From 28a2295f73a844ae34e232fe743297df07f2794f Mon Sep 17 00:00:00 2001
From: Wufisher <1105889424@qq.com>
Date: Thu, 10 Aug 2023 21:59:47 +0800
Subject: [PATCH] =?UTF-8?q?=E7=BA=BF=E6=80=A7=E7=AE=80=E5=8D=95=E5=AE=9E?=
 =?UTF-8?q?=E7=8E=B0=E4=BA=86=EF=BC=9Avecorstores/MyFAISS.py=20TODO:=20?=
 =?UTF-8?q?=E5=A2=9E=E5=8A=A0=E6=98=AF=E5=90=A6=E5=B1=9E=E4=BA=8E=E5=90=8C?=
 =?UTF-8?q?=E4=B8=80=E6=96=87=E6=A1=A3=E7=9A=84=E5=88=A4=E6=96=AD=20(#945)?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 vectorstores/MyFAISS.py | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/vectorstores/MyFAISS.py b/vectorstores/MyFAISS.py
index 835799b..77b40d5 100644
--- a/vectorstores/MyFAISS.py
+++ b/vectorstores/MyFAISS.py
@@ -29,15 +29,17 @@ class MyFAISS(FAISS, VectorStore):
         self.chunk_conent = False
 
     def seperate_list(self, ls: List[int]) -> List[List[int]]:
-        # TODO: 增加是否属于同一文档的判断
+        
         lists = []
         ls1 = [ls[0]]
+        source1 = self.index_to_docstore_source(ls[0])
         for i in range(1, len(ls)):
-            if ls[i - 1] + 1 == ls[i]:
+            if ls[i - 1] + 1 == ls[i] and self.index_to_docstore_source(ls[i]) == source1:
                 ls1.append(ls[i])
             else:
                 lists.append(ls1)
                 ls1 = [ls[i]]
+                source1 = self.index_to_docstore_source(ls[i])
         lists.append(ls1)
         return lists
 
@@ -162,3 +164,8 @@ class MyFAISS(FAISS, VectorStore):
 
     def list_docs(self):
         return list(set(v.metadata["source"] for v in self.docstore._dict.values()))
+    
+    def index_to_docstore_source(self,i:int):
+        _id = self.index_to_docstore_id[i]
+        doc = self.docstore.search(_id)
+        return doc.metadata["source"]