Supported File Types
File formats supported by Mixedbread Stores for ingestion and search.
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
| Format | Extensions |
|---|---|
.pdf | |
| Word | .doc, .docx, .dotx, .docm, .dotm |
| OpenDocument Text | .odt |
| Rich Text Format | .rtf |
| Text | .txt |
| Markdown | .md, .mdx |
| HTML | .html, .htm |
.eml | |
| Outlook Message | .msg |
HTML pages are indexed by their readable content: scripts, styles and navigation are dropped, headings, lists, simple tables and links (absolute http, https and mailto URLs) are kept as markdown, and tables with merged cells are kept as minimal HTML.
Presentations
| Format | Extensions |
|---|---|
| PowerPoint | .ppt, .pptx |
| PowerPoint Slideshow | .ppsx |
| PowerPoint Add-in | .ppam |
| PowerPoint Macro-Enabled | .pptm, .potm, .ppsm |
| OpenDocument Presentation | .odp |
| Keynote (6.5+) | .key |
Spreadsheets
| Format | Extensions |
|---|---|
| Excel Workbook | .xlsx |
| Excel Macro-Enabled Workbook | .xlsm |
| CSV | .csv, .tsv |
Code
| Language | Extensions |
|---|---|
| Python | .py |
| JavaScript | .js |
| TypeScript | .ts |
| Java | .java |
| C# | .cs |
| C | .c, .h |
| C++ | .cpp, .cxx, .cc, .hpp, .hxx |
| Go | .go |
| Ruby | .rb |
| Rust | .rs |
Images
| Format | Extensions |
|---|---|
| JPEG | .jpg, .jpeg |
| PNG | .png |
| WebP | .webp |
| AVIF | .avif |
| GIF | .gif |
| SVG | .svg |
SVG files are rendered to a bitmap before they are embedded, so vector artwork is searched the same way as any other image.
Structured Data
| Format | Extensions |
|---|---|
| JSON | .json |
| JSON Lines | .jsonl, .ndjson |
| XML | .xml |
JSON and XML are indexed as readable key: value text rather than raw syntax. XBRL instances are indexed one fact per line, with each fact's period, dimensions and unit. To control chunking yourself, use the Mixedbread JSON format.
Specialized Formats
| Format | Extensions | Notes |
|---|---|---|
| Mixedbread JSON | .mxjson | Pre-chunked content format |
| Mixedbread JSONL | .mxjsonl | Pre-chunked content format |
The Mixedbread JSON format allows direct ingestion of pre-chunked content. Use it when you have custom chunking logic, need to preserve specific chunk boundaries, or want to include pre-computed metadata like OCR text or transcriptions.
Audio
| Format | Extensions |
|---|---|
| MP3 | .mp3 |
| WAV | .wav |
| OGG | .ogg, .oga |
| M4A | .m4a |
| WebM Audio | .weba |
| AAC | .aac |
| FLAC | .flac |
Audio files require the mixedbread-ai/mxbai-wholembed-v3 encoder.
Video
| Format | Extensions |
|---|---|
| MP4 | .mp4 |
| WebM | .webm |
| QuickTime | .mov |
| AVI | .avi |
| OGG Video | .ogv |
Video files require the mixedbread-ai/mxbai-wholembed-v3 encoder.