From 5cd5529c2d28616c79f387b12ca73ba827472aeb Mon Sep 17 00:00:00 2001
From: uply23333 <uply233@163.com>
Date: Fri, 18 Jul 2025 11:16:36 +0000
Subject: [PATCH] fix(elasticsearch): improve document filtering in full text
 search

---
 .../vdb/elasticsearch/elasticsearch_vector.py         | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/api/core/rag/datasource/vdb/elasticsearch/elasticsearch_vector.py b/api/core/rag/datasource/vdb/elasticsearch/elasticsearch_vector.py
index 44cc5d3e98..ad39717183 100644
--- a/api/core/rag/datasource/vdb/elasticsearch/elasticsearch_vector.py
+++ b/api/core/rag/datasource/vdb/elasticsearch/elasticsearch_vector.py
@@ -147,10 +147,17 @@ class ElasticSearchVector(BaseVector):
         return docs
 
     def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]:
-        query_str = {"match": {Field.CONTENT_KEY.value: query}}
+        query_str: dict[str, Any] = {"match": {Field.CONTENT_KEY.value: query}}
         document_ids_filter = kwargs.get("document_ids_filter")
+
         if document_ids_filter:
-            query_str["filter"] = {"terms": {"metadata.document_id": document_ids_filter}}  # type: ignore
+            query_str = {
+                "bool": {
+                    "must": {"match": {Field.CONTENT_KEY.value: query}},
+                    "filter": {"terms": {"metadata.document_id": document_ids_filter}},
+                }
+            }
+
         results = self._client.search(index=self._collection_name, query=query_str, size=kwargs.get("top_k", 4))
         docs = []
         for hit in results["hits"]["hits"]: