Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Set to 'debug' for verbose output | |
| CHUNK_SIZE | No | Target tokens per chunk for document splitting | 2000 |
| NUM_RESULTS | No | Number of search results to return by default | 5 |
| EMBEDDING_MODEL | No | Hugging Face model to use for embeddings | Xenova/all-MiniLM-L6-v2 |
| VECTRA_INDEX_PATH | No | Vector database location | ./vectra_index |
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 | |