Supported File Formats

Paradigm supports a variety of file formats for search and analysis functionalities. Below, we clarify what each of these capabilities means and how they apply to the different formats.

Understanding Search vs. Analysis

Search: The format can be indexed and retrieved based on structured content, keywords, metadata, and within supported files. This allows users to query their entire knowledge base and quickly find relevant documents without necessarily scoping specific documents.

Analysis: Analysis means the platform can process the full content of a document, including text interpretation, summarization, and contextual insights. The document must be scoped (delimited) within the query.

Some formats support both search and analysis, while others only allow for search-based retrieval.

---

Supported File Formats by Category

1. Text and Documents

Format	Search	Analysis
.pdf (Portable Document Format)	✅	✅
.doc / .docx (Microsoft Word)	✅	✅
.odt (OpenDocument Text)	✅	✅
.md (Markdown)	✅	✅
.txt (Plain Text)	✅	✅
.rtf (Rich Text Format)	❌	❌
.tex (LaTeX)	❌	❌

2. Presentations

Format	Search	Analysis
.ppt / .pptx (Microsoft PowerPoint)	✅	✅
.odp (OpenDocument Presentation)	✅	✅
.pdf (Exported Presentation)	✅	✅
.key (Apple Keynote)	❌	❌

3. Images and Graphics

Format	Search	Analysis
.jpg / .jpeg (JPEG Image)	✅	✅
.png (Portable Network Graphics)	✅	✅
.gif (Graphics Interchange Format)	❌	❌
.svg (Scalable Vector Graphics)	❌	❌
.bmp (Bitmap)	🔄 Candidate	🔄 Candidate
.tiff (Tagged Image File Format)	🔄 Candidate	🔄 Candidate
.webp (WebP Image Format)	🔄 Candidate	🔄 Candidate

4. Spreadsheets and Tables

Format	Search	Analysis
.csv (Comma-Separated Values)	✅ (Text-heavy only)	✅
.xls / .xlsx (Microsoft Excel)	✅ (Text-heavy only)	✅
.ods (OpenDocument Spreadsheet)	✅ (Text-heavy only)	✅

5. Code and Development

Format	Search	Analysis
.html / .xhtml	✅	✅
.css (Cascading Style Sheets)	❌	❌
.js (JavaScript)	❌	❌
.jsx / .tsx (React)	❌	❌
.ts (TypeScript)	❌	❌
.php (PHP)	❌	❌
.py (Python)	❌	❌
.java (Java)	❌	❌
.c / .cpp / .h (C / C++)	❌	❌
.sh (Shell Script)	❌	❌
.json (JavaScript Object Notation)	❌	❌
.yaml / .yml (YAML)	❌	❌
.xml (Extensible Markup Language)	❌	❌
.sql (Structured Query Language)	❌	❌

6. Video and Audio

Format	Search	Analysis
.mp3 (MPEG Audio Layer III)	🔄 Option	🔄 Option
.wav (Waveform Audio)	🔄 Option	🔄 Option
.flac (Free Lossless Audio Codec)	🔄 Option	🔄 Option
.aac (Advanced Audio Codec)	🔄 Option	🔄 Option
.mp4 (MPEG-4 Video)	❌	❌
.mov (QuickTime Video)	❌	❌
.avi (Audio Video Interleave)	❌	❌
.mkv (Matroska Video)	❌	❌

---

What’s next?

LightOn is continuously improving its platform capabilities, and new formats will be supported over time. If you have requests for specific formats, please feel free to contact our team to discuss potential integration.

📢 Stay tuned for future updates!