Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
USE_VLLMNotrue to use local vLLM backend, false to use OpenRouter for chat.true
CHUNK_SIZENoChild chunk size (chars).600
QDRANT_URLNoURL of the Qdrant instance.
VLLM_MODELNoModel served by vLLM.qwen2.5-7b-instruct-awq
MAX_RETRIESNoMax Self-RAG retry loops.3
WEAVIATE_URLNoURL of the Weaviate instance.
CHUNK_OVERLAPNoChild chunk overlap.150
VLLM_BASE_URLNovLLM OpenAI-compatible endpoint.http://localhost:8000/v1
QDRANT_API_KEYNoAPI key for Qdrant, if required.
EMBEDDING_MODELNoDense embedding model (1536-dim) — always via OpenRouter.openai/text-embedding-3-small
LLM_TEMPERATURENoLLM temperature (0 = deterministic).0.0
RETRIEVAL_K_MMRNoDocuments after MMR diversity filter.15
OPENROUTER_MODELNoChat model when routed through OpenRouter.openai/gpt-4.1-mini
PINECONE_API_KEYNoAPI key for Pinecone, required if VECTORDB_PROVIDER=pinecone.
RETRIEVAL_LAMBDANoMMR relevance-vs-diversity balance (0-1).0.5
PARENT_CHUNK_SIZENoParent chunk size (chars).1200
VECTORDB_PROVIDERNoVector DB provider: qdrant, pinecone, weaviate, chroma, or pgvector.qdrant
CHROMA_PERSIST_DIRNoDirectory for Chroma persistence.
OPENROUTER_API_KEYYesRequired for embeddings (via OpenRouter) and for chat when USE_VLLM=false.
RETRIEVAL_K_RERANKNoFinal documents after FlashRank.4
PINECONE_INDEX_NAMENoIndex name for Pinecone.
RETRIEVAL_K_INITIALNoHybrid search candidate pool size.20
RETRIEVAL_COLLECTIONNoCollection name for retrieval.self_rag_documents
VECTORDB_HYBRID_STRATEGYNoHybrid search strategy: rrf, weighted, semantic, two_pass.rrf
PARENT_EXPANSION_COLLECTIONNoCollection for parent expansion. Set to 'null' to disable.self_rag_parents

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

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources