All Products
Search
Document Center

OpenSearch:Customize services

Last Updated:Apr 01, 2026

General-purpose embedding models often underperform in domain-specific retrieval tasks because their training data does not cover your business content. At the same time, high-dimensional vectors drive up storage and compute costs as data volumes grow. AI Search Open Platform lets you address both problems through model customization:

  • Text embedding: Fine-tune a base text embedding model with your own data to improve retrieval accuracy in intelligent search and retrieval-augmented generation (RAG) scenarios.

  • Embedding dimensionality reduction: Train a custom model that compresses high-dimensional vectors into lower-dimensional ones, reducing storage and compute costs without significantly degrading retrieval quality.

In a typical workflow, you first fine-tune a text embedding model, then train a dimensionality reduction model to compress the resulting embeddings.

Prerequisites

Before you begin, make sure you have:

Customize the text embedding service

  1. In the AI Search Open Platform console, go to Model Service > Model Customization and click Create.

  2. On the Model Customization page, configure the following parameters.

    ParameterDescription
    Model NameA name for the model. Used when you invoke the service.
    Model TypeSelect Text Embedding (text-embedding).
    Base ModelThe base model used for training, such as ops-text-embedding-001.
    Dimensionality ReductionEnable to run dimensionality reduction training alongside text embedding training.
    Base Model for ReductionThe model used for dimensionality reduction. Available only when Dimensionality Reduction is enabled.
    Data SourceSelect MaxCompute or OSS.
  3. Configure the data source parameters.

    MaxCompute

    ParameterDescription
    RegionThe region where the MaxCompute project is located.
    Project NameThe name of your MaxCompute project.
    AccessKey IDThe AccessKey ID of the Alibaba Cloud account or RAM user with read and write permissions for MaxCompute. Get one from the AccessKey Management page.
    SecretThe AccessKey secret corresponding to the AccessKey ID.
    Table NameThe name of the table that stores your training data.
    Table PartitionThe partition information of the table.
    Training FieldsGrant GetTableFields permission to the RAM user before selecting fields. Then select the primary key field and String-type text data fields.
    query-doc pairThe query-document pairs used for training. See the sample data in the console for the required format.

    OSS

    ParameterDescription
    RegionThe region where the OSS bucket is located.
    OSS BucketThe name of your OSS bucket.
    Doc DataThe training data files in OSS.
    query-doc pairThe query-document pairs used for training. See the sample data in the console for the required format.
    OSS EndpointGenerated automatically after you complete the preceding configurations.
  4. Click OK. In the dialog that appears, choose how to start training:

    • Create and Train: Starts pre-processing immediately. Training begins after pre-processing completes.

    • Confirm Creation: Adds the model to the list with a To Be Trained status. Start training at any time from the model list.

    Once training completes, the model status changes to Active. At that point, you can deploy the model for production use.

Customize the embedding dimensionality reduction service

  1. In the AI Search Open Platform console, go to Model Service > Model Customization and click Create.

  2. On the Model Customization page, configure the following parameters.

    ParameterDescription
    Model NameA name for the model. Used when you invoke the dimensionality reduction service.
    Model TypeSelect Vector Dimensionality Reduction (embedding-dim-reduction).
    Base ModelThe base model used for training, such as ops-embedding-dim-reduction-001.
    Data SourceSelect MaxCompute or OSS.
  3. Configure the data source parameters.

    MaxCompute

    ParameterDescription
    RegionThe region where the MaxCompute project is located.
    Project NameThe name of your MaxCompute project.
    AccessKey IDThe AccessKey ID of the Alibaba Cloud account or RAM user with read and write permissions for MaxCompute. Get one from the AccessKey Management page.
    SecretThe AccessKey secret corresponding to the AccessKey ID.
    Table NameThe name of the table that stores your training data.
    Table PartitionThe partition information of the table.
    Training FieldsGrant GetTableFields permission to the RAM user before selecting fields. Then select the primary key field and String-type embedding fields. Embedding fields must have between 1,024 and 4,096 dimensions.

    OSS

    ParameterDescription
    RegionThe region where the OSS bucket is located.
    OSS BucketThe name of your OSS bucket.
    Doc DataThe training data files in OSS.
    OSS EndpointGenerated automatically after you complete the preceding configurations.
  4. Click OK. In the dialog that appears, choose how to start training:

    • Create and Train: Starts pre-processing immediately. Training begins after pre-processing completes.

    • Confirm Creation: Adds the model to the list with a To Be Trained status. Start training at any time from the model list.

    Once training completes, the model status changes to Active. Click Experience to test the fine-tuned embedding model before invoking it.

Training status reference

StatusMeaningNext action
To Be TrainedModel created but training not started.Start training from the model list.
Pre-processingTraining data is being prepared.Wait for pre-processing to complete.
TrainingModel training is in progress.Wait for training to complete.
ActiveTraining complete. Model is ready.Deploy or invoke the model.

Invoke the model

After the model status changes to Active, invoke it using the API:

What's next