Jina AI 发布多模态嵌入模型 v5-omni-small-retrieval
原标题：jinaai/jina-embeddings-v5-omni-small-retrieval
AI 摘要
Jina AI 发布了 jina-embeddings-v5-omni-small-retrieval，这是一个多模态嵌入模型，支持文本、图像、视频和音频输入，并生成与文本模型对齐的共享向量空间。该模型约 1.56B 参数，嵌入维度 1024，支持最长 32768 序列，并可通过 Elastic Inference Service 或本地安装使用。该模型在图像、视频和音频基准上定义了开放权重前沿，旨在实现跨模态检索而无需重新索引。
正文节选
--- pipeline_tag: feature-extraction tags: - embedding - qwen3 - jina-embeddings-v5 - feature-extraction - sentence-transformers - multimodal - vision - audio - vllm - video - image-feature-extraction - audio-feature-extraction - video-feature-extraction - sentence-similarity language: - multilingual base_model: jinaai/jina-embeddings-v5-omni-small base_model_relation: finetune inference: false license: cc-by-nc-4.0 library_name: transformers --- <br><br> <p align="center"> <img src="https://hu