Mohamed Shaad's repositories
AI-Agents-CrewAI-Gemini
This repository contains a project that leverages AI agents using CrewAI and Google Gemini to research and write about the latest trends in AI technology, specifically focusing on healthcare.
CodeGeneration-Google-CodeGemma-2B
This repository demonstrates the potential of using Google's CodeGemma-2B Large Language Model (LLM) to assist in generating code.
Customer-Outreach-Campaign-crewAI
This repository demonstrates the use of CrewAI to enhance sales outreach and lead profiling using a combination of advanced AI agents and tools. The project leverages CrewAI agents and LangChain to identify high-value leads and craft personalized outreach campaigns.
Doctor-Assist-crewAI
This project leverages advanced AI agents from crewAI to assist doctors in diagnosing medical conditions and recommending treatment plans based on patient-reported symptoms and medical history. The solution uses Streamlit for the user interface and crewai library to define and manage AI agents and tasks.
Gemini-Groq-Document--Q-A
This project is a Streamlit application that leverages language models and vector embeddings to perform document-based Q&A. It uses LangChain, FAISS, and Google Generative AI embeddings to process and retrieve information from documents stored in a directory.
Hybrid-Search-RAG-LangChain-Pinecone
This repository contains a Google Colab notebook that demonstrates how to set up and use a hybrid search Retrieval-Augmented Generation (RAG) system using LangChain and Pinecone. The hybrid search combines vector embeddings and sparse (BM25) encodings to provide efficient and accurate information retrieval.
500-AI-Machine-learning-Deep-learning-Computer-vision-NLP-Projects-with-code
500 AI Machine learning Deep learning Computer vision NLP Projects with code
Article-Research-Write-AI-Agents
This project sets up agentic automation for planning, writing, and editing articles using AI agents with crewAI.
CodeAssistant-Ollama-CodeLlama
This project provides a user-friendly Gradio interface that enables you to interact with the custom model based on CodeLlama model from Ollama, an open-source large language model platform. Simply enter your prompt in the textbox, and custom model will generate code based on your input.
Conversation-Analysis-LangChain-Groq
This project utilizes the LangChain and Groq to perform various analyses on loan recovery conversations. The primary functionalities include summarizing conversations, identifying key actions or next steps, and undertaking sentiment analysis of both the recovery agent and the borrower.
crewAI-Multi-AI-Agents-Investment-Risk-Analysis
This project automates the process of monitoring market data, developing trading strategies, executing trades, and assessing risks using a team of specialized AI Agents from crewAI. Each agent is equipped with specific roles and goals, and they collaborate to optimize trading decisions and strategies.
Fine-Tune-Llama2-LoRA-QLoRA
This repository contains the code for fine-tuning the Llama-2-7b-chat model on a text instruction dataset using LoRA (Layer-wise Only Relevant Attention) and QLoRA (Quantized LoRA).
Fine-tune-PaliGemma-Image-Captioning
This project demonstrates how to fine-tune PaliGemma model for image captioning. The PaliGemma model, developed by Google Research, is designed to handle images and generate corresponding captions.
Home-Price-Prediction-Economic-Indicators
This project aims to predict home prices using various economic indicators from the Federal Reserve Economic Data (FRED). The project involves data collection, data preparation, model building, and analysis of the results.
Image-Chat-Gemini-Pro-Vision
This Streamlit application allows users to chat with an image using Google's Generative AI, Gemini Pro Vision. Users can upload an image and enter a prompt, and the application will generate a response based on the image and prompt.
Invoice-Extractor-Gemini
The Invoice Extractor project aims to simplify the extraction of vital information from images, specifically focusing on invoices. By harnessing the capabilities of Gemini 1.5, Google's Multimodal Large Language Model (LLM), this application provides a robust solution for parsing invoice data with accuracy and efficiency.
ML-Papers-of-the-Week
🔥Highlighting the top ML papers every week.
Model-Conversion-HuggingFace-GGUF
This project demonstrates how to download a model from Hugging Face, convert it to GGUF format, and upload it back to Hugging Face using a Colab notebook.
Multi-Agent-Customer-Support-Automation
This project leverages the crewAI AI agents to create a sophisticated support system. These agents provide top-notch support and quality assurance for customer inquiries.
Multi-Label-Text-Classification-BERT
This project focuses on multi-label text classification using BERT (Bidirectional Encoder Representations from Transformers). We combine titles and abstracts of articles to classify them into multiple categories simultaneously.
Sentiment-Analysis-API
This API allows you to analyze the sentiment of text input. It uses TextBlob for sentiment analysis.
TextAutocomplete-distilgpt2
This repository contains the code and resources for implementing text autocompletion using the DistilGPT-2 model from Hugging Face within a Jupyter Notebook environment.
TextAutocomplete-HuggingFace
This repository demonstrates how to use the HuggingFace Transformers library to implement text autocompletion in a Jupyter Notebook environment.
TextAutocomplete-LSTM-pytorch
This repository contains a Jupyter Notebook demonstrating text autocompletion using Long Short-Term Memory (LSTM) networks implemented in PyTorch.
TextAutocomplete-LSTM-Tensorflow
Text Autocomplete with TensorFlow LSTM is a project that demonstrates how to build a simple text autocomplete system using TensorFlow and LSTM (Long Short-Term Memory) networks. This project utilizes a dataset of frequently asked questions (FAQs) to train the LSTM model to predict the next word given a sequence of words.
TextGeneration-Llama3-HuggingFace
This repository demonstrates how to leverage the Llama3 large language model from Meta for text generation tasks using Hugging Face Transformers in a Jupyter Notebook environment.
Training-SmallLanguageModel-DiseaseSymptoms
This project utilizes the power of language models, specifically the GPT-2 model, to predict medical symptoms based on input text. By fine-tuning the GPT-2 model on a dataset containing disease names and associated symptoms, we train a language model to generate probable symptoms for a given disease.
Youtube-Video-Summarizer
This is a Streamlit web application that summarizes YouTube videos using Youtube Transcript API and Google's Generative AI model Gemini Pro. The YouTube Video Summarizer allows users to input a YouTube video URL and generates a summary of the video content based on its transcript.