MTEB: Massive Text Embedding Benchmark

[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings

Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard

Codebase for RetroMAE and beyond.

Code & data accompanying the KDD 2017 paper "KATE: K-Competitive Autoencoder for Text"

Efficient LLM inference on Slurm clusters.

Simple customizable evaluation for text retrieval performance of Sentence Transformers embedders on PDFs

Simple script to compute CLIP-based scores given a DALL-e trained model.

StickerSelector 是一个基于语义向量匹配的表情包选择系统，用于让 AI 在聊天中发送真正符合语境的表情包。 与传统依赖关键词或规则的方案不同，StickerSelector 会将 AI 生成的“表情包意图描述”与本地表情包进行语义匹配，从而选出在当前语境下最自然、最像真人会使用的表情。 适用于 AI 聊天机器人、QQ或微信的自动聊天、AI 女友等需要“拟人化表达”的场景。

HSTU-BLaIR: Lightweight Contrastive Text Embedding for Generative Recommender 🌱

Simple script to re-rank images using OpenAI's CLIP https://github.com/openai/CLIP.

Topic Embedding, Text Generation and Modeling using diffusion

Flask API for generating text embeddings using OpenAI or sentence_transformers

Contextual embedding for text blobs.

Чат-бот с LLL + RAG

PL-MTEB: Polish Massive Text Embedding Benchmark

Functionalities to work with colors. Cast colors types, find closest color using text-embeddings, find color complement.

Embedding a text to a vector by pre-trained BERT word embeddings and pooling layers, for the pur[ose of text similarity measuring

CLI that helps with docs splitting, embedding and exposing them in a seamless manner

Automatic generation of descriptive radiological reports from X-RAY scans