Tag Essentials - with AI auto tagging and XFRM support

Tag Essentials - with AI auto tagging and XFRM support [Paid] 2.6.8

No permission to buy (£35.00)
Is there any potential for Ollama (https://ollama.com) support as an alternative to ChatGPT? One site I am starting the process for upgrading to 2.3/3.0 is currently at heads with ChatGPT ripping content that they have not licensed, and while using ChatGPT does not license it to OpenAI, it does have some language that implies that input/output can be used to maintain their services which makes the situation questionable.
 
Is there any potential for Ollama (https://ollama.com) support as an alternative to ChatGPT? One site I am starting the process for upgrading to 2.3/3.0 is currently at heads with ChatGPT ripping content that they have not licensed, and while using ChatGPT does not license it to OpenAI, it does have some language that implies that input/output can be used to maintain their services which makes the situation questionable.
No plans to add Ollama. Never heard of it until I just read your post.
It's something we might be able to do, but honestly we have 6 months worth of urgent development, so if it's not broken, it's not going to get any attention right now.
 
No plans to add Ollama. Never heard of it until I just read your post.
It's something we might be able to do, but honestly we have 6 months worth of urgent development, so if it's not broken, it's not going to get any attention right now.
(y) the fact that it may be considered was already more than I expected. I also do not plan to actually upgrade until ~6 months after 3.0 comes out, and could do without the AI features anyways.
 
Can this turn off WikiTags yet? I'd prefer to use OpenAI tagging only as most the content on my general forum doesn't operate under topics found in Wiki, for the most part.

I can appreciate that AV forums does (to possibly pull a specific camera model Wiki, for example), but I'd just like to use OpenAI suggested tags and that's it.
 
Wikipedia is used to find more information for a tag. ChatGPT adds tags based on the thread title and first post content.
They are two different functions.
 
I could never get it to work without WikiTags (i.e., a tag displaying a Wiki if there was one).

I just want tags auto-created by ChatGPT.

Notice "Use ChatGPT as a fallback."... This means that Wiki is used first, and if no tag, falls back to Wiki. I want it to always query ChatGPT for "Give me 5 forum tags for this text: " (or something to that extent; it will always give you good tags if queried right) and only use those.

No Wiki fallback.
 
1741907360305.webp

But is it going to use Wiki regardless? This seems to suggest it will only use ChatGPT if no Wiki is available at the same time to suggest tags using ChatGPT. Kind of confusing, to say the least.

And, is there an option to batch auto-tag older content? (Will be expensive, I know)
 
But is it going to use Wiki regardless? This seems to suggest it will only use ChatGPT if no Wiki is available at the same time to suggest tags using ChatGPT. Kind of confusing, to say the least.
i believe thats the "description by default" option from my first shot....the wiki is for "description"...different from tag suggestion.
And, is there an option to batch auto-tag older content? (Will be expensive, I know)
yes, but it can be good to do in bits and monitor because its adding new tags then once they are in the system they will more likely suggest again...so you want to block/merge tags as you go if you get me, maybe even run it a second time even, but you can start to get a solid tag list...the tools are there
 
  • Like
Reactions: frm
then once they are in the system they will more likely suggest again
That'd be the plan, but I have a forum with 0 tags so I need to populate it first. :p

Let me see how the updated one runs.

I disabled it because it didn't ChatGPT tag (only Wiki tag) and it was uninstallable (Tag Essentials 2.6.2). Hopefully, after upgrade, it can be uninstalled. But, that wasn't my concern with it as I wanted auto-suggested ChatGPT tags and batch-update tags using GPT only.
 
I think @frm means that he wants to turn off Wikipedia article display on Tags pages. Hence Wiki-tags.
I’m investigating having a single admin option to enable/disable the use of Wikipedia for tag information.

I could never get it to work without WikiTags (i.e., a tag displaying a Wiki if there was one).

I just want tags auto-created by ChatGPT.

Notice "Use ChatGPT as a fallback."... This means that Wiki is used first, and if no tag, falls back to Wiki. I want it to always query ChatGPT for "Give me 5 forum tags for this text: " (or something to that extent; it will always give you good tags if queried right) and only use those.

No Wiki fallback.
I’m not sure whether the ChatGPT fallback has ever worked. I’ll investigate.
And, is there an option to batch auto-tag older content? (Will be expensive, I know)
This is something that I want to do.
There are two issues. The first is cost. It might be possible to burn through your OpenAI credit quickly.
The second is the time it takes to run a ChatGPT query. It’s so long that a batch update of threads is going to have to be a batch process much like the ones we run in the Rebuild caches section.
 
It would be awesome if auto-tagging of old content can be done in relation to SEO analysis data from ahrefs. So that it prioritizes tags that are likely to yield traffic.
 
It would be awesome if auto-tagging of old content can be done in relation to SEO analysis data from ahrefs. So that it prioritizes tags that are likely to yield traffic.
I don’t understand what you’re asking for. Let me have a stab. So you want ChatGPT to analyse the links within the first post and return tags which have the best SEO value for each of the links? Bare in mind that threads have a limit of something like 10 tags.
 
No, I want to feed the ai with terms that have a low keyword difficulty and high search volume. I.e. Keywords many people search for. For example by feeding it a spreadsheet.
Then I want the ai to prioritize these terms, considering that threads have a limit of the number of tags.

Let's say that the ai finds 20 applicable tags, but must choose only 10. The ai will normally just select the most relevant 10.
For SEO purposes it would be an effective strategy to prioritize tags that are likely to result in new traffic.

Does that make sense?
 
There are two issues. The first is cost. It might be possible to burn through your OpenAI credit quickly.
I know this will be the main factor, and am okay with it, for as long as the prompt can give me the best tags possible.

It only has to be run once (and then the rest are on new thread creations), so it's just the cost of doing business to get tags working and possibly get better ranking and/or linking of threads for user navigation to similar topics.

As soon as Wiki is disconnected from Tags and Tags can work solely on GPT, I will hop on and tag up all my threads, letting people know how much it costs to tag X threads with the AI credits.
 
There are two issues. The first is cost. It might be possible to burn through your OpenAI credit quickly.
You could possibly implement an auto-manual feature using a user's main ChatGPT "credits" (i.e., not using OpenAI API... or even free services), Grok, or other AI services.

Export N number of thread X + thread/post 1 thread title/message in JSON format, the user uploads that file and prompts it "for each entry, examine the thread_title and thread_message of the post; give me X thread_tags that closely relate to it no longer than 3 words in length and each word no longer than 10 characters in length; try to use up to 25% of the tags that are hot topics on the subject found in thread_message if they can relate".

Hypothetically you should have a new JSON file with a new "thread_tags" line populated with "this is a, this tag, about something...". That file could be used to import and circumvent OpenAI credits on batch processes.

I'd have to play with how many threads it could tag per process because anything under 100 would take way too much time. But, if it could process 500 for "free" (unsure unsubscribed ChatGPT) with 4o or another model (or even with Grok), a batch update wouldn't take any OpenAI credits to do for as long as the file stays in the same format: "thread_id" (for easier importing), "thread_title", "thread_message", "thread_tags" (added).

The add on would export all the JSON files and would be zipped so that the user could unzip them and process them 1 by 1 until done. Then zipped back up and then decompressed/applied to all threads when done (as ChatGPT can throttle if you do too much, so it might take a day to get done on 50,000+ threads, but it'd be free, unlike with the OpenAI credits).
 
Back
Top Bottom