{"id":383017,"date":"2026-10-10T15:59:48","date_gmt":"2026-10-10T15:59:48","guid":{"rendered":"https:\/\/wordpress.org\/plugins\/ai-provider-for-magnitude\/"},"modified":"2026-10-11T22:02:16","modified_gmt":"2026-10-11T22:02:16","slug":"devbridge-ai-provider-magnitude","status":"publish","type":"plugin","link":"https:\/\/ja.wordpress.org\/plugins\/devbridge-ai-provider-magnitude\/","author":20594762,"comment_status":"closed","ping_status":"closed","template":"","meta":{"version":"0.2.0","stable_tag":"0.2.0","tested":"7.1.3","requires":"7.0","requires_php":"7.4","requires_plugins":null,"header_name":"DevBridge AI Provider for Magnitude","header_author":"Mahbub Hussain","header_description":"Text generation with tool calling and image input on supported models, running locally on your own computer with Magnitude.","assets_banners_color":"1d2766","last_updated":"2026-10-11 22:02:16","external_support_url":"","external_repository_url":"","donate_link":"","header_plugin_uri":"https:\/\/github.com\/DevMahbubHussain\/devbridge-ai-provider-magnitude","header_author_uri":"","rating":0,"author_block_rating":0,"active_installs":0,"downloads":111,"num_ratings":0,"support_threads":0,"support_threads_resolved":0,"author_block_count":0,"sections":["description","installation","faq","changelog"],"tags":{"0.1.0":{"tag":"0.1.0","author":"mahbubwpwist","date":"2026-10-10 16:35:41","revision":3738368},"0.2.0":{"tag":"0.2.0","author":"mahbubwpwist","date":"2026-10-11 22:02:16","revision":3740194}},"upgrade_notice":[],"ratings":[],"assets_icons":{"icon-128x128.png":{"filename":"icon-128x128.png","revision":3738379,"resolution":"128x128","location":"assets","locale":"","width":128,"height":128},"icon-256x256.png":{"filename":"icon-256x256.png","revision":3738379,"resolution":"256x256","location":"assets","locale":"","width":256,"height":256},"icon.svg":{"filename":"icon.svg","revision":3738379,"resolution":false,"location":"assets","locale":false}},"assets_banners":{"banner-1544x500.png":{"filename":"banner-1544x500.png","revision":3738379,"resolution":"1544x500","location":"assets","locale":"","width":1544,"height":500},"banner-772x250.png":{"filename":"banner-772x250.png","revision":3738379,"resolution":"772x250","location":"assets","locale":"","width":772,"height":250}},"assets_blueprints":{},"all_blocks":[],"tagged_versions":["0.1.0","0.2.0"],"block_files":[],"assets_screenshots":{"screenshot-1.png":{"filename":"screenshot-1.png","revision":3740206,"resolution":"1","location":"assets","locale":"","width":939,"height":806}},"screenshots":{"1":"The Magnitude settings screen showing the connection status, server address, available models, and Test Playground."}},"plugin_section":[],"plugin_tags":[2353,25308,226124,258461,285568],"plugin_category":[],"plugin_contributors":[285569],"plugin_business_model":[],"class_list":["post-383017","plugin","type-plugin","status-publish","hentry","plugin_tags-ai","plugin_tags-connector","plugin_tags-llm","plugin_tags-local-ai","plugin_tags-magnitude","plugin_contributors-mahbubwpwist","plugin_committers-mahbubwpwist"],"banners":{"banner":"https:\/\/ps.w.org\/devbridge-ai-provider-magnitude\/assets\/banner-772x250.png?rev=3738379","banner_2x":"https:\/\/ps.w.org\/devbridge-ai-provider-magnitude\/assets\/banner-1544x500.png?rev=3738379","banner_rtl":false,"banner_2x_rtl":false},"icons":{"svg":"https:\/\/ps.w.org\/devbridge-ai-provider-magnitude\/assets\/icon.svg?rev=3738379","icon":"https:\/\/ps.w.org\/devbridge-ai-provider-magnitude\/assets\/icon.svg?rev=3738379","icon_2x":false,"generated":false},"screenshots":[{"src":"https:\/\/ps.w.org\/devbridge-ai-provider-magnitude\/assets\/screenshot-1.png?rev=3740206","caption":"The Magnitude settings screen showing the connection status, server address, available models, and Test Playground."}],"raw_content":"<!--section=description-->\n<p>DevBridge AI Provider for Magnitude connects WordPress to <a href=\"https:\/\/magnitude.dev\/\">Magnitude<\/a>, an open-source inference engine that runs open-weight models on your own hardware.<\/p>\n\n<p>The plugin integrates Magnitude's OpenAI-compatible API with the WordPress AI Client, allowing compatible WordPress plugins to use locally running AI models.<\/p>\n\n<p>This is an independent project. It is not affiliated with, endorsed by, or sponsored by Magnitude AI Inc., the maker of Magnitude. The name Magnitude is used only to identify the service this plugin connects to.<\/p>\n\n<p><strong>Features:<\/strong><\/p>\n\n<ul>\n<li>Text generation with models served by Magnitude.<\/li>\n<li>Tool (function) calling on supported models.<\/li>\n<li>Structured JSON output on supported models.<\/li>\n<li>Image and audio input when supported by the running model.<\/li>\n<li>Automatic model discovery.<\/li>\n<li>Model capabilities are detected from the capabilities reported by Magnitude.<\/li>\n<li>No API key required for local connections.<\/li>\n<li>Integration with the WordPress AI Client.<\/li>\n<li>Connector integration under Settings &gt; Connectors.<\/li>\n<li>Settings page under Settings &gt; Magnitude.<\/li>\n<li>Test Playground for trying prompts against running models.<\/li>\n<li>Adjustable temperature, top P, and maximum token settings in the Test Playground.<\/li>\n<li>Optional system instructions and example prompts.<\/li>\n<li>Ability to select a running model, stop an in-progress request, clear conversation history, and bypass the response cache.<\/li>\n<li>Connection status and server address information.<\/li>\n<\/ul>\n\n<p><strong>Requirements:<\/strong><\/p>\n\n<ul>\n<li>WordPress 7.0 or higher.<\/li>\n<li>PHP 7.4 or higher.<\/li>\n<li>The Magnitude application installed and running.<\/li>\n<li>At least one model downloaded and started in Magnitude.<\/li>\n<\/ul>\n\n<p>Magnitude lists models that are currently running. Start a model in the Magnitude application before expecting it to appear in the connector.<\/p>\n\n<p><strong>Important limitations:<\/strong><\/p>\n\n<ul>\n<li>Magnitude provides text and chat inference. It does not provide image generation, embeddings, or speech generation through this connector.<\/li>\n<li>The default server URL is <code>http:\/\/127.0.0.1:10100\/inference<\/code>.<\/li>\n<li>The first request to a model may take a minute while the model loads.<\/li>\n<li>Magnitude returns one answer per request, so generating multiple variations in a single request is not available through this plugin.<\/li>\n<li>Reasoning models may require a higher token limit to finish thinking and produce a complete answer.<\/li>\n<\/ul>\n\n<h3>External Services<\/h3>\n\n<p>This plugin connects to the Magnitude server configured in Settings &gt; Magnitude or through the <code>DEVBRIDGE_AI_PROVIDER_MAGNITUDE_HOST<\/code> constant.<\/p>\n\n<p>By default, the server address is <code>http:\/\/127.0.0.1:10100\/inference<\/code>, which points to a Magnitude application running on the same computer as WordPress.<\/p>\n\n<p><strong>What data is sent:<\/strong><\/p>\n\n<ul>\n<li>Prompts and context submitted by other plugins through the WordPress AI Client.<\/li>\n<li>Prompts submitted through the Test Playground.<\/li>\n<li>Requests to discover available models.<\/li>\n<li>The API key, if configured in Settings &gt; Connectors.<\/li>\n<\/ul>\n\n<p><strong>When data is sent:<\/strong><\/p>\n\n<ul>\n<li>When a plugin uses the AI Client with Magnitude.<\/li>\n<li>When an administrator submits a prompt through the Test Playground.<\/li>\n<li>When an administrator opens Settings &gt; Connectors or Settings &gt; Magnitude, or manually checks the connection.<\/li>\n<\/ul>\n\n<p>The plugin does not send requests to Magnitude merely because it is activated, and it does not send data from the front end of the website on its own.<\/p>\n\n<p><strong>Where data is sent:<\/strong><\/p>\n\n<p>Data is sent only to the Magnitude server address configured by the site administrator. The plugin does not send prompts or usage data to the plugin author or any other third-party service.<\/p>\n\n<p>Magnitude is a separate application developed by Magnitude AI Inc. For more information, visit <a href=\"https:\/\/magnitude.dev\/\">https:\/\/magnitude.dev\/<\/a>.<\/p>\n\n<!--section=installation-->\n<ol>\n<li>Upload the plugin files to the <code>\/wp-content\/plugins\/devbridge-ai-provider-magnitude\/<\/code> directory, or install the plugin through the WordPress Plugins screen.<\/li>\n<li>Activate the plugin through the Plugins screen in WordPress.<\/li>\n<li>Open Settings &gt; Magnitude.<\/li>\n<li>Ensure the Magnitude application is running and at least one model has been started.<\/li>\n<li>Confirm that the connection status shows Connected and that your running models appear.<\/li>\n<li>To use the plugin through the WordPress AI Client, open Settings &gt; Connectors and configure the Magnitude connector if necessary.<\/li>\n<\/ol>\n\n<p>No API key is required when Magnitude runs on the same computer as WordPress.<\/p>\n\n<!--section=faq-->\n<dl>\n<dt id=\"why%20does%20magnitude%20show%20no%20models%3F\"><h3>Why does Magnitude show no models?<\/h3><\/dt>\n<dd><p>Magnitude lists only models that are downloaded and currently running. Open the Magnitude application, download a model if necessary, start it, and reload the Magnitude settings page.<\/p><\/dd>\n<dt id=\"do%20i%20need%20an%20api%20key%3F\"><h3>Do I need an API key?<\/h3><\/dt>\n<dd><p>No. When Magnitude runs on the same computer as WordPress, leave the API key field under Settings &gt; Connectors empty.<\/p>\n\n<p>The field may be displayed as part of the standard connector interface, but Magnitude does not require a key for local use.<\/p><\/dd>\n<dt id=\"how%20do%20i%20connect%20to%20magnitude%20on%20another%20computer%3F\"><h3>How do I connect to Magnitude on another computer?<\/h3><\/dt>\n<dd><ol>\n<li>Open the Magnitude application on the computer running the model.<\/li>\n<li>Enable Network access in Magnitude.<\/li>\n<li>If the Require API key option is enabled, copy the API key and enter it in the Magnitude connector under Settings &gt; Connectors in WordPress. Save your settings.<\/li>\n<li>Find the network address shown under Reachable at in Magnitude. The address should end in <code>\/inference\/v1<\/code>.<\/li>\n<li>Open Settings &gt; Magnitude in WordPress and enter the reachable address. The plugin handles the <code>\/v1<\/code> API path, so either the base <code>\/inference<\/code> address or the <code>\/inference\/v1<\/code> address can be used.<\/li>\n<\/ol>\n\n<p>You can also define the server address in <code>wp-config.php<\/code>:<\/p>\n\n<pre><code>define( 'DEVBRIDGE_AI_PROVIDER_MAGNITUDE_HOST', 'http:\/\/192.168.1.20:10100\/inference' );\n<\/code><\/pre>\n\n<p>Replace the example IP address with the reachable address of your Magnitude server. When this constant is defined, the settings field is locked.<\/p>\n\n<p>Only HTTP and HTTPS addresses without a username or password are accepted. Use network access only on a network you trust, and configure authentication and network protections appropriately.<\/p><\/dd>\n<dt id=\"why%20is%20a%20reply%20empty%20or%20cut%20short%3F\"><h3>Why is a reply empty or cut short?<\/h3><\/dt>\n<dd><p>Reasoning models may use a significant number of tokens for internal reasoning before producing their final answer. Increase the maximum token limit for the feature you are using.<\/p><\/dd>\n<dt id=\"does%20this%20plugin%20support%20image%20generation%3F\"><h3>Does this plugin support image generation?<\/h3><\/dt>\n<dd><p>No. Magnitude provides text and chat inference through this connector, not image generation. If you need image generation or embeddings in WordPress, consider an AI provider that supports those capabilities, such as a compatible Ollama setup.<\/p><\/dd>\n<dt id=\"does%20this%20plugin%20support%20image%20and%20audio%20input%3F\"><h3>Does this plugin support image and audio input?<\/h3><\/dt>\n<dd><p>Yes, when the running model supports the relevant input type and Magnitude reports that capability. Support depends on the model and the capabilities exposed by Magnitude.<\/p><\/dd>\n<dt id=\"how%20is%20magnitude%20different%20from%20ollama%3F\"><h3>How is Magnitude different from Ollama?<\/h3><\/dt>\n<dd><p>Both Magnitude and Ollama can run open-weight models locally and provide OpenAI-compatible APIs. They are separate applications, and each has its own WordPress connector.<\/p>\n\n<ul>\n<li><strong>Focus:<\/strong> Magnitude is an inference engine designed to optimize inference for the available hardware. Ollama offers a broad library of models and also provides a cloud service.<\/li>\n<li><strong>Performance:<\/strong> Magnitude publishes benchmarks showing performance improvements over llama.cpp on tested hardware. Actual performance depends on your hardware, model, and configuration.<\/li>\n<li><strong>Default address:<\/strong> This plugin uses <code>http:\/\/127.0.0.1:10100\/inference<\/code>. The Ollama API commonly uses <code>http:\/\/localhost:11434<\/code>.<\/li>\n<li><strong>WordPress features:<\/strong> This plugin provides text generation, tool calling, structured JSON output, and supported image and audio input. Image generation and embeddings are not available through Magnitude via this connector.<\/li>\n<\/ul><\/dd>\n<dt id=\"which%20one%20should%20i%20use%3F\"><h3>Which one should I use?<\/h3><\/dt>\n<dd><p>Use the connector that matches the inference application you run. Choose this plugin if you use Magnitude or want to try it. If you need image generation or embeddings, choose a provider that supports those features, such as the Ollama connector.<\/p><\/dd>\n<dt id=\"what%20data%20does%20the%20test%20playground%20store%3F\"><h3>What data does the Test Playground store?<\/h3><\/dt>\n<dd><p><strong>Conversation history:<\/strong> When you test models in the Test Playground under Settings &gt; Magnitude, the multi-turn conversation history is stored in your browser's session storage (<code>sessionStorage<\/code>). It is not stored in the WordPress database. Clearing the history or closing the browser tab removes the session history.<\/p>\n\n<p><strong>Response cache:<\/strong> To reduce repeated inference requests while testing, responses from the Test Playground are cached using WordPress transients for up to 10 minutes. Enable Bypass Cache to skip cached responses and request a fresh result.<\/p>\n\n<p><strong>Uninstall cleanup:<\/strong> When the plugin is deleted, its saved options and temporary transients are removed from the WordPress database on single-site and multisite installations.<\/p><\/dd>\n<dt id=\"is%20this%20plugin%20related%20to%20the%20ollama%20connector%3F\"><h3>Is this plugin related to the Ollama connector?<\/h3><\/dt>\n<dd><p>No. DevBridge AI Provider for Magnitude is an independent project. It was inspired by the AI Provider for Ollama plugin but is not affiliated with Ollama, its makers, or the authors of that plugin.<\/p><\/dd>\n\n<\/dl>\n\n<!--section=changelog-->\n<h4>0.2.0<\/h4>\n\n<ul>\n<li>Added a screenshot of the Magnitude settings screen and Test Playground.<\/li>\n<li>Added a Test Playground under Settings &gt; Magnitude.<\/li>\n<li>Added controls for temperature, top P, and maximum tokens.<\/li>\n<li>Added optional system instructions and quick example prompts.<\/li>\n<li>Added model selection for testing running models.<\/li>\n<li>Added the ability to stop an in-progress request.<\/li>\n<li>Added the ability to clear conversation history.<\/li>\n<li>Added an option to bypass the response cache.<\/li>\n<\/ul>\n\n<h4>0.1.0<\/h4>\n\n<ul>\n<li>Initial release.<\/li>\n<\/ul>","raw_excerpt":"Connect WordPress to Magnitude for local AI text generation, tool calling, structured JSON output, and image and audio input on supported models.","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/ja.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin\/383017","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ja.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin"}],"about":[{"href":"https:\/\/ja.wordpress.org\/plugins\/wp-json\/wp\/v2\/types\/plugin"}],"replies":[{"embeddable":true,"href":"https:\/\/ja.wordpress.org\/plugins\/wp-json\/wp\/v2\/comments?post=383017"}],"author":[{"embeddable":true,"href":"https:\/\/ja.wordpress.org\/plugins\/wp-json\/wporg\/v1\/users\/mahbubwpwist"}],"wp:attachment":[{"href":"https:\/\/ja.wordpress.org\/plugins\/wp-json\/wp\/v2\/media?parent=383017"}],"wp:term":[{"taxonomy":"plugin_section","embeddable":true,"href":"https:\/\/ja.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_section?post=383017"},{"taxonomy":"plugin_tags","embeddable":true,"href":"https:\/\/ja.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_tags?post=383017"},{"taxonomy":"plugin_category","embeddable":true,"href":"https:\/\/ja.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_category?post=383017"},{"taxonomy":"plugin_contributors","embeddable":true,"href":"https:\/\/ja.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_contributors?post=383017"},{"taxonomy":"plugin_business_model","embeddable":true,"href":"https:\/\/ja.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_business_model?post=383017"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}