panarican/openwebui-knowledge-sync

By panarican

•Updated 5 months ago

Image

3.0K

Overview Tags

panarican/openwebui-knowledge-sync repository overview

⁠OpenWebUI Knowledge Sync

Syncs knowledge sources (Google Drive, Git repos) to OpenWebUI⁠ knowledge bases on a configurable schedule.

⁠Quick Start

⁠Docker Compose (Recommended)

Create a docker-compose.yml:

services:
  openwebui-knowledge-sync:
    image: panarican/openwebui-knowledge-sync:latest
    container_name: openwebui-knowledge-sync
    restart: unless-stopped
    env_file:
      - .env
    volumes:
      - ./config.yml:/app/config.yml:ro
      - ./keys:/app/keys:ro
      - ./data:/app/data
      - ./logs:/var/log/openwebui-knowledge-sync

Create a .env file:

# Required
OPENWEBUI_BASE_URL=https://your-openwebui-instance.com
OPENWEBUI_API_KEY=sk-your-api-key-here

# Optional
SYNC_CRON=0 3 * * *
TZ=America/New_York

Create a config.yml (see Configuration section below)
Run:

docker-compose up -d

⁠Docker Run

docker run -d \
  --name openwebui-knowledge-sync \
  --env-file .env \
  -v $(pwd)/config.yml:/app/config.yml:ro \
  -v $(pwd)/keys:/app/keys:ro \
  -v $(pwd)/data:/app/data \
  -v $(pwd)/logs:/var/log/openwebui-knowledge-sync \
  --restart unless-stopped \
  panarican/openwebui-knowledge-sync:latest

⁠Environment Variables

Variable	Required	Default	Description
`OPENWEBUI_BASE_URL`	✅	-	OpenWebUI instance URL
`OPENWEBUI_API_KEY`	✅	-	OpenWebUI API key
`SYNC_CRON`	❌	`0 3 * * *`	Cron schedule (default: daily 3 AM)
`TZ`	❌	`America/New_York`	Timezone for cron
`CONFIG_PATH`	❌	`./config.yml`	Path to config file
`RESET_KNOWLEDGE_BASES`	❌	`true`	Clear KB before sync
`DELETE_ORPHAN_FILES`	❌	`true`	Delete removed files
`DRY_RUN`	❌	`false`	Preview without changes
`PARALLEL_SYNC`	❌	`false`	Sync sources in parallel
`MAX_RETRIES`	❌	`3`	Max retry attempts

⁠Cron Schedule Examples

SYNC_CRON=0 3 * * *       # Daily at 3 AM
SYNC_CRON=0 */6 * * *     # Every 6 hours
SYNC_CRON=0 9,17 * * 1-5  # 9 AM and 5 PM weekdays
SYNC_CRON=*/30 * * * *    # Every 30 minutes

⁠Configuration (config.yml)

knowledgeBases:
  # Google Drive source
  - name: "My Google Docs"
    description: "Documentation from Google Drive"
    source:
      type: google-drive
      folderId: "your-google-drive-folder-id"
      keyFile: "./keys/google-service-account.json"
    outputDir: "./data/knowledge-base/Google-Docs"

  # Git repository source
  - name: "My Wiki"
    description: "GitLab wiki content"
    source:
      type: git
      repo: "[email protected]:your-org/your-project.wiki.git"
      keyFile: "./keys/id_gitlab"
      shallow: true
    outputDir: "./data/knowledge-base/My-Wiki"

⁠Volume Mounts

Path	Description
`/app/config.yml`	Knowledge base configuration
`/app/data`	Synced content (persistent)
`/app/keys`	Service account & SSH keys
`/var/log/openwebui-knowledge-sync`	Sync logs

⁠Manual Sync

Run a sync manually (outside of cron schedule):

docker exec openwebui-knowledge-sync npm run sync

⁠View Logs

# Container logs
docker logs -f openwebui-knowledge-sync

# Sync logs
docker exec openwebui-knowledge-sync cat /var/log/openwebui-knowledge-sync/sync.log

Tag summary

Recent tags

Content type

Image

Digest

sha256:61265ff84…

Size

416.9 MB

Last updated

5 months ago

docker pull panarican/openwebui-knowledge-sync