Kevin Hu
Kevin Hu
I don't think it is feasible to accomplish this through web UI. Check [HTTP API](https://ragflow.io/docs/dev/http_api_reference) / [Python SDK](https://ragflow.io/docs/dev/python_api_reference) out.
Please refer to [this](https://forums.developer.nvidia.com/t/could-not-select-device-driver-with-capabilities-gpu/80200).
Could you paste the error message or `print(response)` if it's convenient ?
Demo site dose not support API invocation.
You can try dev-slim version of docker image since it do not handle embeding inference itself.
For slim version of RAGFlow, it dose not handle embedding procedure itself. You need to use Ollama to deploy an embedding inference.
docker pull the dev version of image and git pull the latest code. > ### Describe your problem > 想运行带embedding的镜像，按照readme里面的方式，修改了RAGFLOW_IMAGE=infiniflow/ragflow:dev，启动ragflow-server会报错找不到service_conf这个文件，我手动把这个文件拷进去，运行则会报错连不上es01，这是为什么？我运行dev-slim这个版本是没有问题可以正常使用的。
Please refer to [this](https://www.biaodianfu.com/pos-tagging-set.html) about POS-tagging. About ner.json, - toxic used for compliance - stock means name of stock - firstnm means Chinese first name
Please refer to [this](https://stackoverflow.com/questions/2056124/nginx-client-max-body-size-has-no-effect).