Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_DPI | No | DPI setting for LLM parser | 150 |
| CACHE_DIR | No | Cache directory for processing | ./.cache |
| LLM_MODEL | No | Model to use with LLM parser | anthropic/claude-3.5-sonnet |
| LOG_LEVEL | No | Logging level | INFO |
| CHUNK_SIZE | No | Target chunk size for LangChain chunker | 1000 |
| PDF_PARSER | No | Parser to use: marker, pymupdf4llm, mineru, docling, llm | marker |
| MINERU_LANG | No | Language setting for MinerU parser | en |
| MINERU_VRAM | No | VRAM setting for MinerU parser | |
| PDF_CHUNKER | No | Chunking strategy to use | unstructured |
| CHUNK_OVERLAP | No | LangChain chunk overlap | 200 |
| MINERU_METHOD | No | Method setting for MinerU parser | auto |
| DOCLING_DO_OCR | No | Enable OCR for Docling parser | false |
| OPENAI_API_KEY | Yes | OpenAI API key for embeddings (required) | |
| EMBEDDING_MODEL | No | OpenAI embedding model | text-embedding-3-large |
| LLM_CONCURRENCY | No | Concurrency setting for LLM parser | 5 |
| VECTOR_SEARCH_K | No | Default search results | 5 |
| DOCLING_TABLE_MODE | No | Table extraction mode for Docling parser | ACCURATE |
| FILE_SCAN_INTERVAL | No | File monitoring interval in seconds | 60 |
| KNOWLEDGEBASE_PATH | No | Directory containing PDF files | ./pdfs |
| OPENROUTER_API_KEY | No | OpenRouter API key, required for LLM parser | |
| EMBEDDING_BATCH_SIZE | No | Embedding batch size | 100 |
| DOCLING_OCR_LANGUAGES | No | Languages for OCR with Docling parser | en |
| DOCLING_DO_TABLE_STRUCTURE | No | Enable table structure extraction for Docling parser | 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 | |