Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Logging level | INFO |
| NEO4J_URI | No | Neo4j connection URI | bolt://neo4j:7687 |
| BATCH_SIZE | No | Embedding batch size | 32 |
| CACHE_PATH | No | Path for embedding cache | /cache |
| INDEX_PATH | No | Path for index metadata | /index |
| NEO4J_USER | No | Neo4j username | neo4j |
| OLLAMA_HOST | No | Ollama API endpoint | http://host.docker.internal:11434 |
| QDRANT_HOST | No | Qdrant server hostname | qdrant |
| QDRANT_PORT | No | Qdrant server port | 6333 |
| CODEBASE_PATH | No | Path to codebase to index | ./sample_codebase |
| MAX_CHUNK_SIZE | No | Maximum chunk size in characters | 2048 |
| NEO4J_PASSWORD | No | Neo4j password | password |
| WORKSPACE_PATH | No | Path to mounted codebase | /workspace |
| EMBEDDING_MODEL | No | Ollama embedding model to use | embeddinggemma:latest |
| ENABLE_GRAPH_DB | No | Enable Neo4j graph database | false |
| ENABLE_FILE_WATCHER | No | Enable real-time file watching | true |
| WATCHER_DEBOUNCE_SECONDS | No | Delay before processing file changes | 2.0 |
| MAX_CONCURRENT_EMBEDDINGS | No | Concurrent embedding requests | 4 |
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 | |