Schema | Conversational Analysis Engine

Conversational Analysis Engine

Describes the environment variables required to run the server.

Name	Required	Description
`DB_HOST`	No	PostgreSQL host. Default: postgres (Docker)
`DB_NAME`	No	PostgreSQL database name. Default: conversation_analysis
`DB_PORT`	No	PostgreSQL port. Default: 5432
`DB_USER`	No	PostgreSQL user. Default: cae_user
`DB_SECRET`	No	PostgreSQL password. Default: cae_password
`LOG_LEVEL`	No	Logging level. Default: INFO
`REDIS_HOST`	No	Redis host. Default: redis (Docker)
`REDIS_PORT`	No	Redis port. Default: 6379
`LLM_API_KEY`	Yes	Your OpenAI API key or alternative provider API key.
`LLM_MODEL_NAME`	No	Model name to use. Default: o3-mini
`LLM_API_BASE_URL`	No	Base URL for the LLM API. Default: https://api.openai.com/v1
`LLM_TIMEOUT_SECONDS`	No	Timeout for LLM calls in seconds. Default: 600
`EMBEDDING_MODEL_NAME`	No	Embedding model name. Default: text-embedding-3-large
`EMBEDDING_MODEL_API_KEY`	No	API key for embedding model (optional, enables semantic caching).
`EMBEDDING_MODEL_BASE_URL`	No	Base URL for embedding model. Default: https://api.openai.com/v1
`DISABLE_PROMETHEUS_METRICS`	No	Set to 'true' to disable Prometheus metrics. Default: 'false'

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.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivityInactive

ResponsivenessNo issues