Knowledge Base Retrieval
Understand how Spaces use Knowledge Bases to provide AI responses based on your organization’s documents
Knowledge Base is a powerful capability that allows the within a to access and leverage your organization’s documents when responding to your questions. This feature transforms generic AI responses into contextual, organization-specific answers grounded in your proprietary information.
What is a Knowledge Base?
A Knowledge Base in Omnifact is a curated collection of documents that are accessible to a Space’s AI assistant. It serves as the specialized knowledge foundation for each Space, providing:
Document Repository
A secure storage location for important files relevant to the Space’s purpose or domain.
Contextual Intelligence
Source material that enhances the AI assistant’s ability to provide relevant, accurate, and organization-specific information.
Proprietary Knowledge
A way to leverage your internal documents that aren’t available to general AI systems.
Shared Reference
A common information source that all Space members can benefit from through the AI assistant.
Benefits of Knowledge Base Retrieval
Domain-Specific Expertise
Domain-Specific Expertise
Knowledge Base retrieval enables the AI assistant to develop specialized expertise in your unique domain. By accessing your organization’s documents, the AI can:
- Understand your specific terminology, products, services, and processes
- Reference internal guidelines, policies, and best practices
- Provide answers that reflect your organization’s unique approach and perspectives
- Deliver insights based on company-specific data and reports
Information Access and Consistency
Information Access and Consistency
The Knowledge Base ensures everyone gets consistent, accurate information:
- Centralized access to important documents through questions
- Consistent answers across the organization based on the same source materials
- Quick of information that might otherwise be buried in folders or drives
- Reduction in time spent searching for information across multiple sources
Secure Information Utilization
Secure Information Utilization
Knowledge Base retrieval offers secure access to sensitive information:
- Proprietary documents remain within your secure environment
- The automatically protects sensitive information during processing
- Information access respects Space membership permissions
- Your confidential data becomes useful without being exposed externally
How Knowledge Base Retrieval Works
When you ask a question in a Space with a Knowledge Base, the AI assistant intelligently processes your and leverages relevant documents to formulate its .
Query Analysis
When you ask a question, the AI assistant analyzes what you’re asking to determine if Knowledge Base documents might contain relevant information.
Document Retrieval
If relevant, the system searches the Knowledge Base to find documents containing information that might help answer your question.
Privacy Protection
Before processing, the Privacy Filter automatically detects and masks any sensitive information in the retrieved documents. When the Privacy Filter is enabled, images are also restricted from being sent to AI models not hosted within the EU.
Information Processing
The AI assistant reads and understands the relevant sections from the documents, extracting the information needed to answer your question.
Response Generation
Using both its general knowledge and the specific information from your Knowledge Base, the AI creates a comprehensive, contextual response.
Knowledge Base retrieval works best with clearly structured documents and specific questions. For optimal results, ask direct questions about information likely to be in your documents.
How to Recognize Knowledge Base Responses
When your AI assistant is using your Knowledge Base to answer questions, the experience looks noticeably different from regular AI responses. Here’s what to look for:
Progress Indicator
During retrieval, a progress indicator at the top of the assistant’s answer area shows real-time status updates like “Understanding query” and “Retrieving documents from Knowledge Base.”
Retrieval Completion
When retrieval completes, the progress indicator shows a filled icon with a message indicating how many documents were found, such as “Retrieved 3 documents from Knowledge Base.”
Multiple Retrieval Attempts
The assistant may perform multiple retrievals during a single response if it needs additional information or if initial results weren’t sufficient, with each attempt showing in the progress indicator.
Source References
The AI response often includes specific references to source documents, helping you understand where information originated and providing transparency about knowledge sources.
Asking Effective Knowledge Base Questions
To get the most from Knowledge Base retrieval, phrase your questions in ways that help the AI assistant find and use the right information.
Be Specific and Direct
Be Specific and Direct
- Good: “What is our company’s policy on remote work according to the employee handbook?”
- Better than: “Tell me about working remotely”
Specific questions help the AI pinpoint exactly what information to look for in your Knowledge Base.
Reference Document Types
Reference Document Types
- Good: “Based on our quarterly reports, how has our market share changed in 2023?”
- Better than: “How is our market share doing?”
Mentioning the type of document can help the AI narrow its search to the most relevant files.
Ask for Summaries and Analysis
Ask for Summaries and Analysis
- Good: “Summarize the key findings from our recent customer satisfaction survey”
- Good: “What are the three main concerns raised in our project risk assessment documents?”
The AI assistant can digest large documents and extract the most important points.
Request Comparisons
Request Comparisons
- Good: “Compare our current marketing strategy with the approach outlined in last year’s plan”
- Good: “What’s different between our 2022 and 2023 compliance requirements?”
The AI can identify similarities and differences across documents in your Knowledge Base.
Common Questions
Does every Space need a Knowledge Base?
Does every Space need a Knowledge Base?
No, Knowledge Bases are optional. Spaces can function effectively without Knowledge Bases for general topic-focused discussions. A Space with well-crafted Space Instructions but no Knowledge Base still provides a specialized AI assistant, just without access to your organization’s documents.
Can the AI assistant understand all file types in the Knowledge Base?
Can the AI assistant understand all file types in the Knowledge Base?
The AI assistant can process common document formats including PDFs, Word documents, Excel files, PowerPoint presentations, text files, and images (PNG, JPG, JPEG, GIF, WebP). The system extracts and indexes the text content from documents and analyzes visual content from images to make them searchable.
How recent is the information from my Knowledge Base?
How recent is the information from my Knowledge Base?
The AI assistant accesses the current version of documents in your Knowledge Base at the time of your query. When you update documents in the Knowledge Base, the AI will use the new information in subsequent conversations.
Can I ask the AI to prioritize Knowledge Base information?
Can I ask the AI to prioritize Knowledge Base information?
Yes, you can explicitly instruct the AI to focus on your Knowledge Base by phrasing your question like: “Based only on our Knowledge Base documents, what is our policy on…” or “Referring specifically to our internal documents, how do we…”
Best Practices
Curate Your Knowledge Base
Keep your Knowledge Base focused and relevant. Include only documents directly related to the Space’s purpose to improve AI retrieval accuracy.
Update Documents Regularly
Maintain current versions of documents in your Knowledge Base to ensure the AI provides the most up-to-date information available.
Use Clear Document Naming
Name your Knowledge Base documents clearly and descriptively to help with organization and make references in AI responses more meaningful.
Test Different Question Types
Experiment with various question formats to discover what works best for retrieving specific types of information from your Knowledge Base.
Adding Knowledge to a Space
To start using Knowledge Base retrieval in your work, you’ll need a Space with documents added to its Knowledge Base. Here’s what to know:
- Use Existing Spaces: The easiest way to benefit from Knowledge Base retrieval is to use Spaces that colleagues in your organization have already created and shared with you
- Join Team Spaces: Many organizations create specialized Spaces with rich Knowledge Bases for different departments or projects
- Admin Permissions Required: If you want to build your own Knowledge Base, note that only Space admins can add or manage documents
- Your Own Space: When you create a Space, you automatically become its admin
- Simple Document Upload: Adding documents is as simple as uploading files through the Space Settings
For a more detailed look at how to add and manage documents in a Space’s Knowledge Base, see our page on Managing Knowledge Bases.
Next Steps
Now that you understand Knowledge Base retrieval, you might want to explore:
- Learn how to Create or Customize a Space
- Enhance collaboration by Sharing Spaces with Colleagues who need access to the same knowledge