Plugin/merge main to plugin/beta 20250122 (#12962)

Signed-off-by: yihong0618 <zouzou0208@gmail.com>
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: kurokobo <kuro664@gmail.com>
Co-authored-by: Hiroshi Fujita <fujita-h@users.noreply.github.com>
Co-authored-by: NFish <douxc512@gmail.com>
Co-authored-by: Gen Sato <52241300+halogen22@users.noreply.github.com>
Co-authored-by: eux <euxuuu@gmail.com>
Co-authored-by: huangzhuo1949 <167434202+huangzhuo1949@users.noreply.github.com>
Co-authored-by: huangzhuo <huangzhuo1@xiaomi.com>
Co-authored-by: lotsik <lotsik@mail.ru>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: Wu Tianwei <30284043+WTW0313@users.noreply.github.com>
Co-authored-by: nite-knite <nkCoding@gmail.com>
Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: gakkiyomi <gakkiyomi@aliyun.com>
Co-authored-by: CN-P5 <heibai2006@gmail.com>
Co-authored-by: CN-P5 <heibai2006@qq.com>
Co-authored-by: Chuehnone <1897025+chuehnone@users.noreply.github.com>
Co-authored-by: yihong <zouzou0208@gmail.com>
Co-authored-by: Kevin9703 <51311316+Kevin9703@users.noreply.github.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: Boris Feld <lothiraldan@gmail.com>
Co-authored-by: mbo <himabo@gmail.com>
Co-authored-by: mabo <mabo@aeyes.ai>
Co-authored-by: Warren Chen <warren.chen830@gmail.com>
Co-authored-by: KVOJJJin <jzongcode@gmail.com>
Co-authored-by: JzoNgKVO <27049666+JzoNgKVO@users.noreply.github.com>
Co-authored-by: jiandanfeng <chenjh3@wangsu.com>
Co-authored-by: zhu-an <70234959+xhdd123321@users.noreply.github.com>
Co-authored-by: zhaoqingyu.1075 <zhaoqingyu.1075@bytedance.com>
Co-authored-by: 海狸大師 <86974027+yenslife@users.noreply.github.com>
Co-authored-by: Xu Song <xusong.vip@gmail.com>
Co-authored-by: rayshaw001 <396301947@163.com>
Co-authored-by: Ding Jiatong <dingjiatong@gmail.com>
Co-authored-by: Bowen Liang <liangbowen@gf.com.cn>
Co-authored-by: JasonVV <jasonwangiii@outlook.com>
Co-authored-by: le0zh <newlight@qq.com>
Co-authored-by: zhuxinliang <zhuxinliang@didiglobal.com>
Co-authored-by: k-zaku <zaku99@outlook.jp>
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: luckylhb90 <luckylhb90@gmail.com>
Co-authored-by: hobo.l <hobo.l@binance.com>
Co-authored-by: jiangbo721 <365065261@qq.com>
Co-authored-by: 刘江波 <jiangbo721@163.com>
Co-authored-by: Shun Miyazawa <34241526+miya@users.noreply.github.com>
Co-authored-by: EricPan <30651140+Egfly@users.noreply.github.com>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: zxhlyh <jasonapring2015@outlook.com>
Co-authored-by: sino <sino2322@gmail.com>
Co-authored-by: Jhvcc <37662342+Jhvcc@users.noreply.github.com>
Co-authored-by: lowell <lowell.hu@zkteco.in>

api/core/indexing_runner.py

@@ -530,7 +530,6 @@ class IndexingRunner:
         # chunk nodes by chunk size
         indexing_start_at = time.perf_counter()
         tokens = 0
-        chunk_size = 10
         if dataset_document.doc_form != IndexType.PARENT_CHILD_INDEX:
             # create keyword index
             create_keyword_thread = threading.Thread(
@@ -539,11 +538,22 @@ class IndexingRunner:
             )
             create_keyword_thread.start()
 
+        max_workers = 10
         if dataset.indexing_technique == "high_quality":
-            with concurrent.futures.ThreadPoolExecutor(max_workers=10) as executor:
+            with concurrent.futures.ThreadPoolExecutor(max_workers=max_workers) as executor:
                 futures = []
-                for i in range(0, len(documents), chunk_size):
-                    chunk_documents = documents[i : i + chunk_size]
+
+                # Distribute documents into multiple groups based on the hash values of page_content
+                # This is done to prevent multiple threads from processing the same document,
+                # Thereby avoiding potential database insertion deadlocks
+                document_groups: list[list[Document]] = [[] for _ in range(max_workers)]
+                for document in documents:
+                    hash = helper.generate_text_hash(document.page_content)
+                    group_index = int(hash, 16) % max_workers
+                    document_groups[group_index].append(document)
+                for chunk_documents in document_groups:
+                    if len(chunk_documents) == 0:
+                        continue
                     futures.append(
                         executor.submit(
                             self._process_chunk,