Update app.py

app.py

@@ -139,6 +139,16 @@ def summarize_map_reduce(data, questions):
         all_answers.extend(chunk_answers)
     return all_answers
 
+def get_class_schema(class_name):
+    """
+    Get the schema for a specific class.
+    """
+    all_classes = client.schema.get()["classes"]
+    for cls in all_classes:
+        if cls["class"] == class_name:
+            return cls
+    return None
+
 st.title("TAPAS Table Question Answering with Weaviate")
 
 # Get existing classes from Weaviate
@@ -155,18 +165,28 @@ else:
 
 # Upload CSV data
 csv_file = st.file_uploader("Upload a CSV file", type=["csv"])
+
+# Display the schema if an existing class is selected
+if selected_class != "New Class":
+    st.write(f"Schema for {selected_class}:")
+    class_schema = get_class_schema(selected_class)
+    if class_schema:
+        properties = class_schema["properties"]
+        schema_df = pd.DataFrame(properties)
+        st.table(schema_df[["name", "dataType"]])  # Display only the name and dataType columns
+
+# Before ingesting data into Weaviate, check if CSV columns match the class schema
 if csv_file is not None:
     data = csv_file.read().decode("utf-8")
     dataframe = pd.read_csv(StringIO(data))
     
-    # Display the schema if an existing class is selected
-    if selected_class != "New Class":
-        st.write(f"Schema for {selected_class}:")
-        class_schema = client.schema.get_class(selected_class)
-        st.write(class_schema)
-    
-    # Ingest data into Weaviate
-    ingest_data_to_weaviate(dataframe, class_name, class_description)
+    # Check if columns match
+    schema_columns = [prop["name"] for prop in class_schema["properties"]]
+    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.")
+    else:
+        # Ingest data into Weaviate
+        ingest_data_to_weaviate(dataframe, class_name, class_description)
 
     # Input for questions
     questions = st.text_area("Enter your questions (one per line)")