fix: Use the identifier column as hash if available (#9405)

* fix: Use the identifier column as hash if available

* Update kb_ingest.py

* [autofix.ci] apply automated fixes

* Update src/backend/base/langflow/components/data/kb_ingest.py

Co-authored-by: Edwin Jose <edwin.jose@datastax.com>

* [autofix.ci] apply automated fixes

* [autofix.ci] apply automated fixes

---------

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Edwin Jose <edwin.jose@datastax.com>

src/backend/base/langflow/components/data/kb_ingest.py

@@ -139,8 +139,8 @@ class KBIngestionComponent(Component):
                 {
                     "column_name": "text",
                     "vectorize": True,
-                    "identifier": False,
-                }
+                    "identifier": True,
+                },
             ],
         ),
         IntInput(
@@ -402,16 +402,22 @@ class KBIngestionComponent(Component):
 
         # Convert each row to a Data object
         for _, row in df_source.iterrows():
-            # Build content text from vectorized columns using list comprehension
-            content_parts = [str(row[col]) for col in content_cols if col in row and pd.notna(row[col])]
+            # Build content text from identifier columns using list comprehension
+            identifier_parts = [str(row[col]) for col in content_cols if col in row and pd.notna(row[col])]
 
-            page_content = " ".join(content_parts)
+            # Join all parts into a single string
+            page_content = " ".join(identifier_parts)
 
             # Build metadata from NON-vectorized columns only (simple key-value pairs)
             data_dict = {
                 "text": page_content,  # Main content for vectorization
             }
 
+            # Add identifier columns if they exist
+            if identifier_cols:
+                identifier_parts = [str(row[col]) for col in identifier_cols if col in row and pd.notna(row[col])]
+                page_content = " ".join(identifier_parts)
+
             # Add metadata columns as simple key-value pairs
             for col in df_source.columns:
                 if col not in content_cols and col in row and pd.notna(row[col]):