AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-08-10 16:59:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: raptor overloading (#7889)

Browse Source 
### What problem does this PR solve?

#7840

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Kevin Hu 2025-05-27 17:41:35 +08:00 committed by GitHub
parent bc578e1e83
commit 28cb4df127
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
rag/svr/task_executor.py
View File

@ -537,7 +537,8 @@ async def do_handle_task(task):
# bind LLM for raptor
chat_model = LLMBundle(task_tenant_id, LLMType.CHAT, llm_name=task_llm_id, lang=task_language)
# run RAPTOR
chunks, token_count = await run_raptor(task, chat_model, embedding_model, vector_size, progress_callback)
async with kg_limiter:
chunks, token_count = await run_raptor(task, chat_model, embedding_model, vector_size, progress_callback)
# Either using graphrag or Standard chunking methods
elif task.get("task_type", "") == "graphrag":
if not task_parser_config.get("graphrag", {}).get("use_graphrag", False):