adai/MemoryBear
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'feature/20251219_lxc' into develop

Browse Source
This commit is contained in:
lixiangcheng1
2025-12-29 11:55:45 +08:00
parent 4d187b9c19 34fa178f11
commit c6d8d6b301
2 changed files with 8 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
api/app/core/rag/graphrag/general/index.py
View File

@@ -186,7 +186,7 @@ async def run_graphrag_for_kb(
chunks = all_document_chunks.get(document_id, []) chunks = all_document_chunks.get(document_id, [])
if not chunks: if not chunks:
callback(msg=f"[GraphRAG] doc:{document_id} has no available chunks, skip generation.") callback(msg=f"[GraphRAG] document:{document_id} has no available chunks, skip generation.")
return return
kg_extractor = LightKGExt if ("method" not in parser_config.get("graphrag", {}) or parser_config["graphrag"]["method"] != "general") else GeneralKGExt kg_extractor = LightKGExt if ("method" not in parser_config.get("graphrag", {}) or parser_config["graphrag"]["method"] != "general") else GeneralKGExt

12
api/app/tasks.py
View File

@@ -198,9 +198,10 @@ def parse_document(file_path: str, document_id: uuid.UUID):
with_resolution = graphrag_conf.get("resolution", False) with_resolution = graphrag_conf.get("resolution", False)
with_community = graphrag_conf.get("community", False) with_community = graphrag_conf.get("community", False)
def callback(msg=None): def callback(*args, msg=None, **kwargs):
nonlocal progress_msg nonlocal progress_msg
progress_msg += f"{datetime.now().strftime('%H:%M:%S')} run graphrag msg: {msg}.\n" message = msg or (args[0] if args else "No message")
progress_msg += f"{datetime.now().strftime('%H:%M:%S')} run graphrag msg: {message}.\n"
progress_msg += f"{datetime.now().strftime('%H:%M:%S')} Start to run graphrag.\n" progress_msg += f"{datetime.now().strftime('%H:%M:%S')} Start to run graphrag.\n"
start_time = time.time() start_time = time.time()
@@ -306,7 +307,7 @@ def build_graphrag_for_kb(kb_id: uuid.UUID):
# 2. get all document_ids from knowledge base # 2. get all document_ids from knowledge base
vector_service = ElasticSearchVectorFactory().init_vector(knowledge=db_knowledge) vector_service = ElasticSearchVectorFactory().init_vector(knowledge=db_knowledge)
total, items = vector_service.search_by_segment(document_id=None, query=None, pagesize=9999, page=1, asc=True) total, items = vector_service.search_by_segment(document_id=None, query=None, pagesize=9999, page=1, asc=True)
document_ids = [item.id for item in db_documents] document_ids = [str(item.id) for item in db_documents]
# 2. using graphrag # 2. using graphrag
if db_knowledge.parser_config.get("graphrag", {}).get("use_graphrag", False): if db_knowledge.parser_config.get("graphrag", {}).get("use_graphrag", False):
@@ -314,8 +315,9 @@ def build_graphrag_for_kb(kb_id: uuid.UUID):
with_resolution = graphrag_conf.get("resolution", False) with_resolution = graphrag_conf.get("resolution", False)
with_community = graphrag_conf.get("community", False) with_community = graphrag_conf.get("community", False)
def callback(msg=None): def callback(*args, msg=None, **kwargs):
print(f"{datetime.now().strftime('%H:%M:%S')} run graphrag msg: {msg}.\n") message = msg or (args[0] if args else "No message")
print(f"{datetime.now().strftime('%H:%M:%S')} run graphrag msg: {message}.\n")
start_time = time.time() start_time = time.time()
task = { task = {