Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WEAVIATE_HOST | No | Weaviate host address | localhost |
| WEAVIATE_PORT | No | Weaviate HTTP port | 8080 |
| GEMINI_API_KEY | Yes | Your Gemini API key | |
| LLM_CONCURRENCY | No | Max concurrent background LLM tasks (embeddings/descriptions/refinements) | 5 |
| WEAVIATE_GRPC_PORT | No | Weaviate gRPC port | 50051 |
| WEAVIATE_BATCH_SIZE | No | Batch size for Weaviate operations | 100 |
| EMBEDDING_MODEL_NAME | No | Gemini model for embeddings | models/embedding-001 |
| GENERATION_MODEL_NAME | No | Gemini model for text generation | models/gemini-pro |
| SEMANTIC_SEARCH_LIMIT | No | Limit for semantic search results | 5 |
| SEMANTIC_SEARCH_DISTANCE | No | Distance threshold for semantic search | 0.7 |
| WATCHER_POLLING_INTERVAL | No | File watcher polling interval in seconds | 5 |
| GENERATE_LLM_DESCRIPTIONS | No | Set to true to enable background LLM description generation and refinement | true |
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |