Looking for the old site?

How To

Browse By

  • Objective

  • Products

  • User Role

    How To
    Documentation
      Learn More

        Deploy a Pre-trained scispaCy Model

        This article uses a pre-packaged model, which you do not need to download to deploy. To use the pre-packaged model, skip to Deploy model to Fusion. The section Create the model describes how to complete this process on your own.

        Create the model (OPTIONAL)

        Skip this section to use the pre-packaged model.
        1. Download the scispacy.ipynb file and open it in Jupyter Notebook (or a similar alternative).

        2. Follow the steps in the notebook, substituting your custom values as needed.

        Deploy model to Fusion

        1. Navigate to Collections > Jobs.

        2. Click the Add button.

        3. Select the Create Seldon Core Model Deployment under Model Deployment Jobs.

          Add Model Deployment job

        4. Enter the values for your model deployment. If you are using the pre-packaged model, use the following values:

          Parameter Value

          Jobs ID

          scispacymodel-seldon-deployment

          Model Name

          scispacymodel

          Docker Repository

          shahanesanket

          Image Name

          scispacy-grpc:1.0

          Output Column Names for Model

          [entities]

          Seldon Core job config

        5. Run the job by clicking Run and selecting Start.

        When the job completes successfully, the model is deployed. Check the list of microservices to verify:

        Fusion microservices

        Import sample data

        1. Download and save the sample data file sampleJSON_body_content.csv.

        2. Navigate to Indexing > Datasources.

        3. Click the Add button and select File Upload.

          Add File Upload job

        4. Click Browse, select the sampleJSON_body_content.csv file, and click Open. Click the Upload File button to complete the upload process.

        5. Assign a value to the Datasource ID parameter. This article uses the ID sample-data.

          Datasource config

        6. Click the Save button.

        Create a Machine Learning stage in the Index Workbench

        1. Navigate to Indexing > Index Workbench.

        2. Click the Load button.

        3. Choose the datasource you created.

        4. Click the Add a Stage button.

        5. Choose the Machine Learning stage.

        6. In the Model ID field, enter scispacymodel.

        7. In the Model input transformation script field, enter the following script:

          var modelInput = new java.util.HashMap()
          var list = new java.util.ArrayList()
          list.add(doc.getFirstFieldValue("body_t"))
          modelInput.put("text", list)
          modelInput
        8. In the Model output transformation script field, enter the following script:

          doc.addField("entities_ss", modelOutput.get("entities"))
        9. Click the Apply button.

        Verify results

        1. Click the Start Job button, and allow the job to finish.

          Index Workbench start job

        2. Check the simulated results. If everything was successful, the results will resemble this:

          Index workbench result