We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Windows
Python Version: 3.11.5
promptflow 1.6.0 promptflow-tools 1.3.0 promptflow_vectordb 0.2.5 langchain 0.1.12 langchain-community 0.0.28 langchain-core 0.1.32 langchain-experimental 0.0.43 langchain-openai 0.0.8 langchain-text-splitters 0.0.1 faiss-cpu 1.7.4
This can be easily reproduced by following the tutorial notebook and then reload the saved Faiss index by rerun the cell
azureml-examples/sdk/python/generative-ai/promptflow/create_faiss_index.ipynb
Lines 122 to 139 in df1e23c
Should successfully load pre-built Faiss index without error
Got ValueError
https://github.com/langchain-ai/langchain/blob/40f846e65da37a1c00d72da9ea64ebb0f295b016/libs/community/langchain_community/vectorstores/faiss.py#L1054-L1089
Should somehow pass allow_dangerous_deserialization=True to use local pickle vector db checkpoint.
allow_dangerous_deserialization=True
I was able to bypass this error by changing promptflow_vectordb/core/engine/langchain_engine.py
promptflow_vectordb/core/engine/langchain_engine.py
# From self.__langchain_faiss = FAISS.load_local(path, LangchainEmbedding(self.__embedding)) # To self.__langchain_faiss = FAISS.load_local(path, LangchainEmbedding(self.__embedding), allow_dangerous_deserialization=True)
The text was updated successfully, but these errors were encountered:
No branches or pull requests
Operating System
Windows
Version Information
Python Version: 3.11.5
Steps to reproduce
This can be easily reproduced by following the tutorial notebook and then reload the saved Faiss index by rerun the cell
azureml-examples/sdk/python/generative-ai/promptflow/create_faiss_index.ipynb
Lines 122 to 139 in df1e23c
Expected behavior
Should successfully load pre-built Faiss index without error
Actual behavior
Got ValueError
https://github.com/langchain-ai/langchain/blob/40f846e65da37a1c00d72da9ea64ebb0f295b016/libs/community/langchain_community/vectorstores/faiss.py#L1054-L1089
Addition information
Should somehow pass
allow_dangerous_deserialization=True
to use local pickle vector db checkpoint.I was able to bypass this error by changing
promptflow_vectordb/core/engine/langchain_engine.py
The text was updated successfully, but these errors were encountered: