@exulu/backend 1.48.2 → 1.49.0

package/mintlify-docs/enterprise-edition.mdx

@@ -1,538 +0,0 @@
----
-title: Enterprise Edition
-description: Production-Ready AI Infrastructure for Teams that Scale. Exulu Enterprise Edition unlocks advanced capabilities for teams building mission-critical AI applications. Get enterprise-grade features including RBAC, advanced document processing, evaluation frameworks, and background job orchestration.
-mode: 'wide'
----
-
-<div style={{ textAlign: 'center', padding: '1rem 0 3rem' }}>
-  <div style={{
-    display: 'flex',
-    gap: '1rem',
-    justifyContent: 'center',
-    flexWrap: 'wrap',
-  }}>
-    <a href="https://exulu.com/contact" className="cta-primary">
-      Request License →
-    </a>
-    <a href="/partners" className="cta-secondary">
-      Work with a Partner
-    </a>
-  </div>
-</div>
-
----
-
-## What's Included in Enterprise Edition
-
-<div style={{
-  display: 'grid',
-  gridTemplateColumns: 'repeat(auto-fit, minmax(300px, 1fr))',
-  gap: '2rem',
-  margin: '3rem 0'
-}}>
-  <div className="feature-card" style={{ padding: '2rem', borderRadius: '1rem', border: '2px solid #8B5CF6' }}>
-    <div className="feature-icon">🔐</div>
-    <h3 style={{ fontSize: '1.25rem', fontWeight: '700', marginBottom: '0.75rem' }}>Role-Based Access Control</h3>
-    <p style={{ color: '#64748b', lineHeight: '1.7' }}>
-      Fine-grained permission management with user and role-based access control. Control who can access which knowledge bases, agents, and resources across your organization. Essential for multi-tenant and enterprise deployments.
-    </p>
-  </div>
-
-  <div className="feature-card" style={{ padding: '2rem', borderRadius: '1rem', border: '2px solid #8B5CF6' }}>
-    <div className="feature-icon">📄</div>
-    <h3 style={{ fontSize: '1.25rem', fontWeight: '700', marginBottom: '0.75rem' }}>Advanced Document Processing</h3>
-    <p style={{ color: '#64748b', lineHeight: '1.7' }}>
-      Enterprise-grade document processing with support for complex formats including PDFs, DOCX, spreadsheets, and more. Intelligent extraction, table parsing, and structure preservation for accurate RAG applications.
-    </p>
-  </div>
-
-  <div className="feature-card" style={{ padding: '2rem', borderRadius: '1rem', border: '2px solid #8B5CF6' }}>
-    <div className="feature-icon">📝</div>
-    <h3 style={{ fontSize: '1.25rem', fontWeight: '700', marginBottom: '0.75rem' }}>Advanced Markdown Chunker</h3>
-    <p style={{ color: '#64748b', lineHeight: '1.7' }}>
-      Sophisticated markdown chunking that preserves document structure, headers, code blocks, and semantic boundaries. Optimized for technical documentation and knowledge bases with complex formatting.
-    </p>
-  </div>
-
-  <div className="feature-card" style={{ padding: '2rem', borderRadius: '1rem', border: '2px solid #8B5CF6' }}>
-    <div className="feature-icon">🎯</div>
-    <h3 style={{ fontSize: '1.25rem', fontWeight: '700', marginBottom: '0.75rem' }}>Agentic Retrieval</h3>
-    <p style={{ color: '#64748b', lineHeight: '1.7' }}>
-      Intelligent, multi-step retrieval that goes beyond simple vector search. Agents can iteratively refine queries, explore multiple search strategies, and intelligently combine results for more accurate answers.
-    </p>
-  </div>
-
-  <div className="feature-card" style={{ padding: '2rem', borderRadius: '1rem', border: '2px solid #8B5CF6' }}>
-    <div className="feature-icon">⚙️</div>
-    <h3 style={{ fontSize: '1.25rem', fontWeight: '700', marginBottom: '0.75rem' }}>Production Queue Management</h3>
-    <p style={{ color: '#64748b', lineHeight: '1.7' }}>
-      Built on BullMQ with full API and UI for managing embedding generation, chunk processing, and background jobs. Configure rate limits, retries, priorities, and monitoring for production workloads at scale.
-    </p>
-  </div>
-
-  <div className="feature-card" style={{ padding: '2rem', borderRadius: '1rem', border: '2px solid #8B5CF6' }}>
-    <div className="feature-icon">✅</div>
-    <h3 style={{ fontSize: '1.25rem', fontWeight: '700', marginBottom: '0.75rem' }}>Evaluation Framework</h3>
-    <p style={{ color: '#64748b', lineHeight: '1.7' }}>
-      Comprehensive evaluation and testing tools for measuring agent performance. Create test cases, run evaluation sets, use LLM-as-a-judge, and track quality metrics over time to ensure consistent AI behavior.
-    </p>
-  </div>
-
-  <div className="feature-card" style={{ padding: '2rem', borderRadius: '1rem', border: '2px solid #8B5CF6' }}>
-    <div className="feature-icon">🔄</div>
-    <h3 style={{ fontSize: '1.25rem', fontWeight: '700', marginBottom: '0.75rem' }}>Template Conversations</h3>
-    <p style={{ color: '#64748b', lineHeight: '1.7' }}>
-      Design complex multi-step workflows by chatting with an AI agent, then save as reusable templates. Schedule automated executions with cron expressions for recurring tasks and standardized reasoning patterns.
-    </p>
-  </div>
-
-  <div className="feature-card" style={{ padding: '2rem', borderRadius: '1rem', border: '2px solid #8B5CF6' }}>
-    <div className="feature-icon">💬</div>
-    <h3 style={{ fontSize: '1.25rem', fontWeight: '700', marginBottom: '0.75rem' }}>Agent Feedback System</h3>
-    <p style={{ color: '#64748b', lineHeight: '1.7' }}>
-      Built-in user feedback collection for agent responses with thumbs up/down, comments, and ratings. Track user satisfaction, identify problem areas, and build evaluation datasets from real user interactions.
-    </p>
-  </div>
-
-  <div className="feature-card" style={{ padding: '2rem', borderRadius: '1rem', border: '2px solid #8B5CF6' }}>
-    <div className="feature-icon">🤖</div>
-    <h3 style={{ fontSize: '1.25rem', fontWeight: '700', marginBottom: '0.75rem' }}>Multi-Agent Tooling</h3>
-    <p style={{ color: '#64748b', lineHeight: '1.7' }}>
-      Advanced orchestration for complex multi-agent systems. Enable agents to delegate tasks, collaborate on problems, and intelligently route requests to specialized agents for sophisticated workflows.
-    </p>
-  </div>
-
-  <div className="feature-card" style={{ padding: '2rem', borderRadius: '1rem', border: '2px solid #8B5CF6' }}>
-    <div className="feature-icon">🎨</div>
-    <h3 style={{ fontSize: '1.25rem', fontWeight: '700', marginBottom: '0.75rem' }}>Custom Branding</h3>
-    <p style={{ color: '#64748b', lineHeight: '1.7' }}>
-      White-label the admin UI and frontend with your own branding, colors, logos, and styling. Deliver a seamless experience to your customers without any Exulu branding visible.
-    </p>
-  </div>
-</div>
-
----
-
-## Activation & Licensing
-
-<div style={{
-  background: 'linear-gradient(135deg, rgba(139, 92, 246, 0.1) 0%, rgba(124, 58, 237, 0.1) 100%)',
-  borderRadius: '1rem',
-  padding: '2rem',
-  margin: '2rem 0'
-}}>
-
-### How to activate Enterprise Edition
-
-Enterprise Edition is activated with an environment variable:
-
-```bash
-# .env file
-EXULU_ENTERPRISE_LICENSE=EXULU_EE_your_license_key_here
-```
-
-Once activated, Enterprise features become available across your Exulu application.
-
-### Getting a license
-
-Contact our sales team to discuss your needs and get an Enterprise license. For implementation help, consider working with one of our [certified implementation partners](/partners).
-
-<div style={{ textAlign: 'center', margin: '2rem 0', display: 'flex', gap: '1rem', justifyContent: 'center', flexWrap: 'wrap' }}>
-  <a href="https://exulu.com/contact" className="cta-primary">
-    Request Enterprise License →
-  </a>
-  <a href="/partners" className="cta-secondary">
-    View Partners
-  </a>
-</div>
-
-</div>
-
----
-
-## Enterprise Features Deep Dive
-
-<AccordionGroup>
-  <Accordion title="🔐 Role-Based Access Control (RBAC)">
-    ### Complete access control system
-
-    Enterprise RBAC provides fine-grained permission management for multi-user and multi-tenant deployments:
-
-    **User Management**
-    - Create and manage users with unique credentials
-    - Assign users to multiple roles
-    - Control access at the resource level
-
-    **Role-Based Permissions**
-    - Define custom roles with specific permissions
-    - Grant read/write access to contexts and agents
-    - Support for private and public resources
-
-    **Context-Level Security**
-    - Control who can read/write to knowledge bases
-    - Set default permissions for new contexts
-    - Override permissions per user or role
-
-    **Use Cases**
-    - **Multi-tenant SaaS**: Isolate customer data
-    - **Enterprise teams**: Different departments access different knowledge bases
-    - **Client services**: Separate agent access per client
-    - **Compliance**: Meet data access audit requirements
-
-    ```typescript
-    // RBAC is configured at the ExuluApp level
-    await app.create({
-      config: {
-        authentication: {
-          enabled: true,
-          jwt: {
-            secret: process.env.JWT_SECRET!
-          }
-        }
-      }
-    });
-    ```
-
-    [Learn more about RBAC →](/core/exulu-authentication)
-  </Accordion>
-
-  <Accordion title="⚙️ Queue Management">
-    ### Production-grade background processing
-
-    Built on BullMQ with complete API and UI:
-
-    **Queue Features**
-    - Embedding generation queues
-    - Document processing pipelines
-    - Rate limiting and throttling
-    - Priority queues
-    - Automatic retries with backoff
-    - Dead letter queues
-    - Job scheduling and cron
-
-    **Monitoring & Management**
-    - Real-time queue dashboard
-    - Job status tracking
-    - Performance metrics
-    - Worker health monitoring
-    - Manual job retry/cancel
-
-    **Use Cases**
-    - Processing thousands of documents
-    - Batch embedding generation
-    - Scheduled data updates
-    - Asynchronous agent tasks
-    - Resource-intensive operations
-
-    ```typescript
-    await app.create({
-      config: {
-        workers: {
-          enabled: true,
-          concurrency: 5,
-          telemetry: {
-            enabled: true
-          }
-        }
-      }
-    });
-    ```
-
-    [Learn more about Queues →](/core/exulu-queues/introduction)
-  </Accordion>
-
-  <Accordion title="✅ Evaluation Framework">
-    ### Test and measure agent quality
-
-    Comprehensive evaluation system for maintaining AI quality:
-
-    **Evaluation Capabilities**
-    - Create test cases and golden datasets
-    - Run evaluation sets against agents
-    - LLM-as-a-judge evaluation
-    - Custom evaluation functions
-    - Compare agent versions
-    - Track metrics over time
-
-    **Quality Metrics**
-    - Accuracy and correctness
-    - Hallucination detection
-    - Response relevance
-    - Tool usage correctness
-    - Latency and performance
-
-    **Workflow Integration**
-    - CI/CD integration
-    - Regression testing
-    - A/B testing
-    - Performance benchmarking
-
-    ```typescript
-    import { ExuluEval } from "@exulu/backend";
-
-    const evaluation = new ExuluEval({
-      id: "customer-support-eval",
-      name: "Customer Support Quality",
-      testCases: [
-        {
-          input: "How do I reset my password?",
-          expectedOutput: "Contains password reset steps"
-        }
-      ]
-    });
-    ```
-
-    [Learn more about Evaluations →](/core/exulu-eval/introduction)
-  </Accordion>
-
-  <Accordion title="🔄 Template Conversations">
-    ### Reusable multi-step workflows
-
-    Design workflows by chatting, then reuse them:
-
-    **Key Features**
-    - Save any conversation as a template
-    - Parameterized inputs and outputs
-    - Multi-step reasoning patterns
-    - Scheduled execution with cron
-    - Template versioning
-    - Share across teams
-
-    **Use Cases**
-    - Standardized report generation
-    - Recurring analysis tasks
-    - Multi-step data processing
-    - Customer onboarding flows
-    - Automated quality checks
-
-    **How it works**
-    1. Have a conversation with your agent
-    2. Save it as a template
-    3. Define input parameters
-    4. Schedule or trigger on-demand
-    5. Collect outputs automatically
-
-    Unlike traditional automation tools, template conversations let you design complex workflows naturally by chatting with AI, then codify them for reuse.
-  </Accordion>
-
-  <Accordion title="🎯 Agentic Retrieval">
-    ### Intelligent multi-step search
-
-    Go beyond simple vector search with agentic retrieval:
-
-    **Advanced Capabilities**
-    - Query preprocessing and expansion
-    - Multi-strategy search (vector + keyword + hybrid)
-    - Iterative query refinement
-    - Result reranking and fusion
-    - Context-aware filtering
-    - Source attribution
-
-    **Intelligence Features**
-    - Automatic query decomposition
-    - Ambiguity detection and clarification
-    - Temporal and entity awareness
-    - Cross-reference resolution
-
-    **Performance Benefits**
-    - Higher accuracy on complex queries
-    - Better handling of ambiguous questions
-    - Improved recall for multi-faceted topics
-    - More relevant context for RAG
-
-    ```typescript
-    // Agentic retrieval is automatically enabled when licensed
-    // Configure search strategies in your context
-    const context = new ExuluContext({
-      id: "docs",
-      embedder: openAIEmbedder,
-      reranker: cohereReranker,
-      // Agentic retrieval uses multiple search strategies
-    });
-    ```
-  </Accordion>
-
-  <Accordion title="📄 Advanced Document Processing">
-    ### Enterprise document parsing
-
-    Handle complex document formats with precision:
-
-    **Supported Formats**
-    - PDFs (text and image-based)
-    - Microsoft Office (DOCX, XLSX, PPTX)
-    - Spreadsheets with table extraction
-    - HTML with structure preservation
-    - Markdown with formatting
-    - Source code with syntax awareness
-
-    **Processing Features**
-    - Table detection and extraction
-    - Image and diagram extraction
-    - Header/footer handling
-    - Multi-column layouts
-    - OCR for scanned documents
-    - Metadata extraction
-
-    **Output Quality**
-    - Structure-preserving chunking
-    - Semantic boundary detection
-    - Reference link preservation
-    - Source attribution
-
-    Perfect for building RAG systems over technical documentation, legal contracts, financial reports, and research papers.
-  </Accordion>
-
-  <Accordion title="💬 Agent Feedback System">
-    ### Collect user feedback at scale
-
-    Built-in feedback collection and analysis:
-
-    **Feedback Collection**
-    - Thumbs up/down on responses
-    - Written comments and notes
-    - Rating scales (1-5 stars)
-    - Custom feedback fields
-    - Session-level feedback
-
-    **Analytics & Insights**
-    - Aggregate feedback scores
-    - Identify problem patterns
-    - Track improvement over time
-    - Export feedback data
-    - Build golden datasets from positive examples
-
-    **Integration**
-    - GraphQL API for feedback
-    - UI components for feedback collection
-    - Webhook notifications
-    - Export to evaluation framework
-
-    Use real user feedback to continuously improve your agents and build better evaluation datasets.
-  </Accordion>
-
-  <Accordion title="🤖 Multi-Agent Tooling">
-    ### Orchestrate complex agent systems
-
-    Advanced capabilities for multi-agent workflows:
-
-    **Orchestration Features**
-    - Agent-to-agent delegation
-    - Intelligent routing
-    - Parallel agent execution
-    - Result aggregation
-    - Failure handling and fallbacks
-
-    **Communication Patterns**
-    - Request/response
-    - Publish/subscribe
-    - Broadcast
-    - Sequential pipelines
-    - Parallel fan-out
-
-    **Use Cases**
-    - Specialized expert agents
-    - Research and synthesis workflows
-    - Multi-perspective analysis
-    - Verification and validation chains
-    - Complex decision-making systems
-
-    Build sophisticated systems where agents collaborate, each contributing their expertise to solve complex problems.
-  </Accordion>
-
-  <Accordion title="🎨 Custom Branding">
-    ### White-label your deployment
-
-    Complete customization of the Exulu UI:
-
-    **Branding Options**
-    - Custom logos and favicons
-    - Color scheme customization
-    - Typography and fonts
-    - Custom CSS and styling
-    - Powered-by attribution removal
-
-    **Application Areas**
-    - Admin UI
-    - Frontend interface
-    - Email templates
-    - PDF exports
-    - Error pages
-
-    Deliver a seamless, branded experience to your customers and team members without any Exulu branding visible.
-  </Accordion>
-</AccordionGroup>
-
----
-
-## Who Should Use Enterprise Edition?
-
-<CardGroup cols={2}>
-  <Card title="Production Applications" icon="rocket">
-    Teams deploying AI applications to production that require enterprise-grade features like RBAC, queue management, and monitoring
-  </Card>
-  <Card title="Multi-Tenant SaaS" icon="users">
-    Companies building SaaS products that need to isolate customer data and provide role-based access control
-  </Card>
-  <Card title="Enterprise Teams" icon="building">
-    Organizations with multiple departments or teams that need granular access control and custom branding
-  </Card>
-  <Card title="High-Volume Processing" icon="brick-wall-shield">
-    Applications processing large volumes of documents or requiring sophisticated queue management and background jobs
-  </Card>
-  <Card title="Quality-Critical Systems" icon="shield-alert">
-    Teams that need comprehensive evaluation frameworks to maintain and measure AI quality over time
-  </Card>
-  <Card title="Complex Workflows" icon="replace-all">
-    Projects requiring template conversations, multi-agent orchestration, and sophisticated retrieval strategies
-  </Card>
-</CardGroup>
-
----
-
-<div style={{
-  padding: '4rem 2rem',
-  background: 'linear-gradient(135deg, #8B5CF6 0%, #7C3AED 100%)',
-  borderRadius: '1rem',
-  margin: '3rem 0',
-  color: 'white'
-}}>
-  <h2 style={{ fontSize: '2.5rem', fontWeight: '800', marginBottom: '1rem', color: 'white' }}>
-    Ready for Enterprise?
-  </h2>
-  <p style={{ fontSize: '1.25rem', marginBottom: '2rem', opacity: 0.9 }}>
-    Get started with an Enterprise license or work with one of our certified implementation partners
-  </p>
-  <div style={{ display: 'flex', gap: '1rem', flexWrap: 'wrap' }}>
-    <a
-      href="https://exulu.com/contact"
-      style={{
-        background: 'white',
-        color: '#8B5CF6',
-        padding: '1rem 2rem',
-        borderRadius: '0.5rem',
-        fontWeight: '600',
-        textDecoration: 'none',
-        display: 'inline-block',
-        transition: 'all 0.3s ease'
-      }}
-    >
-      Request License →
-    </a>
-    <a
-      href="/partners"
-      style={{
-        background: 'transparent',
-        color: 'white',
-        padding: '1rem 2rem',
-        borderRadius: '0.5rem',
-        fontWeight: '600',
-        textDecoration: 'none',
-        display: 'inline-block',
-        border: '2px solid white',
-        transition: 'all 0.3s ease'
-      }}
-    >
-      Work with a Partner →
-    </a>
-  </div>
-</div>

package/mintlify-docs/essentials/code.mdx

@@ -1,35 +0,0 @@
----
-title: 'Code blocks'
-description: 'Display inline code and code blocks'
-icon: 'code'
----
-
-## Inline code
-
-To denote a `word` or `phrase` as code, enclose it in backticks (`).
-
-```
-To denote a `word` or `phrase` as code, enclose it in backticks (`).
-```
-
-## Code blocks
-
-Use [fenced code blocks](https://www.markdownguide.org/extended-syntax/#fenced-code-blocks) by enclosing code in three backticks and follow the leading ticks with the programming language of your snippet to get syntax highlighting. Optionally, you can also write the name of your code after the programming language.
-
-```java HelloWorld.java
-class HelloWorld {
-    public static void main(String[] args) {
-        System.out.println("Hello, World!");
-    }
-}
-```
-
-````md
-```java HelloWorld.java
-class HelloWorld {
-    public static void main(String[] args) {
-        System.out.println("Hello, World!");
-    }
-}
-```
-````

package/mintlify-docs/essentials/images.mdx

@@ -1,59 +0,0 @@
----
-title: 'Images and embeds'
-description: 'Add image, video, and other HTML elements'
-icon: 'image'
----
-
-<img
-  style={{ borderRadius: '0.5rem' }}
-  src="https://mintlify-assets.b-cdn.net/bigbend.jpg"
-/>
-
-## Image
-
-### Using Markdown
-
-The [markdown syntax](https://www.markdownguide.org/basic-syntax/#images) lets you add images using the following code
-
-```md
-![title](/path/image.jpg)
-```
-
-Note that the image file size must be less than 5MB. Otherwise, we recommend hosting on a service like [Cloudinary](https://cloudinary.com/) or [S3](https://aws.amazon.com/s3/). You can then use that URL and embed.
-
-### Using embeds
-
-To get more customizability with images, you can also use [embeds](/writing-content/embed) to add images
-
-```html
-<img height="200" src="/path/image.jpg" />
-```
-
-## Embeds and HTML elements
-
-<iframe
-  width="560"
-  height="315"
-  src="https://www.youtube.com/embed/4KzFe50RQkQ"
-  title="YouTube video player"
-  frameBorder="0"
-  allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture"
-  allowFullScreen
-  style={{ width: '100%', borderRadius: '0.5rem' }}
-></iframe>
-
-<br />
-
-<Tip>
-
-Mintlify supports [HTML tags in Markdown](https://www.markdownguide.org/basic-syntax/#html). This is helpful if you prefer HTML tags to Markdown syntax, and lets you create documentation with infinite flexibility.
-
-</Tip>
-
-### iFrames
-
-Loads another HTML page within the document. Most commonly used for embedding videos.
-
-```html
-<iframe src="https://www.youtube.com/embed/4KzFe50RQkQ"> </iframe>
-```