Merge pull request #900 from YanSte/cleanup-3

Database Cleanup

examples/test_faiss.py

@@ -70,7 +70,7 @@ def main():
         ),
         vector_storage="FaissVectorDBStorage",
         vector_db_storage_cls_kwargs={
-            "cosine_better_than_threshold": 0.3  # Your desired threshold
+            "cosine_better_than_threshold": 0.2  # Your desired threshold
         },
     )
 

lightrag/__init__.py

@@ -1,5 +1,5 @@
 from .lightrag import LightRAG as LightRAG, QueryParam as QueryParam
 
-__version__ = "1.1.7"
+__version__ = "1.1.10"
 __author__ = "Zirui Guo"
 __url__ = "https://github.com/HKUDS/LightRAG"

lightrag/kg/networkx_impl.py

@@ -16,11 +16,12 @@
 
 if not pm.is_installed("networkx"):
     pm.install("networkx")
+
 if not pm.is_installed("graspologic"):
     pm.install("graspologic")
 
-from graspologic import embed
 import networkx as nx
+from graspologic import embed
 
 
 @final

lightrag/lightrag.py

@@ -184,7 +184,7 @@ class LightRAG:
     """Maximum number of concurrent embedding function calls."""
 
     embedding_cache_config: dict[str, Any] = field(
-        default={
+        default_factory=lambda: {
             "enabled": False,
             "similarity_threshold": 0.95,
             "use_llm_check": False,
@@ -727,21 +727,14 @@ async def batch(
 
     async def _process_entity_relation_graph(self, chunk: dict[str, Any]) -> None:
         try:
-            new_kg = await extract_entities(
+            await extract_entities(
                 chunk,
                 knowledge_graph_inst=self.chunk_entity_relation_graph,
                 entity_vdb=self.entities_vdb,
                 relationships_vdb=self.relationships_vdb,
                 llm_response_cache=self.llm_response_cache,
                 global_config=asdict(self),
             )
-            if new_kg is None:
-                logger.info("No new entities or relationships extracted.")
-            else:
-                async with self._entity_lock:
-                    logger.info("New entities or relationships extracted.")
-                    self.chunk_entity_relation_graph = new_kg
-
         except Exception as e:
             logger.error("Failed to extract entities and relationships")
             raise e

lightrag/operate.py

@@ -329,7 +329,7 @@ async def extract_entities(
     relationships_vdb: BaseVectorStorage,
     global_config: dict[str, str],
     llm_response_cache: BaseKVStorage | None = None,
-) -> BaseGraphStorage | None:
+) -> None:
     use_llm_func: callable = global_config["llm_model_func"]
     entity_extract_max_gleaning = global_config["entity_extract_max_gleaning"]
     enable_llm_cache_for_entity_extract: bool = global_config[
@@ -522,16 +522,18 @@ async def _process_single_content(chunk_key_dp: tuple[str, TextChunkSchema]):
         ]
     )
 
-    if not len(all_entities_data) and not len(all_relationships_data):
-        logger.warning(
-            "Didn't extract any entities and relationships, maybe your LLM is not working"
-        )
-        return None
+    if not (all_entities_data or all_relationships_data):
+        logger.info("Didn't extract any entities and relationships.")
+        return
 
-    if not len(all_entities_data):
-        logger.warning("Didn't extract any entities")
-    if not len(all_relationships_data):
-        logger.warning("Didn't extract any relationships")
+    if not all_entities_data:
+        logger.info("Didn't extract any entities")
+    if not all_relationships_data:
+        logger.info("Didn't extract any relationships")
+
+    logger.info(
+        f"New entities or relationships extracted, entities:{all_entities_data}, relationships:{all_relationships_data}"
+    )
 
     if entity_vdb is not None:
         data_for_vdb = {
@@ -560,8 +562,6 @@ async def _process_single_content(chunk_key_dp: tuple[str, TextChunkSchema]):
         }
         await relationships_vdb.upsert(data_for_vdb)
 
-    return knowledge_graph_inst
-
 
 async def kg_query(
     query: str,