#buildinpublic ChatGPT project Enum (feed GPT your data and query it via UI or chatbots - enumhq.com).

Do you think the "human-like" reaction to the offensive behavior is a bad idea?

🤔

#buildinpublic ChatGPT project Enum (feed GPT your data and query it - enumhq.com).

Added the documentation (it's still a work in progress but at least we have something :) see here enumhq.com/docs

Also, still waiting for prod tokens by @crisp_im 🤔

#buildinpublic ChatGPT project Enum (feed GPT your data and query it - enumhq.com).

Added a chatbot and fed our website to it.

You now can try to ask it about Enum... it knows a bit more than you can find on the website 😉

enumhq.com

#buildinpublic ChatGPT project Enum (feed GPT your data and query it - enumhq.com).

Added a new page - Changelog!

enumhq.com/changelog

I like to see the progress and thought users could be interested in it too, to see how it's been developed😃

The ChatGPT davinci-3 model can wriggle if it doesn't know the answer😆

#buildinpublic #ChatGPT

#buildinpublic ChatGPT project Enum (feed GPT your data and query it - enumhq.com).

Provided rendering of formulas and equations.
Not perfect but much better than without it!
☺️

Still, there are some artifacts that should be removed. 😬😁

Day 28 of #buildinpublic Enum - an AI tool for everyone (load multiple data sources and chat).

Working on showing formulas in the interaction with documents!

Still have some problems with Crisp, and, as it turned out, with Namecheap - it has a too powerful spam filter 😬

Day 28 of #buildinpublic Enum - an AI tool for everyone (load multiple data sources and chat).

Working on showing formulas in the interaction with documents!

Also, still fighting with @crisp_im support. My webhooks don't work and support suggests publishing plugin to fix it 🤦‍♀️

Does anybody use some self-hosted documentation for a website?

I was thinking about @mintlify but it looks like they are not open-source anymore.

I looked at Docusaurus but wonder if there are other alternatives?

#buildinpublic

Day 27 of #buildinpublic Enum - an AI tool for everyone (load multiple data sources and chat).

Tried finish implementing plugin for Crisp, failed.
Their webhooks stopped working, even for the experimental project that worked before.
Waited for support.

enumhq.com

Day 26 of #buildinpublic Enum - an AI tool for everyone (load multiple data sources and chat).

Results of my quiet launch:

✅~20 visitors
✅1 signup
✅1 very interesting inquiry (I will disclose the details later).🙃

I'm still working on finishing the Crisp chatbot.

Day 26 (in progress) of #buildinpublic ChatGPT project (feed GPT your data and query it).

Enum enumhq.com is alive!

Please come and try.
Currently, you can:
- add plain text, PDF, and websites
- ask questions in our UI.

Soon: chatbot for Crisp.

Day 25 of #buildinpublic ChatGPT project (feed GPT your data and query it).

Moved long operations like reading PDF files and scraping websites to separate threads, as a result, had to refactor working with the database 😬😆

Tested websites, and I really like it (see pic):

Day 24 of #buildinpublic ChatGPT project (feed GPT your data and query it).

No big progress... fixing bugs there and here and found I didn't protect against overusing ChatGPT tokens.

Maybe it's too early but I want to make sure I will avoid big bills...😬

Day 23 of #buildinpublic ChatGPT project (feed GPT your data and query it).

No big progress... fixing bugs there and here and found I didn't protect against overusing ChatGPT tokens.

Maybe it's too early but I want to make sure I will avoid big bills...😬

Day 23 of #buildinpublic ChatGPT project (feed GPT your data and query it).

Worked on the problem of indexing big (and even not too big PDF files).
Somehow, managed to improve the speed of extracting text from it.
Also, fixed the Qdrand client timeout problem. ☺️

Day 22 of #buildinpublic ChatGPT project (feed GPT your data and query it).

Fixed small and big bugs and found that extracting text from PDF files was not accurate 😕found another library, PdfMiner, and worked pretty nicely but the speed... is slow.

Will work on it tomorrow.

For those who are using ChatGPT API.

It turned out, their UI can do a pretty comprehensive breakdown.

To see the full report just select a day:

#buildinpublic #chatgpt #api

Day 21 of #buildinpublic ChatGPT project (feed GPT your data and query it).

Implemented calculating and visualization limits and usage, also, finished the deployment of the app to AWS, so the product is almost ready for a quiet launch 🙂

Day 20 of #buildinpublic ChatGPT project (feed GPT your data and query it).

Added "pricing" and started working on the limits. When you have a business with paid API like OpenAI, giving free plans could be expensive so I don't want to waste more than I can afford 😬