WeKnora Examples & Use Cases

Explore real-world examples and use cases for WeKnora. Learn how organizations are using WeKnora to build intelligent document understanding and Q&A systems.

Enterprise Knowledge Base

Build intelligent knowledge bases for your organization's documentation, policies, and procedures.

Use Case

A large organization needs to make their internal documentation searchable and queryable. Employees should be able to ask questions about company policies, procedures, and technical documentation.

Implementation Steps

Create a knowledge base for "Company Policies"
Upload all policy documents (PDF, Word, Markdown)
Configure embedding and LLM models
Enable Agent mode for complex queries
Deploy as internal Q&A system

Benefits

Instant access to company information
Reduced time searching through documents
Consistent answers across the organization
Easy to update as policies change

Related Resources

Customer Support Chatbot

Create AI-powered support agents that can answer customer questions using your product documentation.

Use Case

A SaaS company wants to reduce support ticket volume by providing instant answers to common customer questions using their product documentation and help articles.

Implementation

Create knowledge base with product documentation
Upload user guides, FAQ documents, and help articles
Configure for high-precision retrieval
Integrate with customer support platform
Enable web search for real-time information

Example Query

User: "How do I reset my password?"
Bot: "To reset your password, follow these steps:
1. Go to the login page
2. Click 'Forgot Password'
3. Enter your email address
4. Check your email for reset instructions

[Source: User Guide, Chapter 3, Page 12]"
            

Learn More

Research & Documentation System

Transform research papers and technical documentation into searchable, queryable knowledge systems.

Use Case

A research institution needs to make thousands of research papers searchable. Researchers should be able to ask questions like "What are the latest findings on climate change?" and get relevant excerpts from multiple papers.

Features Used

Batch document upload for large collections
Knowledge graph generation for paper relationships
Cross-knowledge base search
Citation tracking and source attribution

Example

Query: "What are the main causes of biodiversity loss?"

Response: "Based on recent research papers, the main causes of 
biodiversity loss include:
1. Habitat destruction and fragmentation
2. Climate change
3. Overexploitation of resources
4. Pollution
5. Invasive species

[Sources: 
- "Global Biodiversity Assessment 2023", pages 45-67
- "Climate Impact on Ecosystems", pages 12-34]"
            

WeChat Integration

Deploy intelligent Q&A services within the WeChat ecosystem through the WeChat Dialog Open Platform.

Use Case

A company wants to provide customer support through WeChat Official Accounts. Customers can ask questions and get instant answers from the company's knowledge base.

Implementation

Deploy WeKnora as backend service
Integrate with WeChat Dialog Open Platform
Configure knowledge base with product information
Enable multi-turn conversation support

Benefits

Zero-code deployment through WeChat platform
Efficient question management
Seamless WeChat ecosystem integration
24/7 automated customer support

Document Upload Examples

Learn how to upload documents using different methods.

Method 1: Web UI Drag and Drop

Navigate to your knowledge base
Click "Upload Documents"
Drag files into the upload area
Wait for processing to complete

Method 2: API Upload

curl -X POST \
  http://localhost:8080/api/v1/knowledgebases/{kb_id}/documents \
  -H "x-api-key: sk-your-api-key" \
  -F "file=@document.pdf" \
  -F "tags=policy,internal"
            

Method 3: Folder Import

Use the Web UI folder import feature
Select a folder containing documents
All documents in the folder will be processed

Documentation

Semantic Search Examples

Examples of semantic search queries and results.

Example 1: Conceptual Query

Query: "How does machine learning work?"

The system finds relevant sections even if they don't 
contain the exact phrase "machine learning", but discuss
related concepts like "neural networks", "algorithms", 
or "pattern recognition".
            

Example 2: Synonym Handling

Query: "automobile maintenance"

Finds documents about "car care", "vehicle service", 
"auto repair" - understanding that these are related concepts.
            

Example 3: Cross-Language Understanding

Semantic search can find relevant content even when using different terminology or phrasing.

Agent Mode Q&A Examples

Examples of complex queries handled by Agent mode.

Example 1: Multi-Step Reasoning

User: "What are the requirements for getting a visa, 
and how long does the process take?"

Agent Process:
1. Searches knowledge base for visa requirements
2. Searches for processing time information
3. Combines information from multiple sources
4. Provides comprehensive answer with sources
            

Example 2: Tool Usage

User: "What's the current weather and how does it 
affect our shipping policies?"

Agent Process:
1. Uses web search tool to get current weather
2. Searches knowledge base for shipping policies
3. Correlates weather conditions with policy rules
4. Provides contextual answer
            

Example 3: Cross-Knowledge Base Query

User: "Compare our product features with competitor X"

Agent Process:
1. Searches internal product knowledge base
2. Uses web search for competitor information
3. Compares features side-by-side
4. Provides structured comparison
            

Learn More

Knowledge Graph Visualization

Examples of knowledge graph generation and visualization.

Use Case

Visualize relationships between different sections of a technical manual to understand document structure and connections.

Features

Interactive graph visualization
Relationship exploration
Contextual understanding
Enhanced retrieval using graph structure

Go Client Examples

Code examples using the WeKnora Go client library.

Basic Search Example

package main

import (
    "context"
    "fmt"
    "log"
    "github.com/Tencent/WeKnora/client"
)

func main() {
    cfg := &client.Config{
        BaseURL: "http://localhost:8080/api/v1",
        APIKey:  "sk-your-api-key",
    }
    
    c := client.New(cfg)
    
    ctx := context.Background()
    
    // Search knowledge base
    results, err := c.Search(ctx, "kb_123", &client.SearchRequest{
        Query:     "What is WeKnora?",
        TopK:      5,
        Threshold: 0.7,
        Rerank:    true,
    })
    
    if err != nil {
        log.Fatal(err)
    }
    
    fmt.Printf("Found %d results:\n", len(results))
    for _, result := range results {
        fmt.Printf("- Score: %.2f\n", result.Score)
        fmt.Printf("  Content: %s\n\n", result.Content[:100])
    }
}
            

Document Upload Example

// Upload a document
file, err := os.Open("document.pdf")
if err != nil {
    log.Fatal(err)
}
defer file.Close()

doc, err := c.UploadDocument(ctx, "kb_123", &client.UploadRequest{
    File: file,
    Tags: []string{"policy", "internal"},
})

if err != nil {
    log.Fatal(err)
}

fmt.Printf("Document uploaded: %s\n", doc.ID)
            

API Documentation

Best Practices

Tips for getting the best results from WeKnora.

Document Preparation

Use well-structured documents with clear headings
Break long documents into logical sections
Add metadata and tags for better organization
Ensure documents are in supported formats

Query Optimization

Ask specific, focused questions
Use natural language - no need for keywords
Break complex questions into simpler ones
Use Agent mode for multi-step queries

Retrieval Tuning

Adjust top_k based on your needs
Use reranking for better precision
Fine-tune similarity thresholds
Test with sample queries

Get Started with Examples

Ready to try these examples? Start by setting up WeKnora and creating your first knowledge base.

Next Steps

Start Building Read Documentation