Ask a question to get started
Enter to send•Shift+Enter new line
TimeWeightedVectorStoreRetriever()
BaseRetriever
The VectorStore to store documents and determine salience.
VectorStore
Keyword arguments to pass to the VectorStore similarity search.
The memory_stream of documents to search through.
The exponential decay factor used as (1.0-decay_rate)**(hrs_passed).
(1.0-decay_rate)**(hrs_passed)
The maximum number of documents to retrieve in a given call.
Other keys in the metadata to factor into the score, e.g. 'importance'.
The salience to assign memories not retrieved from the vector store.
None assigns no salience to documents not fetched from the vector store.
Return documents that are salient to the query.
Add documents to vectorstore.
Time Weighted Vector Store Retriever.
Retriever that combines embedding similarity with recency in retrieving values.
