Update weaviate_utils.py

weaviate_utils.py

@@ -22,37 +22,33 @@ def map_dtype_to_weaviate(dtype):
     else:
         return "string"
 
-def ingest_data_to_weaviate(client, dataframe, class_name, class_description):
-    # Create class schema
+def create_new_class_schema(client, class_name, class_description):
     class_schema = {
         "class": class_name,
         "description": class_description,
-        "properties": []  # Start with an empty properties list
+        "properties": []
     }
-    
-    # Try to create the class without properties first
     try:
         client.schema.create({"classes": [class_schema]})
-    except weaviate.exceptions.SchemaValidationException:
-        # Class might already exist, so we can continue
-        pass
+        st.success(f"Class {class_name} created successfully!")
+    except Exception as e:
+        st.error(f"Error creating class: {e}")
 
-    # Now, let's add properties to the class
-    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(class_name, property_schema)
-        except weaviate.exceptions.SchemaValidationException:
-            # Property might already exist, so we can continue
-            pass
+def ingest_data_to_weaviate(client, csv_file, selected_class):
+    # Convert CSV to DataFrame
+    data = csv_file.read().decode("utf-8")
+    dataframe = pd.read_csv(StringIO(data))
 
-    # Now, let's ingest the data
-    data = dataframe.to_dict(orient="records")
-    client.data_object.create(data, class_name)
+    # Check if columns match the selected class schema
+    class_schema = get_class_schema(client, selected_class)
+    if class_schema:
+        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.")
 
 def get_class_schema(client, class_name):
     try: