Local Docs Retriever
by nelsond20
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HF_HUB_OFFLINE | No | Enables Hugging Face Hub offline mode. Set to 1 after models are cached. | |
| RAG_QDRANT_URL | No | The URL of the Qdrant instance used by the retrieval engine. | http://127.0.0.1:6333 |
| FASTEMBED_CACHE_PATH | No | Path to a prepared FastEmbed model cache, used when running offline on a host without cached models. | |
| RAG_COLLECTION_ALIAS | No | The Qdrant collection alias that points to the active prepared documentation corpus. | docs_current |
| TRANSFORMERS_OFFLINE | No | Enables Transformers offline mode. Set to 1 after models are cached. | |
| RAG_RETRIEVAL_STRATEGY | No | The retrieval strategy used by MCP searches. The default production strategy is sparse; dense and hybrid remain available through the CLI and evaluation commands. | sparse |
| HF_HUB_DISABLE_TELEMETRY | No | Disables Hugging Face Hub telemetry. Set to 1 in offline mode. | |
| HAYSTACK_TELEMETRY_ENABLED | No | Controls Haystack telemetry. Set to False in offline mode. |
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