gardel/lightrag
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix linting errors

Browse Source
This commit is contained in:
zrguo
2024-12-31 17:32:04 +08:00
parent 71e9267f4b
commit d489d9dec0
2 changed files with 105 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

101
lightrag/lightrag.py
View File

@@ -735,7 +735,9 @@ class LightRAG:
logger.debug(f"Starting deletion for document {doc_id}")
# 2. Get all related chunks
chunks = await self.text_chunks.filter(lambda x: x.get("full_doc_id") == doc_id)
chunks = await self.text_chunks.filter(
lambda x: x.get("full_doc_id") == doc_id
)
chunk_ids = list(chunks.keys())
logger.debug(f"Found {len(chunk_ids)} chunks to delete")
@@ -743,14 +745,16 @@ class LightRAG:
for chunk_id in chunk_ids:
# Check entities
entities = [
dp for dp in self.entities_vdb.client_storage["data"]
dp
for dp in self.entities_vdb.client_storage["data"]
if dp.get("source_id") == chunk_id
]
logger.debug(f"Chunk {chunk_id} has {len(entities)} related entities")
# Check relationships
relations = [
dp for dp in self.relationships_vdb.client_storage["data"]
dp
for dp in self.relationships_vdb.client_storage["data"]
if dp.get("source_id") == chunk_id
]
logger.debug(f"Chunk {chunk_id} has {len(relations)} related relations")
@@ -775,31 +779,39 @@ class LightRAG:
# Process entities
for node, data in nodes:
if 'source_id' in data:
if "source_id" in data:
# Split source_id using GRAPH_FIELD_SEP
sources = set(data['source_id'].split(GRAPH_FIELD_SEP))
sources = set(data["source_id"].split(GRAPH_FIELD_SEP))
sources.difference_update(chunk_ids)
if not sources:
entities_to_delete.add(node)
logger.debug(f"Entity {node} marked for deletion - no remaining sources")
logger.debug(
f"Entity {node} marked for deletion - no remaining sources"
)
else:
new_source_id = GRAPH_FIELD_SEP.join(sources)
entities_to_update[node] = new_source_id
logger.debug(f"Entity {node} will be updated with new source_id: {new_source_id}")
logger.debug(
f"Entity {node} will be updated with new source_id: {new_source_id}"
)
# Process relationships
for src, tgt, data in edges:
if 'source_id' in data:
if "source_id" in data:
# Split source_id using GRAPH_FIELD_SEP
sources = set(data['source_id'].split(GRAPH_FIELD_SEP))
sources = set(data["source_id"].split(GRAPH_FIELD_SEP))
sources.difference_update(chunk_ids)
if not sources:
relationships_to_delete.add((src, tgt))
logger.debug(f"Relationship {src}-{tgt} marked for deletion - no remaining sources")
logger.debug(
f"Relationship {src}-{tgt} marked for deletion - no remaining sources"
)
else:
new_source_id = GRAPH_FIELD_SEP.join(sources)
relationships_to_update[(src, tgt)] = new_source_id
logger.debug(f"Relationship {src}-{tgt} will be updated with new source_id: {new_source_id}")
logger.debug(
f"Relationship {src}-{tgt} will be updated with new source_id: {new_source_id}"
)
# Delete entities
if entities_to_delete:
@@ -812,9 +824,11 @@ class LightRAG:
# Update entities
for entity, new_source_id in entities_to_update.items():
node_data = self.chunk_entity_relation_graph._graph.nodes[entity]
node_data['source_id'] = new_source_id
node_data["source_id"] = new_source_id
await self.chunk_entity_relation_graph.upsert_node(entity, node_data)
logger.debug(f"Updated entity {entity} with new source_id: {new_source_id}")
logger.debug(
f"Updated entity {entity} with new source_id: {new_source_id}"
)
# Delete relationships
if relationships_to_delete:
@@ -823,15 +837,21 @@ class LightRAG:
rel_id_1 = compute_mdhash_id(tgt + src, prefix="rel-")
await self.relationships_vdb.delete([rel_id_0, rel_id_1])
logger.debug(f"Deleted relationship {src}-{tgt} from vector DB")
self.chunk_entity_relation_graph.remove_edges(list(relationships_to_delete))
logger.debug(f"Deleted {len(relationships_to_delete)} relationships from graph")
self.chunk_entity_relation_graph.remove_edges(
list(relationships_to_delete)
)
logger.debug(
f"Deleted {len(relationships_to_delete)} relationships from graph"
)
# Update relationships
for (src, tgt), new_source_id in relationships_to_update.items():
edge_data = self.chunk_entity_relation_graph._graph.edges[src, tgt]
edge_data['source_id'] = new_source_id
edge_data["source_id"] = new_source_id
await self.chunk_entity_relation_graph.upsert_edge(src, tgt, edge_data)
logger.debug(f"Updated relationship {src}-{tgt} with new source_id: {new_source_id}")
logger.debug(
f"Updated relationship {src}-{tgt} with new source_id: {new_source_id}"
)
# 6. Delete original document and status
await self.full_docs.delete([doc_id])
@@ -863,19 +883,27 @@ class LightRAG:
for chunk_id in chunk_ids:
# Check entities
entities_with_chunk = [
dp for dp in self.entities_vdb.client_storage["data"]
if chunk_id in (dp.get("source_id") or "").split(GRAPH_FIELD_SEP)
dp
for dp in self.entities_vdb.client_storage["data"]
if chunk_id
in (dp.get("source_id") or "").split(GRAPH_FIELD_SEP)
]
if entities_with_chunk:
logger.error(f"Found {len(entities_with_chunk)} entities still referencing chunk {chunk_id}")
logger.error(
f"Found {len(entities_with_chunk)} entities still referencing chunk {chunk_id}"
)
# Check relationships
relations_with_chunk = [
dp for dp in self.relationships_vdb.client_storage["data"]
if chunk_id in (dp.get("source_id") or "").split(GRAPH_FIELD_SEP)
dp
for dp in self.relationships_vdb.client_storage["data"]
if chunk_id
in (dp.get("source_id") or "").split(GRAPH_FIELD_SEP)
]
if relations_with_chunk:
logger.error(f"Found {len(relations_with_chunk)} relations still referencing chunk {chunk_id}")
logger.error(
f"Found {len(relations_with_chunk)} relations still referencing chunk {chunk_id}"
)
await verify_deletion()
@@ -886,7 +914,9 @@ class LightRAG:
"""Synchronous version of adelete"""
return asyncio.run(self.adelete_by_doc_id(doc_id))
async def get_entity_info(self, entity_name: str, include_vector_data: bool = False):
async def get_entity_info(
self, entity_name: str, include_vector_data: bool = False
):
"""Get detailed information of an entity
Args:
@@ -904,7 +934,7 @@ class LightRAG:
# Get information from the graph
node_data = await self.chunk_entity_relation_graph.get_node(entity_name)
source_id = node_data.get('source_id') if node_data else None
source_id = node_data.get("source_id") if node_data else None
result = {
"entity_name": entity_name,
@@ -929,12 +959,15 @@ class LightRAG:
"""
try:
import tracemalloc
tracemalloc.start()
return asyncio.run(self.get_entity_info(entity_name, include_vector_data))
finally:
tracemalloc.stop()
async def get_relation_info(self, src_entity: str, tgt_entity: str, include_vector_data: bool = False):
async def get_relation_info(
self, src_entity: str, tgt_entity: str, include_vector_data: bool = False
):
"""Get detailed information of a relationship
Args:
@@ -954,8 +987,10 @@ class LightRAG:
tgt_entity = f'"{tgt_entity.upper()}"'
# Get information from the graph
edge_data = await self.chunk_entity_relation_graph.get_edge(src_entity, tgt_entity)
source_id = edge_data.get('source_id') if edge_data else None
edge_data = await self.chunk_entity_relation_graph.get_edge(
src_entity, tgt_entity
)
source_id = edge_data.get("source_id") if edge_data else None
result = {
"src_entity": src_entity,
@@ -972,7 +1007,9 @@ class LightRAG:
return result
def get_relation_info_sync(self, src_entity: str, tgt_entity: str, include_vector_data: bool = False):
def get_relation_info_sync(
self, src_entity: str, tgt_entity: str, include_vector_data: bool = False
):
"""Synchronous version of getting relationship information
Args:
@@ -982,8 +1019,10 @@ class LightRAG:
"""
try:
import tracemalloc
tracemalloc.start()
return asyncio.run(self.get_relation_info(src_entity, tgt_entity, include_vector_data))
return asyncio.run(
self.get_relation_info(src_entity, tgt_entity, include_vector_data)
)
finally:
tracemalloc.stop()

15
lightrag/storage.py
View File

@@ -188,14 +188,18 @@ class NanoVectorDBStorage(BaseVectorStorage):
"""
try:
self._client.delete(ids)
logger.info(f"Successfully deleted {len(ids)} vectors from {self.namespace}")
logger.info(
f"Successfully deleted {len(ids)} vectors from {self.namespace}"
)
except Exception as e:
logger.error(f"Error while deleting vectors from {self.namespace}: {e}")
async def delete_entity(self, entity_name: str):
try:
entity_id = compute_mdhash_id(entity_name, prefix="ent-")
logger.debug(f"Attempting to delete entity {entity_name} with ID {entity_id}")
logger.debug(
f"Attempting to delete entity {entity_name} with ID {entity_id}"
)
# Check if the entity exists
if self._client.get([entity_id]):
await self.delete([entity_id])
@@ -208,7 +212,8 @@ class NanoVectorDBStorage(BaseVectorStorage):
async def delete_entity_relation(self, entity_name: str):
try:
relations = [
dp for dp in self.client_storage["data"]
dp
for dp in self.client_storage["data"]
if dp["src_id"] == entity_name or dp["tgt_id"] == entity_name
]
logger.debug(f"Found {len(relations)} relations for entity {entity_name}")
@@ -216,7 +221,9 @@ class NanoVectorDBStorage(BaseVectorStorage):
if ids_to_delete:
await self.delete(ids_to_delete)
logger.debug(f"Deleted {len(ids_to_delete)} relations for {entity_name}")
logger.debug(
f"Deleted {len(ids_to_delete)} relations for {entity_name}"
)
else:
logger.debug(f"No relations found for entity {entity_name}")
except Exception as e: