PDF / file support #989
brandomagnani
announced in
Announcements
Replies: 2 comments
-
|
@brandomagnani This is a great feature suggestion. We need some time to evaluate the implementation approach. We're considering several options, such as native multimodal model support, leveraging local tooling for parsing, or a solution similar to Claude's Code Skill. |
Beta Was this translation helpful? Give feedback.
0 replies
-
|
Hi @brandomagnani , By leveraging the document-skill from Claude Code and custom commands in Qwen Code, I can easily parse local PDFs into LLM-friendly Markdown files. You can give it a try too! Here are the detailed steps:
description = "Convert local PDF files to markdown"
prompt = """
You need to thoroughly read the `.qwen/skills/pdf/SKILL.md` file to master the techniques for processing PDF files, and ultimately convert the content to markdown format, saving it to a local .markdown file (create the file if it doesn't exist).
"""
|
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment


Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Body:
When attaching PDFs with @Notation (e.g., @document.pdf), the model can't see the PDF content.
Steps to reproduce:
Problem:
PDFs are read successfully but then dropped in converter.ts (lines 426-427).
The converter only handles 'image' and 'audio' types, not 'file' type.
Affected file:
/packages/core/src/core/openaiContentGenerator/converter.tsWhy is this needed?
will be correctly encoded and injected as multimodal input"
Beta Was this translation helpful? Give feedback.
All reactions