Knowledge imported from a file can now carry a link inside your own site, and it appears as a clickable source under the answer. Set it in the Citation link box on the item, or add a url column when importing. No setting changes and no database change.<\/p>","1.21.0":"
The plugin was renamed to AI House Knowledge Chat (slug Adds Install this if you took 1.18.4 for a WordPress.org submission: the directory assigned the slug Five screenshots taken on a real site are now listed in this readme, and the pictures themselves are committed to the directory's One line in this file changed: This is the copy handed to WordPress.org for review. It corrects the readme fields the directory checks (five tags, a short description under 150 characters, Install this before submitting the plugin to WordPress.org: it is the security review. Two real hardening fixes (an oversized picture is now refused before it is decoded, and the hand-over route caps how much text it will store), plus a new automated check that encodes what a reviewer looks for \u2014 every REST route gated, no unprepared query, every file refusing direct access, every admin action with a nonce and a capability, and an uninstall that removes what the plugin created. No new option, no database change: install over 1.18.0.<\/p>","1.18.0":" Install this if the bot ever answered a greeting or a thank-you with "this question is outside the information this website holds". That refusal is fixed in all twelve languages, a question that merely starts politely is still refused correctly, and the default System prompt now says how long an answer may be and what to do when the assistant does not know. If you edited your System prompt yourself, paste the guideline from the project's docs\/17 into it. No new option, no database change: install over 1.17.0.<\/p>","1.17.0":" Install this to collect your visitors' contact details and read them: a person icon in the chat opens a short form (a name, and a phone number or an email address), the chat offers it once after three questions, and a new Customers<\/strong> screen lists everyone with a CSV download and a delete button. The details stay on your own site \u2014 never copied to Supabase \u2014 consent is stored with the exact sentence the visitor agreed to, and WordPress' own Tools \u2192 Export\/Erase Personal Data now find and remove a customer by their email or phone number. This release adds one database table, applied automatically on upgrade. Install it over 1.16.0, deleting the plugin folder first as always.<\/p>","1.16.0":" Install this for three changes to the message box: all the tools (picture, microphone) now sit together on the LEFT of the field, Send is a round arrow instead of the word, and the box strengthens while a question is being typed. The word "Send" still exists for screen readers in all twelve languages \u2014 it moved into the button's accessible name, so nothing is lost. No new option, no database change, no new string. If you are on 1.14.0, install 1.14.1 or later anyway: in 1.14.0 choosing a photo did nothing.<\/p>","1.15.0":" Install this for the redrawn message box: flat icons in a row along the bottom, the field as a filled pill, and the microphone, the picture button and Send all the same height. Nothing was renamed \u2014 no class, attribute, label or translated string \u2014 so the script, the twelve languages and the accessibility labels are untouched, and there is no new option and no database change. The dark theme was corrected with it. If you are on 1.14.0, install 1.14.1 or later anyway: in 1.14.0 choosing a photo did nothing.<\/p>","1.14.1":" Install this if you installed 1.14.0: in that release the attach-a-picture button opened the file picker, but after choosing a photo nothing happened \u2014 no preview, and nothing could be sent. The cause was one line of JavaScript, and this release fixes it. It also adds an automated test that presses the widget's buttons in a real DOM, because the existing checks only read the code and all of them passed while the button was dead. No new option, no database change, no new string: install it over 1.14.0.<\/p>","1.14.0":" Install this for the attach-a-picture button: a visitor can send a photo with their question, and the assistant can read it. Photos are stored privately on your own site (not in the Media Library), are shrunk in the browser before they are sent, are visible only to administrators through a permission-checked link, and are deleted together with the conversation they belong to. The button appears only when the model you selected can actually read an image, and a question is still required \u2014 the knowledge search works on text, so a picture on its own has nothing to look up. This release adds one database column, applied automatically; if your site runs on Nginx, note the limitation stated in the description: Install this for the microphone in the chat: a visitor can speak their question and the words arrive in the text box for them to check before sending. It uses the browser's own speech recognition, so the sound never reaches your server or your AI provider \u2014 but note that browsers do this by sending the audio to their own vendor's service (Chrome to Google). The button appears only in browsers that can do it: on Firefox it stays hidden, and nothing is recorded or stored. No new option, no database change: install over the top. The attach-an-image button is the next release, not this one.<\/p>","1.12.1":" Install this if you installed 1.12.0. That version could show "There has been a critical error on this website" on every page when the plugin folder was only partly updated \u2014 an old file left next to a new one by a File Manager or FTP upload, which is a normal way for an update to go wrong. This version makes the two methods involved optional and routes every question through one defensive call, so a missing method means "the feature is unavailable" instead of a dead site. If your site is already showing that page, delete the Install this for the groundwork of picture and voice input: Install this if you have 1.11.0: Install this for the redesigned Settings screen: the tabs are now a sidebar of nine sections, the screen opens on Install this if you use the knowledge lock: the buttons and the admin code are gone, and the lock is now switched by the file alone \u2014 Install this if you use the knowledge lock, and especially if you have ever typed a wrong unlock code: that path printed a PHP warning on every attempt. Nothing about the lock's behaviour changes \u2014 turning it off from the settings card still needs the admin code, and the message now also tells you the file's path and the two ways to open the site without a code (set Install this if you installed 1.9.8: that version made every wp-admin screen show "There has been a critical error on this website", while your visitors' chat kept working. If you cannot reach the Plugins screen to update, delete the Install this if you want the floating button to say something \u2014 "Contact us", your brand, anything \u2014 or if you want a bubble that invites the click. Both are opt-in: give the button a text on the Language tab, set a delay (in seconds) in General for the bubble, and nothing changes until you do. The bubble is shown once per visitor and can be dismissed with a keyboard. Also fixes the missing signpost for renaming the assistant, which is the bot name on the Language tab. Two new options, no database change: install over the top.<\/p>","1.9.3":" Install this if you have not installed 1.9.2 yet, or if you set up the lock with the settings card: that button used to overwrite the whole lock file, taking the admin code and any policy text you had written into it. New installs now arrive locked, with the code shown once in wp-admin; updating an existing site does not lock it. No database change: install over the top.<\/p>","1.9.2":" Install this if you want the chatbot to answer only from your own content. A public widget whose model answers from general knowledge is a free general-purpose AI on your API key, and one of the two ways that happened had no setting to switch it off. Create the lock (a file in your uploads folder, or the new Knowledge lock card) and a question outside your content is refused without spending a token. Nothing changes until you create the file: no database change, no new option, install over the top.<\/p>","1.9.1":" Install this if you use If you have enabled more than one chat language, install this: the widget's own buttons and messages used to stay in your site's language while the conversation moved to your visitor's, and the "leave your email" form was English for ten of the twelve languages. Both now follow the visitor, in all twelve. No database change, no new option: install over the top.<\/p>","1.8.0":" The AI House dashboard is translated now instead of always English, and Settings \u2192 General \u2192 Interface language lets you choose the language of the plugin's own screens separately from your WordPress profile. Your visitors' chat language is unaffected. One new setting, no database change: install over the top.<\/p>","1.7.2":" If you have enabled Japanese (or Korean) in the language switcher, install this: the detector used to read a Japanese message as Chinese, which moved the interface to Chinese on sites that also enabled it, and left the interface alone on sites that did not. It affects the language the widget speaks, not the answer the model writes. No database change, no new option: install over the top.<\/p>","1.7.1":" Documentation only, and the only reason it is a release at all is that readme.txt ships inside the plugin: the installation steps said four database tables where there are five, and the language section still described the pre-1.7.0 behaviour. If you are on 1.7.0 there is nothing to gain but nothing to lose either.<\/p>","1.7.0":" The chatbot now answers in the language the visitor actually wrote in, rather than the language of the widget's selector \u2014 so a Vietnamese question in an EN widget comes back in Vietnamese, and the interface follows the visitor too. The sentence shown when the AI provider is unreachable now follows as well. No database change, no new option: install over the top.<\/p>","1.6.9":" The question box grows with what you type instead of scrolling your own sentence out of sight, Enter still sends, and Shift+Enter starts a new line. The chat window keeps itself inside the screen while the box grows. Presentation only: no database change, no new option, install over the top.<\/p>","1.6.8":" The Requests screen printed each visitor's clock time wrong by exactly the site's UTC offset \u2014 a request that arrived "2 mins ago" could be shown as tomorrow 04:28 \u2014 while the "ago" label right beside it was correct, because the two halves read the same stored value in two different ways. The clock time now goes through the WordPress function whose documented contract matches that value. Only a site that does not run on UTC could ever see this, and the screen was added in 1.6.6. Presentation only: no database change, no new option, install over the top.<\/p>","1.6.7":" Three things that were invisible are now on screen: Test connection also checks the embedding key (it never did, which is how a green report can sit next to indexing failures), the Status card lists background jobs that gave up along with the error that stopped them, and the indexing progress bar no longer reports impossible numbers. No database change, no new option: install over the top.<\/p>","1.6.6":" The questions visitors leave for a human now have their own screen in the AI House menu, with every field they filled in, filters, paging and the reply\/close buttons \u2014 instead of a card at the bottom of the settings page. The plugin also has a logo now, in the admin menu, on every AI House screen and on the chat widget. No database change, no new option: install over the top.<\/p>","1.6.2":" The Status card now reports the state of the "question for a human" hand-over: how many are waiting, when the last one was saved, and \u2014 if the last visitor attempt failed \u2014 why. Until now a failed submission left no trace anywhere in WordPress, so a form that never reached the database looked exactly like a form nobody had used.<\/p>","1.6.1":" Diagnostics only. When Supabase refuses the conversation-log write because the table is missing a column, the message now names that column and gives both fixes instead of guessing at the primary key \u2014 and sql\/supabase-schema.sql gained a repair block for a table that already holds rows. Nothing changes for a site whose log mirror already works.<\/p>","1.6.0":" Indexing now proves it can read back what it wrote: after each indexing run the plugin asks the vector store for a vector it has just stored and reports whether the knowledge base still recognises its own text. That turns "the index says 26 of 26 but answers without citations" into a number and a next step. Test connection also checks the optional Supabase conversation log by writing and removing a probe row, and the log mirror reports whether it is on, off, or has never managed to copy anything.<\/p>","1.5.9":" Optional: when the chatbot cannot answer a question, it can now ask the visitor for an email address and save the question for a human, with an optional email or webhook notification. Off by default. Deactivate and activate the plugin once so the new requests table is created.<\/p>","1.5.8":" Optional: copy the conversation log into Supabase alongside the vectors, for reading the history from outside WordPress and for taking the write load off MySQL. Off by default, and a failure there can never lose a message or break the chat. Needs the table and primary key from sql\/supabase-schema.sql.<\/p>","1.5.7":" Picking a chat model now sends it one short test message and tells you straight away whether it answers or is a reasoning model \u2014 a reasoning model makes every visitor question return the fallback message and blocks citations entirely. Also closes a leftover path that could pair vectors with the wrong chunk, and makes indexing refuse a short answer from the embedding provider instead of leaving invisible gaps.<\/p>","1.5.6":" Clearer failure messages: a red "LLM" line now says the chat is answering with the fallback message, the empty-reply message names the model and budget, and "Settings in use" no longer prints the embedding model as if it had a doubled prefix.<\/p>","1.5.5":" Re-index your knowledge after updating.<\/strong> Embeddings could be paired with the wrong chunk when the provider returned them out of order, which silently made every similarity score meaningless. The lookup test now checks that the knowledge base can still recognise its own text, and says whether an empty result is missing content or vectors that no longer match the embedding model.<\/p>","1.5.4":" Adds a lookup test on the RAG tab, plus a record of what the knowledge base did on the last question, so an answer without citations says which of the three causes it was. If a lookup finds nothing, the test measures the real best score with the threshold removed and tells you whether to lower Minimum score or re-index.<\/p>","1.5.3":" Answers taken from the cache now keep their sources, the similarity threshold has a setting and a saner default (0.35 instead of 0.72), and an empty "Embedding API key" no longer reads as an error. If the bot answers without citing your content, lower Minimum score on the RAG tab.<\/p>","1.5.2":" Test connection now also verifies that the vector store accepts writes, so a public "anon" Supabase key is caught at the test button instead of after a failed indexing run. The test prints the settings it used, and failed indexing jobs now show their error in the Status log.<\/p>","1.5.1":" Fixes Test connection reporting a false failure when the chat model reasons before it answers, and fixes background indexing jobs that could stay stuck in "processing" so indexing appeared to stop. Test connection now also tells you when your settings have not been saved yet.<\/p>","1.5.0":" OpenRouter can now be used for embeddings too, so one provider and one key can run the whole chatbot. Also fixes the embedding key field description and the "Items per batch" setting.<\/p>","1.4.2":" The chat widget now opens in English instead of Vietnamese, and Vietnamese text renders in a font that has all its accents. Visitors who already picked a language keep their choice.<\/p>","1.4.1":" Fixes 1.4.0 accepting an API key without really testing it, which left the chat answering with the fallback message. Paste the key again after updating.<\/p>","1.4.0":" Paste an API key and the models load straight away \u2014 no need to save first. OpenAI and Gemini also get model lists now.<\/p>","1.3.7":" Fixes "Load paid models" listing the same models as the free button. Load the paid list again to see the paid models.<\/p>","1.3.6":" Reorganises the LLM tab: one API key field that follows the provider, and a paid model list beside the free one. No stored key is affected.<\/p>","1.3.5":" Fixes the "Load free models" button, which gave no visible result. Loaded models now appear in a dropdown beside the field.<\/p>","1.3.4":" Fixes saving the LLM provider: choosing OpenRouter no longer reverts to OpenAI, and the free model list now loads.<\/p>","1.3.3":" Fixes the admin menu: clicking AI House now opens the dashboard instead of the knowledge list.<\/p>","1.3.2":" Fixes a fatal error on PHP 8 that prevented the plugin from being deleted after deactivation. Deletion now removes all plugin data.<\/p>","1.3.1":" Content defaults are now plain English in the settings fields instead of the translated default. Existing Vietnamese defaults that were never edited are upgraded automatically.<\/p>","1.3.0":" Adds knowledge import from Markdown, CSV, JSON and text files, with preview before importing.<\/p>"},"ratings":[],"assets_icons":{"icon-128x128.png":{"filename":"icon-128x128.png","revision":3766617,"resolution":"128x128","location":"assets","locale":"","width":128,"height":128},"icon-256x256.png":{"filename":"icon-256x256.png","revision":3766670,"resolution":"256x256","location":"assets","locale":"","width":256,"height":256}},"assets_banners":{"banner-1544x500.png":{"filename":"banner-1544x500.png","revision":3766617,"resolution":"1544x500","location":"assets","locale":"","width":1544,"height":500},"banner-772x250.png":{"filename":"banner-772x250.png","revision":3766617,"resolution":"772x250","location":"assets","locale":"","width":772,"height":250}},"assets_blueprints":{},"all_blocks":[],"tagged_versions":["1.22.0","1.22.1"],"block_files":[],"assets_screenshots":[],"screenshots":{"1":"Settings \u2192 Get started<\/strong>: nine sections in a sidebar, and the four things that stand between a fresh install and a working assistant \u2014 each one saying whether it is done, and what to do when it is not.","2":"The widget on a real page: the language switcher, both tools on the left<\/strong> of the message box, and Send as an arrow that takes your site's colour.","3":"Overview<\/strong>: messages, sessions, cache hits and average latency, the background job queue, and the provider circuit breaker.","4":"Knowledge<\/strong>: drop in a file, then watch every item it became being chunked and indexed.","5":"Customers<\/strong>: one card per person, the exact sentence they agreed to, Download CSV<\/strong>, and a Delete button on every row."}},"plugin_section":[],"plugin_tags":[2353,5707,2364,226124,70446],"plugin_category":[41],"plugin_contributors":[288711],"plugin_business_model":[],"class_list":["post-390047","plugin","type-plugin","status-publish","hentry","plugin_tags-ai","plugin_tags-chat","plugin_tags-chatbot","plugin_tags-llm","plugin_tags-rag","plugin_category-communication","plugin_contributors-vunguyenbh","plugin_committers-vunguyenbh"],"banners":{"banner":"https:\/\/ps.w.org\/aihouse\/assets\/banner-772x250.png?rev=3766617","banner_2x":"https:\/\/ps.w.org\/aihouse\/assets\/banner-1544x500.png?rev=3766617","banner_rtl":false,"banner_2x_rtl":false},"icons":{"svg":false,"icon":"https:\/\/ps.w.org\/aihouse\/assets\/icon-128x128.png?rev=3766617","icon_2x":"https:\/\/ps.w.org\/aihouse\/assets\/icon-256x256.png?rev=3766670","generated":false},"screenshots":[],"raw_content":"\n AI House answers customer questions using your own website content, with two answer branches:<\/p>\n\n On shared hosting the scarce resource is PHP workers, and a chat request that holds one\nfor several seconds is a real cost. This plugin is built around that limit: every outbound\ncall has a hard timeout, a circuit breaker, an answer cache, and a quota guard.<\/p>\n\n Measured cost per chat request: 3 database queries, 1-3 outbound HTTP calls, and zero writes to wp_options.<\/strong><\/p>\n\n AI House has no server of its own<\/strong>. It sends nothing to the plugin authors, and it collects no analytics. It does call services that you configure, with your own accounts<\/strong>, and this section lists every one of them, what is sent, and where to read their terms.<\/p>\n\n The plugin does nothing until you enter a key.<\/strong> With no key configured there is no outbound request of any kind, other than the two self-tests you can press yourself.<\/p>\n\n What is sent:<\/strong> the visitor's question, the recent turns of that conversation, your system prompt for the current language, and \u2014 when the knowledge base has a match \u2014 the retrieved text chunks. What is not sent:<\/strong> the visitor's IP address, any WordPress user data, your other plugin settings, or anything from your admin screens.<\/p>\n\n The same three providers can supply embeddings (OpenAI, Google and OpenRouter). What is sent:<\/strong> the text of the content you chose to index, split into chunks. This happens only when you press Index knowledge<\/strong>, which you do yourself; nothing is indexed in the background without it.<\/p>\n\n What is sent:<\/strong> the text chunks and their vectors, plus the question's vector when a search runs, so the nearest chunks can be returned. If you turn on the optional conversation mirror, the conversation text is copied there too.<\/p>\n\n If you paste a webhook URL (n8n, Zapier, Make, your own endpoint) and<\/strong> switch on the hand-over form, AI House POSTs the visitor's question and the contact details they typed \u2014 name, email, phone and their note \u2014 to that URL. You<\/strong> choose the destination; the plugin has no default and sends nothing when the field is empty.<\/p>\n\n You are the data controller for your visitors' conversations. Before enabling a provider, read its terms, and tell your visitors what you do with their messages in your own privacy policy. WordPress's own guidance on this is at https:\/\/wordpress.org\/documentation\/article\/privacy\/.<\/p>\n\n Two shortcodes, for two different kinds of page.<\/p>\n\n [mybot title=\"Support\" height=\"480\" theme=\"light\" lang=\"en\"]\n `<\/p>\n\n\n\n\n Attribute\n Default\n What it does\n\n\n\n\n [mybot_help title=\"How can we help?\" subtitle=\"Search the guides, or ask the assistant.\" placeholder=\"Search the help pages\" button=\"Search\" ask=\"Ask the assistant instead\" topics=\"Getting started|\/getting-started, Billing|\/billing\"]\n `<\/p>\n\n\n\n\n Attribute\n Default\n What it does\n\n\n\n\n Every visible word is an attribute, so the page can be written in your visitors' language without touching the plugin. No template is needed: paste the shortcode into an ordinary Page and it renders.<\/p>\n\n\n AI House > Settings > Get started<\/strong> walks through the four things a new install needs, and says which are still missing. Nothing on that screen runs a test by itself.<\/p>\n\n The assistant answers only from your website's content when a file called the knowledge lock<\/strong> is on your server:<\/p>\n\n wp-content\/uploads\/mybot\/khoa-tri-thuc.md\n `<\/p>\n\n To switch it on, create that file with this block at the top:<\/p>\n\n \n `<\/p>\n\n With the lock on, everything is searched against your knowledge base, and a question with nothing above your Minimum score<\/strong> is refused without calling the model<\/strong>, so it costs no tokens and the visitor is offered the \"leave your email\" form instead. Short greetings are still answered. A file with no \u26a0\ufe0f A new install does not arrive locked<\/strong> (changed in 1.10.0: earlier versions created this file for you and handed over an admin code; that code was removed at the request of the plugin's author after it locked people out of their own setting). Until you create the file, the assistant still answers questions your content cannot cover, from the model's own general knowledge, on your API key.<\/p>\n\n You do not need an account with us, and there is no paid tier of this plugin.<\/strong> AI House has no server of its own: it is free, complete, and the code you install is the whole product. No feature is locked, no trial expires, and installing it sends nothing to the authors.<\/p>\n\n What it does need is your own<\/strong> account with the provider you choose \u2014 an API key for the AI model, and optionally a vector database. That is your account, your key, and your bill, and the plugin talks to those services directly from your site.<\/p>\n\n\n No. It uses RAG. Your content is split into chunks, converted to vectors, and stored. When\na visitor asks something, the closest chunks are retrieved and placed in the prompt.\nNothing is trained, updates are instant, and you can see which source produced each answer.<\/p><\/dd>\n Yes. OpenRouter offers free models and Google Gemini has a free embedding tier. Note that\nOpenRouter free models are limited to 20 requests per minute and 50 per day until you have\npurchased 10 credits. AI House checks your remaining quota before calling and returns a\nfriendly message instead of a raw error.<\/p><\/dd>\n The circuit breaker opens after a configurable number of consecutive failures and serves\nyour fallback message immediately, without holding a PHP worker. The real reason is\nrecorded and shown on the dashboard.<\/p><\/dd>\n In the Yes. Each site gets its own tables, options and knowledge base.<\/p><\/dd>\n No. The knowledge post type is not public, so it creates no front-end pages and is\nexcluded from search. Citations therefore show the title only. If you want linked\ncitations, index regular pages or posts instead.<\/p><\/dd>\n Markdown, CSV, JSON and plain text. PDF and DOCX are not supported because extracting\ntext from them requires a PHP library that most shared hosts cannot install. Convert those\ndocuments to Markdown first.<\/p><\/dd>\n\n<\/dl>\n\n\naihouse<\/code>) at the request of the WordPress.org review team, because the previous name was too close to another chatbot product. Delete the old plugin folder after installing this version. Settings, knowledge base and conversations are not affected.<\/p>","1.20.0":"[mybot_help]<\/code>: a help-centre block with a search box over your published pages and a button that opens the assistant. Nothing to configure \u2014 paste the shortcode into an ordinary page. Settings and stored data are untouched.<\/p>","1.19.0":"aihouse<\/code>, so the text domain had to change everywhere, and the automated scan refused the old one. Nothing else changes \u2014 no settings, no data, no behaviour. The translation files were renamed, so pick your language again in Settings if the interface comes up in English.<\/p>","1.18.4":"assets<\/code> folder. No code change, no setting, no string, no database: install it only if you want the readme to match the directory listing.<\/p>","1.18.3":"Contributors:<\/code> now names the real WordPress.org account (vunguyenbh<\/code>) instead of a placeholder. No code, no setting, no database change \u2014 install it only if you want the credits to point at the right person.<\/p>","1.18.2":"Tested up to<\/code> 7.1) and closes the last two places that printed without escaping. It also corrects a number: the coding-standard level published in 1.18.1 was measured on 1.16.0, and the real figure for this tree is now 42 errors and 16 warnings, every one of them explained. No setting, no database change, nothing to reconfigure: install over 1.18.1.<\/p>","1.18.1":".htaccess<\/code> is ignored there, so the folder is unguessable rather than actively denied.<\/p>","1.13.0":"mybot<\/code> folder over FTP and install this version fresh. No database change: install over the top.<\/p>","1.12.0":"Test connection<\/code> now reports whether the selected model can read an image, and message content can carry one. Nothing changes about how the assistant answers today \u2014 a normal question produces exactly the same request as 1.11.1 \u2014 and \/chat<\/code> still accepts text only, so there is no attachment button yet. If you use Test connection<\/code>, you will see one extra line: Vision:<\/code>. No new option, no database change: install over the top.<\/p>","1.11.1":"Knowledge base<\/code> moves up to sit directly under Get started<\/code>, because two of the four setup steps are about content and the section they send you to should be beside them. Nothing else changes \u2014 no option is renamed, no string changes, and no behaviour of the chat or the indexing changes. Install over the top.<\/p>","1.11.0":"Get started<\/code>, the add-ons list is a section instead of its own menu entry, and the report cards have a Status<\/code> section of their own. Every setting stays on the same section and keeps its name, so nothing you configured moves. This release also adds an add-on key field \u2014 and it says in plain words that it stores and shape-checks a key but does NOT verify one, because the licence server it would be verified against does not exist yet. If you do not sell add-ons, ignore that field; nothing on your site waits for a key. New options come with defaults and there is no database change: install over the top.<\/p>","1.10.0":"wp-content\/uploads\/mybot\/khoa-tri-thuc.md<\/code> present means on, che-do: off<\/code> pauses it, deleting it removes it. Nothing in the plugin writes that file any more, so your own text inside it is safe from updates. A new install no longer arrives locked. If you are upgrading, your existing lock file keeps working exactly as it did, including the ma-quan-tri<\/code> line, which is now simply ignored. No database change: install over the top.<\/p>","1.9.10":"che-do: off<\/code> in that file, or delete it). No database change: install over the top.<\/p>","1.9.9":"mybot<\/code> folder over FTP and install this version. No database change: install over the top.<\/p>","1.9.4":"[mybot lang="..."]<\/code> or [mybot title="..."]<\/code> \u2014 both attributes did nothing \u2014 or if any of your visitors use a screen reader, where the \u00d7 button, the question box and the floating launcher were still read in your site's language. No database change, no new option: install over the top.<\/p>","1.9.0":"\n
Providers<\/h4>\n\n
\n
Knowledge sources<\/h4>\n\n
\n
Languages<\/h4>\n\n
\n
Admin dashboard<\/h4>\n\n
\n
Also included<\/h4>\n\n
\n
[mybot]<\/code> shortcode, light and dark themes<\/li>\nExternal services<\/h3>\n\n
AI model provider \u2014 you choose one<\/h4>\n\n
\n
Embedding provider \u2014 only when you index your own content<\/h4>\n\n
Vector database \u2014 optional<\/h4>\n\n
\n
Webhook \u2014 optional, off until you set a URL<\/h4>\n\n
Your responsibilities<\/h4>\n\n
Shortcodes<\/h3>\n\n
[mybot]<\/code> \u2014 the chat widget, inline.<\/strong> Put it on a support page when you want the conversation itself to be the page.<\/p>\n\n`\n<\/code><\/pre>\n\ntitle<\/code>\n the bot's name\n The heading above the chat. Set by you, so the script leaves it alone.\n\n\n height<\/code>\n 480<\/code>\n Height in pixels of the inline widget.\n\n\n theme<\/code>\n light<\/code>\n light<\/code> or dark<\/code>.\n\n\n mode<\/code>\n auto<\/code>\n auto<\/code> (the plugin decides), quick<\/code> (always the model) or deep<\/code> (always your content).\n\n\n lang<\/code>\n the site's chat language\n Which language the chat opens in, when it is one of the twelve.\n\n\n\n\n[mybot_help]<\/code> \u2014 a help-centre block: search over your own pages, then a way to reach a person.<\/strong> This is the shape of a support front page: a heading, a large search box, results as the visitor types, topic links you choose, and a button that opens the assistant. It searches your published<\/strong> pages and posts only \u2014 never the knowledge base you imported, which is private on purpose.<\/p>\n\n`\n<\/code><\/pre>\n\ntitle<\/code>\n \"How can we help?\"\n The heading.\n\n\n subtitle<\/code>\n empty\n One line under the heading.\n\n\n placeholder<\/code>\n \"Search the help pages\"\n Text inside the search field.\n\n\n button<\/code>\n \"Search\"\n The submit button's label.\n\n\n label<\/code>\n \"Search the help pages\"\n What a screen reader announces for the field.\n\n\n ask<\/code>\n \"Ask the assistant instead\"\n The button that opens the chat.\n\n\n topics<\/code>\n empty\n Comma-separated label and URL pairs, drawn as chips under the box. A refused URL scheme is dropped.\n\n\n\n\n\n
mybot<\/code> folder to \/wp-content\/plugins\/<\/code>, or install the ZIP through Plugins > Add New > Upload Plugin.<\/li>\nQuick start with no cost<\/h4>\n\n
\n
Answering only from your own content (the knowledge lock)<\/h4>\n\n
`\n<\/code><\/pre>\n\n`\n<\/code><\/pre>\n\nche-do: off on that line pauses the lock while keeping the file; **deleting the file** removes the lock completely. That is the whole interface \u2014 there is no button, no admin code, and nothing in this plugin ever writes to that file, so a plugin update cannot change it.\n<\/code><\/pre>\n\nMYBOT-LOCK<\/code> block is not a lock file; a file that declares a lock but cannot be read properly (a missing or unknown che-do<\/code>) is treated as on<\/strong>, with the reason shown on the card.<\/p>\n\nAdding your own knowledge<\/h4>\n\n
\n
sql\/supabase-schema.sql<\/code> in the SQL Editor<\/li>\nWhat works without an account of ours<\/h4>\n\n
\n
Does this train or fine-tune a model?<\/h3><\/dt>\n
Can I use it without paying for AI?<\/h3><\/dt>\n
What happens if the AI provider goes down?<\/h3><\/dt>\n
Where are conversations stored?<\/h3><\/dt>\n
{prefix}mybot_messages<\/code> table, written in batches by a background job rather than\nduring the visitor request. Recent messages are sent as context for follow-up questions,\nand old logs are purged automatically.<\/p><\/dd>\nDoes it work on multisite?<\/h3><\/dt>\n
Will my knowledge pages appear in Google?<\/h3><\/dt>\n
Which file formats can I import?<\/h3><\/dt>\n
1.22.0 (26\/10\/2026)<\/h4>\n\n
\n
get_permalink()<\/code>, which is empty for the private knowledge type and for every item imported from a file, so a citation showed a title with nothing to click. Each knowledge item now has its own link<\/strong>, set in a Citation link<\/strong> box on that item's edit screen or by a url<\/code> column in the import file (all three templates include it).<\/li>\n\/dang-ky<\/code>, or a URL on the same host including www.<\/code>. Another domain, javascript:<\/code>, and an empty value are refused, and the check runs when the link is read<\/strong> as well as when it is saved, so a bad URL already in the database cannot reach the widget. On a customer's site, \"the same host\" is that customer's own site.<\/li>\n1.21.0 (18\/10\/2026)<\/h4>\n\n
\n
aihouse<\/code>, and the text domain, plugin header and translation file names all follow it. If an older version is installed, delete that folder after activating this one.<\/li>\n