services.xml

<?xml version="1.0" encoding="utf-8" ?>

<services version="1.0" xmlns:deploy="vespa" xmlns:preprocess="properties" minimum-required-vespa-version="8.311.28">

    <!-- See https://docs.vespa.ai/en/reference/services-container.html -->
    <container id="default" version="1.0">

        <!-- See https://docs.vespa.ai/en/embedding.html#colbert-embedder -->
        <component id="colbert" type="colbert-embedder">
            <transformer-model url="https://huggingface.co/colbert-ir/colbertv2.0/resolve/main/model.onnx"/>
            <tokenizer-model url="https://huggingface.co/colbert-ir/colbertv2.0/raw/main/tokenizer.json"/>
        </component>
        <document-api/>
        <search/>
        <nodes count="1">
            <resources vcpu="4" memory="16Gb" disk="125Gb">
                <gpu count="1" memory="16Gb"/>
            </resources>
        </nodes>
        
    </container>

    <!-- See https://docs.vespa.ai/en/reference/services-content.html -->
    <content id="text" version="1.0">
        <min-redundancy>2</min-redundancy>
        <documents>
            <document type="doc" mode="index" />
        </documents>
        <nodes count="2"/>
        <engine>
            <proton>
                <tuning>
                    <searchnode>
                        <requestthreads>
                            <persearch>4</persearch> <!-- Change the number of threads per search here -->
                        </requestthreads>
                    </searchnode>
                </tuning>
            </proton>
        </engine>
    </content>

</services>