fix llamacloud api and markdown issue (#532)

Author: leehuwuj

llama-index-server/llama_index/server/api/routers/chat.py

@@ -99,18 +99,15 @@ async def _text_stream(
         event: Union[AgentStream, StopEvent],
     ) -> AsyncGenerator[str, None]:
         if isinstance(event, AgentStream):
-            if event.delta.strip():  # Only yield non-empty deltas
-                yield event.delta
+            yield event.delta
         elif isinstance(event, StopEvent):
             if isinstance(event.result, str):
                 yield event.result
             elif isinstance(event.result, AsyncGenerator):
                 async for chunk in event.result:
                     if isinstance(chunk, str):
                         yield chunk
-                    elif (
-                        hasattr(chunk, "delta") and chunk.delta.strip()
-                    ):  # Only yield non-empty deltas
+                    elif hasattr(chunk, "delta") and chunk.delta:
                         yield chunk.delta
 
     stream_started = False

llama-index-server/llama_index/server/services/llamacloud/file.py

@@ -74,7 +74,7 @@ def add_file_to_pipeline(
                 "custom_metadata": {"file_id": file_id, **(custom_metadata or {})},
             }
         ]
-        files = client.pipelines.add_files_to_pipeline(pipeline_id, request=files)
+        files = client.pipelines.add_files_to_pipeline_api(pipeline_id, request=files)
 
         if not wait_for_processing:
             return file_id