kshitijthakkar commited on
Commit
0b8bed8
Β·
1 Parent(s): fb44126

docs: Add judge instructions for API key configuration

Browse files

- Add comprehensive section for hackathon judges and visitors
- Explain step-by-step configuration for both MCP Server and TraceMind-AI
- Clarify why two settings screens are needed (separate sessions)
- Detail HF token permissions: Read for datasets, Write for synthetic data features
- Include security notes about session-only storage and api_name=False
- Provide links to get free API keys with tier information

Files changed (1) hide show
  1. README.md +61 -0
README.md CHANGED
@@ -111,6 +111,67 @@ python app.py
111
 
112
  Visit http://localhost:7860
113
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  ## Configuration
115
 
116
  Create a `.env` file with the following variables:
 
111
 
112
  Visit http://localhost:7860
113
 
114
+ ## 🎯 For Hackathon Judges & Visitors
115
+
116
+ ### Using Your Own API Keys (Recommended)
117
+
118
+ TraceMind-AI integrates with the TraceMind MCP Server to provide AI-powered analysis. To **prevent credit issues during evaluation**, we recommend configuring your own API keys:
119
+
120
+ #### Step-by-Step Configuration
121
+
122
+ **Step 1: Configure MCP Server** (Required for MCP tool features)
123
+
124
+ 1. **Open MCP Server**: https://huggingface.co/spaces/MCP-1st-Birthday/TraceMind-mcp-server
125
+ 2. Go to **βš™οΈ Settings** tab
126
+ 3. Enter your **Gemini API Key** and **HuggingFace Token**
127
+ 4. Click **"Save & Override Keys"**
128
+
129
+ **Step 2: Configure TraceMind-AI** (Optional, for additional features)
130
+
131
+ 1. **Open TraceMind-AI**: https://huggingface.co/spaces/MCP-1st-Birthday/TraceMind
132
+ 2. Go to **βš™οΈ Settings** tab
133
+ 3. Enter your **Gemini API Key** and **HuggingFace Token**
134
+ 4. Click **"Save API Keys"**
135
+
136
+ ### Why Configure Both?
137
+
138
+ - **MCP Server**: Provides AI-powered tools (leaderboard analysis, trace debugging, cost estimation)
139
+ - **TraceMind-AI**: Main UI that calls the MCP server for intelligent analysis
140
+ - They run in **separate sessions** β†’ need separate configuration
141
+ - Configuring both ensures your keys are used for the complete evaluation flow
142
+
143
+ ### Getting Free API Keys
144
+
145
+ Both APIs have generous free tiers:
146
+
147
+ **Google Gemini API Key**:
148
+ - Visit: https://ai.google.dev/
149
+ - Click "Get API Key" β†’ Create project β†’ Generate key
150
+ - **Free tier**: 1,500 requests/day (sufficient for evaluation)
151
+
152
+ **HuggingFace Token**:
153
+ - Visit: https://huggingface.co/settings/tokens
154
+ - Click "New token" β†’ Name it (e.g., "TraceMind Access")
155
+ - **Permissions**:
156
+ - Select "Read" for viewing datasets (sufficient for most features)
157
+ - Select "Write" if you want to use synthetic dataset generation & push features (via MCP server)
158
+ - **Recommended**: Use "Write" permissions for full functionality
159
+ - **Free tier**: No rate limits for public dataset access
160
+
161
+ ### Default Configuration (Without Your Keys)
162
+
163
+ If you don't configure your own keys:
164
+ - Apps will use our pre-configured keys from HuggingFace Spaces Secrets
165
+ - Fine for brief testing, but may hit rate limits during high traffic
166
+ - Recommended to configure your keys for full evaluation
167
+
168
+ ### Security Notes
169
+
170
+ βœ… **Session-only storage**: Keys stored only in browser memory
171
+ βœ… **No server persistence**: Keys never saved to disk
172
+ βœ… **Not exposed via API**: Settings forms use `api_name=False`
173
+ βœ… **HTTPS encryption**: All API calls over secure connections
174
+
175
  ## Configuration
176
 
177
  Create a `.env` file with the following variables: