feat: vision model (#489)

* mongo init

* perf: mongo connect

* perf: tts

perf: whisper and tts

peref: tts whisper permission

log

reabase (#488)

* perf: modal

* i18n

* perf: schema lean

* feat: vision model format

* perf: tts loading

* perf: static data

* perf: tts

* feat: image

* perf: image

* perf: upload image and title

* perf: image size

* doc

* perf: color

* doc

* speaking can not select file

* doc

docSite/content/docs/development/configuration.md

@@ -36,6 +36,7 @@ weight: 520
       "quoteMaxToken": 2000, // 最大引用内容长度
       "maxTemperature": 1.2, // 最大温度值
       "censor": false, // 是否开启敏感词过滤(商业版)
+      "vision": false, // 支持图片输入
       "defaultSystemChatPrompt": ""
     },
     {
@@ -47,6 +48,7 @@ weight: 520
       "quoteMaxToken": 8000,
       "maxTemperature": 1.2,
       "censor": false,
+      "vision": false,
       "defaultSystemChatPrompt": ""
     },
     {
@@ -58,6 +60,19 @@ weight: 520
       "quoteMaxToken": 4000,
       "maxTemperature": 1.2,
       "censor": false,
+      "vision": false,
+      "defaultSystemChatPrompt": ""
+    },
+    {
+      "model": "gpt-4-vision-preview",
+      "name": "GPT4-Vision",
+      "maxContext": 128000,
+      "maxResponse": 4000,
+      "price": 0,
+      "quoteMaxToken": 100000,
+      "maxTemperature": 1.2,
+      "censor": false,
+      "vision": true,
       "defaultSystemChatPrompt": ""
     }
   ],