File Upload

Upload various file types including PDFs, Word documents, PowerPoint presentations, images, videos, and ZIP archives to your Twig AI knowledge base.

Overview

Property	Details
Type	Static
Refresh	Manual
Tier	1 (All Plans)
Max File Size	Varies by plan
Batch Upload	Yes (via ZIP)

Supported File Formats

Documents

• PDF (.pdf) - Text-based PDFs, scanned PDFs with OCR

• Word (.doc, .docx) - Microsoft Word documents

• PowerPoint (.ppt, .pptx) - Microsoft PowerPoint presentations

• Text (.txt) - Plain text files

• Rich Text (.rtf) - Rich Text Format

Spreadsheets

• Excel (.xls, .xlsx) - Microsoft Excel spreadsheets

• CSV (.csv) - Comma-separated values (see QnA CSV for Q&A format)

Images

• JPEG/JPG (.jpg, .jpeg) - Image files with text extraction

• PNG (.png) - Portable Network Graphics

• GIF (.gif) - Graphics Interchange Format

• BMP (.bmp) - Bitmap images

Archives

• ZIP (.zip) - Compressed archives containing multiple files

Other Formats

• Markdown (.md) - Markdown documents

• HTML (.html, .htm) - HTML files

How to Add Files

Step 1: Navigate to Data Sources

1. Log in to your Twig AI account

2. Click Data in the main navigation menu

3. Click Add Data Source or the + button

Step 2: Select Files Connector

1. Choose Files from the list of connectors

2. The connector shows: "Pdf, Ppt, Images, Videos, Word Docs, Zip Files"

Step 3: Configure the Data Source

Basic Information

• Name (required): Give your data source a descriptive name

  • Example: "Product Documentation", "Training Materials", "User Manuals"

• Description (optional): Add details about the content

  • Example: "Q1 2024 product documentation and user guides"

File Upload

1. Click Choose File or drag and drop files into the upload area

2. Select one or multiple files to upload

3. Wait for the upload to complete (progress bar will show status)

Tags (Optional)

• Add tags to organize your data sources

• Example: "product", "documentation", "public", "internal"

• Tags help with filtering and organization

Step 4: Save and Process

1. Review all information

2. Click Save or Create

3. The system will process your files and extract content

4. Processing time varies based on file size and type

Step 5: Verify

1. Check the data source status shows "END_PROCESS" or "Completed"

2. Verify the document count matches your expectations

3. Test the knowledge by asking your AI agent relevant questions

Using ZIP Files for Batch Upload

ZIP archives allow you to upload multiple files at once, saving time and effort.

Creating a ZIP Archive

On Windows:

1. Select all files you want to upload

2. Right-click and choose "Send to" → "Compressed (zipped) folder"

3. Name your ZIP file

On macOS:

1. Select all files you want to upload

2. Right-click and choose "Compress Items"

3. A ZIP file will be created automatically

On Linux:

zip -r my-documents.zip folder-name/

Best Practices for ZIP Files

• Keep ZIP files under the size limit for your plan

• Use clear folder structure inside the ZIP

• Include only supported file formats

• Avoid nested ZIP files (ZIP containing other ZIPs)

Refresh and Updates

Since the Files connector is static, content updates require manual action:

To Update Files:

1. Navigate to your data source

2. Click Edit

3. Upload the new version of the file

4. Click Save to reprocess

To Add More Files:

• Create a new data source for additional files, or

• Update existing data source with a new ZIP containing all files

Best Practices

1. File Organization

• Use descriptive file names

• Group related files together

• Create separate data sources for different topics

• Use tags consistently

2. File Preparation

• Remove sensitive information before uploading

• Ensure text in PDFs is selectable (not images)

• Clean up formatting in Word documents

• Remove password protection from files

3. Optimize for AI Processing

• Use clear headings and structure

• Break large documents into smaller files if possible

• Include table of contents for long documents

• Use consistent terminology

4. File Naming

Good examples:

• product-user-guide-v2.pdf

• api-documentation-2024.docx

• troubleshooting-faq.pdf

Avoid:

• document1.pdf

• final-FINAL-v3-really-final.docx

• untitled.txt

Limitations

File Size Limits

• Check your plan for maximum file size

• Large files take longer to process

• Consider splitting very large documents

Scanned PDFs

• Require OCR (Optical Character Recognition)

• Processing time is longer

• Accuracy depends on scan quality

Unsupported Content

• Encrypted or password-protected files

• Corrupted files

• Proprietary formats without text extraction

• Audio files (except transcription files)

Troubleshooting

Upload Failed

Problem: File upload doesn't complete

Solutions:

• Check file size against plan limits

• Verify file is not corrupted

• Try a different browser

• Check internet connection stability

• Remove special characters from filename

Processing Stuck

Problem: Status shows "PROCESSING" for a long time

Solutions:

• Large files can take several minutes

• Check the process logs for errors

• Contact support if stuck for over 30 minutes

No Content Extracted

Problem: File uploaded but AI can't answer questions

Solutions:

• Verify file contains readable text

• For PDFs, ensure text is selectable

• Check if file format is supported

• Try re-uploading the file

Poor Answer Quality

Problem: AI gives incorrect or incomplete answers

Solutions:

• Ensure document has clear structure

• Add more context files on the same topic

• Check if OCR accuracy is low for scanned docs

• Use better quality source documents

Examples

Example 1: Product Documentation

Name: Product User Guides
Description: Complete user guide collection for all products
Files: 
  - product-a-user-guide.pdf
  - product-b-user-guide.pdf
  - quick-start-guide.pdf
Tags: product, documentation, public

Example 2: Training Materials

Name: Employee Onboarding Training
Description: New hire training materials and presentations
Files: 
  - onboarding-training.zip (contains multiple PPT files)
Tags: training, hr, internal

Example 3: Technical Specifications

Name: API Technical Specs
Description: Technical specifications and integration guides
Files:
  - api-reference-v2.pdf
  - integration-guide.docx
  - code-examples.txt
Tags: technical, api, developer

Next Steps

After uploading files:

1. Test your AI agent with relevant questions

2. Create AI agent personas that use this data

3. Monitor analytics to see how the data is being used

4. Add more data sources to expand knowledge coverage

Related Connectors

• QnA CSV - Structured question-answer pairs

• Data CSV - Tabular data import

• Website - Crawl documentation websites

• Google Drive - Sync files from cloud storage