github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-07 05:52:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

community[major]: breaking change in some APIs to force users to opt-in for pickling (#18696)

Browse Source 
This is a PR that adds a dangerous load parameter to force users to opt in to use pickle.

This is a PR that's meant to raise user awareness that the pickling module is involved.
This commit is contained in:
Eugene Yurtsev
2024-03-06 16:43:01 -05:00
committed by GitHub
parent 0e52961562
commit 4c25b49229
10 changed files with 128 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
libs/community/langchain_community/vectorstores/annoy.py
View File

@@ -429,6 +429,8 @@ class Annoy(VectorStore):
cls,
folder_path: str,
embeddings: Embeddings,
*,
allow_dangerous_deserialization: bool = False,
) -> Annoy:
"""Load Annoy index, docstore, and index_to_docstore_id to disk.
@@ -436,7 +438,25 @@ class Annoy(VectorStore):
folder_path: folder path to load index, docstore,
and index_to_docstore_id from.
embeddings: Embeddings to use when generating queries.
allow_dangerous_deserialization: whether to allow deserialization
of the data which involves loading a pickle file.
Pickle files can be modified by malicious actors to deliver a
malicious payload that results in execution of
arbitrary code on your machine.
"""
if not allow_dangerous_deserialization:
raise ValueError(
"The de-serialization relies loading a pickle file. "
"Pickle files can be modified to deliver a malicious payload that "
"results in execution of arbitrary code on your machine."
"You will need to set `allow_dangerous_deserialization` to `True` to "
"enable deserialization. If you do this, make sure that you "
"trust the source of the data. For example, if you are loading a "
"file that you created, and no that no one else has modified the file, "
"then this is safe to do. Do not set this to `True` if you are loading "
"a file from an untrusted source (e.g., some random site on the "
"internet.)."
)
path = Path(folder_path)
# load index separately since it is not picklable
annoy = dependable_annoy_import()