Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| USE_QDRANT | No | Use Qdrant instead of Supabase (optional) | false |
| SEARXNG_URL | No | Internal SearXNG URL | http://searxng:8080 |
| CRAWL4AI_URL | No | Internal Crawl4AI URL | http://crawl4ai:8000 |
| LLM_PROVIDER | No | The LLM provider to use (e.g., openai, anthropic, groq) | openai |
| USE_SUPABASE | No | Enable Supabase for vector storage | true |
| USE_RERANKING | No | Cross-encoder Reranking (improves result relevance) | false |
| OPENAI_API_KEY | No | Required for contextual embeddings | |
| RERANKING_MODEL | No | The model to use for reranking | cross-encoder/ms-marco-MiniLM-L-12-v2 |
| USE_AGENTIC_RAG | No | Enable advanced RAG features | true |
| NEO4J_BATCH_SIZE | No | Batch size for large repository processing | 50 |
| REPO_MAX_SIZE_MB | No | Maximum repository size | 500 |
| USE_HYBRID_SEARCH | No | Hybrid Search (combines vector + keyword search). Requires PostgreSQL full-text search | false |
| NEO4J_BATCH_TIMEOUT | No | Timeout for batch operations | 120 |
| REPO_MAX_FILE_COUNT | No | Maximum number of files | 10000 |
| USE_KNOWLEDGE_GRAPH | No | Enable Neo4j for code analysis | true |
| CRAWL4AI_MAX_CONCURRENT | No | Maximum concurrent crawling sessions | 20 |
| SUPABASE_MAX_CONNECTIONS | No | Maximum connections for Supabase | 20 |
| USE_CONTEXTUAL_EMBEDDINGS | No | Contextual Embeddings (improves search accuracy by 20-30%). Requires OpenAI API or compatible LLM | false |
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 | |