Mixedbread
Ingest

Supported File Types

Vector Stores natively understand a wide range of file formats through multimodal AI. No extraction needed, the system directly understands text, images, and complex layouts for semantic search.

Documents

FormatExtensions
PDF.pdf
Word.doc, .docx, .dotx, .docm, .dotm
OpenDocument Text.odt
Rich Text Format.rtf
Text.txt
Markdown.md, .markdown, .mdx

Presentations

FormatExtensions
PowerPoint.ppt, .pptx
PowerPoint Slideshow.ppsx
PowerPoint Add-in.ppam
PowerPoint Macro-Enabled.pptm, .potm, .ppsm
OpenDocument Presentation.odp

Code

LanguageExtensions
Python.py
JavaScript.js
TypeScript.ts
Java.java
C#.cs

Images

FormatExtensions
JPEG.jpg, .jpeg
PNG.png
WebP.webp

Specialized Formats

FormatExtensionsNotes
Mixedbread JSON.jsonPre-chunked content format
Mixedbread JSONL.jsonlPre-chunked content format

Coming Soon

Audio Files: .mp3, .wav, .flac, .ogg, .m4a

Video Files: .mp4, .avi, .mov, .wmv, .webm

Next Steps

Now that you know which file types are supported:

Last updated: July 16, 2025