Spaces:
Sleeping
Sleeping
Commit History
-
🐛 Fix Stage 3 feature analysis display issue
- Add proper handling for feature_descriptions field (which is a list) - Add detailed logging to debug stage result content - Now properly displays actual VLM feature analysis instead of generic 'Analysis completed' 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>0c8c84a -
🐛 Fix indentation error in app.py
Remove duplicate try-except blocks and fix code alignment to resolve IndentationError on line 346. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>360e533 -
🚀 Implement progressive results display for real-time UI updates
- Add run_pipeline_progressive() method to pipeline for stage-by-stage callbacks - Update Streamlit app to show each analysis stage result immediately - Display running status indicators and completion checkmarks - Auto-expand completed stages for immediate viewing - Eliminate perceived lag time by showing results as they're generated 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>002b4c1 -
🐛 Add comprehensive logging and remove CMPO mapping
- Add detailed logging throughout analysis pipeline for debugging - Remove CMPO phenotype mapping to simplify app and focus on 4-stage VLM - Add error traceback display for better debugging - Add status messages during analysis process 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>596cd10 -
🐳 Fix Dockerfile OpenGL package dependency
Update libgl1-mesa-glx to libgl1 for Debian trixie compatibility. Add fallback package installation to handle different Debian versions. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>e53b543
-
Fix Streamlit deprecation warning: use_column_width → use_container_width
🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>c6ab96d -
Fix Gemini VLM truncation and improve 4-stage analysis prompts
- Increase max_output_tokens for Gemini from default to 2000 to prevent truncation - Add proper generation_config with temperature and sampling parameters - Update all 4 stage prompts with detailed, biological context-aware questions - Replace technical format requirements with natural language instructions - Improve prompt clarity for better VLM understanding and responses 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>818797a
-
updated app
9d5f53d -
Improve mobile responsiveness and fix random button
ac00bb1 -
updated streamlite version, random button functionality
50f6d31 -
fixes bug
b329e55 -
config changes
4012c3c -
updated stuf
cc1addd -
fixed config
36076d6 -
fixed docker stuff
3de80f2 -
updated docker
abe4b09 -
minimal example
b69e9e7 -
initial commit
cba4849 -
Duplicate from streamlit/streamlit-template-space
Co-authored-by: Franck Abgrall <FranckAbgrall@users.noreply.huggingface.co>252227d
