Update resume.py

resume.py

@@ -1,199 +1,171 @@
-data = '''
-# **SARATH CHANDRA BANDREDDI**
-
+data ="""# **SARATH CHANDRA BANDREDDI** 
 ---
-
 ## **PROFESSIONAL SUMMARY**
-> **Python Developer** focused on AI and Django. Skilled in Python, AI development, and building robust web applications. Dedicated to continuous learning and staying updated with the latest industry trends and technologies. Eager to contribute to innovative software solutions and work collaboratively in a team environment.
+> **AI Engineer Intern** experienced in Python, AI, and Django. Skilled in building full-stack intelligent systems, developing RAG pipelines, working with LLMs, and integrating cutting-edge tools like LangGraph, LlamaIndex, and Gemini. Passionate about crafting impactful AI applications with security and scalability in mind.
 
 ---
-
 ## **TECH STACK**
 - **Languages**: Python, Java, JavaScript, C, R
 - **Scripting**: Shell Scripting
 - **Markup Languages**: HTML, CSS, Jinja Coding
 - **Operating Systems**: Linux, Windows
-- **IDE Tools**: VS Code, RStudio, Pycharm
-- **Libraries/Frameworks**: TensorFlow, Keras, LlamaIndex, Ollama, OpenCV, Sklearn, Numpy, Pandas, Django
+- **IDE Tools**: VS Code, RStudio, PyCharm
+- **Libraries/Frameworks**: TensorFlow, Keras, LlamaIndex, LangChain, LangGraph, Ollama, OpenCV, Sklearn, Pandas, Django, Gradio
 - **Tools / Platforms**: Kaggle, Google Colabs, Git, GitHub, AWS, Figma
-- **Databases**: Oracle, MySQL
-
+- **Databases**: Oracle, MySQL, MongoDB Atlas
 ---
-
 ## **EDUCATION PROFILE**
 | Course                     | Institution                      | CGPA | Duration   |
 |----------------------------|----------------------------------|------|------------|
-| B.Tech-CSE (AI & ML)       | VVIT - Vasireddy Venkatadri      | 8.59 | 2021-2025  |
+| B.Tech-CSE (AI & ML)       | VVIT - Vasireddy Venkatadri      | 8.72 | 2021-2025  |
 | 12th Class                 | Narayana Junior College          | 9.22 | 2020-2021  |
 | 10th Class                 | Narayana High School             | 9.7  | 2018-2019  |
-
 ---
-
 ## **PROJECTS**
 To know more on particular project just ask My2.0
-### 0. [Celebrity Recognition](https://sarath0x8f-ocr-translator.hf.space) (Individual Project)
-- **Technologies**: Tensorflow, Keras, OpenCV, Django
-- **Description**: Developed a face recognition application utilizing the VGGFace architecture with TensorFlow, achieving exceptional accuracy on a 29-class dataset. The system was deployed via Hugging Face.
-<!--- (Developed a face recognition application utilizing the VGGFace architecture with TensorFlow, attaining exceptional accuracy on 
-        a bespoke 29-class dataset. Launched the system through Hugging face space on an online server, showcasing advanced 
-        capabilities in artificial neural networks and computer vision. Check the live application ("live-exegution-link:https://huggingface.co/spaces/Sarath0x8f/Celebrity_Recognition").
-        Leveraged advanced facial recognition techniques using a custom dataset created to simulate real-world conditions and developed Celebrity Recognition Application. 
-        Utilized data augmentation strategies, including shear, zoom, rotation, and brightness adjustments, to enhance model robustness. 
-        Implemented transfer learning with the VGGFace model to accelerate training and improve accuracy to 98, incorporating custom fully connected layers and freezing certain layers for optimal performance. 
-        Explored various optimizers (Adam, Adagrad, RMSprop) to optimize the model, demonstrating the critical role of optimizer selection in deep learning tasks. Integrated advanced training callbacks, such as EarlyStopping and ReduceLROnPlateau, 
-        to prevent overfitting and ensure efficient training processes. Conducted thorough evaluations of the model on training and validation datasets, achieving significant improvements in loss and accuracy metrics. 
-        Developed a deep understanding of data handling, model architecture customization, and training strategies, contributing to a more effective facial recognition model. 
-        Looking forward to further advancements in the field of deep learning and facial recognition.
-        - Mastered creating custom datasets using OpenCV, organizing training and test sets, and achieving 97.86% accuracy.
-        - Trained deep learning models for image classification, leading to the publication of two papers in peer-reviewed journals 
-        focusing on advancements in facial recognition technology.
-        --->
-- **Key Contributions**:
-    - Achieved 97.86% accuracy using custom datasets.
-    - Implemented advanced data augmentation and transfer learning techniques.
-    - Integrated optimization strategies for enhanced model performance.
-    - [Note book link](https://www.kaggle.com/code/sarath02003/face-recognition-using-vggface2)
 
 ### 1. [DearHRSpeakWithMy2.0](https://sarath0x8f-dearhrspeakwithmy2-0.hf.space) (Individual Project)
-- **Technologies**: Hugging Face, Gradio, Python, NLP
-- **Description**: Designed an AI-powered HR interview chatbot that showcases candidate skills and experience professionally.
+- **Technologies**: Hugging Face, Gradio, Python, LLaMA-3-8B, NLP
+- **Description**: Developed a personalized HR interview chatbot that represents the user’s profile, projects, and strengths.
+- **Key Contributions**:
+    - Implemented structured Q&A to reflect candidate personality and readiness.
+    - Hosted on Hugging Face using LLaMA-3 model for real-time interactions.
+<!--- Built to simulate HR interviews with highly personalized answers from LLaMA-3 on Hugging Face Spaces. 
+     Provides interactive Q&A aligned with resume content. Uses Gradio UI and NLP techniques to structure questions, 
+     extract insights, and maintain context across sessions. Designed for demoing AI interview readiness. --->
+
+---
+
+### 2. [Document Query AI Agent](https://sarath0x8f-document-qa-bot.hf.space) (Individual Project)
+- **Technologies**: LlamaIndex, Vector Embeddings, Gradio, Hugging Face
+- **Description**: A file-based chatbot using RAG for document-specific intelligent answers.
+- **Key Contributions**:
+    - Used multiple embedding models and LLMs including Mistral, LLaMA.
+    - Resilient retry mechanism for document parsing failures.
+<!--- Enables real-time semantic search over uploaded documents using RAG. Supports .pdf, .docx, .csv, etc. 
+     Uses LlamaIndex for indexing and retrieval, and HuggingFace models for generation. Modular UI allows model-switching. 
+     Optimized for LLM-assisted document understanding and Q&A. --->
+
+---
+
+### 3. [AI Agent Nexus](https://huggingface.co/spaces/Sarath0x8f/AI-Agents-using-CrewAI) (Individual Project)
+- **Technologies**: Gemini, CrewAI, Serper API, LangChain
+- **Description**: Multi-agent platform for SEO content, game dev, and automation.
 - **Key Contributions**:
-    - Implemented Q&A functionality for accurate candidate profiling.
-    - Integrated meta-llama/Meta-Llama-3-8B-Instruct on Hugging Face.
-    - Structured to emphasize job-relevant strengths and career goals.
-<!--- (Designed an AI-powered chatbot for HR interview support, DearHRSpeakWithMy2.0 serves as a virtual personal assistant for me, 
-presenting detailed insights about the candidate's skills, projects, and experience in a structured, professional format. The bot 
-was inspired by real-world interview experiences where candidates’ key skills in AI/ML were sometimes overlooked. 
-DearHRSpeakWithMy2.0 enhances communication by emphasizing critical, job-relevant details. 
-• Implemented robust question-and-answer functionality, ensuring that the chatbot responds in alignment with the 
-candidate’s profile and objectives.  
-• Integrated on Hugging Face with meta-llama/Meta-Llama-3-8B-Instruct, enabling a tailored and interactive experience through Gradio.  
-• Strategically designed to guide the conversation towards the candidate's strengths and to clarify their career goals, avoiding 
-misalignment in interview focus.)--->
-
-### 2. [The Linguistic Lens Application](https://sarath0x8f-ocr-translator.hf.space) (Individual Project)
-- **Technologies**: Gradio, PaddleOCR, GoogleTranslator, gTTS
-- **Description**: Developed a platform for OCR, translation, and TTS to aid multilingual communication.
+    - Automated SEO content agent and real-time data extractor.
+    - Game development agent supporting multi-level logic testing.
+<!--- Designed as a modular multi-agent AI suite using CrewAI and LangChain. 
+     Includes agents for writing SEO-optimized blog posts, generating game logic, and marketing automation.
+     Showcases practical agentic architecture with workflow handling, using Gemini LLMs and Serper for web search. --->
+
+---
+
+### 4. [SCRAM](https://github.com/21bq1a4210/E2E_Project) (Minor Project)
+- **Technologies**: Gemini LLM, Django, TensorFlow, OpenCV, Keras
+- **Description**: End-to-end campus management system with secure login and facial attendance.
 - **Key Contributions**:
-    - Utilized PaddleOCR, GoogleTranslator, and gTTS for comprehensive text and audio support.
-    - Designed a scalable, modular structure for easy user adaptability.
-    - Enhanced accessibility through integrated OCR and TTS modules.
-<!--- ((OCR), translation, and text-to-speech (TTS) features. The user-friendly interface, built with Gradio, allows users to upload images 
-for real-time text extraction, translation, and audio playback.  
-• Utilized PaddleOCR for precise text extraction, GoogleTranslator for wide-ranging language support, and gTTS for clear 
-audio conversion in multiple languages.  
-• Created a scalable, modular architecture enabling seamless user experiences and adaptability, enhancing accessibility for 
-multilingual interactions.  
-• Designed to provide practical on-the-go linguistic assistance, supporting robust language processing through integrated OCR 
-and TTS modules.)--->
-
-### 3. [Document Query AI Agent](https://sarath0x8f-document-qa-bot.hf.space) (Individual Project)
-- **Technologies**: LLMs, Vector Embeddings , LlamaIndex
-- **Description**: Developed an AI agent for document-based Q&A, integrating LlamaIndex for efficient data retrieval.
-<!---(Welcome to the Document QA Bot, a sophisticated Retrieval-Augmented Generation (RAG) application that utilizes LlamaIndex and Hugging Face models to answer questions based on documents you upload. This bot is designed to empower you with rapid, insightful responses, providing a choice of language models (LLMs) and embedding models that cater to various requirements, including performance, accuracy, and response time.
-
-✨ Application Overview
-With Document QA Bot, you can interactively query your document, receive contextual answers, and dynamically switch between LLMs as needed for optimal results. The bot supports various file formats, allowing you to upload and analyze different types of documents and even some image formats.
-
-Key Features
-Choice of Models: Access a list of powerful LLMs and embedding models for optimal results.
-Flexible Document Support: Multiple file types supported, including images.
-Real-time Interaction: Easily switch between models for experimentation and fine-tuning answers.
-User-Friendly: Seamless experience powered by Gradio's intuitive interface.
-📂 Supported File Formats
-The bot supports a range of document formats, making it versatile for various data sources. Below are the currently supported formats:
-Documents: .pdf, .docx, .doc, .txt, .csv, .xlsx, .pptx, .html
-Images: .jpg, .jpeg, .png, .webp, .svg
-LLMs - mistralai/Mixtral-8x7B-Instruct-v0.1, meta-llama/Meta-Llama-3-8B-Instruct, mistralai/Mistral-7B-Instruct-v0.2
-, tiiuae/falcon-7b-instruct
-Vector embeddings - BAAI/bge-large-en, BAAI/bge-small-en-v1.5, NeuML/pubmedbert-base-embeddings, sentence-transformers/all-mpnet-base-v2
-, BAAI/llm-embedder
-) --->
+    - Built one-shot face recognition attendance system with MTCNN + FaceNet.
+    - Integrated chatbot using Gemini and Google API.
+    - Secured login with two-step verification.
+<!--- Developed complete Django backend for user and complaint management. 
+     Integrated real-time attendance with face recognition using deep learning. 
+     Chatbot AskVVIT helps with college queries. Project prioritizes secure, modular access to academic resources. --->
+
+---
+
+### 5. [Epic-Minds](https://huggingface.co/spaces/Sarath0x8f/Epic-Minds) (Individual Project)
+- **Technologies**: Gemini Flash, MongoDB, LlamaIndex, Hugging Face
+- **Description**: Built RamayanaGPT and GitaGPT for spiritual Q&A using vector databases.
 - **Key Contributions**:
-    - Created resilient query retry mechanisms for robust document parsing.
-
-### 4. SCRAM - Secure Campus Resource and Access Management (Minor Project)
-- **Technologies**: Gemini-pro (LLM), Google API, TensorFlow, Keras, OpenCV, Django
-- **Description**: Developed a Django-based system for campus resource management, including features like user management, complaint registration, face recognition attendance, and a chatbot.
-<!--- (Engineered a robust, secure Django-based system for comprehensive college resource and access management, incorporating 
-        advanced features such as user management, complaint registration, and a chatbot assistant. Seamlessly integrated Gemini-Pro 
-        LLM with Google API and introduced face recognition technology for enhanced attendance tracking.
-        Led the development of a robust and secure Django-based system designed to streamline college resource and access management as part of my End-to-End Project. The platform integrates several key functionalities such as user management, complaint registration, attendance management system, and a chatbot assistant.
-        Here are my contribution to the project:
-        - User Authentication & Security: Developed a comprehensive user authentication system using Django's default authentication and implemented 2-Step Verification (2SV) for password recovery, improving overall system security and reliability. Engineered a single-page application for password recovery with two-step verification, enhancing user convenience.
-        - Face Recognition Attendance System: Created a one short face recognition model using FaceNet and MTCNN to manage attendance, with a unique feature allowing students to mark their attendance only once per day and within the campus premises. This innovation ensures strict attendance integrity and security.
-        - Chatbot Integration: Built and integrated the AskVVIT chatbot to assist with college-related inquiries. Initially deployed with the Gemini Pro LLM and Google API, the chatbot provided an interactive platform for students and staff. Due to response time limitations (one response per minute), the model was later replaced with LLaMA 3.2:1B and also tried with LLaMA 3:latest, significantly enhancing response efficiency.
-        - Backend & Django: Developed Django templates using Jinja and integrating frontend pages with backend functionality. Created models for user registration and attendence management system.
-
-        This project not only enhanced resource management at the college but also introduced modern technologies such as face recognition and AI-driven chatbots, setting a foundation for future advancements in academic institution management systems. 
-        • Devised robust user authentication and 2-FS password authentication, enhancing system security and reliability.
-        • Led the project team, developing comprehensive Django templates, seamlessly integrating custom chatbot functionalities 
-        using LLM and created a one short face recognition for attendance management system .) --->
+    - Scriptural QA system with RAG + multilingual-e5 embeddings.
+    - Integrated structured prompts and query logs for analysis.
+<!--- Developed vector store for Valmiki Ramayana and Bhagavad Gita. 
+     Combined Gemini Flash for responses and MongoDB Atlas for vector index. 
+     Modular structure with multilingual embedding support and UI for exploration. --->
+
+---
+
+### 6. [AI Assistant for PC] (Work in Progress)
+- **Technologies**: LangChain, Custom Agents, File/Info/Web Servers
+- **Description**: Creating a modular personal assistant for desktop automation.
 - **Key Contributions**:
-    - Created a one short face recognition attendance system.
-    - Integrated chatbot using LLaMA 3 and Google API.
-    - Developed secure user authentication with 2SV.
-    - [GitHub Repo]((https://github.com/21bq1a4210/E2E_Project/graphs/contributors))
-
-### 5. [Personal Portfolio](https://21bq1a4210.github.io/MyPortfolio-) (Individual Project)
-- **Technologies**: HTML, CSS, JavaScript
-- **Description**: Designed a responsive personal portfolio showcasing my projects and skills, deployed using GitHub Pages.
-<!--- (Designed and developed a responsive personal portfolio("LINK:https://21bq1a4210.github.io/MyPortfolio-/") website using HTML, CSS, and JavaScript, showcasing strong UI/UX principles. Deployed the website online using GitHub Pages, making it accessible for users worldwide. The website features multiple sections, including Home, About, Services, Portfolio, and Contact, providing a comprehensive overview of my skills and projects. Implemented interactive elements like a contact form integrated with EmailJS for seamless communication and added an AI chatbot, Tidio's Lyro, to enhance user engagement and provide additional information about me. Crafted unique visuals using AI-generated images to personalize the portfolio and demonstrate creativity. This project ignited my interest in web development, transforming initial reluctance into enthusiasm for building dynamic and interactive web experiences.) --->
+    - Custom file_server and info_server architecture.
+    - Context-aware response engine and file management tools.
+<!--- An agentic system for local PC automation tasks like file management, search, alerts. 
+     Designed to combine LangChain-based logic with system-level scripts. 
+     Still expanding with more intelligent task routing agents. --->
+
+---
+
+### 7. [Celebrity Recognition](https://huggingface.co/spaces/Sarath0x8f/Celebrity_Recognition?logs=container) (Individual Project)
+- **Technologies**: VGGFace, TensorFlow, Keras, OpenCV
+- **Description**: Real-time celebrity classifier trained on 29 classes with VGGFace.
 - **Key Contributions**:
-    - Integrated AI chatbot for enhanced engagement.
-    - Implemented a contact form with EmailJS.
-
-### 6. Object Segmentation (Individual Project)
-- **Technologies**: YOLOv8, OpenCV, RoboFlow
-- **Description**: Built an object segmentation model and implemented functionalities for image processing.
-<!--- (Built a versatile Python script using OpenCV and scikit image for image processing tasks.like object segmentation, using YoloV8, OpenCV, sklearn. Implemented functionalities like grayscale contrast nhancement, image similarity measurement (SSIM), and object segmentation YOLOv8 Demonstrated the script s capabilities through image processing, evaluation, and visualization. Planned to explore integration of advanced deep learning models for further functionalities.
-        Here is the ("notebook link: Object_Segmentation_&_ComparisonObject_Segmentation_&_Comparison.ipynb:https://colab.research.google.com/drive/1cpNEx_u70I26Ex0alZZxoFa47p6fpoDz?usp=sharing")) --->
+    - Achieved 97.86% accuracy.
+    - Applied transfer learning and fine-tuning for high precision.
+<!--- Built using pre-trained VGGFace architecture, then fine-tuned on a custom celebrity dataset.
+     Deployed using Hugging Face Spaces with webcam integration.
+     Implemented data augmentation, optimizer tuning, and early stopping. 
+     [Notebook](https://www.kaggle.com/code/sarath02003/face-recognition-using-vggface2) --->
+
+---
+
+### 8. [The Linguistic Lens](https://sarath0x8f-ocr-translator.hf.space) (Individual Project)
+- **Technologies**: PaddleOCR, GoogleTranslator, gTTS, Gradio
+- **Description**: OCR and multilingual translator with voice support.
 - **Key Contributions**:
-    - Developed scripts for object segmentation and image enhancement.
-    - [Notebook Link](https://colab.research.google.com/drive/1cpNEx_u70I26Ex0alZZxoFa47p6fpoDz?usp=sharing)
+    - OCR, translation, and TTS in one app.
+    - UI for uploading and processing images.
+<!--- Text extracted from images via PaddleOCR, translated using Google Translate API,
+     and converted to speech with gTTS.
+     Built for accessibility in multilingual communication. --->
 
 ---
 
-## **CERTIFICATIONS**
-- **Python Programming**: Kaggle, SoloLearn, HackerRank, GUVI
-- **Machine Learning**: Coursera, Kaggle, Microsoft, IBM
-- **Deep Learning**: Kaggle, NPTEL, OpenCV University, IBM
-- **Google Skill Boost**: Introduction to Gen AI LP, Gemini for Google Cloud LP, Gen AI for Developers
-- **Django**: Microsoft
-- **AWS**: AWS Academy Cloud Foundations, AWS Academy Cloud Architecting
-- **NPTEL (exam)**: Java (ELITE), Data Science (ELITE + SILVER), Deep Learning
+### 8. [Object Segmentation](https://colab.research.google.com/drive/1cpNEx_u70I26Ex0alZZxoFa47p6fpoDz?usp=sharing) (Individual Project)
+- **Technologies**: YOLOv8, OpenCV, SSIM
+- **Description**: Tool for object detection, image enhancement, and comparison.
+- **Key Contributions**:
+    - Used SSIM for measuring image similarity.
+    - YOLOv8 for detecting and highlighting objects.
+<!--- Python-based script for side-by-side comparison of objects.
+     Supports grayscale enhancement, noise filtering, and detection overlay.
+     Used in image analytics tasks and visual pipeline experimentation. --->
 
 ---
+## **CERTIFICATIONS**
+- **Python Programming**: [Kaggle](https://www.kaggle.com/learn/certification/sarath02003/python), [SoloLearn](https://www.sololearn.com/en/certificates/CT-NLSO0STL), [HackerRank](https://www.hackerrank.com/certificates/263f6a71988a), [GUVI](https://www.guvi.in/verify-certificate?id=209j6x21oAr815w22s)
+- **Machine Learning**: [Coursera](https://www.coursera.org/account/accomplishments/verify/ZN3LX57MCMD5), [Microsoft](https://learn.microsoft.com/en-us/users/bandreddisarathchandra-3927/achievements/ek5w55lp), [Kaggle](https://www.kaggle.com/learn/certification/sarath02003/intro-to-machine-learning)
+- **Deep Learning**: [OpenCV](https://courses.opencv.org/certificates/9c0b11a53fcb4f56bcb21bcbd72c106a), [NPTEL](https://internalapp.nptel.ac.in/NOC/NOC24/SEM1/Ecertificates/106/noc24-cs59/Course/NPTEL24CS59S125630124930429241.pdf), [IBM](https://www.credly.com/badges/0461b4db-af25-4025-a6b9-4d61997fd1f6/public_url)
+- **Gen AI**: [Google Skill Boost](https://www.cloudskillsboost.google/public_profiles/9bb8b044-6619-4961-b707-4349dceaa1dc)
+- **Django**: [Microsoft Django Developer Badge](https://learn.microsoft.com/en-us/users/bandreddisarathchandra-3927/achievements/ek5w55lp)
+- **AWS**: [Cloud Foundations](https://www.credly.com/badges/a1cc8647-4436-47c5-8d9c-bd089043c033/public_url), [Cloud Architecting](https://www.credly.com/badges/a1cc8647-4436-47c5-8d9c-bd089043c033/public_url)
 
+---
 ## **ACHIEVEMENTS**
-- Runner-up in Python Intramural technical fest at RVR&JC College [LINK]
-- 3⭐ coder in [CodeChef](https://www.codechef.com/users/sarath2003)
+- Runner-up in Python Intramural technical fest at RVR&JC College [Event Photo](https://media.licdn.com/dms/image/D5622AQFKoaWnZ1H1-w/feedshare-shrink_2048_1536/0/1707652131442)
 
 ---
-
 ## **PASSIONS**
-- **Deep Learning Engineer**: Transforming the financial services industry.
-- **Python Developer**: Building efficient, scalable products with Python.
+- **Deep Learning Engineer**: Transforming the financial and edtech sector.
+- **AI Application Builder**: Creating end-to-end systems that interact with real-world users.
 
 ---
-
 ## **HOBBIES**
-- Nurturing plants
-- Exploring new knowledge
-- Sketching with pencil
-- Simplifying complexities through coding
+- Nurturing plants 🌱  
+- Exploring emerging AI tools 🧠  
+- Pencil sketching ✏️  
+- Writing intelligent code 💻  
 
 ---
-
-## **FINDE ME ONLINE**
+## **FIND ME ONLINE**
 - [MyPortfolio](https://21bq1a4210.github.io/MyPortfolio-/)
 - [CodeChef](https://www.codechef.com/users/sarath2003)
 - [Instagram](https://www.instagram.com/sarath_0x8f)
 - [HackerRank](https://www.hackerrank.com/profile/sarath_0x8f)
 
 ---
-
 ## **CONTACT ME**:
 - [LinkedIn](https://www.linkedin.com/in/sarath-chandra-bandreddi-07393b1aa/)
-- [MyPortfolio](https://21bq1a4210.github.io/MyPortfolio-/)
-'''
+- 📧 bandreddysarathchandra@gmail.com
+"""