文本向量化模型合集 — BGE/M3E/Cohere/OpenAI，RAG 系统基石。
pip install sentence-transformersfrom sentence_transformers import SentenceTransformermodel = SentenceTransformer('BAAI/bge-m3')embeddings = model.encode(['文本1', '文本2'], normalize_embeddings=True)支持中英多语言，8192 token 输入API: curl https://api.jina.ai/v1/embeddings -H 'Authorization: Bearer TOKEN'本地: pip install transformers; model = AutoModel.from_pretrained('jinaai/jina-embeddings-v3')支持 8192 token 长文本，30+ 语言from openai import OpenAI; client = OpenAI(api_key='...')resp = client.embeddings.create(model='text-embedding-3-large', input=['text'])text-embedding-3-small: $0.02/1M tokens, large: $0.13/1M tokens