cleaned code

lightrag/lightrag.py

@@ -687,7 +687,7 @@ class LightRAG:
                 return
 
             update_storage = True
-            logger.info(f"[New Docs] inserting {len(new_docs)} docs")
+            logger.info(f"Inserting {len(new_docs)} docs")
 
             inserting_chunks: dict[str, Any] = {}
             for chunk_text in text_chunks:
@@ -914,6 +914,7 @@ class LightRAG:
             if storage_inst is not None
         ]
         await asyncio.gather(*tasks)
+        logger.info("All Insert done")
 
     def insert_custom_kg(self, custom_kg: dict[str, Any]) -> None:
         loop = always_get_an_event_loop()

lightrag/operate.py

@@ -491,11 +491,9 @@ async def extract_entities(
         already_processed += 1
         already_entities += len(maybe_nodes)
         already_relations += len(maybe_edges)
-        now_ticks = PROMPTS["process_tickers"][
-            already_processed % len(PROMPTS["process_tickers"])
-        ]
+
         logger.debug(
-            f"{now_ticks} Processed {already_processed} chunks, {already_entities} entities(duplicated), {already_relations} relations(duplicated)\r",
+            f"Processed {already_processed} chunks, {already_entities} entities(duplicated), {already_relations} relations(duplicated)\r",
         )
         return dict(maybe_nodes), dict(maybe_edges)
 

lightrag/prompt.py

@@ -9,15 +9,14 @@ PROMPTS["DEFAULT_LANGUAGE"] = "English"
 PROMPTS["DEFAULT_TUPLE_DELIMITER"] = "<|>"
 PROMPTS["DEFAULT_RECORD_DELIMITER"] = "##"
 PROMPTS["DEFAULT_COMPLETION_DELIMITER"] = "<|COMPLETE|>"
-PROMPTS["process_tickers"] = ["⠋", "⠙", "⠹", "⠸", "⠼", "⠴", "⠦", "⠧", "⠇", "⠏"]
 
 PROMPTS["DEFAULT_ENTITY_TYPES"] = ["organization", "person", "geo", "event", "category"]
 
-PROMPTS["entity_extraction"] = """-Goal-
+PROMPTS["entity_extraction"] = """---Goal---
 Given a text document that is potentially relevant to this activity and a list of entity types, identify all entities of those types from the text and all relationships among the identified entities.
 Use {language} as output language.
 
--Steps-
+---Steps---
 1. Identify all entities. For each identified entity, extract the following information:
 - entity_name: Name of the entity, use same language as input text. If English, capitalized the name.
 - entity_type: One of the following types: [{entity_types}]
@@ -41,18 +40,17 @@ Format the content-level key words as ("content_keywords"{tuple_delimiter}<high_
 5. When finished, output {completion_delimiter}
 
 ######################
--Examples-
+---Examples---
 ######################
 {examples}
 
 #############################
--Real Data-
+---Real Data---
 ######################
 Entity_types: {entity_types}
 Text: {input_text}
 ######################
-Output:
-"""
+Output:"""
 
 PROMPTS["entity_extraction_examples"] = [
     """Example 1:
@@ -137,7 +135,7 @@ Make sure it is written in third person, and include the entity names so we the
 Use {language} as output language.
 
 #######
--Data-
+---Data---
 Entities: {entity_name}
 Description List: {description_list}
 #######
@@ -205,12 +203,12 @@ Given the query and conversation history, list both high-level and low-level key
   - "low_level_keywords" for specific entities or details
 
 ######################
--Examples-
+---Examples---
 ######################
 {examples}
 
 #############################
--Real Data-
+---Real Data---
 ######################
 Conversation History:
 {history}