[GH-ISSUE #7340] Is it possible to use the API to pass my documents to the model and have it understand them in depth? #66719

Closed
opened 2026-05-04 07:56:54 -05:00 by GiteaMirror · 3 comments
Owner

Originally created by @robotom on GitHub (Oct 24, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7340

I have a basic front end that talks via the Ollama API.

Should I just pass the entire document (300+ pages) as a prompt every time? Or is there some better way to do this.

I want it to know the documents extremely well or as well as possible.

Is this achievable?

Originally created by @robotom on GitHub (Oct 24, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7340 I have a basic front end that talks via the Ollama API. Should I just pass the entire document (300+ pages) as a prompt every time? Or is there some better way to do this. I want it to know the documents extremely well or as well as possible. Is this achievable?
GiteaMirror added the feature request label 2026-05-04 07:56:54 -05:00
Author
Owner

@rick-github commented on GitHub (Oct 24, 2024):

Have a look at the RAG solutions in the integrations list.

<!-- gh-comment-id:2434825237 --> @rick-github commented on GitHub (Oct 24, 2024): Have a look at the RAG solutions in the [integrations list](https://github.com/ollama/ollama?tab=readme-ov-file#community-integrations).
Author
Owner

@pdevine commented on GitHub (Oct 24, 2024):

I'm going to close this as a dupe of #5762 . I think it's a cool idea to have something like this in Ollama, but right now it's beyond the scope. As @rick-github mentioned, there are some existing solutions out there that might work.

<!-- gh-comment-id:2436038398 --> @pdevine commented on GitHub (Oct 24, 2024): I'm going to close this as a dupe of #5762 . I think it's a cool idea to have something like this in Ollama, but right now it's beyond the scope. As @rick-github mentioned, there are some existing solutions out there that might work.
Author
Owner

@robotom commented on GitHub (Oct 24, 2024):

Guess I just want to know, is it recommended to just pass entire walls of text into each prompt? Are there any tunable settings? Or is it just as simple of dumping all the text into the message that I send to the model.

Thanks!

<!-- gh-comment-id:2436486572 --> @robotom commented on GitHub (Oct 24, 2024): Guess I just want to know, is it recommended to just pass entire walls of text into each prompt? Are there any tunable settings? Or is it just as simple of dumping all the text into the message that I send to the model. Thanks!
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#66719