I’ve tinkered with a Discord bot using the official gpt3.5 API. It’s astonishingly cheap. Using the 3.5-turbo model, I’ve never cracked $1 in a month and usually am just a couple cents a week. Obviously this would be different if you’re running a business with it or something, but for personal use like answering questions, writing short blurbs, and entertaining us while drunk…it’s not bad at all in my experience.
You’re billed per token usage. GPT-3.5-Turbo price per 1K tokens is quite low now.
I kinda made my own Custom ChatGPT with Python (and LOTS of coding help from Web CharGPT). It evolved from a few lines shitty script to a version that uses Langchain and has access to custom tools, including custom data indexes and has a persistent memory.
What will ramp up the cost are things like how much context (memory) you want the chatbot to have. If you use something like a recursive summarizer, that summarizes a text by chunks over and over until the text is below a set length, that also uses many API calls that consume tokens. Also, if you want your chatbot to use custom info that you provided to it, solutions like LlamaIndex are easy to use, but require quite some tokens per query.
On my worst month, with lots of usage due to testing and without the latest price drop, I reached 70$.
Loved the depth of this info - although it’s over my head. But I kind of understood? I have a project for next while to focus on. But I hear that it’s possible to do, and that’s exciting
I’m working on a similar project right now with zero coding knowledge. I’ve been trying to find something like langchain all day. I built (by which I mean I coached GPT into building) a web scraper script that can interact with the web to perform searches and then parse the results, but the outputs are getting too big to manage in a hacked together terminal interface.
How are you doing the UI? That’s what I’m finding to be the biggest puzzle that isn’t fun to solve. I’ve been looking at react as a way to do it.
Of the language models you can run locally, I’ve found them to be awkward to use and not perform too well. If anyone knows of any newer ones that do a better job I’d love to know.
Is it cost prohibitive to adopt your own chatgpt?
I’ve tinkered with a Discord bot using the official gpt3.5 API. It’s astonishingly cheap. Using the 3.5-turbo model, I’ve never cracked $1 in a month and usually am just a couple cents a week. Obviously this would be different if you’re running a business with it or something, but for personal use like answering questions, writing short blurbs, and entertaining us while drunk…it’s not bad at all in my experience.
You’re billed per token usage. GPT-3.5-Turbo price per 1K tokens is quite low now.
I kinda made my own Custom ChatGPT with Python (and LOTS of coding help from Web CharGPT). It evolved from a few lines shitty script to a version that uses Langchain and has access to custom tools, including custom data indexes and has a persistent memory.
What will ramp up the cost are things like how much context (memory) you want the chatbot to have. If you use something like a recursive summarizer, that summarizes a text by chunks over and over until the text is below a set length, that also uses many API calls that consume tokens. Also, if you want your chatbot to use custom info that you provided to it, solutions like LlamaIndex are easy to use, but require quite some tokens per query.
On my worst month, with lots of usage due to testing and without the latest price drop, I reached 70$.
Loved the depth of this info - although it’s over my head. But I kind of understood? I have a project for next while to focus on. But I hear that it’s possible to do, and that’s exciting
I know, it’s fuxxing dense all the info about the Open API and Python to create a model.
I don’t even know how I got so far.
I’m working on a similar project right now with zero coding knowledge. I’ve been trying to find something like langchain all day. I built (by which I mean I coached GPT into building) a web scraper script that can interact with the web to perform searches and then parse the results, but the outputs are getting too big to manage in a hacked together terminal interface.
How are you doing the UI? That’s what I’m finding to be the biggest puzzle that isn’t fun to solve. I’ve been looking at react as a way to do it.
I use a Gradio chatbot interface. While Gradio has all kinds of interfaces and there’s one specially designed for chatbots.
IDK if it’s the best option, but it’s what I found on shitty blog tutorials when I started. Even Stable Diffusion WebUI uses it.
It’s quite powerful, but a bitch to learn to use, IMO.
Thanks for the tip! I’ve been looking for something like that. It’ll save me a lot of frustration
Of the language models you can run locally, I’ve found them to be awkward to use and not perform too well. If anyone knows of any newer ones that do a better job I’d love to know.