How to Upload Files
There are three ways to get files into RelayHub:Click the paperclip icon in the chat input bar, select one or more files, and send your message. The files are uploaded, processed, and immediately available for the AI to reference in that conversation.
Open File Hub from the sidebar and click the Upload button. Drag and drop files or browse your filesystem. Files uploaded here are added to your personal library and available across all your conversations.
Supported Formats
| Format | Extensions | What Gets Extracted |
|---|---|---|
| Full text, tables (via PdfPlumber), images sent to vision AI | ||
| Word | .docx | Text, headings, tables, embedded images |
| Excel | .xlsx, .csv | All sheets parsed into queryable tabular data |
| PowerPoint | .pptx | Slide text, speaker notes, table content |
| Images | .png, .jpg | OCR text extraction, chart/diagram interpretation via vision AI |
| JSON | .json | Parsed and indexed as structured data |
| Plain text | .txt, .md | Direct text indexing |
The Processing Pipeline
Every uploaded file passes through three stages automatically:RelayHub reads the file contents using format-specific parsers. PDFs are processed with PyMuPDF for text and PdfPlumber for table extraction. Word and PowerPoint files are parsed for all text elements including headers, footers, and notes. Spreadsheets are converted into structured tabular representations. Images are sent through vision AI for OCR and content recognition.
The extracted text is split into semantically meaningful chunks and converted into vector embeddings using a language model. These embeddings are stored in pgvector (PostgreSQL with vector extensions), enabling fast semantic search. When you ask the AI a question, it searches these embeddings to find the most relevant passages from your documents.
An AI model reads the extracted text and identifies entities (people, companies, products, concepts, dates) and the relationships between them. These are stored as nodes and edges in a knowledge graph that you can explore visually. This step runs as a background worker task and may complete a few seconds after the embeddings are ready.
Processing Times
Most files complete processing in under 30 seconds. Factors that affect processing time:- File size — A 5-page PDF processes in seconds; a 200-page document takes longer
- Tables — PDFs with complex tables require additional extraction passes
- Images — Files containing images trigger vision AI analysis, adding a few seconds per image
- Spreadsheets — Large datasets (10,000+ rows) take longer to chunk and embed
Reprocessing Files
If a file shows an Error status or if you suspect the initial processing missed content, you can reprocess it:- Open the file in File Hub
- Click Reprocess in the file detail panel
- The file goes back through the full pipeline — extraction, embeddings, and knowledge graph
Reprocessing replaces all existing embeddings and knowledge graph data for that file. This is useful after platform updates that improve extraction quality.