPU acceleration.
-        - **Technologies Used**: PyTorch, Object-Oriented Programming (OOP), GitHub
-        - **Reference**: [Link to Project](https://github.com/niharpalem/squateasy_DL)
+        - **Description**: Developed AI platform combining LLaMA-3 70B and Deepseek R1 with low-temperature settings for stable, tailored resume and CV generation
+        - **Key Features**:
+            • Smart Matching Algorithm analyzing profiles against job requirements
+            • LaTeX-Powered Resumes with professional formatting
+            • Automated 4-paragraph Cover Letter Generation
+            • Performance Metrics evaluating match quality
+        - **Technical Achievements**:
+            • Implemented dual-agent architecture: LLaMA-3 8B for profile analysis and 70B for LaTeX generation
+            • Engineered JSON schema validation system for error-free template integration
+            • Achieved 5,000+ LinkedIn impressions with 80% reduction in creation time
+        - **Technologies**: Streamlit, GROQ API (LLaMA-3 70B), LaTeX, JSON Schema
+        - **Reference**: [Link to Project](https://huggingface.co/spaces/Niharmahesh/Resume_and_CV_crafter)
         """)
 
     with tabs[1]:
-        st.header("ASL Translator")
+        st.header("Multi-Agent Job Search System")
         st.markdown("""
-        - **Description**: Crafted a ASL translation system using MediaPipe for point detection and trained a Random Forest Model , achieving 95% accuracy in real-time gesture interpretation. Implemented an adaptive hand skeleton GIF generator for intuitive visual representation.
-        - **Technologies Used**: MediaPipe Hand Detection, Hugging Face Platform
-        - **Reference**: [Link to Project](https://huggingface.co/spaces/Niharmahesh/slr-easz)
+        - **Description**: Built an AI-powered job search assistant using dual-LLaMA architecture for comprehensive job matching and analysis
+        - **Key Features**:
+            • Real-time scraping across LinkedIn, Glassdoor, Indeed, ZipRecruiter
+            • Advanced resume parsing and job matching
+            • Intelligent compatibility scoring system
+        - **Technical Achievements**:
+            • Developed batch processing pipeline handling 60+ positions/search
+            • Reduced job search time by 80% through accurate matching
+            • Implemented specialized agents for input processing, scraping, and analysis
+        - **Technologies**: GROQ API, jobspy, Streamlit, Pandas, LLMOps
+        - **Reference**: [Link to Project](https://huggingface.co/spaces/Niharmahesh/Multi_Agent_Job_search_and_match)
         """)
 
     with tabs[2]:
-        st.header("Face Recognition")
+        st.header("Resume Easz")
         st.markdown("""
-        - **Description**: Integrated fiducial point features, CNN-extracted image features, and Siamese networks in TensorFlow, attaining 85% test accuracy for facial recognition. Optimized for real-world security applications by balancing computational efficiency with accuracy.
-        - **Technologies Used**: TensorFlow, Siamese Networks
-        - **Reference**: [Link to Project](#)
+        - **Description**: Created an AI-driven resume analysis and enhancement tool using LLaMA 3.3 model
+        - **Key Features**:
+            • Quick and in-depth resume analysis options
+            • Comprehensive skill gap analysis
+            • ATS compatibility optimization
+            • Multiple output formats (DOCX, HTML, TXT)
+        - **Technical Implementation**:
+            • Integrated GROQ API for advanced language processing
+            • Built visual diff system for resume changes
+            • Developed custom prompt engineering pipeline
+        - **Technologies**: GROQ API, Streamlit, Python, LLM
+        - **Reference**: [Link to Project](https://resume-easz.streamlit.app/)
         """)
 
     with tabs[3]:
-        st.header("Stock Market Chatbot")
+        st.header("Job Easz")
         st.markdown("""
-        - **Description**: Architected a multilingual stock analysis system using Apache Spark and a custom LLM, boosting query performance by 25% over traditional SQL approaches. Interfaced with Snowflake for efficient financial data retrieval and real-time insights in English and Chinese.
-        - **Technologies Used**: PySpark for Querying, Data Warehousing with Redshift and Snowflake
-        - **Reference**: [Link to Project](#)
+        - **Description**: Engineered comprehensive job aggregation platform for data roles with advanced analytics
+        - **Technical Achievements**:
+            • Designed Airflow pipeline with exponential backoff retry (120-480s intervals)
+            • Optimized concurrent processing reducing runtime from 2h to 40min
+            • Processes ~3000 daily job listings across various data roles
+        - **Key Features**:
+            • Daily updates with comprehensive job role coverage
+            • Custom filtering by role and location
+            • Interactive dashboard for market trends
+            • Automated ETL pipeline
+        - **Technologies**: Python, Airflow, ThreadPoolExecutor, Hugging Face Datasets
+        - **Reference**: [Link to Project](https://huggingface.co/spaces/Niharmahesh/job_easz)
         """)
 
     with tabs[4]:
-        st.header("Twitter Trend Analysis")
+        st.header("Bitcoin Lightning Path Optimization")
         st.markdown("""
-        - **Description**: Engineered an ELT pipeline using GCP's BigQuery for Twitter data processing and sentiment analysis. Integrated Tableau for live, interactive dashboards, showcasing advanced cloud data engineering skills and cost-effective data storage solutions.
-        - **Technologies Used**: Apache Airflow for Automation, Docker, Tableau for Dashboards
-        - **Reference**: [Link to Project](#)
+        - **Description**: Advanced payment routing optimization system for Bitcoin Lightning Network
+        - **Technical Achievements**:
+            • Developed ML classifiers achieving 98.77-99.10% accuracy
+            • Implemented tri-model consensus system for optimal routing
+            • Engineered ensemble models with 0.98 F1-scores
+        - **Implementation Details**:
+            • Created simulation environment for multi-channel transactions
+            • Optimized graph-based algorithms for payment routing
+            • Integrated with Lightning payment interceptor
+        - **Technologies**: XGBoost, Random Forest, AdaBoost, Graph Algorithms
         """)
 
     with tabs[5]:
-        st.header("Restaurant Recommendation System")
+        st.header("National Infrastructure Monitoring")
         st.markdown("""
-        - **Description**: Engineered a recommendation engine using collaborative and content-based filtering, achieving a 15% accuracy increase. Constructed a Flask web app with Folium integration for an interactive, location-based restaurant suggestion interface.
-        - **Technologies Used**: Collaborative Filtering, Content-Based Filtering
-        - **Reference**: [Link to Project](#)
+        - **Description**: Developed satellite imagery analysis system for infrastructure change detection
+        - **Technical Achievements**:
+            • Fine-tuned ViT+ResNet-101 ensemble on 40GB satellite dataset
+            • Achieved 85% accuracy in change detection
+            • Implemented 8 parallel GPU threads for enhanced performance
+        - **Key Features**:
+            • Temporal analysis with 1km resolution
+            • Interactive map interface with bounding box selection
+            • Automatic image chipping for 256x256 inputs
+            • Contrast adjustment optimization
+        - **Technologies**: Change ViT Model, Google Earth Engine, PyTorch, Computer Vision
+        - **Reference**: [Link to Project](https://huggingface.co/spaces/Niharmahesh/Data298)
         """)
 
     with tabs[6]:
-        st.header("Bitcoin Lightning Path Optimization")
+        st.header("Stock Market Analysis with OpenAI Integration")
         st.markdown("""
-        - **Description**: Implemented a graph-based algorithm to optimize payment routing in the Bitcoin Lightning Network. Created a simulation environment to validate improved efficiency in multi-channel transactions under various network conditions.
-        - **Technologies Used**: Graph-Based Algorithms, Simulation Environments
-        - **Reference**: [Link to Project](#)
+        - **Description**: Created comprehensive stock market analysis system with multilingual capabilities
+        - **Technical Achievements**:
+            • Built Spark streaming pipeline with 30% efficiency improvement
+            • Orchestrated Airflow Docker pipeline for Snowflake integration
+            • Developed bilingual GPT-3.5 chatbot for SQL query generation
+        - **Key Features**:
+            • Real-time financial metric calculations
+            • Custom indicator generation
+            • Multilingual query support
+            • Automated data warehousing
+        - **Technologies**: PySpark, Apache Airflow, Snowflake, OpenAI GPT-3.5
         """)
 
     with tabs[7]:
-        st.header("National Infrastructure Monitoring")
+        st.header("Twitter Trend Analysis")
         st.markdown("""
-        - **Description**: Utilized satellite imagery to detect changes between different time frames by fine-tuning a Change ViT model. Developed a UI where users can draw bounding boxes on a Python map library; these coordinates are used in Google Earth Engine (GEE) to extract Sentinel-2 imagery. Users can select the resolution of images for caching. The processing function includes contrast adjustments and automatic image chipping as the model requires 256x256 inputs, generating change masks effectively.
-        - **Technologies Used**: Satellite Imagery Analysis, Change ViT Model, Google Earth Engine (GEE), Python Map Libraries
-        - **Reference**: [Link to Project](https://huggingface.co/spaces/Niharmahesh/Data298)
+        - **Description**: Engineered comprehensive Twitter analytics platform using GCP services
+        - **Technical Achievements**:
+            • Developed GCP pipeline processing 40k tweets
+            • Achieved 40% efficiency improvement through custom Airflow operators
+            • Implemented real-time trend analysis algorithms
+        - **Key Features**:
+            • Automated ETL workflows
+            • Interactive Tableau dashboards
+            • Viral metrics tracking
+            • Engagement rate calculations
+        - **Technologies**: Google Cloud Platform, BigQuery, Apache Airflow, Tableau
         """)
+
     with tabs[8]:
-        st.header("JobEasz: Data Job Search Platform")
+        st.header("Restaurant Recommendation System")
         st.markdown("""
-        - **Description**: Developed a comprehensive job aggregation platform for data-related roles, leveraging advanced data engineering techniques to streamline the job search process. The platform unifies listings from major job sites, provides daily updates, and offers real-time market trend visualizations.
-        - **Technologies Used**: Python for Web Scraping, PyArrow & Pandas for Data Processing, Hugging Face Datasets for Storage, Streamlit for Frontend, Plotly for Visualization
+        - **Description**: Built hybrid recommendation system combining multiple filtering approaches
+        - **Technical Achievements**:
+            • Created hybrid TF-IDF and SVD-based filtering system
+            • Achieved 43% improvement in recommendation relevance
+            • Reduced computation time by 65%
         - **Key Features**:
-            • Daily updates with ~3000 jobs across various data roles in the US
-            • Custom filtering by role and location
-            • Direct application links to original postings
-            • Automated ETL pipeline for data extraction and processing
-            • Cloud-based storage for scalability and performance
-        - **Data Engineering Highlights**:
-            • Efficient data parsing and processing using PyArrow
-            • Scalable data storage and retrieval with Hugging Face Datasets
-            • Real-time data transformation and interactive visualizations
-        - **Skills**: Web Scraping, Python, Streamlit, Hugging Face, ETL, Data Cleaning, Dashboard Building
-        - **Reference**: [Link to Project](https://huggingface.co/spaces/Niharmahesh/job_easz)
+            • Location-based suggestions
+            • Personalized recommendations
+            • Interactive web interface
+            • Efficient matrix factorization
+        - **Technologies**: Collaborative Filtering, Content-Based Filtering, Flask, Folium
         """)
+
     with tabs[9]:
-        st.header("Prompt Easz")
+        st.header("ASL Translator")
         st.markdown("""
-    - **Description**: Developed a prompt converter using sentence transformers to tailor prompts based on predefined styles (e.g., ELI5, chain of thoughts, role play). The tool aims to make learning new topics less overwhelming by providing customized prompts.
-    - **Technologies Used**: Sentence Transformers, Cosine Similarity, Vector Embeddings, Google's all-MiniLM-L6-v2 model
-    - **Key Features**:
-        - Converts user prompts to vector embeddings
-        - Suggests updated prompts based on similarity to predefined styles
-        - Offers 10 main prompt types with 3-4 variations each
-        - Covers 10 predefined categories
-        - Allows users to customize prompt strength and style
-    - **Reference**: [Link to Project](https://huggingface.co/spaces/Niharmahesh/PromptEasz)
-    """)
+        - **Description**: Developed real-time American Sign Language translation system
+        - **Technical Achievements**:
+            • Achieved 95% accuracy in real-time gesture interpretation
+            • Implemented adaptive hand skeleton GIF generator
+            • Optimized MediaPipe integration for point detection
+        - **Key Features**:
+            • Real-time hand tracking
+            • Visual feedback system
+            • Intuitive gesture recognition
+            • Accessible interface
+        - **Technologies**: MediaPipe Hand Detection, Random Forest, Hugging Face Platform
+        - **Reference**: [Link to Project](https://huggingface.co/spaces/Niharmahesh/slr-easz)
+        """)
+
     with tabs[10]:
-        st.header("Resume Easz")
+        st.header("Squat Easy")
         st.markdown("""
-    **Resume Easz**: An LLM-powered application for resume analysis and enhancement
-
-    Resume Easz is an innovative AI-driven tool that analyzes and enhances resumes based on job descriptions. Leveraging the power of prompt engineering and the GROQ API, it utilizes the versatile Llama 3.3 model to provide comprehensive resume analysis and improvement.
-
-    **Key Features**:
-    - Upload DOCX resumes for analysis
-    - Input job descriptions for targeted optimization
-    - Quick or in-depth analysis options
-    - AI-enhanced resume generation
-    - Multiple output formats (DOCX, HTML, TXT)
-
-    **Analysis Types**:
-    1. **Quick Analysis**:
-        - Skills Match: Top 5 required skills with proficiency ratings
-        - Experience Alignment: Comparison of required vs. demonstrated experience
-        - Pros and Cons: Top 3 strengths and areas for improvement
-        - Match Percentage: Overall compatibility score with explanation
-    2. **In-Depth Analysis**:
-        - Comprehensive Skill Gap Analysis
-        - Detailed Experience and Impact Analysis
-        - Content Enhancement Recommendations
-        - Strategic Recommendations for Competitive Edge
-        - Application Strategy Suggestions
-    3. **Resume Enhancement**:
-        - Optimizes content based on analysis
-        - Improves formatting and structure
-        - Highlights key achievements and skills
-        - Ensures ATS compatibility
-
-    **User Experience**:
-    - Intuitive Streamlit interface
-    - Visual diff to highlight resume changes
-    - Multiple download options (DOCX, HTML, TXT)
-
-    **Limitations**:
-    - GROQ API token limit (100,000 tokens per model)
-    - Potential wait times for API rate limits
-
-    This powerful tool streamlines the job application process by providing tailored resume optimization, increasing candidates' chances of success in their job search.
-     - **Reference**: [Link to Project](https://resume-easz.streamlit.app/)
-""")
-
-
+        - **Description**: Developed deep learning system for squat form analysis and error detection
+        - **Technical Achievements**:
+            • Engineered custom BiLSTM architecture in PyTorch
+            • Achieved 81% training and 75% test accuracy
+            • Implemented CUDA-based GPU acceleration
+        - **Key Features**:
+            • Real-time form analysis
+            • Six-type error classification
+            • Video processing pipeline
+            • Performance optimization
+        - **Technologies**: PyTorch, BiLSTM, CUDA, Object-Oriented Programming
+        - **Reference**: [Link to Project](https://github.com/niharpalem/squateasy_DL)
+        """)
 def display_skills():
     st.markdown('## Skills')
     st.write("""