A comprehensive reference for all topics related to Natural Language Processing

Projects and useful articles / links

Awesome list (courses, books, videos etc.) and implementation of Machine Learning Algorithms

Python library for feature selection for text features. It has filter method, genetic algorithm and TextFeatureSelectionEnsemble for improving text classification models. Helps improve your machine learning models

This repo contains my work & The code base for this TensorFlow Developer specialization offered by deeplearning.AI

An attempt to predict next day's stock price movements using sentiments in tweets with cashtags. Six different ML algorithms were deployed (LogReg, KNN, SVM etc.). Main libraries used: Pandas & Numpy

Using Spacy and NLTK module with Tf-Idf algorithm for text-summarisation. This code will give you the summary of inputted article. You can input text directly or from .txt file, .pdf file or from wikipedia url.

A cryptocurrency-focused AI chatbot that utilizes real-time on-chain blockchain data. This advanced chatbot is designed to engage in natural language Q&A interactions and can seamlessly invoke relevant APIs when users pose queries that necessitate API calls.

SumBot Free Code - AI-Powered Message Summarization ChatBot

Document based ChatGPT

Ambiente de Desenvolvimento Integrado (ADI) contando com um explorador de arquivos, editor de código, compilador e outros.

Machine translation using the seq2seq model

BookGPTs: Revolutionizing Book Interactions with AI. Create GPTs for any e-book, making technology accessible for all to engage in rich, AI-powered book discussions. No technical expertise required – upload a document and bring your favorite books to conversational life!

This is a Flask backend that allows users to upload a PDF file and receive a simplified and humorous explanation of its contents using OpenAI's GPT-3 API. The application uses NLTK to split the PDF text into smaller chunks to stay within the API's maximum token limit, and PyPDF2 to extract the text from the PDF file.

This repository contains code for generating blog content using the LLama 2 language model. It integrates with Streamlit for easy user interaction. Simply input your blog topic, desired word count, and writing style to generate engaging blog content.

How to build a chatbot to parse conditional statements

This project fine-tunes the LLaMA-3.1-8B model using LoRA adapters for parameter-efficient training. It leverages chat templates for conversation structuring, utilizes 4-bit quantization for memory efficiency, and saves the fine-tuned model for deployment on the Hugging Face Hub.

In this project our goal is to acheive the problem of converting audio data into textual data.

A prototype legal text search engine that uses a semantic search algorithm in order to find related keywords and sort the results by relevance.