Update weaviate_utils.py

weaviate_utils.py

@@ -36,22 +36,43 @@ def create_new_class_schema(client, class_name, class_description):
         st.success(f"Class {class_name} created successfully!")
     except Exception as e:
         st.error(f"Error creating class: {e}")
-
+        
 def ingest_data_to_weaviate(client, csv_file, selected_class):
-    # Convert CSV to DataFrame
+    # Read the CSV data
     data = csv_file.read().decode("utf-8")
     dataframe = pd.read_csv(StringIO(data))
 
-    # Check if columns match the selected class schema
+    # Fetch the schema for the selected class
     class_schema = get_class_schema(client, selected_class)
-    if class_schema:
+
+    # If the schema is empty, create it based on the CSV columns
+    if not class_schema or not class_schema["properties"]:
+        for column_name, data_type in zip(dataframe.columns, dataframe.dtypes):
+            property_schema = {
+                "name": column_name,
+                "description": f"Property for {column_name}",
+                "dataType": [map_dtype_to_weaviate(data_type)]
+            }
+            try:
+                client.schema.property.create(selected_class, property_schema)
+            except weaviate.exceptions.SchemaValidationException:
+                # Property might already exist, so we can continue
+                pass
+    else:
+        # If the schema is not empty, compare it with the CSV columns
         schema_columns = [prop["name"] for prop in class_schema["properties"]]
-        if set(dataframe.columns) == set(schema_columns):
-            data = dataframe.to_dict(orient="records")
-            client.data_object.create(data, selected_class)
-            st.success("Data ingested successfully!")
-        else:
-            st.error("The columns in the uploaded CSV do not match the schema of the selected class.")
+        if set(dataframe.columns) != set(schema_columns):
+            st.error("The columns in the uploaded CSV do not match the schema of the selected class. Please check and upload the correct CSV or create a new class.")
+            return
+
+    # Ingest the data into Weaviate
+    data = dataframe.to_dict(orient="records")
+    client.data_object.create(data, selected_class)
+
+    # Display a preview of the ingested data
+    st.write(f"Your CSV was successfully integrated into the vector database under the class '{selected_class}'")
+    st.write(dataframe.head())  # Display the first few rows of the dataframe as a preview
+
 
 def get_class_schema(client, class_name):
     try: