feat: add pptx reader support #5022
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
9 tasks
kausmeows
reviewed
Oct 14, 2025
…ecificity - Changed agent model to OpenAIChat with id "gpt-4o-mini" for improved performance. - Updated file path parameter from 'file' to 'path' for consistency. - Enhanced the query prompt to specify key topics and main points in the presentation content.
…into feat/add-pptx-reader
willemcdejongh
approved these changes
Oct 23, 2025
Mustafa-Esoofally
pushed a commit
that referenced
this pull request
Oct 23, 2025
## Summary Add support for reading Microsoft PowerPoint (.pptx) files by implementing a dedicated PPTXReader class. This follows the same pattern as the existing DocxReader, using python-pptx to extract text content from presentation slides. PPTX files are now properly handled instead of falling back to the generic TextReader which would fail on binary PowerPoint files. Key changes: - Added PPTXReader class in knowledge/reader/pptx_reader.py - Added PPTX content type to the ContentType enum - Updated ReaderFactory to route .pptx files to the PPTX reader - Supports both sync and async reading with proper slide text extraction ## Type of change - [ ] Bug fix - [x] New feature - [ ] Breaking change - [ ] Improvement - [ ] Model update - [ ] Other: --- ## Checklist - [x] Code complies with style guidelines - [x] Ran format/validation scripts (`./scripts/format.sh` and `./scripts/validate.sh`) - [x] Self-review completed - [ ] Documentation updated (comments, docstrings) - [ ] Examples and guides: Relevant cookbook examples have been included or updated (if applicable) - [ ] Tested in clean environment - [ ] Tests added/updated (if applicable) --- ## Additional Notes Requires python-pptx package: `pip install python-pptx` This implementation only handles the modern .pptx format. The older .ppt format would require a different approach since it's a binary format that needs specialized parsing. --------- Co-authored-by: Kaustubh <[email protected]>
dirkbrnd
added a commit
to agno-agi/agno-docs
that referenced
this pull request
Oct 23, 2025
## Description Add documentation for the new PPTX reader feature that allows reading Microsoft PowerPoint (.pptx) files. ## Type of Change - [ ] Bug fix (errors, broken links, outdated info) - [x] New content - [ ] Content improvement - [ ] Other: ____ ## Related Issues/PRs - Related SDK PR: [agno-agi/agno#5022](agno-agi/agno#5022) — **Feat: Add PPTX Reader** ## Checklist - [x] Content is accurate and up-to-date - [ ] All links tested and working - [ ] Code examples verified (if applicable) - [x] Spelling and grammar checked - [ ] Screenshots updated (if applicable) --------- Co-authored-by: Dirk Brand <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
Add support for reading Microsoft PowerPoint (.pptx) files by implementing a dedicated PPTXReader class.
This follows the same pattern as the existing DocxReader, using python-pptx to extract text content from presentation slides. PPTX files are now properly handled instead of falling back to the generic TextReader which would fail on binary PowerPoint files.
Key changes:
Type of change
Checklist
./scripts/format.shand./scripts/validate.sh)Additional Notes
Requires python-pptx package:
pip install python-pptxThis implementation only handles the modern .pptx format. The older .ppt format would require a different approach since it's a binary format that needs specialized parsing.