diff --git a/langchain/vectorstores/faiss.py b/langchain/vectorstores/faiss.py
index 6dd7fd544e7..1489bf8ff06 100644
--- a/langchain/vectorstores/faiss.py
+++ b/langchain/vectorstores/faiss.py
@@ -192,7 +192,7 @@ class FAISS(VectorStore):
         Args:
             embedding: Embedding vector to look up documents similar to.
             k: Number of Documents to return. Defaults to 4.
-            filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None.
+            filter (Optional[Dict[str, Any]]): Filter by metadata. Defaults to None.
             fetch_k: (Optional[int]) Number of Documents to fetch before filtering.
                       Defaults to 20.
             **kwargs: kwargs to be passed to similarity search. Can include:
@@ -218,7 +218,11 @@ class FAISS(VectorStore):
             if not isinstance(doc, Document):
                 raise ValueError(f"Could not find document for id {_id}, got {doc}")
             if filter is not None:
-                if all(doc.metadata.get(key) == value for key, value in filter.items()):
+                filter = {
+                    key: [value] if not isinstance(value, list) else value
+                    for key, value in filter.items()
+                }
+                if all(doc.metadata.get(key) in value for key, value in filter.items()):
                     docs.append((doc, scores[0][j]))
             else:
                 docs.append((doc, scores[0][j]))
diff --git a/tests/integration_tests/vectorstores/test_faiss.py b/tests/integration_tests/vectorstores/test_faiss.py
index d33e6d7827e..37a66e8eb5b 100644
--- a/tests/integration_tests/vectorstores/test_faiss.py
+++ b/tests/integration_tests/vectorstores/test_faiss.py
@@ -96,6 +96,34 @@ def test_faiss_with_metadatas_and_filter() -> None:
     assert output == [Document(page_content="bar", metadata={"page": 1})]
 
 
+def test_faiss_with_metadatas_and_list_filter() -> None:
+    texts = ["foo", "bar", "baz", "foo", "qux"]
+    metadatas = [{"page": i} if i <= 3 else {"page": 3} for i in range(len(texts))]
+    docsearch = FAISS.from_texts(texts, FakeEmbeddings(), metadatas=metadatas)
+    expected_docstore = InMemoryDocstore(
+        {
+            docsearch.index_to_docstore_id[0]: Document(
+                page_content="foo", metadata={"page": 0}
+            ),
+            docsearch.index_to_docstore_id[1]: Document(
+                page_content="bar", metadata={"page": 1}
+            ),
+            docsearch.index_to_docstore_id[2]: Document(
+                page_content="baz", metadata={"page": 2}
+            ),
+            docsearch.index_to_docstore_id[3]: Document(
+                page_content="foo", metadata={"page": 3}
+            ),
+            docsearch.index_to_docstore_id[4]: Document(
+                page_content="qux", metadata={"page": 3}
+            ),
+        }
+    )
+    assert docsearch.docstore.__dict__ == expected_docstore.__dict__
+    output = docsearch.similarity_search("foor", k=1, filter={"page": [0, 1, 2]})
+    assert output == [Document(page_content="foo", metadata={"page": 0})]
+
+
 def test_faiss_search_not_found() -> None:
     """Test what happens when document is not found."""
     texts = ["foo", "bar", "baz"]