From e366c16db5bf9aede607888bfda000988dec4d1b Mon Sep 17 00:00:00 2001
From: Jyong <76649700+JohnJyong@users.noreply.github.com>
Date: Tue, 10 Sep 2024 18:21:22 +0800
Subject: [PATCH] revert page column (#8217)

---
 api/core/rag/datasource/vdb/vector_factory.py                 | 2 +-
 .../nodes/knowledge_retrieval/knowledge_retrieval_node.py     | 4 ----
 api/core/workflow/nodes/llm/llm_node.py                       | 1 -
 3 files changed, 1 insertion(+), 6 deletions(-)

diff --git a/api/core/rag/datasource/vdb/vector_factory.py b/api/core/rag/datasource/vdb/vector_factory.py
index 7d2db140df2ad1..bb24143a41ac8d 100644
--- a/api/core/rag/datasource/vdb/vector_factory.py
+++ b/api/core/rag/datasource/vdb/vector_factory.py
@@ -27,7 +27,7 @@ def gen_index_struct_dict(vector_type: VectorType, collection_name: str) -> dict
 class Vector:
     def __init__(self, dataset: Dataset, attributes: list = None):
         if attributes is None:
-            attributes = ["doc_id", "dataset_id", "document_id", "doc_hash", "page"]
+            attributes = ["doc_id", "dataset_id", "document_id", "doc_hash"]
         self._dataset = dataset
         self._embeddings = self._get_embeddings()
         self._attributes = attributes
diff --git a/api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py b/api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py
index 19deca162aed24..53e8be64153d99 100644
--- a/api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py
+++ b/api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py
@@ -163,9 +163,6 @@ def _fetch_dataset_retriever(self, node_data: KnowledgeRetrievalNodeData, query:
             for item in all_documents:
                 if item.metadata.get("score"):
                     document_score_list[item.metadata["doc_id"]] = item.metadata["score"]
-                # both 'page' and 'score' are metadata fields
-                if item.metadata.get("page"):
-                    page_number_list[item.metadata["doc_id"]] = item.metadata["page"]
 
             index_node_ids = [document.metadata["doc_id"] for document in all_documents]
             segments = DocumentSegment.query.filter(
@@ -200,7 +197,6 @@ def _fetch_dataset_retriever(self, node_data: KnowledgeRetrievalNodeData, query:
                                 "document_id": document.id,
                                 "document_name": document.name,
                                 "document_data_source_type": document.data_source_type,
-                                "page": page_number_list.get(segment.index_node_id, None),
                                 "segment_id": segment.id,
                                 "retriever_from": "workflow",
                                 "score": document_score_list.get(segment.index_node_id, None),
diff --git a/api/core/workflow/nodes/llm/llm_node.py b/api/core/workflow/nodes/llm/llm_node.py
index 6dfd27861eefc4..049c2114882830 100644
--- a/api/core/workflow/nodes/llm/llm_node.py
+++ b/api/core/workflow/nodes/llm/llm_node.py
@@ -451,7 +451,6 @@ def _convert_to_original_retriever_resource(self, context_dict: dict) -> Optiona
                 "segment_position": metadata.get("segment_position"),
                 "index_node_hash": metadata.get("segment_index_node_hash"),
                 "content": context_dict.get("content"),
-                "page": metadata.get("page"),
             }
 
             return source