Infinity is a high-throughput, low-latency REST API for serving vector embeddings, supporting a wide range of text-embedding models and frameworks.
-
Updated
May 22, 2024 - Python
Infinity is a high-throughput, low-latency REST API for serving vector embeddings, supporting a wide range of text-embedding models and frameworks.
This is a RAG implementation using Open Source stack. BioMistral 7B has been used to build this app along with PubMedBert as an embedding model, Qdrant as a self hosted Vector DB, and Langchain & Llama CPP as an orchestration frameworks.
Recomendação de documentos no domínio jurídico para o projeto Querido Diário
lightweight Vercel-Friendly version of BMX, the BookMark eXtractor https://github.com/cooperability/BMX-bookmark-extractor
Machine Learning project, Computer Science a.y. 2023-2024
ColBERT humor dataset for the task of humor detection, containing 200,000 jokes/news
This repo contains everything about transformers and NLP.
Fast and memory-efficient library for WordPiece tokenization as it is used by BERT.
A semantic food search web application built with Django, Solr, SBERT, Docker and Heroku
training literature bert classification.
Simple State-of-the-Art BERT-Based Sentence Classification with Keras / TensorFlow 2. Built with HuggingFace's Transformers.
Using LLMs and graph algorithms to understand the semantics of Japanese Kanji
Review: Deep Learning for Sentence Semantic Similarity
Space Model framework that allows for maintaining generalizability, and enhances the performance on the downstream task by utilizing task-specific context attribution. It is an external LLM layer, that improves accuracy in classification task for multiple datasets, such as HateXplain, IMDB movies reviews and more.
My solutions for IISc selection-problems
A Retrieval-Augmented Generation (RAG) System for PDF Chat using Qdrant Vector Database.
RAG (Retrieval Augmented Generation) and vector search to translate natural language into SQL queries for PostgreSQL databases.
A web based Job Portal for Candidates and employers with resume ranking capabilities
In this project, we demonstrate the process of building a text classification model using the BERT (Bidirectional Encoder Representations from Transformers) architecture. Our goal is to classify texts into two categories: AI-generated and human-written.
RAG architecture to retrieve and embed pdfs
Add a description, image, and links to the bert-embeddings topic page so that developers can more easily learn about it.
To associate your repository with the bert-embeddings topic, visit your repo's landing page and select "manage topics."