Welcome to the Generative AI and NLP Projects repository. This repository contains a collection of projects that explore various advanced techniques in Natural Language Processing (NLP). Each project leverages different models and methodologies to address specific NLP tasks, demonstrating the versatility and power of modern NLP frameworks.
- 🗂️ Chat with PDFs - Using LangChain and RAG
- 📰 Newsletter Generator App Using CrewAI
- 📈 Stock Market Assistant Using PEFT and QLoRA
- 🔍 Sentiment Analysis with Sequence Models (LSTM, BiSTM and CNN)
- 🔄 Seq-to-Seq Models for Machine Translation
This project allows users to interact with the contents of multiple PDFs through a chat interface. By leveraging the LangChain and Retrieval-Augmented Generation (RAG) models, the application can answer questions based on the information within the uploaded PDFs.
- Upload multiple PDFs and create a searchable database of their contents.
- Use a large language model to answer questions based on relevant sections of the PDFs.
- Display the thought process of each agent involved in the automation process.
- Python
- Streamlit
- PyPDF2
- LangChain
- OpenAI API
- Hugging Face Hub
To set up and run the application, follow the instructions in the project's README.
This project automates the generation of newsletters using a team of autonomous agents built with CrewAI. The GUI allows users to input a topic and personal message, and then displays the process of generating a newsletter, which can be downloaded as an HTML file.
- Automated generation of newsletters based on user-provided topics.
- Display the process of agents finding, summarizing, and formatting content.
- Download the generated newsletter in HTML format.
- Python
- CrewAI
- Streamlit
To set up and run the application, follow the instructions in the project's README.
This project leverages advanced NLP techniques to analyze stock market trends by decoding unstructured data from news articles and social media. The tool provides sentiment analysis and text summarization to offer accessible market insights.
- Sentiment analysis and text summarization of financial news.
- Integration with various NLP models to extract actionable insights.
- User-friendly interface for analyzing stock market trends.
- Python
- Mistral
- Gemma
- BERT
- FAISS
To set up and run the application, follow the instructions in the project's README.
This project explores various neural network architectures for performing sentiment analysis on text data. The models include LSTM, BiLSTM, and CNNs, evaluated using different optimizers and hyperparameters.
- Comparative analysis of multiple neural network architectures.
- Use of pre-trained embeddings to enhance model performance.
- Detailed performance metrics and model comparisons.
- Python
- PyTorch
- NumPy
- Pandas
- Matplotlib
- NLTK
To set up and run the experiments, follow the instructions in the project's README.
This project investigates sequence-to-sequence (Seq2Seq) models for machine translation tasks. The project includes experiments with LSTM, BiLSTM, and Transformer models, evaluating their performance in translating text.
- Experiments with various Seq2Seq architectures.
- Use of pre-trained Word2Vec embeddings.
- Analysis of model performance using BLEU score and other metrics.
- Python
- PyTorch
- NumPy
- Pandas
- Matplotlib
To set up and run the experiments, follow the instructions in the project's README.
The Generative AI and NLP Projects repository demonstrates the application of cutting-edge NLP techniques across various domains. Each project provides a unique perspective on solving complex NLP tasks, showcasing the potential and versatility of modern NLP frameworks.
For detailed information and setup instructions, please refer to the individual README files for each project. If you have any questions or feedback, feel free to reach out to the project contributors.