Images and context windows
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 10.5k
- Forks
- 1.2k
- Avg merge
- 4m
- Merged PRs (30d)
- 1
Description
I'm trying to use multimodal models in order to analyze some pdfs files.
I want to know how the images impact on the context window: pdfs are long and having one image per page i wanted to know what's the maximum number of page i can analyze per query. I read that images don't afflict context window directly, but I can't figure out how they are managed in order to be used by the models.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue names no source file, test, or entry point. Start by checking the Ollama Python documentation and multimodal request handling for how PDF pages and images contribute to context limits. Done means documenting the image and page limits clearly enough to answer the reported usage question.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai
- Issue type
- Documentation
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100