Configuration Examples
The examples that follow demonstrate how you might use server properties to configure your system. A complete sample configuration file is available at examples/ai-dba-server.yaml in the project repository.
#=====================================================
# HTTP SERVER CONFIGURATION
#=====================================================
http:
# Address to listen on (host:port or :port)
address: ":8080"
# TLS/HTTPS Configuration
tls:
enabled: false
# cert_file: "/etc/ai-workbench/certs/cert.pem"
# key_file: "/etc/ai-workbench/certs/key.pem"
# chain_file: "/etc/ai-workbench/certs/chain.pem"
# Trusted reverse proxies (CIDR ranges)
# trusted_proxies:
# - "10.0.0.0/8"
# - "172.16.0.0/12"
# CORS origin for cross-origin deployments
# cors_origin: "https://workbench.example.com"
# Authentication Configuration
auth:
max_failed_attempts_before_lockout: 10
max_user_token_days: 0
rate_limit_window_minutes: 15
rate_limit_max_attempts: 10
# Local username and password login
local:
enabled: true
# Federated (OpenID Connect) login
# oidc:
# enabled: true
# issuer: "https://idp.example.com"
# client_id: "pgedge-workbench"
# client_secret_file: "/etc/pgedge/oidc-client-secret.txt"
# redirect_url: "https://workbench.example.com/api/v1/auth/oidc/callback"
audit_retention_days: 90
#=====================================================
# CONNECTION SECURITY
#=====================================================
connection_security:
allow_internal_networks: false
# allowed_hosts:
# - "db.example.com"
# - "192.168.1.0/24"
# blocked_hosts:
# - "169.254.169.254"
# ssl_cert_dir: "/etc/pgedge/ai-dba-workbench/certs"
#=====================================================
# DATABASE CONNECTION
#=====================================================
database:
host: "localhost"
port: 5432
database: "ai_workbench"
user: "postgres"
# password: ""
# password_file: "/etc/pgedge/password.txt"
sslmode: "prefer"
pool_max_conns: 20
pool_min_conns: 0
pool_max_conn_idle_time: "30m"
statement_timeout: "30s"
#=====================================================
# EMBEDDING GENERATION
#=====================================================
embedding:
enabled: false
provider: "ollama"
model: "nomic-embed-text"
ollama_url: "http://localhost:11434"
# voyage_api_key_file: "~/.voyage-api-key"
# openai_api_key_file: "~/.openai-api-key"
# gemini_api_key_file: "~/.gemini-api-key"
#=====================================================
# LLM CONFIGURATION (Chat Proxy and AI Analysis)
#=====================================================
llm:
provider: "anthropic"
model: "claude-sonnet-5"
# anthropic_api_key_file: "~/.anthropic-api-key"
# openai_api_key_file: "~/.openai-api-key"
# gemini_api_key_file: "~/.gemini-api-key"
ollama_url: "http://localhost:11434"
max_tokens: 4096
temperature: 0.7
max_iterations: 50
compact_tool_descriptions: "auto"
# reasoning_effort: "medium"
# prompt_caching: "auto"
# extra_body: {}
#=====================================================
# KNOWLEDGEBASE CONFIGURATION
#=====================================================
knowledgebase:
enabled: false
# database_path: "/usr/share/pgedge/postgres-mcp-kb/kb.db"
embedding_provider: "ollama"
embedding_model: "nomic-embed-text"
embedding_ollama_url: "http://localhost:11434"
#=====================================================
# CHAT MEMORY CONFIGURATION
#=====================================================
memory:
enabled: true
#=====================================================
# BUILT-IN TOOLS, RESOURCES, AND PROMPTS
#=====================================================
builtins:
tools:
query_database: true
get_schema_info: true
similarity_search: true
execute_explain: true
count_rows: true
list_probes: true
describe_probe: true
query_metrics: true
list_connections: true
get_alert_history: true
get_alert_rules: true
get_metric_baselines: true
get_blackouts: true
get_timeline_events: true
query_datastore: true
describe_datastore: true
generate_embedding: true
search_knowledgebase: true
store_memory: true
recall_memories: true
delete_memory: true
resources:
system_info: true
connection_info: true
#=====================================================
# PATHS AND DATA DIRECTORIES
#=====================================================
# secret_file: "/etc/ai-workbench/server.secret"
# custom_definitions_path: "/etc/ai-workbench/defs.yaml"
# data_dir: "/var/lib/ai-workbench/data"
Sample: Development Configuration
http:
address: ":8080"
tls:
enabled: false
auth:
local:
enabled: true
connection_security:
allow_internal_networks: true
database:
host: "localhost"
port: 5432
database: "ai_workbench"
user: "postgres"
sslmode: "disable"
embedding:
enabled: true
provider: "ollama"
model: "nomic-embed-text"
llm:
provider: "ollama"
model: "llama3:latest"
Sample: Production Configuration
http:
address: ":8443"
tls:
enabled: true
cert_file: "/etc/ai-workbench/certs/cert.pem"
key_file: "/etc/ai-workbench/certs/key.pem"
trusted_proxies:
- "10.0.0.0/8"
- "172.16.0.0/12"
cors_origin: "https://workbench.example.com"
auth:
local:
enabled: true
max_failed_attempts_before_lockout: 5
max_user_token_days: 90
connection_security:
allow_internal_networks: false
allowed_hosts:
- "db.internal.example.com"
blocked_hosts:
- "169.254.169.254"
database:
host: "db.internal.example.com"
port: 5432
database: "ai_workbench_prod"
user: "ai_workbench"
sslmode: "verify-full"
pool_max_conns: 20
embedding:
enabled: true
provider: "voyage"
model: "voyage-3"
voyage_api_key_file: "/etc/ai-workbench/voyage-key"
llm:
provider: "anthropic"
model: "claude-sonnet-5"
anthropic_api_key_file: "/etc/ai-workbench/ant-key"
secret_file: "/etc/ai-workbench/server.secret"
data_dir: "/var/lib/ai-workbench/data"