feat: implement backend image classification with TensorFlow.js model

- Extend shared types for image classification, including PredictionProbability, UploaderMetadata, and ImageClassificationRecord.
- Create image_classifications table in the database with necessary fields and foreign key constraints.
- Implement disease mappers to convert database rows to shared disease records.
- Develop uploader client to handle image uploads to external service.
- Create image model service to load and classify images using TensorFlow.js.
- Add API routes for image classification, including GET for history and POST for new classifications.
- Implement frontend components for image classification form and display results.
- Update dashboard to integrate image classification functionality and display results.
- Document implementation plan for backend image classification.

apps/web/src/lib/api-client.ts

@@ -3,6 +3,7 @@ import type {
   DiseaseCatalogItem,
   ManualClassificationRequest,
   ManualClassificationRecord,
+  ImageClassificationRecord,
   DashboardSummary,
 } from '@zeavis/shared';
 
@@ -20,7 +21,6 @@ async function fetchApi<T>(endpoint: string, options?: RequestInit): Promise<T>
         errorMessage = errorData.error;
       }
     } catch {
-      // Response is not JSON, use default error message
     }
     throw new Error(errorMessage);
   }
@@ -53,6 +53,20 @@ export const apiClient = {
     });
   },
 
+  async getImageClassifications(): Promise<ImageClassificationRecord[]> {
+    return fetchApi('/api/v1/classifications/image');
+  },
+
+  async createImageClassification(file: File): Promise<ImageClassificationRecord> {
+    const formData = new FormData();
+    formData.append('file', file);
+
+    return fetchApi('/api/v1/classifications/image', {
+      method: 'POST',
+      body: formData,
+    });
+  },
+
   async getDashboardSummary(): Promise<DashboardSummary> {
     return fetchApi('/api/v1/dashboard/summary');
   },