PromptAI

[robert]

I created a successor for my module PromptChatGPT (https://processwire.com/talk/topic/28311-processchatgpt/) with the even more creative name PromptAI. It is more or less a complete rewrite based on the Neuron AI framework.

Short description:

PromptAI is a Processwire CMS module that utilizes AI to process text fields upon saving. The processed text can be saved back to the original field or a different one on the same page. For image fields, the AI can write image descriptions or populate custom image subfields.

The main additions are:

• Multiple prompt support
• Provider select support
• System instructions
• Support for Image fields

All infos can be found here: https://github.com/robertweiss/PromptAI

Use cases could include text summaries, proofreading, or generating alt texts for images.

Happy prompting 😊

 

[robert]

PromptAI Module Update V1.1: New Config UI & Individual Buttons! 🎉

Hey everyonre, I just pushed an update to the PromptAI module that replaces the old textarea  configuration with a proper form interface at Setup > Prompt AI. No more typing template::source::target::prompt manually – now you get actual fields and buttons like a civilized person! 😄 

I also added an "Individual Prompt Buttons" option that lets you create separate "Save + [Custom Label]" buttons for each prompt configuration instead of one generic button. So you can have "Save + Create Summary", "Save + Generate Alt Text", etc. and run just the specific prompt you want.

Existing configs migrate automatically, so updates should run smoothly. Feedback welcome as always.

The module has now been added to the ProcessWire module list: https://processwire.com/modules/prompt-ai/

[robert]

PromptAI v1.2 is out!

New stuff:

• Repeater field support (including Repeater Matrix) – see the Readme for details
• Better config format using JSON and IDs instead of names
• Auto-migration handles the upgrade for you

Your existing configs will automatically convert to the new format, so everything should just work. Still worth making a backup though 😄

[robert]

v1.3 released with added support for Pagefile fields – now you can process documents with AI. This is especially useful for creating summaries, extracting key points, or generating descriptions for uploaded documents. Supported formats are PDF, RTF, Markdown, JSON, XML, CSV, and plain text files.

[robert]

Hey everyone! Just pushed two quick updates to PromptAI with some improvements:

v1.4 Changes

• New "Overwrite Target" option: You can now choose whether AI responses should overwrite existing content in target fields (disabled by default to protect your existing content)

v1.5 Changes

• Multiple template support per prompt: Configure a single prompt to work across multiple templates – no more duplicate configs!
• Native ProcessWire forms: Refactored config interface to use proper PW form elements
• Better template selection: Upgraded to ASMSelect for smoother template picking. This was a bit difficult to combine with dynamic JS fieldset creation and involved some brittle DOM hacking, so if anyone knows a simple way to combine Alpine JS and the ASMSelect JS part, I'd be happy to learn

As always, please test thoroughly before going live. Bug reports and feedback welcome on GitHub 😊

[robert]

v1.6 released with one tiny change: the overwrite target field setting is now configurable per prompt instead of globally. This allows you to have some prompts that preserve existing content while others overwrite it, giving you more granular control over AI processing behaviour. Needed the functionality for a client, so I thought it would be a nice addition for the module.

[Jorge]

Hi @robert.
Thanks for your work on this module.

I have an issue.
Setup 🡢 Prompt Ai returns this:

Can you help?

Thank you. Have a nice week.

[robert]

Hi @Jorge, I‘m afk till friday but will have a look when I‘m back!

[robert]

Hi @Jorge, I think I found the bug causing your error, I mixed up the native _() and the Processwire __() function 😅 Fixed version is on Github, does this resolve your issue? https://github.com/robertweiss/PromptAI

[JoZ3]

Hello, very good module. Is there any possibility of integrating Deepseek or adding a custom API query URL?

I currently use your module with Deepseek. All I did was change the OpenAI URL to the Deepseek URL, and it works very well, but it would be ideal if it were integrated.

Another thing: is there any option for it to work with SEO Maestro?

[robert]

Hi! I’ve just released v1.7 with native DeepSeek support as an AI provider. Note that, due to limitations in the Neuron AI framework’s DeepSeek integration, file and image uploads aren’t supported at the moment.

Regarding SEO Maestro: I haven’t worked with it before, and it looks like it uses custom subfields which aren't compatible with my current config form. It will take a bit more engineering to support properly. I’ll take a closer look about how to add subfield support in general, but I don’t expect to ship this in the near future.

[JoZ3]

14 hours ago, robert said:

Hi! I’ve just released v1.7 with native DeepSeek support as an AI provider. Note that, due to limitations in the Neuron AI framework’s DeepSeek integration, file and image uploads aren’t supported at the moment.

For me, it's perfect. Text generation is sufficient. I use it to help me with tags, which are a bit tedious for SEO.

14 hours ago, robert said:

Regarding SEO Maestro: I haven’t worked with it before, and it looks like it uses custom subfields which aren't compatible with my current config form. It will take a bit more engineering to support properly. I’ll take a closer look about how to add subfield support in general, but I don’t expect to ship this in the near future.

I was looking at it, and SEO Maestro hasn't been updated in quite some time, so it's not worth the effort 🙂

Personally, I really like PromptAI. It's a great help for things that are a bit tedious. It would be good if you could query the configured field, as Fluency does, for greater control and review before recording and publishing

[robert]

I like this idea – thanks! I’ll explore this further and see if I can come up with a clean implementation when I have time.

[robert]

PromptAI v2.3 — Inline Mode, Streaming, Placeholders, and more

Hi everyone,

It's been a while since the last update for PromptAI, and quite a lot has changed. Here's a summary of what's new since the last public release.

Inline Mode

The biggest addition is a new Inline Mode that adds magic wand buttons directly next to your fields. Instead of the "Save + Send to AI" workflow, you can now trigger AI processing on individual fields without saving the page first. The response streams in live and replaces the field content — but nothing is saved until you hit Save.

Both modes (Page Mode and Inline Mode) can be mixed freely in the same configuration. Each prompt is configured as either "page" or "inline".

Inline mode works with all supported field types: text fields, TinyMCE/CKEditor fields, image descriptions, file descriptions, and custom subfields — including inside repeaters.

Streaming Responses

AI responses now stream in real-time via Server-Sent Events (SSE). You can watch the text appear token by token instead of waiting for the full response. This obviously only works in inline mode.

Placeholder Support

Prompts can now reference other field values from the page using `{page.fieldname}` syntax. Inside repeaters, use `{item.fieldname}` to access the current repeater item's fields.

Examples:
- Summarize the following text to 400 characters: {page.body}
- Create an SEO meta description for a page titled '{page.title}'
- Write a caption for this gallery item titled '{item.title}' from the {page.gallery_name} collection

This makes prompts context-aware without having to send field content manually.

Multi-Field Selection

Instead of configuring a single source field per prompt, you can now select multiple fields. The same prompt will be applied to each selected field. This replaces the old source/target field concept — the "target" is now only used for subfield options in file/image fields.

AI Tools (experimental)

The module now ships with three experimental tools that allow the AI to query your ProcessWire installation:

- getPages — find pages by selector
- getPage — get detailed info about a single page
- getFields — list available templates and their fields

These are disabled by default and must be enabled in module configuration. They're meant as starting points — their usefulness depends heavily on your use case and I recommend to create your own for each projects specific demand.

Other Changes

- PHP 8.3 is now required to use this module

Important: Backup Before Updating

The internal configuration structure has changed significantly. The old `sourceField`/`targetField` concept has been replaced with a multi-field `fields` array and a separate `targetSubfield` option. There is no automatic migration for this change. I'm sorry for the inconvenience — the old structure simply didn't support the new features.

I attached two short screen videos showing the prompt config screen with example prompts and one page edit screen where I showcase some of the predefined prompts.

As always, feedback and bug reports are welcome — either here or on GitHub.
 

[robert]

Published Version 2.4 with support for custom user role permissions:

• promptai allows to use the prompts in page edit
• promptai-config allows to add/edit new prompts