services.xml

<?xml version="1.0" encoding="utf-8" ?>
<!-- Copyright Vespa.ai. Licensed under the terms of the Apache 2.0 license. See LICENSE in the project root. -->
<services version="1.0" xmlns:deploy="vespa" xmlns:preprocess="properties" minimum-required-vespa-version="8.327.49">

  <container id="default" version="1.0">
     <!-- See https://docs.vespa.ai/en/embedding.html#huggingface-embedder -->
    <component id="e5_small" type="hugging-face-embedder">
      <transformer-model url="https://github.com/vespa-engine/sample-apps/raw/master/examples/model-exporting/model/e5-small-v2-int8.onnx"/>
      <tokenizer-model url="https://raw.githubusercontent.com/vespa-engine/sample-apps/master/examples/model-exporting/model/tokenizer.json"/>
      <prepend> <!-- E5 prompt instructions -->
        <query>query:</query>
        <document>passage:</document>
      </prepend>
    </component>
    <document-api/>

    <secrets>
      <bedrock-api-key vault="sample-apps" name="aws-bedrock-token" />
    </secrets>

    <!-- Setup the client to Bedrock -->
    <component id="openai" class="ai.vespa.llm.clients.OpenAI">
      <config name="ai.vespa.llm.clients.llm-client">
        <endpoint>https://bedrock-runtime.us-east-1.amazonaws.com/openai/v1</endpoint>
        <apiKeySecretName>bedrock-api-key</apiKeySecretName>
        <model>openai.gpt-oss-20b-1:0</model>
      </config>
    </component>
   
    <search>

      <chain id="bedrock" inherits="vespa">
        <searcher id="ai.vespa.search.llm.RAGSearcher">
          <config name="ai.vespa.search.llm.llm-searcher">
            <providerId>openai</providerId>
          </config>
        </searcher>
      </chain>

    </search>
    <nodes>
      <node hostalias="node0" />
    </nodes>
  </container>

  <content id="msmarco" version="1.0">
    <redundancy>1</redundancy>
    <documents>
      <document mode="index" type="passage"/>
    </documents>
    <nodes>
      <node hostalias="node1" distribution-key="0" />
    </nodes>
  </content>

</services>