Merge branch 'clear-text-before-insert' into simplify-cli-arguments

lightrag/api/lightrag_server.py

@@ -181,6 +181,8 @@ def create_app(args):
                             "Skip document scanning(another scanning is active)"
                         )
 
+            ASCIIColors.green("\nServer is ready to accept connections! 🚀\n")
+
             yield
 
         finally:

lightrag/api/routers/document_routes.py

@@ -161,7 +161,7 @@ class DocumentManager:
         """Scan input directory for new files"""
         new_files = []
         for ext in self.supported_extensions:
-            logging.info(f"Scanning for {ext} files in {self.input_dir}")
+            logging.debug(f"Scanning for {ext} files in {self.input_dir}")
             for file_path in self.input_dir.rglob(f"*{ext}"):
                 if file_path not in self.indexed_files:
                     new_files.append(file_path)

lightrag/api/utils_api.py

@@ -492,7 +492,5 @@ def display_splash_screen(args: argparse.Namespace) -> None:
     Make sure to include the X-API-Key header in all your requests.
     """)
 
-    ASCIIColors.green("Server is ready to accept connections! 🚀\n")
-
     # Ensure splash output flush to system log
     sys.stdout.flush()

lightrag/lightrag.py

@@ -581,7 +581,7 @@ class LightRAG:
                 await self._insert_done()
 
     async def apipeline_enqueue_documents(
-        self, input: str | list[str], ids: list[str] | None
+        self, input: str | list[str], ids: list[str] | None = None
     ) -> None:
         """
         Pipeline for Processing Documents
@@ -595,9 +595,6 @@ class LightRAG:
         if isinstance(input, str):
             input = [input]
 
-        # Clean input text and remove duplicates
-        input = list(set(self.clean_text(doc) for doc in input))
-
         # 1. Validate ids if provided or generate MD5 hash IDs
         if ids is not None:
             # Check if the number of IDs matches the number of documents
@@ -611,6 +608,8 @@ class LightRAG:
             # Generate contents dict of IDs provided by user and documents
             contents = {id_: doc for id_, doc in zip(ids, input)}
         else:
+            # Clean input text and remove duplicates
+            input = list(set(self.clean_text(doc) for doc in input))
             # Generate contents dict of MD5 hash IDs and documents
             contents = {compute_mdhash_id(doc, prefix="doc-"): doc for doc in input}