Text Embedder

This node applies the provided embedding model to create embeddings of the texts contained in a string column of the input table.

A text embedding is a dense vector of floating point values capturing the semantic meaning of the text by mapping it to a high-dimensional space. Similarities between embedded entities are then derived by how close they are to each other in said space. These embeddings are often used to find semantically similar documents e.g. in vector stores.

Different embedding models encode text differently, resulting in incomparable embeddings. If this node fails to execute with 'Execute failed: Error while sending a command.', refer to the description of the node that provided the embedding model.

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 Embedding Model Selector 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.