graphrag
by smittysmee
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EMBED_GPU | No | Set to '1' to run the embedding service with GPU support via docker compose. | 0 |
| ANTHROPIC_API_KEY | No | Anthropic API key used for optional entity enrichment via 'make enrich'. | |
| GRAPHRAG_EMBEDDING_CUDA | No | Set to 'true' to enable CUDA for ONNX embedding on GPU. | false |
| GRAPHRAG_EMBEDDING_BACKEND | No | The embedding backend to use. Defaults to 'onnx' for local CPU inference. Set to 'http' to use a remote OpenAI-compatible embeddings API. | onnx |
| GRAPHRAG_EMBEDDING_BASE_URL | No | Base URL for the HTTP embedding backend (OpenAI /v1/embeddings format). Required when GRAPHRAG_EMBEDDING_BACKEND=http. |
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