<style>p { margin: 0; }span.fr-emoticon.fr-emoticon-img { background-repeat: no-repeat !important; font-size: inherit; height: 1em; width: 1em; min-height: 20px; min-width: 20px; display: inline-block; margin: -0.1em 0.1em 0.1em; line-height: 1; vertical-align: middle; } span.fr-emoticon { font-weight: normal; font-family: "Apple Color Emoji", "Segoe UI Emoji", "NotoColorEmoji", "Segoe UI Symbol", "Android Emoji", "EmojiSymbols"; display: inline; line-height: 0; } blockquote { border-left: solid 2px #5e35b1; color: #5e35b1; margin-left:0; padding-left:5px;}blockquote blockquote{ border-color: #00bcd4; color: #00bcd4;}blockquote blockquote blockquote{ border-color: #43a047; color: #43a047;} table.grid{ border-collapse: collapse;} table.grid td, table.grid th { border: 1px solid #ddd;} .fr-fic.fr-dib{ display: block; margin: 5px auto;}.fr-fic.fr-dib.fr-fir{ text-align: right; margin: 5px 0 5px auto;}.fr-fic.fr-dib.fr-fil{ text-align: left; margin: 5px auto 5px 0;}.fr-fic.fr-dii{ float: none; margin: 5px auto;}.fr-fic.fr-dii.fr-fil{ float: left; margin: 5px auto;}.fr-fic.fr-dii.fr-fir{ float: right; margin: 5px auto;}img.fr-dib.fr-fir { margin-right: 0; text-align: right;}img.fr-dib.fr-fil { margin-left: 0; text-align: left;}img.fr-dib { margin: 5px auto; display: block; float: none;}img.fr-bordered { box-sizing: content-box; border: solid 5px #CCC;}img.fr-shadow { box-shadow: 10px 10px 5px 0px #cccccc;}img.fr-rounded { border-radius: 10px; -moz-border-radius: 10px; -webkit-border-radius: 10px; -moz-background-clip: padding; -webkit-background-clip: padding-box; background-clip: padding-box;}</style><p data-pasted="true"><strong>In this guide we will cover:</strong></p><p><strong>- What is the Amazon Bedrock Integration?</strong></p><p data-pasted="true"><strong>- Connecting to Amazon Bedrock</strong></p><p><br></p><p><span style="color: rgb(226, 80, 65);"><strong>Note: This Integration is available from v2.244+.</strong></span></p><p><br></p><p data-pasted="true"><span style="font-size: 14pt;"><strong>What is the Amazon Bedrock Integration?</strong></span></p><p>The native integration with Amazon Bedrock can be used to write responses on Tickets or improve on response Agent's have written themselves. It can also be integrated into your Live Chat to respond to a Customer, taking the given context into account.</p><p><br></p><p>There is various other functionality that can be achieved once Amazon Bedrock is connected to your Halo instance. For information on the functionality available checkout <a href="https://www.usehalo.com/guides/2137" target="_blank" rel="noopener noreferrer">Leveraging AI in Halo</a>. </p><p><br></p><p>A list of available models and their pricing per million tokens can be found <a href="https://aws.amazon.com/bedrock/pricing/" target="_blank" rel="noopener noreferrer">here</a>.</p><p><br></p><p data-pasted="true"><strong><em>Note: Currently this connection cannot be used with AI Agents, external MCP servers, and runbook-based functionality.</em></strong></p><p><br></p><p data-pasted="true"><strong><span style="font-size: 14pt;">Connecting to Amazon Bedrock</span></strong></p><p>To enable this Integration, head to Configuration > Integrations, and head to the AI section. Here you you will find the Amazon Bedrock module. Hover over the Integration, and click the '+' icon to enable it. </p><p><br></p><p><strong><em>Note: If the Integration is already enabled it will instead show a cross when hovered over. If this is the case you can skip this step and click into the module to open the configuration. </em></strong></p><p><br></p><p><strong><img src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6Ijc5ZWRhYTg2LTg1NGEtNGUyMy1hZTUxLTFlMzBjMTRiNzI3MSJ9.BU1p_fH-y4zfk_Fv39RDzgorLWMSfEloR784WtSYM-A" class="fr-fic fr-fil fr-dib" width="1163" style="width: 1165px; height: 234.186px;" height="234"></strong></p><p><span style="font-size: 10pt;"><strong>Fig 1. Enabling the module </strong></span></p><p><br></p><p>Once enabled, click into the module to configure your connection. Here specify the Region, and Model to use for your connection. If this is left blank, it will use "openai.gpt-oss-20b".</p><p><br></p><p>In order to create the connection you will need an API Key. To generate this Key you will need to head into your Amazon Bedrock account, and follow the steps outlined <a href="https://docs.aws.amazon.com/bedrock/latest/userguide/api-keys.html" target="_blank" rel="noopener noreferrer">here</a>. Once generated, copy and paste this Key into the "API Key" field. </p><p><br></p><p><img src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6IjI5NWQzYzQ0LTE1MjYtNDc2NC04MzAwLTdjMjg3MTE4ZjJlMiJ9.2NsSwFg__rXhohv-Z0Z6cvMm1eFE6gH-THNC5Tzm8zY" class="fr-fic fr-fil fr-dib" width="724" style="width: 726px; height: 466.352px;" height="466"></p><p data-pasted="true"><span style="font-size: 10pt;"><strong>Fig 2. Connecting to Amazon Bedrock </strong></span></p><p><br></p><p>Next, click the "AI Config" button to redirect to Configuration > AI. Here you will be able to select your Amazon Bedrock connection as your default AI connection.</p><p><br></p><p><img src="https://halo.haloservicedesk.com/api/attachment/image?token=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpZCI6IjIwMGEwNjA1LTZkZWEtNDI0My1hZTY2LTI5MjU1ZTVhMGIzNiJ9.bTgYDY-KYuth-JCW8riPw-fk8HWcu-vMWEd_ee8IIDg" class="fr-fic fr-fil fr-dib" width="436" style="width: 438px; height: 385.836px;" height="386"></p><p data-pasted="true"><span style="font-size: 10pt;"><strong>Fig 3. Setting Amazon Bedrock as the Default AI Connection</strong></span></p><p><br></p><p>For more information on how to leverage AI in Halo, see our guide linked <a href="https://www.usehalo.com/guides/2137" target="_blank" rel="noopener noreferrer">here</a>. </p><p><br></p><p data-pasted="true"><strong><em>Note: The Amazon Bedrock Integration uses the Amazon Titan Text Embedding v2 model to generate embeddings for tickets, articles and services. IF you have previously used the OpenAI / Azure OpenAI connection to create embeddings, you must clear the vector database before switching to Amazon Bedrock, as the old vectors will be incompatible.</em></strong></p><p><br></p><p><br></p>
