Update flagging functionality in app.py and flagging.py to use metadata for user information and change dataset name to versioned format

app.py

@@ -69,21 +69,26 @@ def inference(image):
 
 
 def flag_img_input(
-    image: gr.Image, flag_option: str = "misdetection", username: str = "anonymous"
+    image: gr.Image, name: str = "misdetection", email: str = "anonymous@example.com"
 ):
     """Wrapper for flagging"""
-    logger.info("Flagging image - option: %s, user: %s", flag_option, username)
+    logger.info("Flagging image - name: %s, email: %s", name, email)
 
     # Decode blob data if necessary
     if is_blob_data(image):
         image = decode_blob_data(image)
 
-    hf_writer.flag([image], flag_option=flag_option, username=username)
+    metadata = {
+        "name": name,
+        "email": email,
+    }
+
+    hf_writer.flag([image], metadata=metadata)
     logger.info("Image flagged successfully")
 
 
 # Flagging
-dataset_name = "SEA-AI/crowdsourced-sea-images"
+dataset_name = "SEA-AI/crowdsourced-sea-images-v2"
 hf_writer = HuggingFaceDatasetSaver(get_token(), dataset_name)
 flagged_counter = FlaggedCounter(dataset_name)
 
@@ -148,6 +153,10 @@ with gr.Blocks(theme=theme, css=css, title="SEA.AI Vision Demo") as demo:
             flag: gr.Button(FLAG_TXT, interactive=True, visible=visible),
             notice: gr.Markdown(value=NOTICE, visible=visible),
         }
+    
+    # add hidden textbox for name and email (hacky but well...)
+    name = gr.Textbox(label="name", visible=False, value="anonymous")
+    email = gr.Textbox(label="email", visible=False, value="[email protected]")
 
     # This needs to be called prior to the first call to callback.flag()
     hf_writer.setup([img_input], "flagged")
@@ -160,7 +169,7 @@ with gr.Blocks(theme=theme, css=css, title="SEA.AI Vision Demo") as demo:
         show_api=False,
     ).then(
         flag_img_input,
-        [img_input],
+        [img_input, name, email],
         [],
         preprocess=False,
         show_api=True,

flagging.py

@@ -108,11 +108,10 @@ class HuggingFaceDatasetSaver(FlaggingCallback):
             except huggingface_hub.utils.EntryNotFoundError:
                 pass
 
-    def flag(
+    def flag(  # pylint: disable=arguments-differ
         self,
         flag_data: list[Any],
-        flag_option: str = "",
-        username: str | None = None,
+        metadata: dict[str, str] | None = None,
     ) -> int:
         if self.separate_dirs:
             # JSONL files to support dataset preview on the Hub
@@ -131,8 +130,7 @@ class HuggingFaceDatasetSaver(FlaggingCallback):
             components_dir=components_dir,
             path_in_repo=path_in_repo,
             flag_data=flag_data,
-            flag_option=flag_option,
-            username=username or "",
+            metadata=metadata if metadata is not None else {},
         )
 
     def _flag_in_dir(
@@ -141,12 +139,11 @@ class HuggingFaceDatasetSaver(FlaggingCallback):
         components_dir: Path,
         path_in_repo: str | None,
         flag_data: list[Any],
-        flag_option: str = "",
-        username: str = "",
+        metadata: dict[str, str],
     ) -> int:
         # Deserialize components (write images/audio to files)
         features, row = self._deserialize_components(
-            components_dir, flag_data, flag_option, username
+            components_dir, flag_data, metadata
         )
 
         # Write generic info to dataset_infos.json + upload
@@ -226,8 +223,7 @@ class HuggingFaceDatasetSaver(FlaggingCallback):
         self,
         data_dir: Path,
         flag_data: list[Any],
-        flag_option: str = "",
-        username: str = "",
+        metadata: dict[str, str],
     ) -> tuple[dict[Any, Any], list[Any]]:
         """Deserialize components and return the corresponding row for the flagged sample.
 
@@ -279,10 +275,9 @@ class HuggingFaceDatasetSaver(FlaggingCallback):
                     )
                 else:
                     row.append("")
-        features["flag"] = {"dtype": "string", "_type": "Value"}
-        features["username"] = {"dtype": "string", "_type": "Value"}
-        row.append(flag_option)
-        row.append(username)
+        for key, value in metadata.items():
+            features[key] = {"dtype": "string", "_type": "Value"}
+            row.append(value)
         return features, row
 
 
@@ -299,8 +294,7 @@ class myHuggingFaceDatasetSaver(HuggingFaceDatasetSaver):
         self,
         data_dir: Path,
         flag_data: list[Any],
-        flag_option: str = "",
-        username: str = "",
+        metadata: dict[str, str],
     ) -> tuple[dict[Any, Any], list[Any]]:
         """Deserialize components and return the corresponding row for the flagged sample.
 
@@ -353,8 +347,7 @@ class myHuggingFaceDatasetSaver(HuggingFaceDatasetSaver):
                     )
                 else:
                     row.append("")
-        features["flag"] = {"dtype": "string", "_type": "Value"}
-        features["username"] = {"dtype": "string", "_type": "Value"}
-        row.append(flag_option)
-        row.append(username)
+        for key, value in metadata.items():
+            features[key] = {"dtype": "string", "_type": "Value"}
+            row.append(value)
         return features, row