Document Management

KnowSync transforms your documents into intelligent, searchable knowledge. This guide covers everything you need to know about uploading, organizing, and managing your documents effectively.

Uploading Documents

Supported File Types

KnowSync supports a wide range of document formats, with availability depending on your subscription plan:

Free Plan:

• PDF files (.pdf) - Reports, manuals, presentations
• Text files (.txt) - Plain text documents
• Word documents (.docx) - Microsoft Word files

Starter Plan adds:

• Code files (.js, .ts, .py, .java, .cpp, .go, .rs, .php, etc.)
• Markdown files (.md, .mdx)
• CSV files (.csv) - Data and spreadsheets
• JSON files (.json) - Configuration and data files

Professional Plan adds:

• Archive files (.zip, .tar, .gz) - Compressed document collections
• PowerPoint (.pptx) - Presentation files
• Excel (.xlsx) - Spreadsheet files
• RTF files (.rtf) - Rich text format
• HTML files (.html) - Web pages

Enterprise Plan adds:

• Custom file parsers - Support for proprietary formats
• Database exports - Direct integration with SQL exports
• API document imports - Automated ingestion from external systems

Upload Limits

Upload limits vary by subscription tier:

Free Plan:

• 3 files maximum per upload session
• 5MB per file size limit
• 100MB total storage across all documents

Starter Plan:

• 10 files maximum per upload session
• 10MB per file size limit
• 10GB total storage

Professional Plan:

• 25 files maximum per upload session
• 25MB per file size limit
• 100GB total storage

Enterprise Plan:

• Unlimited files per upload session
• 100MB per file size limit
• 1TB total storage

Upload Methods

Drag and Drop:

1. Navigate to your knowledge base
2. Drag files directly onto the upload area
3. Files process automatically after upload
4. Monitor processing status in real-time

File Browser:

1. Click Upload Documents button
2. Use file browser to select documents
3. Select multiple files with Ctrl/Cmd+click
4. Confirm upload to begin processing

Bulk Upload (Professional+ plans):

1. Prepare documents in a folder structure
2. Create a ZIP archive of your documents
3. Upload the archive file
4. KnowSync automatically extracts and processes contents

Chat Conversation Indexing

Transform AI conversations into searchable knowledge base documents. This feature allows you to preserve valuable chat discussions and make them discoverable for future reference.

How Chat Indexing Works

Access Method:

1. Navigate to any chat conversation in your organization
2. Open the chat history sidebar
3. Find the conversation you want to preserve
4. Click the three dots menu next to the conversation
5. Select "Index as Document"

Processing Pipeline:

• Conversation content is converted to structured markdown
• Full embedding processing creates vector representations
• Document becomes searchable via semantic and full-text search
• Integration with RAG pipeline for future AI conversations

Chat Document Structure

Indexed conversations include:

Message Flow:

• Complete conversation history in chronological order
• User questions and AI responses
• Conversation metadata (date, duration, token count)

AI Context:

• Reasoning processes and thought chains
• Tool usage and function calls
• Source citations and document references
• Model information and processing details

Search Optimization:

• Automatic tagging with "chat", "conversation", "export"
• Source URL linking back to original conversation
• Collection assignment (if specified during indexing)

Managing Chat Documents

Organization:

• Chat documents appear alongside uploaded files in your knowledge base
• Use collections to group related conversations by topic or project
• Apply additional tags for better categorization

Plan Considerations:

• Chat documents count toward your total document limit
• Free plan: 5 documents total (including chats)
• Starter plan: 25 documents total
• Professional/Enterprise: Unlimited documents

Best Practices:

• Index conversations with actionable solutions or important decisions
• Use descriptive titles before indexing for better searchability
• Regularly review and delete outdated chat documents
• Consider grouping related conversations in collections

Document Processing

AI-Powered Processing Pipeline

KnowSync uses advanced AI to process your documents:

Text Extraction:

• OCR for scanned PDFs and images
• Intelligent formatting preservation
• Metadata extraction (title, author, creation date)
• Language detection and character encoding

Content Analysis:

• Automatic summarization and key point extraction
• Topic modeling and categorization
• Entity recognition (names, dates, locations)
• Relationship mapping between documents

Chunking and Indexing:

• Smart text segmentation for optimal retrieval
• Vector embeddings for semantic search
• Full-text search index creation
• Cross-reference generation

Processing Status

Monitor document processing through the dashboard:

Processing States:

• Queued: Document waiting for processing
• Extracting: Text and metadata extraction in progress
• Analyzing: AI analysis and content understanding
• Indexing: Search index creation
• Complete: Document ready for search and chat
• Failed: Processing error - review and retry

Processing Time:

• Small documents (< 1MB): 30 seconds - 2 minutes
• Medium documents (1-10MB): 2-10 minutes
• Large documents (10MB+): 10-30 minutes
• Bulk uploads: 15 minutes - 2 hours depending on volume

Error Handling

Common processing issues and solutions:

Corrupted Files:

• Re-upload the original file
• Try converting to a supported format
• Contact support for specialized file recovery

OCR Failures:

• Ensure scanned documents have clear, readable text
• Higher resolution images produce better OCR results
• Consider manual text entry for critical but unreadable documents

Format Issues:

• Update to the latest file format version
• Remove password protection before upload
• Check file isn't corrupted by opening in native application

Organizing Documents

Collections

Collections help organize related documents for easier management and access:

Creating Collections:

1. Navigate to Documents in your dashboard
2. Click Create Collection
3. Choose a descriptive name and optional description
4. Set collection permissions for team access
5. Begin adding relevant documents

Collection Types:

• Project Collections: Documents for specific projects or initiatives
• Team Collections: Shared knowledge for team collaboration
• Topic Collections: Documents grouped by subject matter
• Client Collections: Materials organized by customer or client

Smart Collections (Professional+ plans):

• Automatically group documents by topic using AI
• Dynamic collections based on document metadata
• Suggested document additions based on content similarity

Tags and Metadata

Enhance document discoverability with tags and metadata:

Manual Tagging:

• Add descriptive tags during or after upload
• Use consistent tag naming conventions
• Create tag hierarchies for complex organization

Auto-Generated Tags (Starter+ plans):

• AI-generated tags based on content analysis
• Suggested tags based on similar documents
• Topic extraction and keyword identification

Custom Metadata Fields (Professional+ plans):

• Define custom fields specific to your organization
• Track document versions, approval status, or review dates
• Filter and search by custom metadata

Document Search and Discovery

AI-Powered Search

KnowSync offers multiple search methods to find information quickly:

Semantic Search:

• Natural language queries: "How do we handle customer complaints?"
• Concept-based matching beyond exact keyword matches
• Understanding of context and intent

Traditional Search:

• Exact phrase matching with quotation marks
• Boolean operators (AND, OR, NOT)
• Wildcard searches with asterisks (*)

Advanced Filters:

• Filter by document type, upload date, or file size
• Search within specific collections or tags
• Author, title, or metadata-based filtering

Search Best Practices

Effective Query Strategies:

• Use natural, conversational language
• Be specific about context: "API authentication errors" vs "errors"
• Combine multiple concepts: "customer onboarding process for enterprise clients"

Refining Results:

• Use filters to narrow down large result sets
• Sort by relevance, date, or document type
• Preview documents before opening full content

Version Control and History

Document Versions

Track changes and maintain document history:

Version Tracking:

• Automatic versioning when documents are re-uploaded
• View previous versions and changes
• Restore earlier versions if needed

Change Detection:

• Highlight differences between document versions
• Track who made changes and when
• Maintain audit trail for compliance

Version Management (Professional+ plans):

• Compare versions side-by-side
• Merge changes from multiple versions
• Branch and tag versions for release management

Document History

Access History:

• Track who accessed documents and when
• Monitor popular content and usage patterns
• Identify knowledge gaps and frequently requested information

Modification History:

• Log all document updates and changes
• Track metadata modifications and tag updates
• Maintain complete audit trail

Collaboration Features

Document Sharing

Share documents securely with team members:

Internal Sharing:

• Share with specific team members or entire organization
• Set view, edit, or admin permissions per document
• Create shared collections for team collaboration

External Sharing (Professional+ plans):

• Generate secure sharing links for external stakeholders
• Set expiration dates and access limits
• Password protection for sensitive documents

Public Sharing (Enterprise plans):

• Create public knowledge bases for customer support
• Embed documents in external websites
• White-label sharing with custom branding

Real-Time Collaboration

Collaborative Editing (Starter+ plans):

• Multiple team members can annotate documents simultaneously
• Real-time updates and change notifications
• Comment threads for discussion and feedback

Review Workflows (Professional+ plans):

• Document approval processes with custom workflows
• Review assignments and status tracking
• Automated notifications for review deadlines

Storage Management

Monitoring Usage

Track your storage usage and plan accordingly:

Storage Dashboard:

• Real-time storage usage vs. plan limits
• Breakdown by document type and collection
• Historical usage trends and projections

Usage Alerts:

• Notifications at 75% and 90% of storage limit
• Weekly usage reports via email
• Proactive upgrade recommendations

Storage Optimization

Document Cleanup:

• Identify duplicate and unused documents
• Archive older documents to reduce active storage
• Delete unnecessary document versions

Compression Strategies:

• Optimize PDF files before upload
• Use appropriate image compression for visual documents
• Convert documents to more efficient formats when possible

API and Integration

Document API

Programmatic access to your document management:

Upload API:

• Bulk upload via REST API
• Automated document ingestion from external systems
• Integration with CI/CD pipelines for documentation

Management API:

• Retrieve document metadata and status
• Update tags, collections, and permissions
• Delete and archive documents programmatically

Search API:

• Integrate KnowSync search into your applications
• Custom search interfaces and results display
• Real-time search suggestions and autocomplete

Webhook Integration

Document Events:

• Notifications when documents finish processing
• Alerts for upload failures or errors
• Updates when documents are modified or shared

Custom Workflows:

• Trigger external processes when documents are uploaded
• Integrate with project management tools
• Automate document routing and approval processes

Best Practices

Organization Strategy

Consistent Naming:

• Develop naming conventions for documents and collections
• Include dates and version numbers where appropriate
• Use descriptive titles that indicate content and purpose

Logical Hierarchy:

• Create nested collections that mirror your organization structure
• Group related documents by project, department, or function
• Balance depth and accessibility in your folder structure

Maintenance Routine

Regular Cleanup:

• Monthly review of unused and outdated documents
• Quarterly audit of collection organization
• Annual review of tagging strategy and metadata

Quality Control:

• Establish document quality standards
• Regular review of AI-generated tags and metadata
• Validation of critical document processing results

Troubleshooting

Common Issues

Slow Processing:

• Large files take longer - consider breaking into smaller documents
• High usage periods may cause delays
• Check file format compatibility

Search Problems:

• Allow 24-48 hours for new documents to be fully indexed
• Try different search terms or approaches
• Check document permissions and access rights

Upload Failures:

• Verify file size and format restrictions
• Check network connectivity and stability
• Ensure sufficient storage space available

Getting Support

Self-Service:

• Check processing status in document dashboard
• Review error messages for specific guidance
• Consult API documentation for integration issues

Contact Support:

• Free: Community forums and documentation
• Paid: Email support with response time guarantees
• Enterprise: Dedicated support with phone and chat access