Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Port to run the server on | 8000 |
| DEBUG | No | Enable debug mode | false |
| TIMEOUT | No | Worker timeout in seconds | 120 |
| WORKERS | No | Number of worker processes | 4 |
| KEEPALIVE | No | Keep-alive timeout in seconds | 5 |
| LOG_LEVEL | No | Logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL) | INFO |
| USE_CACHE | No | Enable/disable caching system | true |
| USE_FEEDBACK | No | Enable/disable feedback system | true |
| USE_VECTOR_DB | No | Enable/disable vector DB integration | true |
| CACHE_MAX_SIZE | No | Maximum number of items in cache | 1000 |
| CACHE_TTL_SECONDS | No | Cache time-to-live in seconds | 3600 |
| PROMETHEUS_METRICS | No | Set to 'true' to expose Prometheus metrics at /metrics | |
| WIKIDATA_VECTORDB_API_KEY | No | API key for the vector DB service. Required for enhanced semantic search, though the server can function without it through graceful degradation. |
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 | |