Escapes AzureCosmosDBNoSqlVectorStore hybrid & full text queries that…

… contain single quotes
langchain-ai · Jan 22, 2025 · e2db28a · e2db28a
1 parent 3f1d209
commit e2db28a
Show file tree

Hide file tree

Showing 2 changed files with 22 additions and 2 deletions.
diff --git a/libs/community/langchain_community/vectorstores/azure_cosmos_db_no_sql.py b/libs/community/langchain_community/vectorstores/azure_cosmos_db_no_sql.py
@@ -635,15 +635,17 @@ def _construct_query(
                 raise ValueError(
                     "search text cannot be None for FULL_TEXT_RANK queries."
                 )
+            terms = [f"'{term.replace("'", "\\'")}'" for term in search_text.split()]
             query += f""" ORDER BY RANK FullTextScore(c.{self._text_key}, 
-            [{", ".join(f"'{term}'" for term in search_text.split())}])"""
+            [{", ".join(terms)}])"""
         elif query_type == CosmosDBQueryType.VECTOR:
             query += " ORDER BY VectorDistance(c[@embeddingKey], @embeddings)"
         elif query_type == CosmosDBQueryType.HYBRID:
             if search_text is None:
                 raise ValueError("search text cannot be None for HYBRID queries.")
+            terms = [f"'{term.replace("'", "\\'")}'" for term in search_text.split()]
             query += f""" ORDER BY RANK RRF(FullTextScore(c.{self._text_key}, 
-            [{", ".join(f"'{term}'" for term in search_text.split())}]), 
+            [{", ".join(terms)}]), 
             VectorDistance(c.{self._embedding_key}, {embeddings}))"""
         else:
             query += ""

diff --git a/libs/community/tests/integration_tests/vectorstores/test_azure_cosmos_db_no_sql.py b/libs/community/tests/integration_tests/vectorstores/test_azure_cosmos_db_no_sql.py
@@ -295,6 +295,15 @@ def test_from_documents_full_text_and_hybrid(
         assert len(output) == 5
         assert "Standard Poodles" in output[0].page_content
 
+        # Full text search successfully queries for data with a single quote
+        output = store.similarity_search(
+            "'Retrievers'", k=5, query_type=CosmosDBQueryType.FULL_TEXT_RANK
+        )
+
+        assert output
+        assert len(output) == 5
+        assert "Retrievers" in output[0].page_content
+
         # Full text search BM25 ranking with filtering
         pre_filter = PreFilter(
             conditions=[
@@ -321,6 +330,15 @@ def test_from_documents_full_text_and_hybrid(
         assert len(output) == 5
         assert "Border Collies" in output[0].page_content
 
+        # Hybrid search successfully queries for data with a single quote
+        output = store.similarity_search(
+            "'outdoor activities'", k=5, query_type=CosmosDBQueryType.HYBRID
+        )
+
+        assert output
+        assert len(output) == 5
+        assert "Border Collies" in output[0].page_content
+
         # Hybrid search RRF ranking with filtering
         pre_filter = PreFilter(
             conditions=[