feat: remove CSV support for knowledge base creation

script-docs/hub/ui/index.rst

@@ -180,7 +180,6 @@ The interface below displays the knowledge base details that need to be filled o
 - ``File``: The document to upload, containing the knowledge base content. Supported formats are:
     - **JSON**: A JSON file containing an array of objects
     - **JSONL**: A JSON Lines file with one object per line
-    - **CSV**: A CSV File (Deprecated)
 
 
 **JSON/JSONL format requirements:**
@@ -197,13 +196,6 @@ Each object in your JSON or JSONL file should have the following structure:
 - ``text`` (required): The document content
 - ``topic`` (optional): The topic classification for the document
 
-**CSV format requirements:**
-
-.. warning::
-    **Importing a knowledge base with CSV is deprecated** and will be removed in future versions. Please use JSON or JSONL formats for new knowledge bases.
-
-For CSV files, the format should have one column named ``text`` with the document content. If you're uploading a knowledge base with pre-defined topics, the file should have two columns with the first row labeled ``text,topic``.
-
 **General rules for all formats:**
     - If the ``text`` has a value but the ``topic`` is blank, the ``topic`` will be set to 'Others'. However, if all topics are blank, the ``topic`` will be automatically generated.
     - If both the ``text`` and ``topic`` are blank, or if the ``text`` is blank but the ``topic`` has a value, the entry will not be imported.

src/giskard_hub/resources/knowledge_bases.py

@@ -27,8 +27,8 @@ def create(  # pylint: disable=too-many-arguments
         name: str,
         data: Union[str, List[dict[str, str]]],
         description: Union[str, None] = None,
-        document_column: Union[str, NotGiven] = NOT_GIVEN,
-        topic_column: Union[str, NotGiven] = NOT_GIVEN,
+        document_column: str = "text",
+        topic_column: str = "topic",
     ) -> KnowledgeBase:
         """
         Create a new knowledge base.
@@ -40,13 +40,13 @@ def create(  # pylint: disable=too-many-arguments
         name : str
             The name of the knowledge base.
         data : str or list[dict[str, str]]
-            Either a filepath (str) to a JSON or JSONL file, or a list of dicts containing "text" and "topic" (optional) keys.
+            Either a filepath (str) to a JSON or JSONL file, or a list of dicts containing document and topic keys.
         description : str, optional
             Description of the knowledge base.
-        document_column : str, optional
-            Name of the document column.
-        topic_column : str, optional
-            Name of the topic column.
+        document_column : str, default "text"
+            Column name for document content in the data.
+        topic_column : str, default "topic"
+            Column name for topic classification in the data.
 
         Returns
         -------
@@ -58,7 +58,7 @@ def create(  # pylint: disable=too-many-arguments
                 "project_id": project_id,
                 "name": name,
                 "description": description,
-                "column": document_column,
+                "document_column": document_column,
                 "topic_column": topic_column,
             }
         )

tests/test_knowledge_bases.py

@@ -329,41 +329,6 @@ def test_create_with_list_of_dicts(self, mock_client):
         assert result.id == "kb-list"
         assert result.n_documents == 3
 
-    def test_create_with_csv_file_error(self, mock_client):
-        """Test creating a knowledge base with a CSV file (should error - not supported)."""
-        resource = KnowledgeBasesResource(mock_client)
-
-        # Create a temporary CSV file
-        csv_content = """text,topic
-First document content,topic1
-Second document content,topic2
-Third document content,topic3"""
-
-        with tempfile.NamedTemporaryFile(
-            mode="w", suffix=".csv", delete=False
-        ) as temp_file:
-            temp_file.write(csv_content)
-            temp_file_path = temp_file.name
-
-        try:
-            # Test that it raises an error for unsupported file format
-            with pytest.raises(
-                ValueError,
-                match="Only JSON and JSONL files are supported for file input",
-            ):
-                resource.create(
-                    project_id="project-id",
-                    name="CSV Knowledge Base",
-                    data=temp_file_path,
-                )
-
-            # Verify no API call was made due to validation error
-            mock_client.post.assert_not_called()
-
-        finally:
-            # Clean up temp file
-            Path(temp_file_path).unlink(missing_ok=True)
-
     def test_create_with_single_dict_error(self, mock_client):
         """Test creating a knowledge base with a single dict (should error - needs list)."""
         resource = KnowledgeBasesResource(mock_client)