OmniDocs RAG
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RAG_DEVICE | No | cuda / cpu / auto | auto |
| RAG_DB_PATH | No | ChromaDB storage location | ./chroma_db |
| GITHUB_TOKEN | No | GitHub API token (higher rate limits) | |
| RAG_DOCS_PATH | No | Folder to scan for files | parent directory |
| RAG_WATCH_PATH | No | Directory to watch for auto-reindex | |
| RAG_EMBED_MODEL | No | Embedding model | BAAI/bge-m3 |
| RAG_RERANK_MODEL | No | Cross-Encoder model | BAAI/bge-reranker-v2-m3 |
| RAG_WATCH_COLLECTION | No | Collection for file watcher | docs_v4 |
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 | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ElvinBayramov/OmniDocs-RAG'
If you have feedback or need assistance with the MCP directory API, please join our Discord server