cuffe

You can self-host here: https://retool.com/self-hosted. Most people deploy it as a docker container on an EC2 instance but there’s various options

Retool Forms is completely free. No arbitrary limits on the number of users, forms or submissions. I'll make this clearer on the landing page.

For building Retool Apps/Workflows, our pricing is here: https://retool.com/pricing

Sorry just updated!

Agree, the table is the component we’ve spent the most time building: https://retool.com/components/table-new

Here are the docs: https://docs.retool.com/apps/forms. Just added a link to them from the landing page. Agree we should also add a quick demo to the landing page

Hi all, engineer who worked on forms @ Retool here. Excited to get HN’s feedback on a new product I’ve been working on: Retool Forms. There are a ton of form builders out there (e.g. Typeform, Google Forms, Airtable Forms, etc.) and honestly we weren’t really looking to build another one. But as a developer, I wanted my data in my database, not in another SaaS app (which probably has a shoddy API, like every example I listed above). Surprisingly, the only way to build a form on top of my database was by a) building my own backend (probably via node), and b) building my own frontend (probably via React, and then maybe via formik). There was no “one click” form-on-top-of-my-database tool available.

So we decided to build a form builder. It allows you to:

1. Send data directly to your database (Postgres in our case), your data warehouse, or wherever else you want it

2. Write JS almost anywhere on the front-end, including libraries like moment and lodash, for custom validations, conditional logic, and data parsing

3. Run any arbitrary code in form submission (or validation), via our Workflows product

4. Store it in our database (where we give you a connection string), or your own database

5. Self-host it in your own VPC

And it’s free with no arbitrary limits on the number of users, forms or submissions.

I’m hoping to ship a bunch more features like integration to any REST API, more styling options, etc. If you have any feedback please let me know!

we'd love to make the migration as easy as possible and would definitely be open to building an import tool. In the meantime if you're migrating feel free to email me at jamie at retool.com and I'd be happy to help import

Thanks for the feedback. We're currently working on customization with the url parser and trimming headers/etc makes a lot of sense. If you're able to share more about your use case (jamie AT retool DOT com), happy to get it tuned on your dataset

Thanks! Yes agree this is very important. We do show references from Retool Vectors out of the box, so you can see what embeddings were used to generate a response. If it'd be helpful I can walk you through a few internal Q&A bot examples which display references - jamie AT retool DOT com

Today we use a cosine similarity search but we're planning to integrate with more vector databases and allow you to customize the search logic soon. Is there a particular query method you're looking for?

I checked in with an engineer who’s focussing on app performance. You're right that this screen should not be 6MB. One part of the bloat is due to our webpack configuration. In lighthouse, you can see that >50% of the app.js file is unused for login. Most of this is actually used for the app after login.

We’re working on getting this down significantly but, that being said, the login page isn’t our highest priority. It’s the first thing customers see, but >99% of the time, they’ll already be logged in and navigate straight to the apps page, or a specific Retool app. For these pages, we’ve:

1. re-written our core runtime to avoid excessive message passing with iframes (up to 75% faster page load for slowest apps)

2. parallelized resource fetching with JS execution

3. cached app graph information in IndexedDB

4. tweaked webpack chunking strategy to avoid very small JS/CSS chunks

5. optimized resource fetching to avoid over fetching

Hope that’s helpful context. Definitely let me know if you have thoughts/other ideas

Yes working on adding llama2 and AWS bedrock support right now for open source models. But we also want to let users bring their own models - is there a specific model you're looking for?

Who knows longer-term I'd love to help users fine-tune their own models on llama2/gpt-3.5!

Excited to already see some great open source projects in this space (Langchain, Llamaindex, Axilla, etc) many of which we're exploring using for this project.

Just to be clear Retool Vectors is completely free (we're even taking on the LLM costs). We put the embeddings in a free postgres DB (and soon other open source vector DB providers) and give you the connection string so you can take it anywhere

We changed our pricing earlier this year to be a lot more affordable for use cases with high end user counts (https://retool.com/blog/pricing-v2/). Let me know if that works better for you?

If you’re looking for external apps, check out portals (https://retool.com/products/portals) that has custom volume discounts for many, many users

That's a fair concern and something we're working on improving every day! It's fairly common when you consider Retool in the context of other development platforms. VSCode is a 200MB download and is considered small in the desktop space. Even gdocs is ~30MB.

For context, these resources are cached on your machine. So you should find that the actual data transferred significantly decreases after the first visit.

Agree we're working on building this exact flow into the product now. But in the meantime I have a Workflow (our version of a webhook/cron job) that does this internally that I can send it to you if you want. Just ping me at jamie AT Retool DOT com

Awesome - would love to see how we can integrate here. Will reach out

Absolutely, happy to help! jamie at retool DOT com

Thanks! Yes so under the hood it's all in a postgres DB with a pgvector column + some metadata. If you go to retool database, you can grab the connection string and use the embeddings with your own apps. I'd like to open this up to bring your own database and integrate with other common vector DBs (Chroma, Pinecone, Mongo vector, etc) next

TBH, I was pretty surprised too. It made me pretty skeptical of off-the-shelf AI apps in general. I now think that most actually effective AI apps will need to be developed in-house, and that “bolting on” AI to existing apps (e.g. Intercom, Salesforce, etc.) won’t work. I think there are a few reasons:

1. A lot of the useful data for answering questions is in our public docs and community forum answers, which Intercom doesn’t have access to. (And we wouldn’t feel comfortable giving them access to our internal Slack anyhow.) For example, we’ve debugged complicated OAuth issues in Slack, and there is a lot of “context” there that is helpful for answering future OAuth questions (but isn’t available to Intercom).

2. Intercom doesn’t allow you to customize prompts or customize context easily. In our case, for a highly technical product, “prompt engineering” allowed us to radically improve answer quality. We could also use chain-of-thought prompting, which Intercom didn’t support. Together these two improvements probably doubled the answer success rate.

3. We needed to integrate with our data warehouse for in-product context. For example, if a customer has an error with a particular product/feature, knowing what plan they’re on, which features they’re using, which feature flags are enabled, etc. is quite helpful.

When I was building our support chatbot powered by a vectorized DB, I couldn’t actually find a project that helped with syncing Intercom chat data, Discourse community forum data, and web crawling data into a vectorized database. Do you have any suggestions? This was really a “scratch my own itch” product (not something to “generate leads for retool sales”), so genuinely asking out of curiosity! (If there are better products maybe we should kill this project and just recommend people use that instead, haha.)

And no, this is definitely not making money. (It’s free after all, so I guess we’re probably losing money on this.) To be honest, as an engineer @ Retool, I work on things because I think they’re cool and could be useful to our customers… not because it has to make my company money.

Hi all, eng who worked on vectors @ Retool here. We’re excited to get HN’s feedback on a new product I’ve been working on: Retool vectors. There’s been a lot of hype around AI, but as I was thinking about what we could launch, there were really very few AI apps that are today _actually_ delivering business value. For example, there are tons of chatbots, summarization bots, etc., but it wasn’t clear how to use them. There were bots that we could use for answering support tickets (we use Intercom), but when we tried using them, the results were far worse than expected (it only managed to close ~5% of our tickets, and required substantial human intervention).

I then tried building a custom AI chatbot for our support team, powered by a vector database (with previous answers, our docs, and community forum data). In my prototypes, the successful response rate was much higher (around 5 - 7x higher, ~30%). But it was surprisingly hard to build this bot: I needed to stitch together vector databases, custom integrations with Intercom, cronjobs to sync data, etc.

That’s why we built Retool Vectors. The idea is that we want to build a vector database that has full ETL from whatever inputs you have (e.g. Intercom, a postgres database, Salesforce, a community forum, a website, etc.). It’s always kept up to date. (We’re still working on some of these features, but I decided to try and launch this week because I just wanted to get feedback from HN, haha.) I think the industry has now settled on vector databases as the best way to provide context to LLMs. I hope that Retool Vectors can be a much easier way of getting data into it.

If you have any feedback please let me know!

PM at Retool here. Built this template that should have most of what you need for the MySQL admin panel: https://retool.com/templates/mysql-admin-panel. You can get started self-hosting with docker here: https://retool.com/self-hosted/. We have a CSV upload component but let me know if you get stuck and happy to help answer questions here or jamie at retool dot com.

PM at Retool, agreed this is hard problem. Like you said, most projects fail so Retool can help you validate and get to success or failure faster. But yeah totally agree that performance, making diffs cleaner, and code search are some things we’re really working on.

Hi - Retool PM here. Any feedback on what you're finding heavy weight? Would love to help you get started fast

Totally agree, we were looking for a similar “some code” approach. Automatisch and other no-code automation products (Zapier, n8n, etc) are awesome for non-technical users to automate simple tasks. We started building Workflows (http://retool.com/workflows) because we were looking for something faster than writing cron jobs/spinning up more infra. Products like Zapier, often times weren’t customizable enough without the ability to really write code or secure enough to connect to something like our production databases. Would love any feedback!

Retool PM here - we're working on tablets right now but have also considered opening up to desktop apps. Are there any particularly use cases you're thinking of where you'd need desktop over web?

Retool Workflows PM here. Thanks for the mention. We just launched in beta and would love any feedback. You can authenticate to your DBs/APIs, write any logic in code and then schedule it or trigger from a webhook. We also price on data throughput (not tasks/steps/etc) so you can use it economically for large jobs. Ping me a note on jamie@retool.com if you give it a try https://retool.com/products/workflows

Totally agree that developing in no-code tools is incredibly frustrating. This was one of the main reasons we built Workflows for developers. Code is and always has been a great way to automate. Too often we found the GUI getting in the way of what is simple to build and maintain using code.

By focusing on developers we were able to lean into supporting existing development workflows: versioning with Git, testing with staging environments, debugging with dev tools, monitoring with Datadog, etc.

Our goal is to remove all the boilerplate (spinning up a new box, managing access permissions, setting up staging data and environments, etc) that it takes to just get to writing the business logic unique to you. In my experience this causes as much debt as the logic itself!

I hope you can kick the tires on the new product — would love any feedback on how this could be even better for devs

Would love to know more about what kinds of integrations you're looking for? For querying data sources, we have integrations for most databases and core APIs. Anything we don't currently support you can hit with our REST, GraphQL, gRPC integrations in a Postman-like experience.

We're also working on NPM module support (so you can pull in any SDK) right now.