Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KNOWLEDGE_OCR__ENABLED | No | Whether to enable OCR for scanned documents. Default is true. | true |
| KNOWLEDGE_OCR__LANGUAGE | No | OCR language code (e.g., 'eng', 'fra'). Default is eng. | eng |
| KNOWLEDGE_LOGGING__LEVEL | No | Logging verbosity level (DEBUG, INFO, etc.). Default is INFO. | INFO |
| KNOWLEDGE_OCR__FORCE_OCR | No | Whether to force OCR on all documents regardless of text extraction quality. Default is false. | false |
| KNOWLEDGE_LOGGING__FORMAT | No | The format for log messages ('text'). Default is text. | text |
| KNOWLEDGE_EMBEDDING__DEVICE | No | Computation device for embeddings (e.g., 'cpu' or 'cuda'). Default is cpu. | cpu |
| KNOWLEDGE_SEARCH__MAX_TOP_K | No | Maximum number of search results allowed. Default is 50. | 50 |
| KNOWLEDGE_CHUNKING__STRATEGY | No | The strategy used for chunking (e.g., 'sentence'). Default is sentence. | sentence |
| KNOWLEDGE_CHUNKING__CHUNK_SIZE | No | The number of characters per document chunk. Default is 500. | 500 |
| KNOWLEDGE_EMBEDDING__BATCH_SIZE | No | Number of embeddings to process per batch. Default is 32. | 32 |
| KNOWLEDGE_EMBEDDING__MODEL_NAME | No | The Sentence Transformers model name to use for embeddings. Default is sentence-transformers/all-MiniLM-L6-v2. | sentence-transformers/all-MiniLM-L6-v2 |
| KNOWLEDGE_SEARCH__DEFAULT_TOP_K | No | Default number of search results to return. Default is 10. | 10 |
| KNOWLEDGE_CHUNKING__CHUNK_OVERLAP | No | The number of overlapping characters between chunks. Default is 50. | 50 |
| KNOWLEDGE_STORAGE__DOCUMENTS_PATH | No | The directory path where documents are stored. Default is ./data/documents. | ./data/documents |
| KNOWLEDGE_STORAGE__VECTOR_DB_PATH | No | The directory path for the ChromaDB vector database. Default is ./data/chromadb. | ./data/chromadb |
| KNOWLEDGE_OCR__CONFIDENCE_THRESHOLD | No | OCR confidence threshold. Default is 0.0. | 0.0 |
| KNOWLEDGE_PROCESSING__MAX_FILE_SIZE_MB | No | Maximum allowed file size in MB for processing. Default is 100. | 100 |
| KNOWLEDGE_PROCESSING__MAX_CONCURRENT_TASKS | No | Maximum number of background indexing tasks to run concurrently. Default is 3. | 3 |
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 | |