Видео

thanks for your video lesson. very useful.... I have data that is returned as base 64 string to create a pdf. Not sure what to do next to download it automatically to the browser.. Do you have any tutorial on that? thanks

I did exactly the same, with a several pages document, I can split 10 chunks only. Do you have an idea of what's goin on please ?

So cool! Works perfectly for the API setup call, but when trying it on the actual workflow i keep getting an "Unexpected B token" error.

Hello and very nice video ! I however have a question, If I want to create a thing and return it's ID to frontend, can I use the App connector method. And does the action "Run [bewf-name]" actually waits for the response before going to step 2 of the frontend workflow ?

Is this only possible with a paid version of bubble?

I find this alternative of the app connector very interesting. What could be some other use cases for using this option?

having the following problem when calling the chunk_text api event in Bubble backend WF. Can someone help me? "Workflow error - The service Pinecone - Upsert Vectors just returned an error (HTTP 400). Please consult their documentation to ensure your call is setup properly. Raw error: Octal/hex numbers are not valid JSON values. "values": [-0,011428926, -0,000166 ^ "

I’m curious to know if this could be done by using app data in bubble instead of pinecone.

Very comprehensive video, good stuff! Would be great if you can make another video on this topic but with the new Pinecone Assistant connected with OpenAI Assistant (which is connected and operating in Bubble)

How to convert pdf to text? I'm looking for a way to the bot give answers after reading a file.

Hey, what tool are you using for those effects as your mouse moves? There's so many startups for that already - wondering which you picked!

Super cool!!

Awesome content, perfect walkthrough! thank you for your generosity on sharing this and putting the effort to make it great.

How to save it in DB as a separate entities?

thank you and be courageous you are important and helping more than you think

Next video please continue and put them into list

Thank you for this tutorial! With it I was able to get data returned in a consistent format (finally!) but I am really struggling to use the json that is returned and wonder if you might be able to help me figure it out. I have the following json which I was able to get returned to me from OpenAI using function calling. I need to display the raw json array of products for each category in a different display group. In otherwords I am trying to extract the json string under products for each category and displaying the extracted json in a display group. I both need to display the raw products json for each category separately as well as USE this raw products array in a future API call. I absolutely can not figure out how to do this. I have been trying for several days. I have tried a few different plugins to no avail. Does anyone know how to do this? { "lists": [ { "category": "ENUMValue1", "products": [ { "name": "name1", "rating": 95, "url": "url1" }, { "name": "name2", "rating": 95, "url": "url2" }, ] }, { "category": "ENUMValue2", "products": [ { "name": "name1", "rating": 95, "url": "url1" }, { "name": "name2", "rating": 95, "url": "url2" }, ] }, { "category": "ENUMValue3", "products": [ { "name": "name1", "rating": 95, "url": "url1" }, { "name": "name2", "rating": 95, "url": "url2" }, ] } ] }

Is this process now different with the introduction of OpenAI's Assistants API?

Thank you for this! Keep it up🙂

This is the cleanest solution I've seen to converting strings into usable JSON. Appreciate the detailed walkthrough here!

So damn helpful. Every last one of your videos goes through something I need right now and can't find documented anywhere else. Wanted to just say thank you!

Thanks very helpful

Make more bubble videos, please. Yours are the best. 😁

thank you so much

Hi, which browser do you use? :) It looks cool

Your tutorials are the clearest and best in the bubble community. Feel like these videos should have 20x views!

Exactly what I need, thanks for your effort.

Espectacular tutorial! Very easy to follow. It's the first video I watched from you and I'm def subscribing. Here is a timeline of the video: 00:01 Learn how to connect Bubble with OpenAI and Pinecone for document question-answering 04:06 Setting up OpenAI and Pinecone APIs 08:25 Building a curl command for Pinecone API 12:47 API setup for database, OpenAI embedding, and Pinecone upsert 17:19 Convert PDF to text and chunk it into smaller pieces using a backend workflow 21:22 Create a document chunk and split it into an array of words 25:34 Process for chunking and connecting text content with Pinecone and Bubble 29:38 Create a workflow to chunk text and send it to Pinecone

thank you for this video!

I've tried this several times. Any idea why I get zero matches at minute 7.10? Not sure what I've missed. 🥲

hey I have it set up where there are 5 different chatbots, each of the chatbots has its own pdf's, Now when the user deletes a chatbot how do I delete everything related to that chatbot in pinecone, (because when they add a chatbot It will use the same namespace as the one that was deleted), also need to be able to change the knowledge base within that specific namespace, lie they can add or delete certain files in that chatbot

Great tutorial. i tried to build it.. it works. But how to do it for different users? As for now, different users will see the same thing & content @Blank Slate Labs

Have to STRONGLY disagree with the use of JSON-safe formatting for the api calls (vs. keeping quotes in)... Couldn't help but laugh when you forgot at the end! Thanks so much for this, truly one of the better resources out there for integrating these new AI tools with Bubble.

Awesome videos, very good content. Thank you. What screen recording are you using? Looks very smooth.

Fantastic tutorial! Would love if you could also show us other implementations like: - How to update your vector database - How to implement the status of the upload to Pinecone - How to search for multiple uploads Thank you so much for sharing this so far

Hi! Was wondering if the parameter in "select until#" has to be the chunk_size or if it has to be start_index+chunk_size. In this case chunk_size would remain 100 all the time and start_indext changes from 0 to 95, 190, etc. then the command would say i.e. from item #190 to item #100.. Would that work or generate an error? Such a precious tutorial btw! Thanks!

Those tutorials are great! I really appreciate providing full guidance on how to put everything together with working example. Have you tried your demo app with Excel or CSV files? I am trying to build similar app but want to analyze the uploaded Excel or CSV similar to what GPT Code Interpreter does. I believe it was still not available functionality at the time you created the tutorial. Do you think that now is possible to query files directly to OpenAI to analyze and interact with them in similar fashion or still need to split the files to chunks and rely on Pinecone?

Hey mate, what is your browser?

👏🏼

I've been searching forever to try to find something like your video! I've got hundreds of PDFs, mp3s and URLs that I would like to search to get answers from. With mp3s I'd have to get them transcribed. Can I upload a zip file to bubble or put them all on dropbox and store there for Bubble to connect with?

Woukd you be able to make a similar video but instead of document loader, we are using hugging face dataset. The same querying and upserting pinecone and everything into a openai chatbot. Ive been scouring everywhere and you put out the most value. Keep it up man!

Would love to see a tutorial on scraping a website without a sitemap to store in pinecone!

Thanks for your video! Is pinecone the only option though?

Hi there, I am impressed by your work and channel. How would I be able to contact and hop on a call with you?

Text in the diagrams is too small!

If I want to make it an extended discussion (instead of a single question and answer) how can I make OpenAI remember what was discussed during the conversation? Any hints to help me search would be appreciated

Excellent tutorial! Please I can't get past the stage of initializing the Upsert Vectors call at 15:27. I keep on getting this response "Raw error for the API read ECONNRESET" on bubble

having a problem with 15.42 minutes, it came up as There was an issue setting up your call. Raw response for the API Status code 400 Expected an object key or }. 34, 0.0023024268, ^ please help

Does it work for image embeddings?

I watched another video in which the developer did not chunk the text and then embedding them, as he said that embedding include chunking