Bpemb alternatives for AI agents.

Bringing BERT into modernity via both architecture changes and scaling

Retrieval and Retrieval-augmented LLMs

A tool for learning vector representations of words and entities from Wikipedia

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。

Fast State-of-the-Art Static Embeddings

Persian NLP Toolkit

100+ Chinese Word Vectors 上百种预训练中文词向量

Solves basic Russian NLP tasks, API for lower level Natasha projects

Implementation of the node2vec algorithm.

unified embedding model

VectorFlow is a high volume vector embedding pipeline that ingests raw data, transforms it into vectors and writes it to a vector DB of your choice.

Nomic Developer API SDK

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.

The Clay Foundation Model - An open source AI model and interface for Earth

WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.

Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate, LanceDB).