Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
-
Updated
May 16, 2025 - Python
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
DeText: A Deep Neural Text Understanding Framework for Ranking and Classification Tasks
Train Models Contrastively in Pytorch
Open Source Text Embedding Models with OpenAI Compatible API
Interactive tree-maps with SBERT & Hierarchical Clustering (HAC)
Code implementation for our ICPR, 2020 paper titled "Improving Word Recognition using Multiple Hypotheses and Deep Embeddings"
Flask API for generating text embeddings using OpenAI or sentence_transformers
Topic Embedding, Text Generation and Modeling using diffusion
KRLawGPT : Generative Pre-trained Transformer for producing Korean Legal Text
Docsifer is a powerful tool for converting various data formats into Markdown for applications such as indexing, text analysis, and more. It supports PDF, PowerPoint, Word, Excel, Images, Audio, HTML, and other text-based formats, and leverages LLMs to enhance performance.
Use CLIP to create matching texts + embeddings for given images; useful for XAI, adversarial training
LightweightEmbeddings is a fast, free, and unlimited API service for multilingual embeddings and reranking, with support for both text and images and guaranteed uptime.
Graph Attention Networks for Entity Summarization is the model that applies deep learning on graphs and ensemble learning on entity summarization tasks.
M.Sc. mini project for NLP class (M908)
A Python-based search engine for OpenAI's ChatGPT conversation history, enabling efficient semantic search and interactive engagement with archived chats using text embeddings
DYnamic Attributed Node rolEs (DYANE) is an attributed dynamic-network generative model based on temporal motifs and attributed node behavior.
Text Embeddings Inference (TEI)'s unofficial python wrapper library for batch processing with asyncio
A RAG (Retrieval-Augmented Generation) application which combines retrieval-based and generative approaches to improve the accuracy and relevance of AI-generated responses.
Retrieve text embeddings, but cache them locally if we have already computed them.
The Website Categorizer is a service that classifies websites by extracting metadata and content, generating embeddings, and matching them to predefined tags using cosine similarity.
Add a description, image, and links to the text-embeddings topic page so that developers can more easily learn about it.
To associate your repository with the text-embeddings topic, visit your repo's landing page and select "manage topics."