Bot/AI/GPT Blog: https://johnsonbots.blogspot.com/
This system allows you to have conversations with the ChatGPT conversation bots from OpenAI. This system handles rather deep-ply conversations with memory, and is not simply a question-answer system. The result is not just a chatbot, but is an amazingly human-like simulation of a real person.
You need an OpenAI account (visit https://platform.openai.com/ ). You can use gpt-3.5-turbo or gpt-4o which are cheap, efficient, and effective. I find it to be very cheap for the fun I've had with it!
Note gpt-4 is quite expensive! Use gpt-4o.
If you want the thing to actually *talk* in audio, check out my blog article
https://johnsonbots.blogspot.com/2023/07/have-yourself-automatically-speak-in.html
The free code in there can easily be adapted to put the ConvoBot output into audio!
The system now also works with OpenAI-compatible APIs - make sure the endpoints end with /chat/completions
The thing can be worn as an attachment, or rezzed as an in-world object. There is an API-like pair of scripts that will let you modify it to do what you want - e.g., accept input from some device or other, send output to some other device, via channel messaging, link to other object, etc. But as delivered it simply listens to nearby chat and then replies.
The system as delivered does not respond to "attachment-talk" or "green talk", but only to avatar "white chat". This can be altered easily by editing the i/o script.
The personality of the bot is defined by a "biography" that is written in plain English. There are a number of example bio's included, to illustrate using the bot as
1. a good friend named Sally (built in on delivery)
2. a store worker
3. a nanny
4. a wild and crazy party girlbot
5. a famous and annoying scientist
These can be altered and tuned to get the bot to behave how you like it. The results are really amazing! Enjoy the system and let me know if you set up a bio you really like - I'd love to add it (suitably edited for privacy) to the library of possibilities.
A version is included which works with the Nanite Systems vox system - output goes to vox and gets processed by its filters! The device is attached under the name GPTAI.
Version 1.7 adds a command to change the API address (URL) to something other than OpenAI's. This allows you to access OpenAI-equivalent services. Customers have used the system with alternate APIs, e.g., Venice, or a local server. Remember to uncomment (remove //) from the ctrl script to activate this feature.
GENERATIVE AI NEWS - Thanks to BonnieBelle86 for pointing out the openrouter system - another OpenAI-api-workalike! It works fine with my systems, substitute the OpenAI URL with https://openrouter.ai/api/v1/chat/completions and get an account and API key from https://openrouter.ai/ , stick that into my code too. Lots of models available and at very competitive prices - see https://openrouter.ai/docs#models
Version 1.6 repairs a problem introduced by a format change in http return by the OpenAI API on 6/8/23 - please contact me if you have any garbled output issues. The fix is to replace the gptconnect-bot... script which requires rez at a sandbox or a place you have rez rights.
Version 1.5 adds "speaker id" so that GPT will know who said what. There are also filtering lines put into the gptconnect-io script to respond only when a "trigger" word is heard in input (e.g., name) and/or when the speaker is less than a certain distance away. Let me know if there are any problems!
Version 1.4 adds long-term memory of conversations that will survive reboots, and also provides user-defined filtering of out-of-character responses to make conversations even more realistic.
Version 1.3 improves memory usage so that the thing should run out of memory much less often.
Version 1.2 supports full unicode/utf-8 in and out despite the mishandling of it by the OpenAI API. Now you can ask it to speak any foreign language and even translate from one language to another...!
The slightly revised version 1.1 fixes a few small errors with, in fact, error handling.
You should be able to request redelivery to update your systems.
I also did some billing tests. The price of using this thing appears to be about 1000 tokens = 1k token per prompt-response (depends on the bio you use and what you ask!). At present this means billing from OpenAI at the level of $0.002 USD per prompt-response, or a penny for 5 prompt-responses. What else can you get for a penny these days?
Have fun!
Stone Johnson (musichero)
stone.johnson.78@gmail.com
- ready to go (requires OpenAI account and api-key OR OpenAI-workalike API)
- set up for realistic conversation with deep memory (not stimulus-response)
- has personality definition "biography" with a few examples included
- open architecture so you can integrate it into your creations
- works with Nanite Systems vox, full unicode support for foreign languages!
PERFECTION!
Love it!
A ridiculous amount of fun
Fair warning… this is addictive. I love it.
I now have a pet raven who despises me. It goes completely mental when anyone says “Quoth the raven” and is plotting its escape from the cage and ultimately my demise. Even tries to enlist the help of others.
And I couldn’t be more pleased.
Amazing!
I build an amazing bot using this interface with some additional enhancements. I named it Lucy. For people interested, you can find Lucy here: http://maps.secondlife.com/secondlife/Hauwai/50/244/90
An excellent product at a very affordable price
An excellent product at a very affordable price.
Perfect for open AI chat.
This is by far the best ChatAPI on the market, far better than more expensive ChatAPI HUD's that I've tried!
Thank you musichero
Brilliant, our Animesh bartender is alive now!
I can hardly believe I upgraded our Animesh bartender onto a whole new level of interactivity for just 99 L$. The setup process was a piece of cake, I only had to copy the scripts from the included box to the Animesh model, make a few minor changes to them, and things were working. It was VERY easy to make her respond only when she hears her name, and I wrote a little bio for her to shape her character. In the beginning I received error messages, but I quuckly found out that was because I tried to have her use GPT-4, and I don't have access to it yet. GPT 3.5. Turbo is working like a charm though, and tokens for the API are a lot cheaper. Yes, beware that you will need a paid subscruiption to the OpenAI API, butprices are super low when you use 3.5 Turbo. Our bartender has been very busy for 3 days now, and my balance currently is 58 Cents. So don't worry.
If you want to try her out, she can be found at The Getaway Lounge at https://maps.secondlife.com/secondlife/Wahoo/149/87/22. Her name is Sonya.
Great but even better with an additional feature
Hi, I bought the product and it works as described. Therefore 5 stars. Unfortunately, I can't use it as I want. I run a club and wanted to breathe life into my bartender. The problem with this is that the bot reacts to everything that is said in the public chat. That's why i suggest adding an additional feature:
It would be great if only a request would be sent to ChatGPT when the name of the bot is mentioning in the local chat (option to activate this feature in the settings). Thus, the bot would only respond when addressed. This also saves traffic and costs. In a club it makes little sense if the bot reacts to everything. I think with this feature, this product could be used in many other areas.
