Short-term developer needed for AI chatbot enhancements

[georgecollier]

@peter.stubbs

Be capable of vectorizing a PDF on the fly and keep the load time under 2 minutes

[FREE API] Convert Any File To Text (ChatGPT + more use cases)

Hello, Another free API available, with ChatGPT building the docs that I don’t have the patience to write (I have verified information is correct): (Pretty Much) Anything To Text [Asset 3 copy] by Not Quite Unicorns Demo: Try it out here Anything To Text API Reference Overview This API provides a service to extract text from various file types and online sources (like YouTube). After processing the provided data, it sends the result asynchronously to a specified webhook. Base URL The base …

[FREE API] Easy OpenAI + Pinecone Upsert / Embeddings

Hey folks, If you’re using OpenAI + Pinecone to generate embeddings and store vectors, this API might be of use to you. Prior to creating this API, my Bubble workflow was Convert the file into text Split the text into chunks of n words Run a recursive workflow to get embeddings for each chunk of text in batches of 100 Upsert each batch of embeddings into the Pinecone database Go to the next batch This used HEAPS of WUs and was really slow. I’ve just created a simple API that will handle it f…

Using these two extracts and vectorises an entire Harry Potter book in about 20 seconds.

@peter.stubbs

• Be capable of supporting multiple concurrent users (ideally up to 10)

Any app should be able to do this?

@peter.stubbs

• Query returns should show the source information (page number as a minimum)

Pass the returned memories’ unique IDs in the prompt to ChatGPT, instructing it to provide URLs formatted as BBCode / Markdown.

Add the returned memories to a list on the Message data type to display them at the bottom using a repeating group.