github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-07-07 21:50:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

community[patch]: FAISS VectorStore deserializer should be opt-in (#22861)

Browse Source 
FAISS deserializer uses pickle module. Users have to opt-in to
de-serialize.
This commit is contained in:
Eugene Yurtsev 2024-06-13 15:48:13 -04:00 committed by GitHub
parent ce0b0f22a1
commit 77209f315e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 15 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
libs/community/langchain_community/vectorstores/faiss.py
View File

@ -1105,9 +1105,24 @@ class FAISS(VectorStore):
cls, cls,
serialized: bytes, serialized: bytes,
embeddings: Embeddings, embeddings: Embeddings,
*,
allow_dangerous_deserialization: bool = False,
**kwargs: Any, **kwargs: Any,
) -> FAISS: ) -> FAISS:
"""Deserialize FAISS index, docstore, and index_to_docstore_id from bytes.""" """Deserialize FAISS index, docstore, and index_to_docstore_id from bytes."""
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 know 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.)."
)
index, docstore, index_to_docstore_id = pickle.loads(serialized) index, docstore, index_to_docstore_id = pickle.loads(serialized)
return cls(embeddings, index, docstore, index_to_docstore_id, **kwargs) return cls(embeddings, index, docstore, index_to_docstore_id, **kwargs)