> ## Documentation Index > Fetch the complete documentation index at: https://docs.utari.ai/llms.txt > Use this file to discover all available pages before exploring further. # Knowledge Base Tool > Store and retrieve information from your personal knowledge library using semantic search, file organization, and intelligent information retrieval capabilities. ## Overview The Knowledge Base tool enables your Utari workers to store, organize, and intelligently retrieve information from a personal knowledge library. Using semantic search and natural language queries, agents can find relevant information across documents, maintain organized file structures, and access contextual knowledge to inform their responses and actions. ## Knowledge Base Capabilities Find information using natural language queries across all knowledge base files Upload, organize, enable/disable, and delete files and folders Synchronize knowledge base to local workspace for fast access View all folders and files in the knowledge base hierarchy Control which files are active and searchable for specific agents Cleanup and optimization operations for knowledge base health The Knowledge Base uses semantic search, meaning it understands the meaning and context of queries rather than just matching keywords. Ask questions naturally, and the system finds relevant information even if exact words don't match. ## Understanding the Knowledge Base ### What is Semantic Search? Unlike traditional keyword search, semantic search understands: * **Meaning and Context**: "How do I improve sales?" finds information about "increasing revenue" and "customer conversion" * **Related Concepts**: Searching for "pricing strategy" finds documents about "monetization" and "value-based pricing" * **Natural Language**: Ask questions as you would ask a person * **Intent Recognition**: Understands what you're really looking for **Example**: * Query: "How should we position our product?" * Finds: Documents about "market positioning," "competitive advantage," "value proposition," and "target audience definition" ### Global vs. Local Knowledge Base **Location**: Cloud-based, accessible across all agents **Purpose**: * Centralized knowledge repository * Shared across workspace * Persistent storage * Version controlled **Management**: * Upload files from sandbox * Create folder structure * Enable/disable for specific agents * Delete when no longer needed **Use Cases**: * Company SOPs and guidelines * Reusable templates * Shared reference materials * Brand guidelines * Product documentation **Location**: \~/knowledge-base-global in workspace **Purpose**: * Fast local access * Working copy for agent * Synced from global KB * Temporary processing **Creation**: * Sync from global KB * Downloads enabled files * Maintains folder structure * Updates when synced **Use Cases**: * Real-time access during tasks * Processing and analysis * Quick reference * Local file operations ## Using Semantic Search ### Basic Search ``` Search the knowledge base for information about our pricing strategy Find documents related to customer onboarding best practices What does our knowledge base say about competitive positioning? Look for information about Q4 marketing campaigns ``` The system: * Understands the semantic meaning of your query * Searches all indexed files in knowledge base * Ranks results by relevance * Returns most pertinent information ``` Found 3 relevant documents: 1. "Pricing Strategy 2024.pdf" (95% relevance) "Our tiered pricing model focuses on value-based pricing aligned with customer segments..." 2. "Product Positioning.md" (87% relevance) "Price positioning relative to competitors emphasizes our premium quality and comprehensive features..." 3. "Sales Playbook.docx" (78% relevance) "When discussing pricing with prospects, emphasize ROI and total cost of ownership..." ``` Worker uses found information to: * Answer your questions * Inform recommendations * Create content aligned with guidelines * Reference established procedures ### Targeted Search Search within specific files or folders: ```text Search Specific File theme={null} Search the "Brand Guidelines.pdf" for logo usage rules Look in "Sales Playbook.docx" for objection handling Find information about pricing in "Product Documentation" ``` ```text Search by Topic theme={null} Search knowledge base for: - Brand voice guidelines - Customer success strategies - Product roadmap priorities - Team workflows and processes ``` ```text Search for Examples theme={null} Find examples of: - Successful customer case studies - Email templates for outreach - Presentation formats - Report structures ``` ### Advanced Search Techniques Ask about concepts, not just keywords: ``` ❌ Search for "increase revenue metrics dashboard reporting" βœ… "How do we track and report on revenue growth?" The semantic search understands the intent and finds: - Revenue tracking methodologies - Dashboard KPIs - Reporting best practices - Metrics definitions ``` Ask direct questions: ``` "What are our content approval processes?" "How do we handle customer complaints?" "When should we escalate support issues?" "Who approves marketing budgets?" ``` The system finds procedural documents and guidelines that answer these questions. Provide context for better results: ``` ❌ "Email templates" βœ… "Email templates for following up with warm leads in B2B sales" More context = more relevant results ``` Search for multiple related aspects: ``` "Find information about our brand voice, tone guidelines, and content style preferences" Returns documents covering all related aspects of brand communication. ``` ## Managing Knowledge Base Files ### Listing Knowledge Base Contents ``` List all files in the knowledge base Show me what's in the knowledge base What files are indexed and searchable? ``` ``` Knowledge Base Contents: πŸ“ Marketing/ πŸ“ Brand Guidelines/ πŸ“„ Brand Voice Guide.pdf (enabled, 2.3 MB) πŸ“„ Logo Usage.pdf (enabled, 1.1 MB) πŸ“„ Color Palette.pdf (enabled, 0.5 MB) πŸ“ Templates/ πŸ“„ Email Templates.docx (enabled, 0.8 MB) πŸ“„ Social Media Guide.pdf (disabled, 1.2 MB) πŸ“ Sales/ πŸ“„ Sales Playbook.pdf (enabled, 4.5 MB) πŸ“„ Pricing Strategy.docx (enabled, 1.3 MB) πŸ“„ Objection Handling.pdf (enabled, 0.9 MB) πŸ“ Product/ πŸ“„ Product Roadmap.pdf (enabled, 2.1 MB) πŸ“„ Feature Specs.docx (disabled, 3.2 MB) Total: 10 files (8 enabled, 2 disabled) Total size: 18.9 MB ``` ``` Show me which files are enabled for this agent List disabled knowledge base files Which files are still indexing? ``` ### Uploading Files to Knowledge Base Files must exist in the workspace before uploading: ``` Files in workspace: /workspace/documents/New_SOP.pdf βœ“ /workspace/reports/Q4_Analysis.docx βœ“ ``` ``` Create a new folder in the knowledge base called "SOPs" Create folder "Customer Success/Onboarding" ``` ``` Upload "New_SOP.pdf" to the knowledge base in the "SOPs" folder Upload all files from /workspace/documents to knowledge base folder "Documentation" ``` ``` File uploaded successfully! βœ“ File: New_SOP.pdf Location: Knowledge Base/SOPs/ Size: 1.2 MB Status: Indexing... The file will be searchable once indexing completes (typically 1-2 minutes) ``` ``` Enable "New_SOP.pdf" for this agent File enabled! βœ“ Now available for semantic search and retrieval ``` ### Organizing with Folders ``` Create knowledge base folders: - Marketing/ - Brand Guidelines/ - Content Templates/ - Campaign Playbooks/ - Sales/ - Playbooks/ - Scripts/ - Case Studies/ - Product/ - Documentation/ - Roadmaps/ - Specifications/ ``` ``` Upload files to appropriate folders: - Brand_Voice.pdf β†’ Marketing/Brand Guidelines/ - Sales_Script.docx β†’ Sales/Scripts/ - Product_Specs.pdf β†’ Product/Specifications/ ``` ``` - Use descriptive folder names - Group related documents - Maintain consistent structure - Regular cleanup of outdated files ``` ### Enabling and Disabling Files ``` Enable "Sales Playbook.pdf" for Sales Agent Disable "Internal Memo.pdf" for Customer-Facing Agent Enable all files in the "Marketing" folder for Content Agent ``` ``` Content Agent: βœ“ Brand guidelines βœ“ Content templates βœ“ Style guides βœ— Sales playbooks βœ— Product specs Sales Agent: βœ“ Sales playbooks βœ“ Pricing strategy βœ“ Case studies βœ— Internal HR docs βœ— Engineering specs ``` ``` Only enable files directly relevant to each agent: - Reduces search scope - Improves relevance - Faster search performance - More focused results ``` ### Deleting Files and Folders ``` List all files modified before 2023 Show me outdated sales materials Which files haven't been accessed in 6 months? ``` ``` Delete "Old_Pricing_2022.pdf" from knowledge base Remove the "Archived" folder and all contents ``` ``` Warning: Deleting "Sales Playbook Old.pdf" This file is enabled for: - Sales Agent - Training Agent Deletion is permanent and cannot be undone. Confirm deletion? ``` ``` Deleted successfully βœ“ Removed: - Old_Pricing_2022.pdf (1.2 MB) - Archived/ folder (5 files, 6.8 MB) Freed space: 8.0 MB Remaining files: 15 ``` ## Syncing Knowledge Base ### Global KB Sync ``` Sync knowledge base to local workspace Download all enabled knowledge base files Update local knowledge base copy ``` ``` Syncing knowledge base... Downloading enabled files: βœ“ Brand Guidelines.pdf (2.3 MB) βœ“ Sales Playbook.pdf (4.5 MB) βœ“ Product Roadmap.pdf (2.1 MB) βœ“ Content Templates.docx (0.8 MB) ... Creating folder structure in ~/knowledge-base-global/ βœ“ Marketing/Brand Guidelines/ βœ“ Sales/ βœ“ Product/ Total downloaded: 15 files, 18.9 MB ``` ``` Files now available locally at: ~/knowledge-base-global/ Can be accessed for: - Fast reading - Processing - Analysis - Reference ``` ``` Sync again when: - New files added to global KB - Existing files updated - File enablement changes - Starting new work session ``` ## Knowledge Base Maintenance ### Cleanup Operations ``` Run knowledge base cleanup Optimize knowledge base performance Clean up orphaned files ``` ``` Performing maintenance... βœ“ Removing orphaned index entries βœ“ Consolidating file metadata βœ“ Optimizing search indices βœ“ Clearing temporary files βœ“ Validating file integrity βœ“ Compacting databases Cleanup complete! Results: - Freed space: 1.2 GB - Optimized search index - Removed 47 orphaned entries - Validated 150 files ``` ``` Schedule cleanup: - Monthly for active knowledge bases - Quarterly for stable knowledge bases - After bulk uploads or deletions - When search performance degrades ``` ## Use Cases and Workflows ### Reference-Based Content Creation ``` User: Create a blog post about our new feature Agent workflow: 1. Search knowledge base for: - Brand voice guidelines - Product documentation - Previous blog examples 2. Found and referenced: - Brand Voice Guide.pdf: Tone, style, vocabulary - Product Specs.pdf: Feature details - Top Blog Posts.md: Successful examples 3. Create blog post following: - Brand voice (professional but approachable) - Accurate feature information - Proven content structure Result: Brand-consistent, accurate content ``` ### Procedure-Guided Task Execution ``` User: Process the new client onboarding Agent workflow: 1. Search: "client onboarding procedures" 2. Found: Customer_Onboarding_SOP.pdf 3. Follow procedure: - Welcome email (template from KB) - Account setup checklist (from SOP) - Schedule kickoff meeting (per guidelines) - Send onboarding materials (from KB templates) 4. Execute each step according to documented process Result: Consistent, compliant onboarding ``` ### Question Answering with Context ``` User: How should we position against Competitor X? Agent workflow: 1. Search knowledge base for: - "competitive positioning" - "Competitor X" - "differentiation strategy" 2. Found relevant sections in: - Competitive_Analysis_2024.pdf - Market_Positioning.docx - Sales_Battlecard_CompetitorX.pdf 3. Synthesize answer using: - Established positioning framework - Competitor-specific intelligence - Approved messaging Result: Strategically sound, aligned response ``` ### Multi-Document Synthesis ``` User: Create Q4 strategy recommendations Agent workflow: 1. Search knowledge base for: - Past quarter performance - Market trends - Strategic priorities - Competitive intelligence 2. Found and analyzed: - Q3_Results.pdf - Market_Trends_2024.pdf - Strategic_Plan.docx - Competitor_Analysis.pdf - Customer_Feedback.xlsx 3. Synthesize insights across documents 4. Generate recommendations based on: - Historical performance - Market conditions - Strategic alignment - Competitive landscape Result: Data-informed, strategically aligned recommendations ``` ## Best Practices Maintain clear folder hierarchy mirroring your organizational structure Use clear, searchable file names: "Brand\_Voice\_Guide\_2024.pdf" not "doc1.pdf" Keep knowledge base current by updating or replacing outdated files Only enable relevant files for each agent to improve search quality Regularly remove obsolete files and run maintenance Include version/date in file names for evolving documents Use consistent file formats (PDF for final, DOCX for editable) Include README files in folders explaining contents and purpose ## Supported File Types * **PDF** (.pdf) - Best for final documents, reports, guides * **Word** (.docx, .doc) - Editable documents * **Text** (.txt) - Plain text files * **Markdown** (.md) - Formatted text documentation * **RTF** (.rtf) - Rich text format * **Excel** (.xlsx, .xls) - Data, tables, analysis * **CSV** (.csv) - Tabular data * **TSV** (.tsv) - Tab-separated values * **PowerPoint** (.pptx, .ppt) - Presentation decks * **PDF** (converted presentations) * **JSON** (.json) - Structured data * **YAML** (.yml, .yaml) - Configuration files * **XML** (.xml) - Structured documents * **Code files** (.py, .js, .java, etc.) ## Troubleshooting Check: * Files are enabled for the agent * Files have finished indexing (check with ls\_kb) * Try broader or different search terms * Verify files actually contain relevant information * Run sync to update local copy * Check if files are in correct format Verify: * File was successfully uploaded * Check with list contents to see all files * File is not being filtered from view * File finished processing * Refresh or re-list contents Possible causes: * Large file size (may take longer) * Complex document structure * High system load * Wait 5-10 minutes for large files * Check file isn't corrupted * Try re-uploading if stuck Ensure: * File exists in workspace sandbox first * File path is correct * File format is supported * Sufficient storage space * File isn't corrupted * Try smaller file or different format Improve by: * Using more specific, natural language queries * Providing context in your search * Checking if right files are enabled * Ensuring files contain expected information * Trying question-based queries * Updating knowledge base with better documents Try: * Check network connection * Verify permissions on files * Run sync again * Check available disk space * List contents to see what should sync * Contact support if persists ## Summary You've successfully learned how to: Perform semantic search using natural language queries Upload and organize files in the knowledge base Create folder structures for organization Enable and disable files strategically for agents Sync knowledge base to local workspace List and review knowledge base contents Delete files and folders when no longer needed Perform maintenance and cleanup operations Apply best practices for knowledge management The Knowledge Base tool transforms static documents into an intelligent, searchable knowledge library that agents can query naturally to find relevant information, follow established procedures, and create content aligned with organizational guidelinesβ€”making institutional knowledge accessible and actionable. ## Next Steps Learn to activate knowledge for specific workers Upload SOPs and documents to knowledge base Configure agents with knowledge access Access pre-built knowledge resources