ThinkDrop Vision Service
by lukaizhi5559
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | The port on which the service runs | 3006 |
| API_KEY | Yes | Your vision API key | |
| VLM_MODEL | No | The VLM model to use | openbmb/MiniCPM-V-2_6 |
| OCR_ENGINE | No | The OCR engine to use | paddleocr |
| VLM_DEVICE | No | The device to use for VLM (auto, cpu, cuda) | auto |
| VLM_ENABLED | No | Enable or disable VLM (lazy-loaded) | true |
| OCR_LANGUAGE | No | The language for OCR | en |
| USER_MEMORY_API_KEY | No | API key for the user memory service | |
| WATCH_CHANGE_THRESHOLD | No | Change threshold for watch mode | 0.08 |
| USER_MEMORY_SERVICE_URL | No | URL of the user memory service | http://localhost:3003 |
| WATCH_DEFAULT_INTERVAL_MS | No | Default interval for watch mode in milliseconds | 2000 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityInactive
ResponsivenessNo issues