Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
RUNS_DIRYesDirectory for run traces. Default: ./runs
QDRANT_URLYesURL for Qdrant vector database. Default: http://localhost:6333
UPLOAD_DIRYesDirectory for uploaded files. Default: ./data/uploads
TOP_K_RERANKYesNumber of chunks to keep after reranking. Default: 5
RERANKER_MODELYesCross-encoder reranker model. Default: cross-encoder/ms-marco-MiniLM-L-6-v2
TAVILY_API_KEYNoAPI key for Tavily web search. Optional; without it, web search is unavailable.
TOP_K_RETRIEVEYesNumber of candidates to retrieve from vector search. Default: 20
OLLAMA_BASE_URLYesBase URL for Ollama server. Default: http://localhost:11434
OLLAMA_LLM_MODELYesOllama LLM model to use for generation. Default: llama3.1
LANGCHAIN_API_KEYNoAPI key for LangSmith tracing. Optional.
LANGCHAIN_PROJECTNoLangSmith project name. Default: docagent. Optional.
QDRANT_COLLECTIONYesQdrant collection name. Default: docagent_chunks
OLLAMA_EMBED_MODELYesOllama embedding model to use. Default: nomic-embed-text

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