local-RAG-backend
by suwa-sh
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GROUP_ID | No | Tenant identifier. | default |
| NEO4J_URI | No | Connection URI for the Neo4j database. | bolt://localhost:7687 |
| NEO4J_USER | No | Username for the Neo4j database. | neo4j |
| CHUNK_OVERLAP | No | Overlap size between document chunks. | 0 |
| LLM_MODEL_KEY | Yes | API key for the LLM model. | |
| LLM_MODEL_URL | No | Base URL for the OpenAI-compatible LLM API. | https://api.openai.com/v1 |
| CHUNK_SIZE_MAX | No | Maximum size for document chunks. | 2000 |
| CHUNK_SIZE_MIN | No | Minimum size for document chunks. | 200 |
| LLM_MODEL_NAME | No | Model name used for graph search and general processing. | gpt-4o-mini |
| NEO4J_PASSWORD | No | Password for the Neo4j database. | password |
| RERANK_MODEL_NAME | No | Model name used for reranking search results. | gpt-4.1-nano |
| EMBEDDING_MODEL_KEY | No | API key for the embedding model. | dummy |
| EMBEDDING_MODEL_URL | No | Base URL for the OpenAI-compatible Embedding API. | http://host.docker.internal:11434/v1 |
| EMBEDDING_MODEL_NAME | No | Model name for generating embeddings. | kun432/cl-nagoya-ruri-large:latest |
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
ActivityInactive
ResponsivenessNo issues