Docq.AI

Your private ChatGPT. Secure Q&A on your business docs which unlocks knowledge and reduces inter-team dependencies. #GenAI #RAG

[Docq.AI @docqai]

https://t.co/h5eei3KQLH is a private and secure Chat GPT alternative. It can unlock knowledge from your confidential docs. Make your employees more productive. Your confidential data doesn't have to leave your organisation.

[DHH @dhh]

Grok 3 is shockingly capable in the handful of tests I've done so far. Not sure there's much point in keeping that $20/month ChatGPT subscription any longer. Love how freaking fast it is too! Wonder if that'll hold once rolled out to all?

[Docq.AI @docqai]

We had _Spaces_ first! Just for the record :)

[Docq.AI @docqai]

It's the little things. Adding the file upload feature to the Chrome extension.

Oh did we forget to mention... We released a Chrome extension, in the Chrome store now!

[Mira Murati @miramurati]

I shared the following note with the OpenAI team today.

[Leonie @helloiamleonie]

Chunking techniques for RAG:

Fixed-length: Simple but rigid.
Sentence-based: Natural but variable size.
Paragraph-based: Logical but inconsistent lengths.
Recursive chunking: Flexible but uses different logic.
Semantic: Context-aware but computationally expensive.
Sliding window: Flexible overlap but potential redundancy.
Document-based: Preserves structure but may be too large.

Experiment with different methods. Find what works for your data.

[Docq.AI @docqai]

💯 this

[Leonie @helloiamleonie]

RAG is 80% retrieval, 20% generation.

The quality of retrieval dictates the quality of generation.

If you do anything, please learn retrieval.

[Docq.AI @docqai]

We released a bunch of updates to the backend in prep for something new coming out soon! 🎉

- Web API improvements and fixes
- UI improvements as part of Streamlit upgrade (though moving towards getting off Streamlit)
- Demo on Streamlit community cloud fixed.

[Docq.AI @docqai]

@KelvinTapiwana1 Hi, how did Coral AI work out for your use case?

https://t.co/mzYTsXEI9H

[Kelvin Tapiwanashe @KelvinTapiwana1]

@CoralAINews How do i get it

[Docq.AI @docqai]

@moh3n_GhN Hi, we would love to try your Persian PDFs in Docq, and see what you think. How can we help?

https://t.co/ibIPunGyx1

[Mohsen.Ghafari @moh3n_GhN]

@CoralAINews hi. please help me. how to create custom model from many pdfs in Persian language? tank you.

[Docq.AI @docqai]

@aaliya_va Hi. Just putting us on your radar. 🙏🏾

[Janaka Abeywardhana @janaka_a]

@ThePeterMick Private ChatGPT/Perplexity for businesses @docqai https://t.co/MhwChjzlqZ

[Janaka Abeywardhana @janaka_a]

The improved version of the @docqai Chrome extension is coming along nicely.

UI is powered by @chakra_ui.

Creating that custom component for Space selection was 10x easier, faster, and more enjoyable to dev with Chakra (+ Copilot).

[Janaka Abeywardhana @janaka_a]

This OpenAI structured outputs feature, released the other day, is a big deal.

It might not sound cool/sexy but it's important. Anybody building real AI products knows that _reliably_ binding LLM output to the UI and other parts of the software system is hard. >>

[Eddie Forson @Ed_Forson]

Boom I'm organising another Space tomorrow!

We'll cover the latest AI/LLM news and talk about what each of us is working on.

Join if interested!

https://t.co/VpP2Xrr7Cj

[Docq.AI @docqai]

Finetuning models shouldn't be your opening move!

https://t.co/uvGY5QrMdM

[Docq.AI @docqai]

@helloiamleonie @itsajchan @weaviate_io As soon as you have hybrid in your architecture it opens up a lot of interesting possibilities like this one.

[Docq.AI @docqai]

@helloiamleonie @itsajchan @weaviate_io Yep, we also concluded through some experimentation hybrid (vector + keyword search) yields bettr results and more often.

[Jack Bridger @jacksbridger]

StreamPot is now working 🫖

Plz try it. Plz roast it. Plz use it for all your video processing needs.

[Docq.AI @docqai]

Azure OpenAI GPT-4o 🎉

[Gavin @GavinSherry]

Good suggestion by pundits to run on fewer chips. Turns out that made @GroqInc faster 🏎️🏎️🏎️