Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
QUAESTIO_LLM_MODELNoModel name for the primary LLM backend.
QUAESTIO_DOCKER_PATHNoPath to the Docker executable.
QUAESTIO_LLM_API_KEYNoAPI key for the primary LLM backend.
QUAESTIO_LLM_BASE_URLNoBase URL of the primary LLM API endpoint.https://integrate.api.nvidia.com/v1
QUAESTIO_TESSERACT_PATHNoPath to the Tesseract OCR executable.
QUAESTIO_EMBEDDING_MODELNoModel name for embeddings.
QUAESTIO_TRANSLATION_OCRNoWhether to use OCR for translation. Options: auto, never, required.auto
QUAESTIO_TRANSLATION_MODENoTranslation mode. Options: never, auto, required.auto
QUAESTIO_TRANSLATOR_MODELNoModel name for the translation backend.
QUAESTIO_EMBEDDING_API_KEYNoAPI key for the embedding backend.
QUAESTIO_EMBEDDING_BASE_URLNoBase URL of the embedding API endpoint.
QUAESTIO_TRANSLATOR_API_KEYNoAPI key for the translation backend.
QUAESTIO_VERIFIER_LLM_MODELNoModel name for the semantic verifier backend.
QUAESTIO_KNOWLEDGE_BASE_PATHNoPath to the local knowledge base JSON file../data/knowledge.json
QUAESTIO_LLM_TIMEOUT_SECONDSNoTimeout in seconds for primary LLM requests.45
QUAESTIO_SECONDARY_LLM_MODELNoModel name for the secondary LLM backend.
QUAESTIO_TRANSLATOR_BASE_URLNoBase URL of the translation LLM API endpoint.
QUAESTIO_SANDBOX_PYTHON_IMAGENoDocker image used for running Python code in the sandbox.python:3.12-slim
QUAESTIO_VERIFIER_LLM_API_KEYNoAPI key for the semantic verifier backend.
QUAESTIO_SECONDARY_LLM_API_KEYNoAPI key for the secondary LLM backend.
QUAESTIO_VERIFIER_LLM_BASE_URLNoBase URL of the independent semantic verifier LLM API endpoint.
QUAESTIO_SECONDARY_LLM_BASE_URLNoBase URL of the secondary LLM API endpoint used for consensus.
QUAESTIO_TRANSLATION_OCR_LANGUAGENoOCR language codes, e.g. por+eng.por+eng
QUAESTIO_EMBEDDING_TIMEOUT_SECONDSNoTimeout in seconds for embedding requests.30
QUAESTIO_TRANSLATOR_TIMEOUT_SECONDSNoTimeout in seconds for translation requests.30
QUAESTIO_TRANSLATION_TARGET_LANGUAGENoTarget language code for translation.en
QUAESTIO_VERIFIER_LLM_TIMEOUT_SECONDSNoTimeout in seconds for semantic verifier requests.45

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