fixed refactored code

src/embeddingbuddy/data/parser.py

@@ -16,11 +16,26 @@ class NDJSONParser:
     @staticmethod
     def parse_text(text_content: str) -> List[Document]:
         documents = []
-        for line in text_content.strip().split("\n"):
+        for line_num, line in enumerate(text_content.strip().split("\n"), 1):
             if line.strip():
-                doc_dict = json.loads(line)
-                doc = NDJSONParser._dict_to_document(doc_dict)
-                documents.append(doc)
+                try:
+                    doc_dict = json.loads(line)
+                    doc = NDJSONParser._dict_to_document(doc_dict)
+                    documents.append(doc)
+                except json.JSONDecodeError as e:
+                    raise json.JSONDecodeError(
+                        f"Invalid JSON on line {line_num}: {e.msg}",
+                        e.doc,
+                        e.pos
+                    )
+                except KeyError as e:
+                    raise KeyError(
+                        f"Missing required field {e} on line {line_num}"
+                    )
+                except (TypeError, ValueError) as e:
+                    raise ValueError(
+                        f"Invalid data format on line {line_num}: {str(e)}"
+                    )
         return documents
 
     @staticmethod
@@ -28,10 +43,29 @@ class NDJSONParser:
         if "id" not in doc_dict:
             doc_dict["id"] = str(uuid.uuid4())
 
+        # Validate required fields
+        if "text" not in doc_dict:
+            raise KeyError("'text'")
+        if "embedding" not in doc_dict:
+            raise KeyError("'embedding'")
+
+        # Validate embedding format
+        embedding = doc_dict["embedding"]
+        if not isinstance(embedding, list):
+            raise ValueError(f"Embedding must be a list, got {type(embedding).__name__}")
+        
+        if not embedding:
+            raise ValueError("Embedding cannot be empty")
+        
+        # Check that all embedding values are numbers
+        for i, val in enumerate(embedding):
+            if not isinstance(val, (int, float)) or val != val:  # NaN check
+                raise ValueError(f"Embedding contains invalid value at index {i}: {val}")
+
         return Document(
             id=doc_dict["id"],
             text=doc_dict["text"],
-            embedding=doc_dict["embedding"],
+            embedding=embedding,
             category=doc_dict.get("category"),
             subcategory=doc_dict.get("subcategory"),
             tags=doc_dict.get("tags"),

src/embeddingbuddy/ui/callbacks/data_processing.py

@@ -9,30 +9,52 @@ class DataProcessingCallbacks:
 
     def _register_callbacks(self):
         @callback(
-            Output("processed-data", "data"),
+            [
+                Output("processed-data", "data", allow_duplicate=True),
+                Output("upload-error-alert", "children", allow_duplicate=True),
+                Output("upload-error-alert", "is_open", allow_duplicate=True),
+                Output("upload-success-alert", "children", allow_duplicate=True),
+                Output("upload-success-alert", "is_open", allow_duplicate=True),
+            ],
             Input("upload-data", "contents"),
             State("upload-data", "filename"),
+            prevent_initial_call=True,
         )
         def process_uploaded_file(contents, filename):
             if contents is None:
-                return None
+                return None, "", False, "", False
 
             processed_data = self.processor.process_upload(contents, filename)
 
             if processed_data.error:
-                return {"error": processed_data.error}
+                error_message = self._format_error_message(processed_data.error, filename)
+                return (
+                    {"error": processed_data.error},
+                    error_message,
+                    True,  # Show error alert
+                    "",
+                    False,  # Hide success alert
+                )
 
-            return {
-                "documents": [
-                    self._document_to_dict(doc) for doc in processed_data.documents
-                ],
-                "embeddings": processed_data.embeddings.tolist(),
-            }
+            success_message = f"Successfully loaded {len(processed_data.documents)} documents from {filename or 'file'}"
+            return (
+                {
+                    "documents": [
+                        self._document_to_dict(doc) for doc in processed_data.documents
+                    ],
+                    "embeddings": processed_data.embeddings.tolist(),
+                },
+                "",
+                False,  # Hide error alert
+                success_message,
+                True,   # Show success alert
+            )
 
         @callback(
-            Output("processed-prompts", "data"),
+            Output("processed-prompts", "data", allow_duplicate=True),
             Input("upload-prompts", "contents"),
             State("upload-prompts", "filename"),
+            prevent_initial_call=True,
         )
         def process_uploaded_prompts(contents, filename):
             if contents is None:
@@ -60,3 +82,40 @@ class DataProcessingCallbacks:
             "subcategory": doc.subcategory,
             "tags": doc.tags,
         }
+
+    @staticmethod
+    def _format_error_message(error: str, filename: str | None = None) -> str:
+        """Format error message with helpful guidance for users."""
+        file_part = f" in file '{filename}'" if filename else ""
+        
+        # Check for common error patterns and provide helpful messages
+        if "embedding" in error.lower() and ("key" in error.lower() or "required field" in error.lower()):
+            return (
+                f"❌ Missing 'embedding' field{file_part}. "
+                "Each line must contain an 'embedding' field with a list of numbers."
+            )
+        elif "text" in error.lower() and ("key" in error.lower() or "required field" in error.lower()):
+            return (
+                f"❌ Missing 'text' field{file_part}. "
+                "Each line must contain a 'text' field with the document content."
+            )
+        elif "json" in error.lower() and "decode" in error.lower():
+            return (
+                f"❌ Invalid JSON format{file_part}. "
+                "Please check that each line is valid JSON with proper syntax (quotes, braces, etc.)."
+            )
+        elif "unicode" in error.lower() or "decode" in error.lower():
+            return (
+                f"❌ File encoding issue{file_part}. "
+                "Please ensure the file is saved in UTF-8 format and contains no binary data."
+            )
+        elif "array" in error.lower() or "list" in error.lower():
+            return (
+                f"❌ Invalid embedding format{file_part}. "
+                "Embeddings must be arrays/lists of numbers, not strings or other types."
+            )
+        else:
+            return (
+                f"❌ Error processing file{file_part}: {error}. "
+                "Please check that your file is valid NDJSON with required 'text' and 'embedding' fields."
+            )

src/embeddingbuddy/ui/components/sidebar.py

@@ -11,14 +11,18 @@ class SidebarComponent:
         return dbc.Col(
             [
                 html.H5("Upload Data", className="mb-3"),
+                self.upload_component.create_error_alert(),
+                self.upload_component.create_success_alert(),
                 self.upload_component.create_data_upload(),
                 self.upload_component.create_prompts_upload(),
                 self.upload_component.create_reset_button(),
                 html.H5("Visualization Controls", className="mb-3"),
-                self._create_method_dropdown(),
-                self._create_color_dropdown(),
-                self._create_dimension_toggle(),
-                self._create_prompts_toggle(),
+            ]
+            + self._create_method_dropdown()
+            + self._create_color_dropdown()
+            + self._create_dimension_toggle()
+            + self._create_prompts_toggle()
+            + [
                 html.H5("Point Details", className="mb-3"),
                 html.Div(
                     id="point-details", children="Click on a point to see details"

src/embeddingbuddy/ui/components/upload.py

@@ -51,3 +51,25 @@ class UploadComponent:
             className="mb-3",
             style={"width": "100%"},
         )
+
+    @staticmethod
+    def create_error_alert():
+        """Create error alert component for data upload issues."""
+        return dbc.Alert(
+            id="upload-error-alert",
+            dismissable=True,
+            is_open=False,
+            color="danger",
+            className="mb-3",
+        )
+
+    @staticmethod
+    def create_success_alert():
+        """Create success alert component for successful uploads."""
+        return dbc.Alert(
+            id="upload-success-alert",
+            dismissable=True,
+            is_open=False,
+            color="success",
+            className="mb-3",
+        )

src/embeddingbuddy/ui/layout.py

@@ -9,7 +9,7 @@ class AppLayout:
 
     def create_layout(self):
         return dbc.Container(
-            [self._create_header(), self._create_main_content(), self._create_stores()],
+            [self._create_header(), self._create_main_content()] + self._create_stores(),
             fluid=True,
         )