Hacker News new | ask | show | jobs
AI Business Toolkit (share.streamlit.io)
44 points by naouarb 1030 days ago
5 comments

I think this is a nice idea and decent proof of concept, but it's not good enough at anything to be useful right now. Everything it does can be done directly in ChatGPT/Code Interpreter.

There's definitely value to be created in being the layer that provides easy access to AI tools that are built to do the specific set of tasks an end user needs. On the other hand, it's going to be really challenging to compete with large incumbents who have both the distribution channel and the data. If Salesforce builds something like this, you don't have to give it all the company info that this tool is asking for, and anything it create can be immediately saved/used in the appropriate place for the business.

Integration with your existing data and services is really going to be key for this sort of thing - I would encourage anybody building something like this to have a clear strategy along those two dimensions before spending a lot of time writing code.

"I think this is a nice idea and decent proof of concept, but it's not good enough at anything to be useful right now. Everything it does can be done directly in ChatGPT/Code Interpreter."

It may be that this may well wind-up being said about virtually every ChatGPT "app" that gets produced. After all, these apps essentially are just prepending some text to a ChatGPT prompt.

Prompts all the way down
I just remembered this ancient comment on HackerNews :-)

"... you can already build such a system yourself quite trivially by getting ..." [0]

[0] https://news.ycombinator.com/item?id=9224

Hah - I feel like mine is more reasonable than that, but human exceptionalism being what it is, I'm sure he would've thought the same. Still, I'd say asking ChatGPT to do these tasks is a fair bit more trivial than what that comment describes.
The things that are specific about a "thin wrapper" to ChatGPt versus a "thin wrapper" to some other program or system, is that a ChatGPT wrapper has to end-up as "plain old English/language". This has the challenge that any/many people can generate this language 'cause language generate is what (nearly all) people do (while creating even a "trivial" command line string is a specialized skill) and also the challenge that such an app will inherit ChatGPT's quality of being never more than "mostly" reliable at any given task (as a result of GPT-3-4 being just a product of an amazing brutal large text averaging process).
Yeah, it's a cool demo and proof of concept, and perhaps useful for casual users. Might even be a nice way to draw people into the platform for other things. But for most business use cases the integration with existing data and services is a lot (if not the bulk of the work), and can't be fulfilled by this.
Not being able to try it out with giving you my OpenAI API key is a big turn-off. I'm not doing that.
Generate a specific key for that, and set a hard limit when trying it out? Would be cool if limits could be set per key, but I don't think that is possible (yet?). Love the hard limit feature, so much better than what cloud providers pull.
I wonder why this was downvoted. That's exactly what my impression was, too.
I was turned off by that and the error "You do not provide an API key. Please enter your openai key".
Hello, the community! I would like to share with you a generative AI application based on langchain and openai: https://ai-business.streamlit.app/

It provides 4 services:

Mail Generator: helps to generate sales newsletters mail

Social Media Content Generator: Create content for social media

Business Advisory: helps to perform SWOT audit, business advisory and generate new business ideas

and Ask your data: Q/A chatbot based on CSV file

"You do not provide an API key. Please enter your openai key"

I'm not entering my openai key to a random website. My billing is tied to that.

This really makes it difficult to demo the product.

I can share with you ( in private) an openai key to demo
Hi, please put some examples or allow us to test some examples with limited outputs, etc.

The AI space is ripe with a lot of new businesses appearing, and many of them want a lot of our personal information, neverminding API keys.

It's very hard to really know what the tool can do or compare it to other services if we cannot at least see some examples on why this implementation is worth interest over other services without some way to test it without giving up information I personally would rather not share until I understand why I should use this instead of just building my own project around available models.

the app is totally free of use. you just need to provide an API key. I canot use my own key in public way since it costs money. But I can Share with interested people a key so they can test the app. Feel free to send me request of needed.
Neat. Do you have some examples SWOT generations? My (somewhat similar) project currently does SWOT analysis using custom database schema like so: https://imgur.com/a/1Ufu3Yr

Originally planned the features just to show people what they could ask AI but it is really powerful enough to generate entire SWOT analysis.

Is this open source? I'd think it'd be cool to expand on it. For instance, I have two prompts I run to get ideas about x topic for youtube shorts, then to choose one, and write a script that has x,y,z criteria (good image prompts, sense of humor, etc). Having a cool plug/play thing for this would be a cool use case.
the application is free of use. You just need an openai api key
Ooh, you use streamlit for it. I missed the .app tld and thought, this was a offer by stramlit.io!
yes, it is offer by streamlit for free
What I really want to see is a tool which will open a scan of a check/invoice and review it to find:

- Invoice number --- it should resave the pixel image using that number as the file name - check amount and date --- this could be written out as a meta-file using the invoice number as a file name

that would let me automate pretty much the last aspect of my day job which is suited to automation which is not yet automated.

Why not use existing OCR/document extraction tools [0]? There are a number of options, and even a custom implementation is probably a reasonable side project given some standardized structure.

[0]: https://rossum.ai/lp/data-extraction

The structure isn't standardized --- it's a random check design placed on top of an invoice which may be printed from a wide variety of printers at some random scale, and possibly photocopied multiple times.
Extracting data from PDFs can be done with Bing AI if you open it on Edge. It can’t operate on the files (save) though.
Neat. Does the code live anywhere?