Yuichiro Utsumi

@flefevre LiteLLM seems to support the following routes: - `/openai/deployments/{model}/chat/completions` - `/openai/deployments/{model}/embeddings` I could use Language model (Completion model) and Embedding model by specifying the LiteLLM server URL as follows:...

I faced the same error when Dify is behind a proxy server. By the following steps, this was resolved and model providers could be installed. 1. Edit `docker/ssrf_proxy/squid.conf.template` to specify...

Ping

I faced the same error when deploying Dify in the environment with my company's forward proxy server. This error disappeared by specifying `172.*.*.*` in `noProxy` variable in `.docker/config.json`. Previously, when...

@justinthelaw A non-existing container image, such as `nvcr.io/nvidia/driver:550-6.8.0-50-generic-ubuntu22.04`, is pulled unsuccessfully, resulting in an ImagePullBackOff error.