From f46448d04c83aa84827012eadd54bd91e15fddf7 Mon Sep 17 00:00:00 2001
From: Kevin Hu <kevinhu.sh@gmail.com>
Date: Mon, 17 Feb 2025 14:06:06 +0800
Subject: [PATCH] Remove <think> for KG extraction. (#5027)

### What problem does this PR solve?

#4946

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
---
 graphrag/general/extractor.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/graphrag/general/extractor.py b/graphrag/general/extractor.py
index ffcb889a5..50184002f 100644
--- a/graphrag/general/extractor.py
+++ b/graphrag/general/extractor.py
@@ -15,6 +15,7 @@
 #
 import logging
 import os
+import re
 from collections import defaultdict, Counter
 from concurrent.futures import ThreadPoolExecutor
 from copy import deepcopy
@@ -59,6 +60,7 @@ class Extractor:
         if response:
             return response
         response = self._llm.chat(system, hist, conf)
+        response = re.sub(r"<think>.*</think>", "", response)
         if response.find("**ERROR**") >= 0:
             raise Exception(response)
         set_llm_cache(self._llm.llm_name, system, response, history, gen_conf)