Build apps and workflows powered by AI: Use pre-built AI actions to summarize text, classify images, extract entities, and more. OpenAI’s gpt-4 & gpt-3.5-turbo are available out of the box. You can enter your API key, and swap in other LLMs any time.
Create data-aware AI chatbots in 30 seconds: Upload PDFs, crawl websites, and connect SaaS tools into Retool Vectors, our all-new managed vector store. Ask questions about your data & get helpful answers instantly.
Code, query, and debug faster: Ask our AI assistant questions, and it’ll generate code that just works, with context into your app’s components and data sources.
Get started today by logging into your cloud account! Retool AI for self-hosted customers will come in the next release—v3.12.
The new vectorised database is incredible.
Would love to know how it's attached to the chat system - at the moment you can edit the chat message and system prompt, would be cool to see how the vectorised data is used and what is the process flow of the vector search is.
Hey @maillme thanks for the question. We work closely with OpenAI so that we can support their latest updates in Retool with our native integration. Happy to share that we support GPT-4 Turbo (with vision) and DALL·E 3 in Retool today.
FYI - I accessed the gpt4-vision-preview API manually through Retool, and it works - but, it only works with a url, and not with Base64 data.
When I try with GPT manually, it says the Base 64 data is too long.
So, my question to you is - has anyone in Retool managed to get GPT4-vision to provide a response with a Base64 file (I.e. file stored on retool storage) ?
Also - my previous question still stands, I think it is maybe incorrect (the API) in your end. As I can do manually myself.
thanks a lot for any help!
This is a big use-case for us if we can get GPT vision working through retool.
Hey @maillme - which AI Action type are you using? I just tried building an app with the "Generate text from image" action type (with gpt-4-visual selected as the model) and it seems to work for me with base64 data. Can you send over a screenshot of your setup? Alternatively, feel free to email me directly: dworsky@retool.com
Any ETA when GPT-4-Turbo will be available for the Chat Generation use in the Retool AI module? Notice that the default 4 models are the only options available at the moment for GPT4/32k and GPT3.5/16K.
Thanks @dworsky for the reply,
I've sent you an email on this.
I tried to recreate your example - but still get the same error I was getting previously.
So to test my API Key etc (which I had tested outrwith Retool already) - i created an API resource, and ran a GPT vision query manually - and this seemed to work (using a URL, as the Base64 data is too large for some reason).
So I think my API Key is fine.
So I'm at a loss - check your inbox,
thanks again - really appreciate the help here,
Neil
To close the loop on questions above, Retool AI is available on both Cloud and Self Hosted Retool. For self-hosted, you can use Retool AI features on v3.14 and above.
In terms of the models available, we have several models exposed as options for Cloud, including gpt-4-turbo-preview. For self-hosted v3.14 and above, the list of available models is more scoped until later versions. At v3.26 we introduced gpt-4-1106-preview and by v3.30 we began including gpt-4-turbo-preview which points to the latest version available from OpenAI.
For more technical documentation on the available features, check out all of our Retool AI docs from this jumping off point.
Thanks all of you for your feedback and questions on Retool AI features! We've really enjoyed seeing what questions and feedback you have, and what you're working on building with Retool AI since this product area was announced.
It's been particularly cool to read your use case showcases in our Community Show & Tell category with the ai tag as part of our recent Retool AI challenge. Keep those coming if you have some cool functionality you'd like to share with the community!
As Retool AI has been live for about 6 months since this announcement, I'm going to go ahead and close this topic. We'd love to help with your questions via new topics in the Queries and Resources, App Building, or Workflows categories going forward. If you've got Feature Requests, as always please do share them in that category or comment your interest on an existing one! Please tag your AI topics and feature requests with ai so we can keep them organized.
