Hosted vectors add another bill.
Pinecone and Qdrant are useful at scale. Most WordPress sites do not need that bill before the chatbot proves itself.
Alpha Chat indexes your posts, pages, and public custom post types, then answers visitor questions with retrieval-augmented generation. It cites sources, keeps the vector store in MySQL, and skips weak model calls when retrieval has nothing useful.
I built it because most WordPress chatbot plugins either push you into a hosted upsell or bolt a generic bot onto your site. This one is GPL code you can inspect, extend, and uninstall cleanly.

That is risky. A visitor asks about your refund policy, course outline, pricing, plugin docs, or support limits. A generic chatbot guesses. You get a polished answer and a support mess.
Pinecone and Qdrant are useful at scale. Most WordPress sites do not need that bill before the chatbot proves itself.
Buttons, fields, and panels inherit random theme styles. Shadow DOM isolation avoids that fight.
If there is no relevant context, Alpha Chat can return your fallback instead of paying for a weak answer.
You can inspect the PHP, TypeScript, REST routes, database schema, and uninstall cleanup.
The flow is boring in the right way: chunk content, embed it, retrieve matching passages, call the selected model, and show source cards under the reply.
wp_alpha_chat_chunks. Vector search runs inside WordPress by default.message -> moderation -> embedding -> MySQL vector search -> retrieved chunks -> model response -> source cards
Alpha Chat is built around what WordPress site owners actually worry about: speed, data control, support handoff, admin visibility, and plugin cleanup when you uninstall.
Read the plugin readmeThat does not make it the right answer for every site. If you need a managed AI support suite with agents, billing, and enterprise reporting, buy that. If you want clean WordPress code you control, Alpha Chat is the better starting point.
Use Alpha Chat when you want a self-controlled WordPress chatbot for docs, product pages, course content, blog archives, or support triage.
Skip it if you need a full help desk suite with human agent routing and enterprise SLAs.
The default setup is practical for normal WordPress sites, but it is not locked down. You can replace the LLM provider, embedding provider, or vector store with filters. You can also modify retrieved chunks before they hit the prompt.
alpha_chat_llm_provideralpha_chat_vector_storealpha_chat_retrieved_chunksalpha_chat_display_widgetadd_filter('alpha_chat_llm_provider', function ($default) { return new MyPlugin\Providers\LocalLLM(); });Download the ZIP, upload it in WordPress, add your provider keys, index your knowledge base, and place the block or shortcode where you want chat to appear.
alpha-chat.zip in Plugins > Add New.alpha_chat shortcode, or the floating launcher.Only to the AI provider you configure. Embeddings go through OpenAI. Chat requests go through OpenAI or Anthropic, depending on your settings. Alpha Chat does not send telemetry to a separate vendor endpoint.
Yes. Alpha Chat stores vectors in wp_alpha_chat_chunks and computes cosine similarity in PHP. One less service before you have proved the chatbot is useful.
The floating launcher is off by default. If you do not enable it site-wide, frontend assets load only where you place the block or alpha_chat shortcode, and the script uses defer.
Yes. Alpha Chat supports Anthropic Claude Opus 4.7, Sonnet 4.6, and Haiku 4.5 for chat. You still need OpenAI for embeddings and moderation.
Start with the ZIP. Read the code when you need to. Replace the provider later if your setup demands it.