CreateCohereEmbeddings 2025.10.9.21

Bundle

com.snowflake.openflow.runtime | runtime-cohere-nar

Description

Uses Cohere to create embeddings for text. The input text can be provided as a single FlowFile or as a record-oriented FlowFile.

Tags

chatbot, cohere, embeddings, gen ai, generative ai, llm, nlp, openflow, text

Input Requirement

Supports Sensitive Dynamic Properties

false

Properties

PropertyDescription
Cohere API KeyThe API Key for authenticating to Cohere
Embedding TypeSpecifies the types of embeddings you want to get back.
Embeddings ModelThe model to use for embeddings, available models are listed at https://docs.cohere.com/reference/embed
Embeddings Record PathThe path to the field in the record where the embeddings are to be written.
Input TypeSpecifies the type of input passed to the model. Required for embedding models v3 and higher.
Max Batch SizeThe maximum number of records to include in each batch sent to Cohere
Record ReaderThe record reader to use for reading record-oriented data. If the incoming data is to be treated as plaintext, this property should be left unset.
Record WriterThe Record Writer to use for writing the output
Text Record PathThe path to the field in the record that contains the text to be embedded. If the incoming data is to be treated as plaintext, this property should be left unset.
Truncate PolicyOne of NONEEND to specify how the API will handle inputs longer than the maximum token length.
UserAn identifier for the remote user on whose behalf the request is being made.

Relationships

NameDescription
failureThe original FlowFile will be routed to this relationship if the embeddings could not be created
successThe embeddings will be routed to this relationship

Writes attributes

NameDescription
record.countThe number of records written to the output
mime.typeThe MIME type of the output data, based on the chosen Record Writer

Use cases

Create embeddings for text using Cohere’s Embedding model