@oadank/dsh-input-tools 0.3.13 → 0.3.14
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +6 -2
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -18,7 +18,9 @@
|
|
|
18
18
|
| 语音气泡 | 用户/AI 语音消息可点击播放,尾部复制转写文本 |
|
|
19
19
|
|
|
20
20
|
### 图片
|
|
21
|
-
- 输入框图片按钮上传 →
|
|
21
|
+
- 输入框图片按钮上传 → **文本模型也能发图**:图片转本地路径文本,AI 自动调视觉 MCP 识图后回答
|
|
22
|
+
- 附件存储自动生成**带扩展名的别名**(jpg/png/webp→png),zai-vision 等按扩展名校验的
|
|
23
|
+
识图工具可直接读取(源码补丁包含,无需额外配置)
|
|
22
24
|
|
|
23
25
|
### 余额
|
|
24
26
|
- 直连模型时输入框右侧实时显示余额(¥xx)
|
|
@@ -81,7 +83,9 @@ setup 脚本自动完成:装插件进 profile → 注册 → 检查 ffmpeg →
|
|
|
81
83
|
### 依赖
|
|
82
84
|
|
|
83
85
|
- **ffmpeg**(语音转码必需):Windows `winget install ffmpeg`;Linux `sudo apt install ffmpeg`
|
|
84
|
-
-
|
|
86
|
+
- **视觉 MCP**(图片识图必需):在 dsh 设置里配置至少一个视觉 MCP 服务,AI 用它的工具识图:
|
|
87
|
+
- `zai-vision`(推荐,通用):`npx -y @z_ai/mcp-server`,配 `Z_AI_BASE_URL=http://localhost:11434/v1/`(本地 ollama 跑 qwen3-vl 等视觉模型),按扩展名校验(已由补丁解决)
|
|
88
|
+
- `visionqa`(本机自建服务)
|
|
85
89
|
|
|
86
90
|
## 配置
|
|
87
91
|
|