A simple web application to generate vector embeddings for PDF document, store them in a vector database (Pinecone), and enable semantic search and information retrieval using OpenAI's language models.

Vector embeddings generation for a csv file, storing embeddings in the vector database and query the csv file using openai language model

Build Generative AI, custom Question/Answer or Information Retrival Application using LlamaIndex, Google Gemini

Advance Resume Parser: This project was built during the Mined Hackathon organized by Nirma University.

Use Cohere and OpenSearch to analyze customer feedback in an MLOps pipeline

SSAT Analogy Solver: Test Vector Embedding Against Web Scrapped Questions

PDF Bundle extracts text from PDFs in AWS S3, splits it, stores embeddings in Pinecone, and uses query vector embeddings based on cosine similarities for efficient search and retrieval.

Python Implementation of lexical vector embedding similarity scoring, zero-shot classification of images and n-gram based scoring to compare textual summaries

Developed using custom data for answering questions from a given domain knowledge

Hands-on with Milvus vector db

Detection as well as identification of faces

Pawsitive Retrieval RAG Project - Erdos Institute Deep Learning Boot Camp - Spring 2024

Experimenting with Wagtail vector search (and possibly chat) by creating a blog

An LLM app leveraging RAG with LangChain and GPT-4 mini to analyze earnings call transcripts, assess company performance, using natural language queries (NLP), FAISS (vector database), and Hugging Face re-ranking models.

Seamlessly interact with PDF, CSV, Website and Handwritten Notes

Extends the Paper QA package for use with the author's Zotero database papers in organic chemistry, drug discovery & development, cheminformatics and the applications of machine learning to these areas

An End-to-End RAG Pipeline for handling Question and Answer in the Data Science domain

Image Retrieval with Azure Computer Vision 4.0