OpenAI Embedder
Overview
You can use this Snap to generate an embedding vector based on the provided input data. The Snap processes the input document to generate the corresponding embedding for the output document, regardless of the batch size.
- Transform-type Snap
- Works in Ultra Tasks when the Batch size is set to 1.
Prerequisites
None.
Limitations
- The free tier allows up to 3 requests per minute, that totals 200 requests per day. The first paid tier offers 500 requests per minute with no daily limit.
Snap views
View | Description | Examples of upstream and downstream Snaps |
---|---|---|
Input | This Snap has at the most one document input view. The Snap requires the text to generate the embedding vector. | Mapper |
Output | This Snap has at the most one document output view. The Snap provides the embedded vectors, and the original input document. | Mapper |
Error |
Error handling is a generic way to handle errors without losing data or failing the Snap execution. You can handle the errors that the Snap might encounter when running the pipeline by choosing one of the following options from the When errors occur list under the Views tab. The available options are:
Learn more about Error handling in Pipelines. |
Snap settings
- Suggestion icon (): Indicates a list that is dynamically populated based on the configuration.
- Expression icon (): Indicates whether the value is an expression (if enabled) or a static value (if disabled). Learn more about Using Expressions in SnapLogic.
- Add icon (): Indicates that you can add fields in the field set.
- Remove icon (): Indicates that you can remove fields from the field set.
Field / Field set | Type | Description |
---|---|---|
Label | String |
Required. Specify a unique name for the Snap. Modify this to be more appropriate, especially if more than one of the same Snaps is in the pipeline. Default value: OpenAI Embedder Example: Embedding data |
Model name | String/Expression/Suggestion |
Specify the model name to use for the embeddings vector calculation. Learn more about the list of models from OpenAI that are compatible with the embeddings API. Default value: N/A Example: text-embedding-3-small |
Batch size | Integer/Expression |
Required.
Specify the number of documents batched per request. If running in Ultra mode, this must be set to 1.
Note:
Maximum value: 2048 Default value: N/A Example: 50 |
Text to embed | String/Expression |
Required. Specify the text to generate the embedding vector. Default value: N/A Example: $msg |
Model parameters |
Appears when you enable expression for the Model name and/or specify the value as text-embedding-3. Specify the parameters to tune the model runtime. |
|
Dimensions | Decimal/Expression |
Specify the output dimensions of the embedding vector for the text-embedding-3 models. Value must be between 1 and the maximum dimension for the model. Learn more about how to get embeddings. Minimum value: 1 Default value: N/A Example: 1536 |
Snap execution | Dropdown list |
Select one of the three modes in which the Snap executes.
Available options are:
Default value: Validate & Execute Example: Execute only |