Popular GitHub Repositories for Word Similarity

提取微信聊天记录，将其导出成HTML、Word、Excel文档永久保存，对聊天记录进行分析生成年度聊天报告，用聊天数据训练专属于个人的AI聊天助手

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Machine learning, in numpy

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database?.

100+ Chinese Word Vectors 上百种预训练中文词向量

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Unsupervised text tokenizer for Neural Network-based text generation.

Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）

Retrieval and Retrieval-augmented LLMs

大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP

Best Practices, code samples, and documentation for Computer Vision.

A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge bases. It can effectively overcome the shortcomings of the traditional RAG vector similarity calculation model.

Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!

text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。

Tutorials on getting started with PyTorch and TorchText for sentiment analysis.

搜索所有中文NLP数据集，附常用英文NLP数据集

On-device wake word detection powered by deep learning