The node generates a Chroma vector store by processing a string column containing documents with the provided embeddings model. For each document, the embeddings model extracts a numerical vector that represents the semantic meaning of the document. These embeddings are then stored in the vector store, along with their corresponding documents. Downstream nodes, such as the Vector Store Retriever node , utilize the vector store to find documents with similar semantic meaning when given a query.
- Type: org.knime.python3.nodes.PythonBinaryBlobFileStorePortObjectEmbeddings
The embeddings model to use for the vector store.
- Type: TableDocuments
Table containing a string column representing documents that will be used in the vector store.