You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: units/en/unit2/lemonade-server.mdx
+22-30Lines changed: 22 additions & 30 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -65,7 +65,7 @@ Lemonade Server supports CPU inference across all platforms and engines on Windo
65
65
66
66
### Tiny Agents and NPX Setup
67
67
68
-
This section of the course assumes you have already installed `npx` and `Tiny Agents`. If you haven't, please refer to the [Tiny Agents](https://huggingface.co/learn/mcp-course/en/unit2/tiny-agents) section of the course.
68
+
This section of the course assumes you have already installed `npx` and `Tiny Agents`. If you haven't, please refer to the [Tiny Agents](https://huggingface.co/learn/mcp-course/en/unit2/tiny-agents) section of the course. Please make sure to use `huggingface_hub[mcp]==0.33.2`.
69
69
70
70
## Running your Tiny Agents application with AMD NPU and iGPU
71
71
@@ -81,13 +81,11 @@ To run your Tiny Agents application with AMD NPU and iGPU, simply point to the M
81
81
"servers": [
82
82
{
83
83
"type": "stdio",
84
-
"config": {
85
-
"command": "C:\\Program Files\\nodejs\\npx.cmd",
86
-
"args": [
87
-
"mcp-remote",
88
-
"http://localhost:7860/gradio_api/mcp/sse"
89
-
]
90
-
}
84
+
"command": "C:\\Program Files\\nodejs\\npx.cmd",
85
+
"args": [
86
+
"mcp-remote",
87
+
"http://localhost:7860/gradio_api/mcp/sse"
88
+
]
91
89
}
92
90
]
93
91
}
@@ -103,13 +101,11 @@ To run your Tiny Agents application with AMD NPU and iGPU, simply point to the M
103
101
"servers": [
104
102
{
105
103
"type": "stdio",
106
-
"config": {
107
-
"command": "npx",
108
-
"args": [
109
-
"mcp-remote",
110
-
"http://localhost:7860/gradio_api/mcp/sse"
111
-
]
112
-
}
104
+
"command": "npx",
105
+
"args": [
106
+
"mcp-remote",
107
+
"http://localhost:7860/gradio_api/mcp/sse"
108
+
]
113
109
}
114
110
]
115
111
}
@@ -126,7 +122,7 @@ You can then choose from a variety of models to run on your local machine. For t
126
122
127
123
Now let's enhance our end-to-end application by enabling access to local files and introducing an assistant that processes sensitive information entirely on-device. Specifically, this assistant will help us evaluate candidate resumes and support decision-making in the hiring process—all while keeping the data private and secure.
128
124
129
-
To do this, we'll use the [Desktop Commander](https://github.com/wonderwhy-er/desktop-commander) MCP server, which allows you to run commands on your local machine and provides comprehensive file system access, terminal control, and code editing capabilities.
125
+
To do this, we'll use the [Desktop Commander](https://github.com/wonderwhy-er/DesktopCommanderMCP) MCP server, which allows you to run commands on your local machine and provides comprehensive file system access, terminal control, and code editing capabilities.
130
126
131
127
Let's setup a project with a basic Tiny Agent.
132
128
@@ -147,13 +143,11 @@ Let's then create a new `agent.json` file in the `file-assistant` folder.
147
143
"servers": [
148
144
{
149
145
"type": "stdio",
150
-
"config": {
151
-
"command": "C:\\Program Files\\nodejs\\npx.cmd",
152
-
"args": [
153
-
"-y",
154
-
"@wonderwhy-er/desktop-commander"
155
-
]
156
-
}
146
+
"command": "C:\\Program Files\\nodejs\\npx.cmd",
147
+
"args": [
148
+
"-y",
149
+
"@wonderwhy-er/desktop-commander"
150
+
]
157
151
}
158
152
]
159
153
}
@@ -169,13 +163,11 @@ Let's then create a new `agent.json` file in the `file-assistant` folder.
0 commit comments