Please see the set of transform project conventions for details on general project conventions, transform configuration, testing and IDE set up.
- Michele Dolfi ([email protected])
This transform is using sentence encoder models to create embedding vectors of the text in each row of the input .parquet table.
The embeddings vectors generated by the transform are useful for tasks like sentence similarity, features extraction, etc which are also at the core of retrieval-augmented generation (RAG) applications.
| input column name | data type | description |
|---|---|---|
| the one specified in content_column_name configuration | string | the content used in this transform |
| output column name | data type | description |
|---|---|---|
| the one specified in output_embeddings_column_name configuration | array[float] |
the embeddings vectors of the content |
The transform can be tuned with the following parameters.
| Parameter | Default | Description |
|---|---|---|
model_name |
BAAI/bge-small-en-v1.5 |
The HF model to use for encoding the text. |
content_column_name |
contents |
Name of the column containing the text to be encoded. |
output_embeddings_column_name |
embeddings |
Column name to store the embeddings in the output table. |
When invoking the CLI, the parameters must be set as --text_encoder_<name>, e.g. --text_encoder_column_name_key=myoutput.
Here is a sample notebook
To use the transform image to transform your data, please refer to the running images quickstart, substituting the name of this transform image and runtime as appropriate.
Following the testing strategy of data-processing-lib
Currently we have:
Please see the set of transform project conventions for details on general project conventions, transform configuration, testing and IDE set up.
This project wraps the text_encoder transform with a Ray runtime.
Text Encoder configuration and command line options are the same as for the base python transform.
Here is a sample notebook
In addition to those available to the transform as defined here, ray launcher options are available.
To use the transform image to transform your data, please refer to the running images quickstart, substituting the name of this transform image and runtime as appropriate.