Gateway
- Overview
- Call any LLM
- Call the OpenAI Responses API
- Configure models & providers
- Configure functions & variants
- Create a prompt template
- Generate structured outputs
- Generate embeddings
- Batch Inference
- Episodes
- Inference Caching
- Inference-Time Optimizations
- Metrics & Feedback
- Multimodal Inference
- Retries & Fallbacks
- Streaming Inference
- Tool Use (Function Calling)
- Benchmarks
- Clients
- Configuration Reference
- Data Model
Optimization
Evaluations
Experimentation
Deployment
Deployment
Deploy Postgres (optional)
Learn how to deploy Postgres for advanced TensorZero features.
Most TensorZero deployments will not require Postgres.
Deploy
You can self-host Postgres or use a managed service (e.g. AWS RDS, Supabase, PlanetScale).Follow the deployment instructions for your chosen service.Internally, we test TensorZero using self-hosted Postgres 14.If you find any compatibility issues, please open a detailedGitHub Discussion.
Configure
Connect to Postgres
To configure TensorZero to use Postgres, set theTENSORZERO_POSTGRES_URL environment variable with your Postgres connection details..env
TENSORZERO_POSTGRES_URL="postgres://[username]:[password]@[hostname]:[port]/[database]"# Example:TENSORZERO_POSTGRES_URL="postgres://myuser:mypass@localhost:5432/tensorzero"Apply Postgres migrations
Unlike with ClickHouse,TensorZero does not automatically apply Postgres migrations.You must apply migrations manually withgateway --run-postgres-migrations.- Docker Compose
- Docker
If you’ve configured the gateway with Docker Compose, you can run the migrations with:SeeDeploy the TensorZero Gateway for more details.
docker-compose run --rm gateway --run-postgres-migrationsIn most other cases, you can run the migrations with:
docker run --rm --network host \ -e TENSORZERO_POSTGRES_URL \ tensorzero/gateway --run-postgres-migrations⌘I