This node establishes a connection with a Mistral AI embedding model. After successfully authenticating using the Mistral AI Authenticator node, you can select a model from the curated list of known embedding models.
If Mistral AI releases a new embedding model that is not contained in the predefined list, you can also select from a list of all available Mistral AI models.
Whether to select from the curated list of known embedding models or from all models available for the provided API key.
Available options:
Select a Mistral AI embedding model.
Select from all models available for the provided API key. The selected model must be compatible with the Mistral AI embeddings API. This configuration will overwrite the default model selection when set.
Maximum number of documents sent per embedding API request. The Mistral AI API rejects requests with more than 256 inputs.
The number of batches sent to the Mistral AI API at the same time. Increasing this value can speed up embedding of large document collections, but setting it too high may trigger API rate limit errors.
You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.
To use this node in KNIME, install the extension KNIME Python Extension Development (Labs) from the below update site following our NodePit Product and Node Installation Guide:
A zipped version of the software site can be downloaded here.
Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.
Try NodePit Runner!