update the cv modal inference proxy server with optimization #6
Reference in New Issue
Block a user
No description provided.
Delete Branch "poc_1_3"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Summary by CodeRabbit
New Features
Bug Fixes
Documentation
ℹ️ Recent review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID:
49efd638-5734-4822-ab59-890a0403488a📥 Commits
Reviewing files that changed from the base of the PR and between
3435cfefa0and1f5e71b46a.⛔ Files ignored due to path filters (3)
workspace/sprint_1_2/PRODUCT_VISUALIZATION/home_screen.pngis excluded by!**/*.pngworkspace/sprint_1_2/PRODUCT_VISUALIZATION/interactive_diagnosis.pngis excluded by!**/*.pngworkspace/sprint_1_2/PRODUCT_VISUALIZATION/the_diagnosis_screen.pngis excluded by!**/*.png📒 Files selected for processing (48)
.gitignoreproj_level_reading/PROPOSAL/VKIST_MSK_PILOT_PROPOSAL.mdworkspace/sprint_1_2/CODEBASE/backend/cv_inference_server.pyworkspace/sprint_1_2/CODEBASE/backend/implementation/adapters/triton_adapter.pyworkspace/sprint_1_2/CODEBASE/backend/implementation/tasks/__init__.pyworkspace/sprint_1_2/CODEBASE/backend/implementation/tasks/cv_tasks.pyworkspace/sprint_1_2/CODEBASE/backend/logging/logging_config.pyworkspace/sprint_1_2/CODEBASE/backend/routers/cv_inference.pyworkspace/sprint_1_2/CODEBASE/backend/routers/run_cv_inference.shworkspace/sprint_1_2/CODEBASE/backend/services/celery_app.pyworkspace/sprint_1_2/CODEBASE/backend/services/cv_celery_service.pyworkspace/sprint_1_2/CODEBASE/backend/services/cv_inference_service.pyworkspace/sprint_1_2/CODEBASE/backend/services/triton_runtime_service.pyworkspace/sprint_1_2/CODEBASE/backend/services/triton_warmup.pyworkspace/sprint_1_2/CODEBASE/backend/start_celery_workers.shworkspace/sprint_1_2/CODEBASE/frontend/implementation/.gitignoreworkspace/sprint_1_2/CODEBASE/frontend/implementation/config/frontend.config.yamlworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/components/molecules/CalibrationControls.tsxworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/components/molecules/ClinicalChatPanel.tsxworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/components/molecules/ClinicalChatThought.tsxworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/components/molecules/RecordingModeSelector.tsxworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/components/molecules/SeverityBadge.tsxworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/components/organisms/DiagnosticCanvas.tsxworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/components/organisms/ReviewDiagnosticSessionPanel.tsxworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/components/organisms/SideNavBar.tsxworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/components/shells/WorkspaceShell.tsxworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/data/calibrationMetricHelp.tsworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/data/calibrationTiers.tsworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/hooks/useClinicalChat.tsworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/hooks/useSegmentationOverlay.tsworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/lib/cvAnalyzeApi.tsworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/lib/llm/clinicalChatConfig.tsworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/lib/llm/llmWorkerClient.tsworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/lib/llm/modelLoadProgress.tsworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/lib/llm/opfsModelStore.tsworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/lib/llm/runClinicalChatTurn.tsworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/pages/ClinicalWorkspacePage.tsxworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/vite-env.d.tsworkspace/sprint_1_2/CODEBASE/frontend/implementation/src/workers/llm.worker.tsworkspace/sprint_1_2/CODEBASE/frontend/implementation/tsconfig.jsonworkspace/sprint_1_2/CODEBASE/frontend/implementation/tsconfig.tsbuildinfoworkspace/sprint_1_2/CODEBASE/frontend/implementation/vite.config.tsworkspace/sprint_1_2/CODEBASE/infra/implementation/cicd/jenkin_run.shworkspace/sprint_1_2/CODEBASE/infra/implementation/cicd/suggested_cicd_pipeline.mdworkspace/sprint_1_2/CODEBASE/infra/implementation/cicd/the_pipeline.mdworkspace/sprint_1_2/CODEBASE/infra/implementation/triton_run/modal_triton.pyworkspace/sprint_1_2/CODEBASE/infra/implementation/triton_run/run.shworkspace/sprint_1_2/CODEBASE/requirements.txt📝 Walkthrough
Walkthrough
This change adds a Celery-backed CV inference pipeline, concurrent Triton execution, segmented clinical chat streaming, resumable model-install handling, frontend configuration, UI updates, deployment changes, and pilot/CI/CD documentation.
Changes
CV inference pipeline
backend/services/*,backend/implementation/tasks/*,backend/routers/cv_inference.py,backend/logging/*backend/implementation/adapters/*,backend/services/triton_*,backend/services/cv_inference_service.py,backend/cv_inference_server.pyfrontend/implementation/src/lib/cvAnalyzeApi.ts,src/hooks/useSegmentationOverlay.ts,src/components/organisms/DiagnosticCanvas.tsx,src/pages/ClinicalWorkspacePage.tsxbackend/start_celery_workers.sh,backend/routers/run_cv_inference.sh,frontend/implementation/vite.config.ts,requirements.txtClinical chat workflow
frontend/implementation/src/lib/llm/*,src/workers/llm.worker.ts,src/hooks/useClinicalChat.tsfrontend/implementation/src/lib/llm/modelLoadProgress.ts,opfsModelStore.ts,src/hooks/useClinicalChat.tsfrontend/implementation/src/components/molecules/ClinicalChatPanel.tsx,ClinicalChatThought.tsx,src/lib/llm/clinicalChatConfig.tsProduct and infrastructure artifacts
proj_level_reading/PROPOSAL/*,infra/implementation/cicd/*frontend/implementation/config/*,src/components/*,src/data/*,src/components/shells/*,src/vite-env.d.ts.gitignore,infra/implementation/triton_run/*,requirements.txtEstimated code review effort: 5 (Critical) | ~120 minutes
Sequence Diagram(s)
✨ Finishing Touches
📝 Generate docstrings
🧪 Generate unit tests (beta)
poc_1_3Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.
❤️ Share
Comment
@coderabbitai helpto get the list of available commands.