Spaces:
Running
Running
Commit
·
040fd52
1
Parent(s):
ffe25f1
docs: Update Gemini model version and fix typos
Browse files- Change Gemini 2.5 Pro → 2.5 Flash throughout documentation
- Fix typo in MCP_INTEGRATION.md (Compre → Compare)
- Update cost estimation documentation with correct model name
- MCP_INTEGRATION.md +1 -1
- screens/documentation.py +3 -3
MCP_INTEGRATION.md
CHANGED
|
@@ -458,7 +458,7 @@ with gr.Blocks() as app:
|
|
| 458 |
| `analyze_leaderboard` | Leaderboard tab | Generate AI insights when user loads leaderboard |
|
| 459 |
| `estimate_cost` | New Evaluation tab | Predict costs before submitting evaluation |
|
| 460 |
| `debug_trace` | Trace Visualization | Answer questions about execution traces |
|
| 461 |
-
| `compare_runs` | Agent Chat | Compare two evaluation runs side-by-side |
|
| 462 |
| `analyze_results` | Agent Chat | Analyze detailed test results with optimization recommendations |
|
| 463 |
| `get_top_performers` | Agent Chat | Efficiently fetch top N models (90% token reduction) |
|
| 464 |
| `get_leaderboard_summary` | Agent Chat | Get high-level statistics (99% token reduction) |
|
|
|
|
| 458 |
| `analyze_leaderboard` | Leaderboard tab | Generate AI insights when user loads leaderboard |
|
| 459 |
| `estimate_cost` | New Evaluation tab | Predict costs before submitting evaluation |
|
| 460 |
| `debug_trace` | Trace Visualization | Answer questions about execution traces |
|
| 461 |
+
| `compare_runs` | Compare Runs/Agent Chat | Compare two evaluation runs side-by-side |
|
| 462 |
| `analyze_results` | Agent Chat | Analyze detailed test results with optimization recommendations |
|
| 463 |
| `get_top_performers` | Agent Chat | Efficiently fetch top N models (90% token reduction) |
|
| 464 |
| `get_leaderboard_summary` | Agent Chat | Get high-level statistics (99% token reduction) |
|
screens/documentation.py
CHANGED
|
@@ -1841,7 +1841,7 @@ TraceMind-MCP-Server demonstrates:
|
|
| 1841 |
- ✅ Standards-compliant MCP implementation
|
| 1842 |
- ✅ SSE transport for Gradio integration
|
| 1843 |
- ✅ Real-world use case (agent evaluation)
|
| 1844 |
-
- ✅ Gemini 2.5
|
| 1845 |
- ✅ Production-ready deployment on HF Spaces
|
| 1846 |
|
| 1847 |
**Used by**: TraceMind-AI (Track 2) for autonomous agent chat
|
|
@@ -2174,7 +2174,7 @@ TraceMind provides **AI-powered cost estimation** before you submit jobs:
|
|
| 2174 |
|
| 2175 |
**Data Sources**:
|
| 2176 |
1. **Historical Data** (preferred): Analyzes past runs from leaderboard
|
| 2177 |
-
2. **MCP Server** (fallback): Uses `estimate_cost` MCP tool with Gemini 2.5
|
| 2178 |
|
| 2179 |
### Estimation Process
|
| 2180 |
|
|
@@ -2219,7 +2219,7 @@ TraceMind provides **AI-powered cost estimation** before you submit jobs:
|
|
| 2219 |
```markdown
|
| 2220 |
## 💰 Cost Estimate - AI Analysis
|
| 2221 |
|
| 2222 |
-
**🤖 Powered by MCP Server + Gemini 2.5
|
| 2223 |
|
| 2224 |
*This estimate was generated by AI analysis since no historical
|
| 2225 |
data is available for this model.*
|
|
|
|
| 1841 |
- ✅ Standards-compliant MCP implementation
|
| 1842 |
- ✅ SSE transport for Gradio integration
|
| 1843 |
- ✅ Real-world use case (agent evaluation)
|
| 1844 |
+
- ✅ Gemini 2.5 Flash integration
|
| 1845 |
- ✅ Production-ready deployment on HF Spaces
|
| 1846 |
|
| 1847 |
**Used by**: TraceMind-AI (Track 2) for autonomous agent chat
|
|
|
|
| 2174 |
|
| 2175 |
**Data Sources**:
|
| 2176 |
1. **Historical Data** (preferred): Analyzes past runs from leaderboard
|
| 2177 |
+
2. **MCP Server** (fallback): Uses `estimate_cost` MCP tool with Gemini 2.5 Flash
|
| 2178 |
|
| 2179 |
### Estimation Process
|
| 2180 |
|
|
|
|
| 2219 |
```markdown
|
| 2220 |
## 💰 Cost Estimate - AI Analysis
|
| 2221 |
|
| 2222 |
+
**🤖 Powered by MCP Server + Gemini 2.5 Flash**
|
| 2223 |
|
| 2224 |
*This estimate was generated by AI analysis since no historical
|
| 2225 |
data is available for this model.*
|