Large text output to ChatGPT edit. 3000 tokens limit

How to proceed a large text tokens to being edited with ChatGPT 3000 tokens limit?

Hello @wint,

Your request seems vague and I’m not exactly sure what issue(s) you are facing.

Can you please provide the following?

1. Screenshots of module fields and filters

Please share screenshots of relevant module fields and filters in question? It would really help other community members to see what you’re looking at.

You can upload images here using the Upload icon in the text editor:
Screenshot_2023-10-07_111039

2. Scenario blueprint

Please export the scenario blueprint file to allow others to view the mappings and settings. At the bottom of the scenario editor, you can click on the three dots to find the Export Blueprint menu item.

Screenshot_2023-08-24_230826
(Note: Exporting your scenario will not include private information or keys to your connections)

Uploading it here will look like this:

blueprint.json (12.3 KB)

3. And most importantly, Output bundles

Please provide the output bundles of the modules by running the scenario, then click the white speech bubble on the top-right of each module, save the bundle contents in your text editor as a bundle.json file, and upload it here into this discussion thread.
Screenshot_2023-10-06_141025

Providing the output bundles will allow others to replicate what is going on in the scenario even if they do not use the external service.

Following these steps will allow others to assist you here. Thanks!

Hello @wint nice to meet you.

Like Sam said, maybe we need more info about your question, but until then I will try to provide an answer.
I wonder which version of GPT Chat you use. To have access to more tokens, you can use the GPT 4 Turbo version, which has a capacity of 100,000 tokens.

Don’t hesitate to contact us if you require further assistance.
//VLAD

2 Likes

I mean about the OpenAI module as edit function (image below). I have a large text transcribe output from Whisper-1 and want to edit with ChatGPT API instruction. I can’t, limit of 3000 tokens there. No GPT-4 or more large window tokens context options there.

Instead of using “Create an Edit” module, you could just use “Create a Completion” module, which allows you to select more models, especially the model that Wemakefuture mentioned that can have larger inputs.

3 Likes

I see. I need to edit the text by correcting incorrect words, correctly formatting the paragraphs, creating a well-organized text structure. Will the completion instruction accomplish it?

You can send “System” instructions (prompt), as well as “User” text input that you want to be edited.

E.g.:

Screenshot_2023-11-28_211105

3 Likes

Thanks. I’m doing several tests. If I have any further questions regarding this topic I will post them here, otherwise I will mark them as resolved. If you can, check out my other topics too.

No problem, glad I could help. Let me know if it works for you!

2 Likes

It works but not as I intended. It’s difficult to get the instructions between system and user right. He completes a lot of things instead of editing according to instructions. I need to make several attempts to get it right. I will attach the output bundle.
bundle.json (3.1 KB)