This node reads a FAISS vector store create with LangChain from a local path. If you want to create a new vector store, use the FAISS Vector Store Creator instead.
A vector store is a data structure or storage mechanism that stores a collection of numerical vectors along with their corresponding documents. The vector store enables efficient storage, retrieval, and similarity search operations on these vectors and their associated data.
If the vector store was created with LangChain in Python, the embeddings model is not stored with the vectorstore, so it has to be provided separately via the matching Embeddings Model Connector node.
On execution, the node will extract a document from the store to obtain information about the document's metadata. This assumes that each document in the vector store has the same kind of metadata attached to it.
Note : If you use the Credentials Configuration node and do not select the "Save password in configuration (weakly encrypted)" option for passing the API key for the embeddings connector node, the Credentials Configuration node will need to be reconfigured upon reopening the workflow, as the credentials flow variable was not saved and will therefore not be available to downstream nodes.