From 03ac39368fe60201a3f071d7d360c39f59c77cbf Mon Sep 17 00:00:00 2001
From: Anirudh Suresh <anirudhtx@gmail.com>
Date: Mon, 15 May 2023 19:39:16 -0500
Subject: [PATCH] Fixing DeepLake Overwrite Flag (#4683)

# Fix DeepLake Overwrite Flag Issue

Fixes Issue #4682: essentially, setting overwrite to False in the
DeepLake constructor still triggers an overwrite, because the logic is
just checking for the presence of "overwrite" in kwargs. The fix is
simple--just add some checks to inspect if "overwrite" in kwargs AND
kwargs["overwrite"]==True.

Added a new test in
tests/integration_tests/vectorstores/test_deeplake.py to reflect the
desired behavior.


Co-authored-by: Anirudh Suresh <ani@Anirudhs-MBP.cable.rcn.com>
Co-authored-by: Anirudh Suresh <ani@Anirudhs-MacBook-Pro.local>
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
---
 langchain/vectorstores/deeplake.py            |  8 ++--
 .../vectorstores/test_deeplake.py             | 47 +++++++++++++++++++
 2 files changed, 52 insertions(+), 3 deletions(-)

diff --git a/langchain/vectorstores/deeplake.py b/langchain/vectorstores/deeplake.py
index dc9a2106..01ed62df 100644
--- a/langchain/vectorstores/deeplake.py
+++ b/langchain/vectorstores/deeplake.py
@@ -120,10 +120,12 @@ class DeepLake(VectorStore):
         self.dataset_path = dataset_path
         creds_args = {"creds": kwargs["creds"]} if "creds" in kwargs else {}
 
-        if (
-            deeplake.exists(dataset_path, token=token, **creds_args)
-            and "overwrite" not in kwargs
+        if deeplake.exists(dataset_path, token=token, **creds_args) and not kwargs.get(
+            "overwrite", False
         ):
+            if "overwrite" in kwargs:
+                del kwargs["overwrite"]
+
             self.ds = deeplake.load(
                 dataset_path,
                 token=token,
diff --git a/tests/integration_tests/vectorstores/test_deeplake.py b/tests/integration_tests/vectorstores/test_deeplake.py
index f858c904..634d5237 100644
--- a/tests/integration_tests/vectorstores/test_deeplake.py
+++ b/tests/integration_tests/vectorstores/test_deeplake.py
@@ -83,6 +83,53 @@ def test_deeplakewith_persistence() -> None:
     # Or on program exit
 
 
+def test_deeplake_overwrite_flag() -> None:
+    """Test overwrite behavior"""
+    dataset_path = "./tests/persist_dir"
+    if deeplake.exists(dataset_path):
+        deeplake.delete(dataset_path)
+
+    texts = ["foo", "bar", "baz"]
+    docsearch = DeepLake.from_texts(
+        dataset_path=dataset_path,
+        texts=texts,
+        embedding=FakeEmbeddings(),
+    )
+    output = docsearch.similarity_search("foo", k=1)
+    assert output == [Document(page_content="foo")]
+
+    docsearch.persist()
+
+    # Get a new VectorStore from the persisted directory, with no overwrite (implicit)
+    docsearch = DeepLake(
+        dataset_path=dataset_path,
+        embedding_function=FakeEmbeddings(),
+    )
+    output = docsearch.similarity_search("foo", k=1)
+    # assert page still present
+    assert output == [Document(page_content="foo")]
+
+    # Get a new VectorStore from the persisted directory, with no overwrite (explicit)
+    docsearch = DeepLake(
+        dataset_path=dataset_path,
+        embedding_function=FakeEmbeddings(),
+        overwrite=False,
+    )
+    output = docsearch.similarity_search("foo", k=1)
+    # assert page still present
+    assert output == [Document(page_content="foo")]
+
+    # Get a new VectorStore from the persisted directory, with overwrite
+    docsearch = DeepLake(
+        dataset_path=dataset_path,
+        embedding_function=FakeEmbeddings(),
+        overwrite=True,
+    )
+    output = docsearch.similarity_search("foo", k=1)
+    # assert page no longer present
+    assert output == []
+
+
 def test_similarity_search(deeplake_datastore: DeepLake, distance_metric: str) -> None:
     """Test similarity search."""
     output = deeplake_datastore.similarity_search(