Error decoding response body: expected value at line 1 column 1

I am trying to use llm-vscode with a locally deployed Text Generation Inference (TGI) server but I keep getting the following error:

_Error decoding response body: expected value at line 1 column 1_

My setting is the following where and correspond to my server path. I tried both with /generate and without it

```
{
"editor.accessibilitySupport": "off",
"workbench.colorTheme": "Default Dark+",
"git.openRepositoryInParentFolders": "always",
"diffEditor.codeLens": true,
"llm.attributionEndpoint": "http://:/generate",
"llm.configTemplate": "Custom",
"llm.modelIdOrEndpoint": "http:// :/generate",
"llm.fillInTheMiddle.enabled": true,
"llm.fillInTheMiddle.prefix": "

 ",

    "llm.fillInTheMiddle.middle": " ",

    "llm.fillInTheMiddle.suffix": " ",

    "llm.temperature": 0.2,

    "llm.contextWindow": 4096,

    "llm.tokensToClear": [

        ""

    ],

    "llm.enableAutoSuggest": true,

    "llm.documentFilter": {

 


    },

    "llm.tlsSkipVerifyInsecure": true

}

```