rag
by akshayvarala
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATA_DIR | No | Base data directory. | |
| MCP_HOST | No | MCP server host. | |
| MCP_PORT | No | MCP server port. | |
| LOG_LEVEL | No | Log level. | |
| CHUNK_SIZE | No | Chunk size for ingestion. | |
| QDRANT_PATH | No | Path to Qdrant data directory. | |
| CHUNK_OVERLAP | No | Chunk overlap for ingestion. | |
| ALLOWED_INPUT_DIR | No | Allowed input directory for ingestion. | |
| QDRANT_COLLECTION | No | Qdrant collection name. | |
| EMBEDDING_PROVIDER | Yes | Embedding provider. One of: qwen_local, st_local, openai, cohere. | |
| EMBEDDING_DIMENSION | No | Embedding dimension (e.g., 1024). | |
| EMBEDDING_BATCH_SIZE | No | Embedding batch size. | |
| EMBEDDING_MODEL_PATH | No | Path to the GGUF embedding model (required for qwen_local). |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
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 | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues