Upload app.py

app.py

@@ -176,16 +176,37 @@ def load_data_and_setup_chroma():
                              parsed = json.loads(item) if isinstance(item, str) else item
                              parsed_metadatas.append(parsed if isinstance(parsed, dict) else {})
                          except:
-                             parsed_metadatas.append({})
-                     metadatas_list = parsed_metadatas
-
-                collection.add(
-                    ids=batch_df['id'].tolist(),
-                    embeddings=batch_df['embedding'].tolist(),
-                    documents=batch_df['document'].tolist(),
-                    metadatas=metadatas_list
-                )
-            except Exception as e:
+                              parsed_metadatas.append({})
+                      metadatas_list = parsed_metadatas
+
+                 # --- Clean None values from metadata ---
+                 cleaned_metadatas = []
+                 for meta_dict in metadatas_list:
+                     cleaned_dict = {}
+                     if isinstance(meta_dict, dict):
+                         for key, value in meta_dict.items():
+                             # Replace None with empty string, keep other valid types
+                             if value is None:
+                                 cleaned_dict[key] = ""
+                             elif isinstance(value, (str, int, float, bool)):
+                                 cleaned_dict[key] = value
+                             else:
+                                 # Attempt to convert other types to string, or skip
+                                 try:
+                                     cleaned_dict[key] = str(value)
+                                     logging.warning(f"Converted unexpected metadata type ({type(value)}) to string for key '{key}'.")
+                                 except:
+                                     logging.warning(f"Skipping metadata key '{key}' with unconvertible type {type(value)}.")
+                     cleaned_metadatas.append(cleaned_dict)
+                 # -----------------------------------------
+
+                 collection.add(
+                     ids=batch_df['id'].tolist(),
+                     embeddings=batch_df['embedding'].tolist(),
+                     documents=batch_df['document'].tolist(),
+                     metadatas=cleaned_metadatas # Use cleaned list
+                 )
+             except Exception as e:
                 logging.error(f"Error adding batch {i+1}/{num_batches} to in-memory Chroma: {e}")
                 error_count += 1
             progress_bar.progress((i + 1) / num_batches, text=f"Loading embeddings... Batch {i+1}/{num_batches}")