xiaochen-zhou commented on code in PR #9673:
URL: https://github.com/apache/seatunnel/pull/9673#discussion_r2271585117
##########
docs/en/transform-v2/embedding.md:
##########
@@ -19,7 +19,7 @@ different API endpoints.
| secret_key | string | yes | - | The
secret key required for additional authentication with the embedding service.
|
| aws_region | string | no | | AWS
Region. Required for use Amazon Bedrock model.
|
| single_vectorized_input_number | int | no | 1 | The
number of inputs vectorized in one request. Default is 1.
|
-| vectorization_fields | map | yes | - | A
mapping between input fields and their corresponding output vector fields.
|
+| vectorization_fields | map | yes | - | A
mapping between input fields and their corresponding output vector fields.
Supports multimodal field specifications with format
`field_name:modality_type`. |
| model | string | yes | - | The
specific model to use for embedding (e.g: `text-embedding-3-small` for OPENAI).
|
| api_path | string | no | - | The API
endpoint for the embedding service. Typically provided by the model provider.
|
| dimension | int | no | - | TThe
vector dimension defaults to 2048. The Embedding-3 model supports custom vector
dimensions, and it is recommended to choose dimensions of 256, 512, 1024, or
2048. |
Review Comment:
> Please help modify it. There's an extra "T" here
OK.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
