Skip to main content

๐Ÿ“– Reference

๐Ÿ“– Reference

Reference

The technical details behind every knob, endpoint, and configuration option.

HridaAI is highly configurable. This section is the canonical source of truth for environment variables, API endpoints, network architecture, reverse proxy setups, and production monitoring. Whether you're tuning a single setting or architecting a multi-node deployment, start here.

โš™๏ธ
Environment Variable Configuration

Every flag, path, and secret HridaAI reads at startup, in one place. Over 200 environment variables control authentication, model routing, storage, logging, and more. Understand ConfigVar behavior, troubleshoot ignored settings, and find the exact variable you need.

๐Ÿ”Authentication & signup โ€” ENABLE_SIGNUP, ENABLE_LOGIN_FORM, HRIDAAI_ADMIN_EMAIL, OIDC/LDAP/SCIM
๐Ÿค–Model connections โ€” Ollama, OpenAI, direct pipeline URLs, timeouts, load balancing
๐Ÿ’พStorage & databases โ€” SQLite, PostgreSQL, S3/GCS/Azure Blob, Redis
๐Ÿ“ŠLogging & audit โ€” GLOBAL_LOG_LEVEL, JSON logging, audit log levels and paths
๐Ÿง RAG & retrieval โ€” Chunk size, overlap, embedding engines, reranking, vector DB selection
Browse all environment variables โ†’โ†’
๐Ÿ”Œ
API Endpoints

OpenAI-compatible and Anthropic-compatible APIs, plus RAG, file management, and Ollama proxy routes. HridaAI exposes a full REST API authenticated via Bearer tokens or JWTs. Use the same endpoints the web UI uses to build automations, chatbots, and custom integrations.

๐Ÿ’ฌChat completions โ€” POST /api/chat/completions, OpenAI-compatible
๐Ÿ”ฎAnthropic messages โ€” POST /api/v1/messages, works with the Anthropic SDK and Claude Code
๐Ÿฆ™Ollama proxy โ€” /ollama/api/*, passthrough to native Ollama endpoints
๐Ÿ“„File & knowledge โ€” Upload files, build knowledge collections, query via RAG
๐Ÿ”งFilters (inlet/stream/outlet) โ€” Inlet, stream, and outlet hooks for every request
Explore the API โ†’โ†’
๐Ÿ”’
HTTPS Configuration

Terminate TLS in front of HridaAI with Nginx, Caddy, or HAProxy. Step-by-step reverse proxy configurations for securing your deployment with HTTPS. Each guide includes certificate handling, WebSocket support, and production-hardened settings.

๐ŸŸขNginx โ€” Full config with SSL termination, WebSocket proxying, and headers
โšกCaddy โ€” Automatic HTTPS with minimal configuration
๐Ÿ”„HAProxy โ€” Enterprise-grade load balancing with TLS offloading
โ˜๏ธCloudflare Tunnel โ€” Expose HridaAI securely without opening ports
๐Ÿ”’Tailscale โ€” Private encrypted access across your devices, no public exposure
๐Ÿงชngrok โ€” Instant HTTPS tunnels for development and testing
Set up HTTPS โ†’โ†’
๐Ÿ”‘
API Keys

Programmatic access to HridaAI for scripts, bots, and integrations. Generate personal access tokens that let external code call the same endpoints the web UI uses. Each key inherits the permissions of the user who created it.

๐Ÿ”Bearer token auth โ€” Standard Authorization: Bearer header, works with any HTTP client
๐Ÿ›ก๏ธScoped to user โ€” Key inherits your role and group permissions
๐ŸšซEndpoint restrictions โ€” Optionally limit which API routes a key can access
Set up API keys โ†’โ†’
๐Ÿ“Š
Monitoring

Observe your deployment with Uptime Kuma, OpenTelemetry, Prometheus, and Grafana. Production monitoring guides covering health checks, model connectivity verification, distributed tracing, metrics, and structured logs. Integrate with your existing observability stack or set up a new one from scratch.

โœ…Health checks โ€” Basic, model connectivity, and deep health checks with Uptime Kuma
๐Ÿ“กOpenTelemetry โ€” Traces, metrics, and logs piped to any OTLP-compatible backend
๐Ÿ“ˆDashboards โ€” Prometheus + Grafana for real-time system and model metrics
Set up monitoring โ†’โ†’
๐ŸŒ
Network Diagrams

See how HridaAI, Ollama, and Docker communicate across different deployment topologies. Visual C4 diagrams covering host networking, Docker Compose stacks, separate networks, and platform-specific differences. Useful for debugging connectivity issues or planning your architecture.

๐Ÿ–ฅ๏ธmacOS / Windows โ€” Host Ollama, Compose stack, separate networks, host-network pitfalls
๐ŸงLinux โ€” Same topologies with Linux-specific networking behavior
View network diagrams โ†’โ†’
This content is for informational purposes only and does not constitute a warranty, guarantee, or contractual commitment. Hrida AI is proprietary software owned by Zlabs Innovation, provided "as is." See your license for applicable terms. ยฉ 2026 Zlabs Innovation. All rights reserved.