Feat: Use data pipeline to visualize the parsing configuration of the knowledge base (#10423)

### What problem does this PR solve?

#9869

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: jinhai <haijin.chn@gmail.com>
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: chanx <1243304602@qq.com>
Co-authored-by: balibabu <cike8899@users.noreply.github.com>
Co-authored-by: Lynn <lynn_inf@hotmail.com>
Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com>
Co-authored-by: huangzl <huangzl@shinemo.com>
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
Co-authored-by: Wilmer <33392318@qq.com>
Co-authored-by: Adrian Weidig <adrianweidig@gmx.net>
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Yongteng Lei <yongtengrey@outlook.com>
Co-authored-by: Liu An <asiro@qq.com>
Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com>
Co-authored-by: BadwomanCraZY <511528396@qq.com>
Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com>
Co-authored-by: Russell Valentine <russ@coldstonelabs.org>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Billy Bao <newyorkupperbay@gmail.com>
Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com>
Co-authored-by: TensorNull <tensor.null@gmail.com>
Co-authored-by: TeslaZY <TeslaZY@outlook.com>
Co-authored-by: Ajay <160579663+aybanda@users.noreply.github.com>
Co-authored-by: AB <aj@Ajays-MacBook-Air.local>
Co-authored-by: 天海蒼灆 <huangaoqin@tecpie.com>
Co-authored-by: He Wang <wanghechn@qq.com>
Co-authored-by: Atsushi Hatakeyama <atu729@icloud.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: Mohamed Mathari <155896313+melmathari@users.noreply.github.com>
Co-authored-by: Mohamed Mathari <nocodeventure@Mac-mini-van-Mohamed.fritz.box>
Co-authored-by: Stephen Hu <stephenhu@seismic.com>
Co-authored-by: Shaun Zhang <zhangwfjh@users.noreply.github.com>
Co-authored-by: zhimeng123 <60221886+zhimeng123@users.noreply.github.com>
Co-authored-by: mxc <mxc@example.com>
Co-authored-by: Dominik Novotný <50611433+SgtMarmite@users.noreply.github.com>
Co-authored-by: EVGENY M <168018528+rjohny55@users.noreply.github.com>
Co-authored-by: mcoder6425 <mcoder64@gmail.com>
Co-authored-by: lemsn <lemsn@msn.com>
Co-authored-by: lemsn <lemsn@126.com>
Co-authored-by: Adrian Gora <47756404+adagora@users.noreply.github.com>
Co-authored-by: Womsxd <45663319+Womsxd@users.noreply.github.com>
Co-authored-by: FatMii <39074672+FatMii@users.noreply.github.com>

rag/nlp/search.py

@@ -383,7 +383,7 @@ class Dealer:
         vector_column = f"q_{dim}_vec"
         zero_vector = [0.0] * dim
         sim_np = np.array(sim)
-        filtered_count = (sim_np >= similarity_threshold).sum()    
+        filtered_count = (sim_np >= similarity_threshold).sum()
         ranks["total"] = int(filtered_count) # Convert from np.int64 to Python int otherwise JSON serializable error
         for i in idx:
             if sim[i] < similarity_threshold:
@@ -444,12 +444,27 @@ class Dealer:
     def chunk_list(self, doc_id: str, tenant_id: str,
                    kb_ids: list[str], max_count=1024,
                    offset=0,
-                   fields=["docnm_kwd", "content_with_weight", "img_id"]):
+                   fields=["docnm_kwd", "content_with_weight", "img_id"],
+                   sort_by_position: bool = False):
         condition = {"doc_id": doc_id}
+
+        fields_set = set(fields or [])
+        if sort_by_position:
+            for need in ("page_num_int", "position_int", "top_int"):
+                if need not in fields_set:
+                    fields_set.add(need)
+        fields = list(fields_set)
+
+        orderBy = OrderByExpr()
+        if sort_by_position:
+            orderBy.asc("page_num_int")
+            orderBy.asc("position_int")
+            orderBy.asc("top_int")
+
         res = []
         bs = 128
         for p in range(offset, max_count, bs):
-            es_res = self.dataStore.search(fields, [], condition, [], OrderByExpr(), p, bs, index_name(tenant_id),
+            es_res = self.dataStore.search(fields, [], condition, [], orderBy, p, bs, index_name(tenant_id),
                                            kb_ids)
             dict_chunks = self.dataStore.getFields(es_res, fields)
             for id, doc in dict_chunks.items():