Ollama运行嵌入式模型(Embedding Model)

安装Ollama

省略,参考:https://www.jianshu.com/p/ca6af4c96581

运行嵌入模型

# 运行 nomic-embed-text 嵌入模型
ollama pull nomic-embed-text

# 运行 mxbai-embed-large 嵌入模型
ollama pull mxbai-embed-large

通过Ollama API测试嵌入模型

curl http://10.3.6.38:11434/api/embed -d '{
  "model": "nomic-embed-text",
  "input": "Llamas are members of the camelid family"
}'

效果:

[root@bogon ~]# curl http://10.3.6.38:11434/api/embed -d '{
  "model": "nomic-embed-text",
  "input": "Llamas are members of the camelid family"
}'
{"model":"nomic-embed-text","embeddings":[[0.014543912,0.014353983,-0.15859936,-0.05635971,0.013833548,0.00045747016,-0.082582116,-0.07535395,-0.040231105,-0.005863341,-0.0068954662,0.047798615,0.07013451,0.017024966,0.0392089,-0.020978166,-0.060597282,-0.017331367,0.04145304,0.024633398,-0.06402724,...省略很多....,-0.06301445]],"total_duration":788713071,"load_duration":519436478,"prompt_eval_count":10}[

可惜,ollama目前还不支持Reranker Model的运行

最后编辑于
©著作权归作者所有,转载或内容合作请联系作者
平台声明:文章内容(如有图片或视频亦包括在内)由作者上传并发布,文章内容仅代表作者本人观点,简书系信息发布平台,仅提供信息存储服务。

推荐阅读更多精彩内容