update api prices, openai dev day

app.py

@@ -1096,6 +1096,11 @@ def content_tab_settings():
         st.session_state.config['leafmachine']['cropped_components']['save_cropped_annotations'] = st.multiselect("Components to crop",  
                 ['ruler', 'barcode','label', 'colorcard','map','envelope','photo','attached_item','weights',
                 'leaf_whole', 'leaf_partial', 'leaflet', 'seed_fruit_one', 'seed_fruit_many', 'flower_one', 'flower_many', 'bud','specimen','roots','wood'],default=default_crops)
+        
+        st.subheader('Create OCR Overlay Image')
+        st.write('This will plot bounding boxes around all text that Google Vision was able to detect. If there are no boxes around text, then the OCR failed, so that missing text will not be seen by the LLM when it is creating the JSON object. The created image will be viewable in the VoucherVisionEditor.')
+        st.session_state.config['leafmachine']['do_create_OCR_helper_image'] = st.checkbox("Create image showing an overlay of the OCR detections", st.session_state.config['leafmachine'].get('do_create_OCR_helper_image', False))
+    
     with col_cropped_2:
         ba = os.path.join(st.session_state.dir_home,'demo', 'ba','ba2.png')
         image = Image.open(ba)

vouchervision/OCR_google_cloud_vision.py

@@ -60,10 +60,14 @@ def detect_text(path, client):
     else:
         return '', None, None
     
-def overlay_boxes_on_image(path, bounds):
-    image = Image.open(path)
-    draw_boxes(image, bounds, "green")
-    return image
+def overlay_boxes_on_image(path, bounds,do_create_OCR_helper_image):
+    if do_create_OCR_helper_image:
+        image = Image.open(path)
+        draw_boxes(image, bounds, "green")
+        return image
+    else:
+        image = Image.open(path)
+        return image
 
 
 

vouchervision/VoucherVision_Config_Builder.py

@@ -35,6 +35,7 @@ def build_VV_config():
     LLM_version_user = 'Azure GPT 4'
     prompt_version = 'Version 2' # from ["Version 1", "Version 1 No Domain Knowledge", "Version 2"]
     use_LeafMachine2_collage_images = False # Use LeafMachine2 collage images
+    do_create_OCR_helper_image = False
 
     batch_size = 500
 
@@ -49,12 +50,12 @@ def build_VV_config():
     return assemble_config(dir_home, run_name, dir_images_local,dir_output,
                     prefix_removal,suffix_removal,catalog_numerical_only,LLM_version_user,batch_size,
                     path_domain_knowledge,embeddings_database_name,use_LeafMachine2_collage_images,
-                    prompt_version, use_domain_knowledge=False)
+                    prompt_version, do_create_OCR_helper_image, use_domain_knowledge=False)
 
 def assemble_config(dir_home, run_name, dir_images_local,dir_output,
                     prefix_removal,suffix_removal,catalog_numerical_only,LLM_version_user,batch_size,
                     path_domain_knowledge,embeddings_database_name,use_LeafMachine2_collage_images,
-                    prompt_version, use_domain_knowledge=False):
+                    prompt_version, do_create_OCR_helper_image_user, use_domain_knowledge=False):
     
 
     # Initialize the base structure
@@ -104,6 +105,7 @@ def assemble_config(dir_home, run_name, dir_images_local,dir_output,
 
     LLM_version = LLM_version_user 
     use_RGB_label_images = use_LeafMachine2_collage_images # Use LeafMachine2 collage images
+    do_create_OCR_helper_image = do_create_OCR_helper_image_user
     
     cropped_components_section = {
         'do_save_cropped_annotations': True,
@@ -166,6 +168,7 @@ def assemble_config(dir_home, run_name, dir_images_local,dir_output,
     config_data['leafmachine']['project'] = project_section
     config_data['leafmachine']['LLM_version'] = LLM_version
     config_data['leafmachine']['use_RGB_label_images'] = use_RGB_label_images
+    config_data['leafmachine']['do_create_OCR_helper_image'] = do_create_OCR_helper_image
     config_data['leafmachine']['cropped_components'] = cropped_components_section
     config_data['leafmachine']['modules'] = modules_section
     config_data['leafmachine']['data'] = data_section
@@ -187,6 +190,7 @@ def build_api_tests(api):
     suffix_removal = ''
     catalog_numerical_only = False
     batch_size = 500
+    do_create_OCR_helper_image = False
 
 
     # ### Option 1: "GPT 4" of ["GPT 4", "GPT 3.5", "Azure GPT 4", "Azure GPT 3.5", "PaLM 2"]
@@ -234,7 +238,7 @@ def build_api_tests(api):
                 config_data, dir_home = assemble_config(dir_home, run_name, dir_images_local,dir_output,
                     prefix_removal,suffix_removal,catalog_numerical_only,LLM_version_user,batch_size,
                     path_domain_knowledge,embeddings_database_name,use_LeafMachine2_collage_images,
-                    prompt_version)
+                    prompt_version, do_create_OCR_helper_image)
                 
                 write_config_file(config_data, os.path.join(dir_home,'demo','demo_configs'),filename=filename)
 
@@ -258,6 +262,7 @@ def build_demo_tests(llm_version):
     suffix_removal = ''
     catalog_numerical_only = False
     batch_size = 500
+    do_create_OCR_helper_image = False
 
 
     # ### Option 1: "GPT 4" of ["GPT 4", "GPT 3.5", "Azure GPT 4", "Azure GPT 3.5", "PaLM 2"]
@@ -306,23 +311,23 @@ def build_demo_tests(llm_version):
                         config_data, dir_home = assemble_config(dir_home, run_name, dir_images_local,dir_output,
                             prefix_removal,suffix_removal,catalog_numerical_only,LLM_version_user,batch_size,
                             path_domain_knowledge,embeddings_database_name,use_LeafMachine2_collage_images,
-                            prompt_version, use_domain_knowledge=True)
+                            prompt_version, do_create_OCR_helper_image, use_domain_knowledge=True)
                     else:
                         config_data, dir_home = assemble_config(dir_home, run_name, dir_images_local,dir_output,
                             prefix_removal,suffix_removal,catalog_numerical_only,LLM_version_user,batch_size,
                             path_domain_knowledge,embeddings_database_name,use_LeafMachine2_collage_images,
-                            prompt_version)
+                            prompt_version, do_create_OCR_helper_image)
                 elif llm_version == 'palm':
                     if prompt_version in ['Version 1 PaLM 2']:
                         config_data, dir_home = assemble_config(dir_home, run_name, dir_images_local,dir_output,
                             prefix_removal,suffix_removal,catalog_numerical_only,LLM_version_user,batch_size,
                             path_domain_knowledge,embeddings_database_name,use_LeafMachine2_collage_images,
-                            prompt_version, use_domain_knowledge=True)
+                            prompt_version, do_create_OCR_helper_image, use_domain_knowledge=True)
                     else:
                         config_data, dir_home = assemble_config(dir_home, run_name, dir_images_local,dir_output,
                             prefix_removal,suffix_removal,catalog_numerical_only,LLM_version_user,batch_size,
                             path_domain_knowledge,embeddings_database_name,use_LeafMachine2_collage_images,
-                            prompt_version)
+                            prompt_version, do_create_OCR_helper_image)
                 
                 
                 write_config_file(config_data, os.path.join(dir_home,'demo','demo_configs'),filename=filename)

vouchervision/utils_VoucherVision.py

@@ -604,7 +604,7 @@ class VoucherVision():
                 self.logger.info(f'Working on {i+1}/{len(self.img_paths)} --- Finished OCR')
                 if len(self.OCR) > 0:
                     self.logger.info(f'Working on {i+1}/{len(self.img_paths)} --- Creating OCR Overlay Image')
-                    self.overlay_image = overlay_boxes_on_image(path_to_crop, self.bounds)
+                    self.overlay_image = overlay_boxes_on_image(path_to_crop, self.bounds, self.cfg['leafmachine']['do_create_OCR_helper_image'])
                     self.logger.info(f'Working on {i+1}/{len(self.img_paths)} --- Saved OCR Overlay Image')
                     
                     self.write_json_to_file(txt_file_path_OCR, {"OCR":self.OCR})
@@ -672,7 +672,7 @@ class VoucherVision():
                     self.logger.info(f'Working on {i+1}/{len(self.img_paths)} --- Finished OCR')
 
                     self.logger.info(f'Working on {i+1}/{len(self.img_paths)} --- Creating OCR Overlay Image')
-                    self.overlay_image = overlay_boxes_on_image(path_to_crop, self.bounds)
+                    self.overlay_image = overlay_boxes_on_image(path_to_crop, self.bounds, self.cfg['leafmachine']['do_create_OCR_helper_image'])
                     self.logger.info(f'Working on {i+1}/{len(self.img_paths)} --- Saved OCR Overlay Image')
                     
                     self.write_json_to_file(txt_file_path_OCR, {"OCR":self.OCR})