The node generates a Chroma vector store that uses the given embeddings model to map documents to a numerical vector that captures the semantic meaning of the document.
By default, the node embeds the selected documents using the embeddings model, but it is also possible to create the vector store from existing embeddings by specifying the corresponding embeddings column in the node dialog.
Downstream nodes, such as the Vector Store Retriever , utilize the vector store to find documents with similar semantic meaning when given a query.
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.
Note : Chroma changed their data layout which requires downstream nodes to create temporary copies when reading an outdated vector store. To migrate an outdated vector store, the Vector Store Data Extractor can be used to extract its data, which can then be used to create a new vectorstore.