tonym/NastyNAS
1
0
Fork 0
Code Issues 70 Pull Requests Actions Packages Projects Releases Wiki Activity

Configure AnythingLLM Chat Interface #32

New Issue
Open
opened 2025-09-14 08:10:17 +00:00 by tonym · 0 comments
tonym commented 2025-09-14 08:10:17 +00:00
Owner
Copy Link

AnythingLLM Chat Interface Configuration for Unraid 7.0.1

Container Installation

  • From Community Applications: Search "AnythingLLM"
  • Container Selection: Mintplexlabs/anythingllm
  • Repository: ghcr.io/mintplexlabs/anythingllm:latest

Container Configuration

Basic Settings:

  • Container Port: 3001
  • Host Port: 3001
  • Network Mode: bridge
  • Repository Path: ghcr.io/mintplexlabs/anythingllm:latest

Volume Mappings:

  • Storage: /mnt/user/appdata/anythingllm:/app/server/storage
  • Config: /mnt/user/appdata/anythingllm/hotdir:/app/collector/hotdir
  • Outputs: /mnt/user/appdata/anythingllm/outputs:/app/collector/outputs

Environment Variables:

  • PUID: 99
  • PGID: 100
  • TZ: America/Chicago
  • UMASK: 002
  • UID: 99
  • GID: 100
  • JWT_SECRET: (generate secure random string)
  • LLM_PROVIDER: localai (if using LocalAI)
  • EMBEDDING_ENGINE: native

Initial Configuration

  1. First Access: http://[SERVER_IP]:3001
  2. Setup Wizard:
    • Create admin account
    • Choose LLM provider (LocalAI recommended)
    • Configure embedding engine
  3. Authentication: Set strong admin password

Service Configuration

LLM Provider Setup:

  • LocalAI Integration: http://[SERVER_IP]:8080/v1
  • API Key: Configure if required
  • Model Selection: Choose appropriate model for workload

Workspace Configuration:

  • Default Workspace: Create initial workspace
  • Document Processing: Configure supported formats
  • Chat Settings: Set system prompts and parameters

Vector Database:

  • Engine: LanceDB (default)
  • Embedding Model: all-MiniLM-L6-v2 (local)
  • Chunk Size: 1000 (default)

Integration Points

LocalAI Connection:

  • URL: http://[SERVER_IP]:8080
  • Models: Ensure models are loaded in LocalAI
  • API Compatibility: OpenAI-compatible endpoints

Document Sources:

  • Upload Directory: /app/collector/hotdir
  • Supported Formats: PDF, TXT, DOCX, MD
  • Auto-processing: Configure watch folders

Monitoring & Notifications

Uptime Kuma Integration:

Health Checks:

  • Container Health: Docker health check enabled
  • Service Status: API endpoint monitoring
  • Resource Usage: Memory and CPU monitoring

Backup Configuration

Kopia Integration:

  • Backup Paths:
    • /mnt/user/appdata/anythingllm/storage (database)
    • /mnt/user/appdata/anythingllm/env (environment)
  • Schedule: Daily at 2:00 AM
  • Retention: 30 daily, 12 monthly

Critical Files:

  • Database: SQLite files in storage directory
  • Configuration: Environment variables
  • Documents: Uploaded document cache

Testing Procedures

Health Checks:

  1. Container Status: docker ps | grep anythingllm
  2. Port Accessibility: curl http://[SERVER_IP]:3001/api/system/ping
  3. Web Interface: Access via browser

Functionality Tests:

  1. Chat Interface: Test basic chat functionality
  2. Document Upload: Test file processing
  3. LLM Integration: Verify LocalAI connectivity
  4. Workspace Creation: Test workspace management

Integration Tests:

  1. LocalAI Connection: Test model responses
  2. Document Processing: Upload and query documents
  3. API Endpoints: Test REST API functionality

Troubleshooting

Common Issues:

  1. LLM Connection Failed:

    • Verify LocalAI is running and accessible
    • Check API URL and authentication
    • Ensure models are loaded in LocalAI

  2. Document Processing Issues:

    • Check file permissions in hotdir
    • Verify supported file formats
    • Monitor processing logs

  3. Database Errors:

    • Check storage directory permissions
    • Verify SQLite database integrity
    • Review container logs for errors

Permission Fixes:

sudo chown -R 99:100 /mnt/user/appdata/anythingllm
sudo chmod -R 755 /mnt/user/appdata/anythingllm

Log Locations:

  • Container Logs: docker logs anythingllm
  • Application Logs: /mnt/user/appdata/anythingllm/storage/logs
  • System Logs: /var/log/syslog

Maintenance

Regular Tasks:

  1. Database Cleanup: Monthly workspace optimization
  2. Document Cleanup: Remove old processed files
  3. Log Rotation: Configure log size limits
  4. Security Updates: Update container regularly

Performance Optimization:

  1. Memory Allocation: Adjust container memory limits
  2. Storage Management: Monitor disk usage
  3. Cache Cleanup: Clear embedding cache periodically
  4. Model Management: Optimize loaded models

Security Maintenance:

  1. Password Policy: Enforce strong passwords
  2. API Security: Rotate JWT secrets periodically
  3. Access Control: Review user permissions
  4. Network Security: Limit external access
# AnythingLLM Chat Interface Configuration for Unraid 7.0.1 ## Container Installation - **From Community Applications:** Search "AnythingLLM" - **Container Selection:** Mintplexlabs/anythingllm - **Repository:** ghcr.io/mintplexlabs/anythingllm:latest ## Container Configuration **Basic Settings:** - **Container Port:** 3001 - **Host Port:** 3001 - **Network Mode:** bridge - **Repository Path:** ghcr.io/mintplexlabs/anythingllm:latest **Volume Mappings:** - **Storage:** /mnt/user/appdata/anythingllm:/app/server/storage - **Config:** /mnt/user/appdata/anythingllm/hotdir:/app/collector/hotdir - **Outputs:** /mnt/user/appdata/anythingllm/outputs:/app/collector/outputs **Environment Variables:** - **PUID:** 99 - **PGID:** 100 - **TZ:** America/Chicago - **UMASK:** 002 - **UID:** 99 - **GID:** 100 - **JWT_SECRET:** (generate secure random string) - **LLM_PROVIDER:** localai (if using LocalAI) - **EMBEDDING_ENGINE:** native ## Initial Configuration 1. **First Access:** http://[SERVER_IP]:3001 2. **Setup Wizard:** - Create admin account - Choose LLM provider (LocalAI recommended) - Configure embedding engine 3. **Authentication:** Set strong admin password ## Service Configuration **LLM Provider Setup:** - **LocalAI Integration:** http://[SERVER_IP]:8080/v1 - **API Key:** Configure if required - **Model Selection:** Choose appropriate model for workload **Workspace Configuration:** - **Default Workspace:** Create initial workspace - **Document Processing:** Configure supported formats - **Chat Settings:** Set system prompts and parameters **Vector Database:** - **Engine:** LanceDB (default) - **Embedding Model:** all-MiniLM-L6-v2 (local) - **Chunk Size:** 1000 (default) ## Integration Points **LocalAI Connection:** - **URL:** http://[SERVER_IP]:8080 - **Models:** Ensure models are loaded in LocalAI - **API Compatibility:** OpenAI-compatible endpoints **Document Sources:** - **Upload Directory:** /app/collector/hotdir - **Supported Formats:** PDF, TXT, DOCX, MD - **Auto-processing:** Configure watch folders ## Monitoring & Notifications **Uptime Kuma Integration:** - **Monitor Type:** HTTP - **URL:** http://[SERVER_IP]:3001/api/system/ping - **Check Interval:** 60 seconds - **Alert Threshold:** 3 failures **Health Checks:** - **Container Health:** Docker health check enabled - **Service Status:** API endpoint monitoring - **Resource Usage:** Memory and CPU monitoring ## Backup Configuration **Kopia Integration:** - **Backup Paths:** - /mnt/user/appdata/anythingllm/storage (database) - /mnt/user/appdata/anythingllm/env (environment) - **Schedule:** Daily at 2:00 AM - **Retention:** 30 daily, 12 monthly **Critical Files:** - **Database:** SQLite files in storage directory - **Configuration:** Environment variables - **Documents:** Uploaded document cache ## Testing Procedures **Health Checks:** 1. **Container Status:** docker ps | grep anythingllm 2. **Port Accessibility:** curl http://[SERVER_IP]:3001/api/system/ping 3. **Web Interface:** Access via browser **Functionality Tests:** 1. **Chat Interface:** Test basic chat functionality 2. **Document Upload:** Test file processing 3. **LLM Integration:** Verify LocalAI connectivity 4. **Workspace Creation:** Test workspace management **Integration Tests:** 1. **LocalAI Connection:** Test model responses 2. **Document Processing:** Upload and query documents 3. **API Endpoints:** Test REST API functionality ## Troubleshooting **Common Issues:** 1. **LLM Connection Failed:** - Verify LocalAI is running and accessible - Check API URL and authentication - Ensure models are loaded in LocalAI 2. **Document Processing Issues:** - Check file permissions in hotdir - Verify supported file formats - Monitor processing logs 3. **Database Errors:** - Check storage directory permissions - Verify SQLite database integrity - Review container logs for errors **Permission Fixes:** ```bash sudo chown -R 99:100 /mnt/user/appdata/anythingllm sudo chmod -R 755 /mnt/user/appdata/anythingllm ``` **Log Locations:** - **Container Logs:** docker logs anythingllm - **Application Logs:** /mnt/user/appdata/anythingllm/storage/logs - **System Logs:** /var/log/syslog ## Maintenance **Regular Tasks:** 1. **Database Cleanup:** Monthly workspace optimization 2. **Document Cleanup:** Remove old processed files 3. **Log Rotation:** Configure log size limits 4. **Security Updates:** Update container regularly **Performance Optimization:** 1. **Memory Allocation:** Adjust container memory limits 2. **Storage Management:** Monitor disk usage 3. **Cache Cleanup:** Clear embedding cache periodically 4. **Model Management:** Optimize loaded models **Security Maintenance:** 1. **Password Policy:** Enforce strong passwords 2. **API Security:** Rotate JWT secrets periodically 3. **Access Control:** Review user permissions 4. **Network Security:** Limit external access
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
No items
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
tonym
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: tonym/NastyNAS#32
No description provided.
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?