MTEB: Massive Text Embedding Benchmark

An implementation of the TaxRetrievalBenchmark task for the 🤗 Massive Text Embedding Benchmark (MTEB) framework.

Site for skywardAI, AI-copilot for conversation

Local-GenAI-Search is a generative search engine based on Llama 3, langchain and qdrant that answers questions based on your local files

Project for Information Retrieval

Model to classify and categorize user complaints into categories for specific departments using LLMs.

An editing tool that uses AI to transcribe, understand content and search for anything in your footage, integrated with ChatGPT and other AI models

Efficient few-shot learning with Sentence Transformers

A convenient way to link, deduplicate, aggregate and cluster data(frames) in Python using deep learning

Efficient Retrieval Augmentation and Generation Framework

Backend for the AI-copilot

The project's goal is to help job seekers understand the basic qualifications for specific jobs and evaluate the suitability of their skills for those positions. Additionally, the program aims to assist recruiters in enhancing their resume selection processes by analyzing and understanding job advertisements ....

By: Anshuman Gupta, Prince Choudhary and Tisha Patel. Exploring Diverse Domains Of Wisdom Through Conversational Journeys

To make LLM faster we need faster retrieval system. Here comes Embedding Quantization. Embedding quantization is great technique to save cost on Vector DB, significantly faster retrieval while preserving retrieval performance.

This repository contains an easy and intuitive approach to few-shot classification using sentence-transformers or spaCy models, or zero-shot classification with Huggingface.

This repository, called fast sentence transformers, contains code to run 5X faster sentence transformers using tools like quantization and ONNX.

LLM is a very powerful tool. It often performs more than required (hallucinations) and may tend to generate output in a pattern it finds best. We need RAG to harness the power of LLM in a controlled manner. In this work we implement a simple RAG system with Codegemma and an in-memory Vector Database.

Implementing Vector Database on CoNaLa dataset to retrieve program snippets relevant to user queries. This is a very simple simulation of a Vector Database.

NLP Sentiment Classification Project

The API of Bedlessbot which handles machine-learning related tasks.