How to Deploy the Gateway?

Managed Deployment by Portkey for quick setup without infrastructure concerns
Local Deployment for complete control & customization
Enterprise Deployment for advanced features and dedicated support

Managed Deployment

Portkey runs this same Gateway on our API and processes billions of tokens daily. Portkey's API is in production with companies like Postman, Haptik, Turing, MultiOn, SiteGPT, and more.

Sign up for the free developer plan (10K request/month) here or discuss here for enterprise deployments.

Check out the API docs here.

Local Deployment

Do NPM or Bun Install
Run a Node.js Server
Deploy on Cloudflare Workers
Deploy using Docker
Deploy using Docker Compose
Deploy on Replit
Deploy on Zeabur

Node

$ npx @portkey-ai/gateway

Bun

$ bunx @portkey-ai/gateway

Deploy to App Stack

F5 Distributed Cloud

Create an App Stack Site
Retrieve the global kubeconfig

export DISTRIBUTED_CLOUD_TENANT=mytenantname
# find tenant id in the F5 Distributed Cloud GUI at
# Account -> Account Settings -> Tenant Overview -> Tenant ID
export DISTRIBUTED_CLOUD_TENANT_ID=mytenantnamewithextensionfoundintheconsole
# create an API token in the F5 Distributed Cloud GUI at
# Account -> Account Settings -> Credentials -> Add Credentials 
# set Credential Type to API Token, not API Certificate
export DISTRIBUTED_CLOUD_API_TOKEN=myapitoken
export DISTRIBUTED_CLOUD_SITE_NAME=appstacksitename
export DISTRIBUTED_CLOUD_NAMESPACE=mydistributedcloudnamespace
export DISTRIBUTED_CLOUD_APP_STACK_NAMESPACE=portkeyai
export DISTRIBUTED_CLOUD_APP_STACK_SITE=myappstacksite
export DISTRIBUTED_CLOUD_SERVICE_NAME=portkeyai
# adjust the expiry date to a time no more than 90 days in the future
export KUBECONFIG_CERT_EXPIRE_DATE="2021-09-14T09:02:25.547659194Z"
export PORTKEY_GATEWAY_FQDN=the.host.nameof.theservice
export PORTKEY_PROVIDER=openai
export PORTKEY_PROVIDER_AUTH_TOKEN=authorizationtoken

curl --location --request POST 'https://$DISTRIBUTED_CLOUD_TENANT.console.ves.volterra.io/api/web/namespaces/system/sites/$DISTRIBUTED_CLOUD_SITE_NAME/global-kubeconfigs' \
--header 'Authorization: APIToken $DISTRIBUTED_CLOUD_API_TOKEN' \
--header 'Access-Control-Allow-Origin: *' \
--header 'x-volterra-apigw-tenant: $DISTRIBUTED_CLOUD_TENANT'\
--data-raw '{"expirationTimestamp":"$KUBECONFIG_CERT_EXPIRE_DATE"}'

Save the response in a YAML file for later use.
more detailed instructions for retrieving the App Stack kubeconfig file

Copy the deployment YAML

wget https://raw.githubusercontent.com/Portkey-AI/gateway/main/deployment.yaml

Apply the manifest

export KUBECONFIG=path/to/downloaded/global/kubeconfig/in/step/two
# apply the file downloaded in step 3
kubectl apply -f deployment.yaml

Create Origin Pool

# create origin pool
curl --request POST \
  --url https://$DISTRIBUTED_CLOUD_TENANT.console.ves.volterra.io/api/config/namespaces/$DISTRIBUTED_CLOUD_NAMESPACE/origin_pools \
  --header 'authorization: APIToken $DISTRIBUTED_CLOUD_API_TOKEN' \
  --header 'content-type: application/json' \
  --data '{"metadata": {"name": "$DISTRIBUTED_CLOUD_SERVICE_NAME","namespace": "$DISTRIBUTED_CLOUD_NAMESPACE","labels": {},"annotations": {},"description": "","disable": false},"spec": {"origin_servers": [{"k8s_service": {"service_name": "$DISTRIBUTED_CLOUD_SERVICE_NAME.$DISTRIBUTED_CLOUD_APP_STACK_NAMESPACE","site_locator": {"site": {"tenant": "$DISTRIBUTED_CLOUD_TENANT_ID","namespace": "system","name": "$DISTRIBUTED_CLOUD_APP_STACK_SITE"}},"inside_network": {}},"labels": {}}],"no_tls": {},"port": 8787,"same_as_endpoint_port": {},"healthcheck": [],"loadbalancer_algorithm": "LB_OVERRIDE","endpoint_selection": "LOCAL_PREFERRED","advanced_options": null}}'

or use the UI 5. Create an HTTP Load Balancer, including header injection of Portkey provider and credentials

curl --request POST \
  --url https://$DISTRIBUTED_CLOUD_TENANT.console.ves.volterra.io/api/config/namespaces/$DISTRIBUTED_CLOUD_NAMESPACE/http_loadbalancers \
  --header 'authorization: APIToken $DISTRIBUTED_CLOUD_API_TOKEN' \
  --header 'content-type: application/json' \
  --data '{"metadata": {"name": "$DISTRIBUTED_CLOUD_SERVICE_NAME","namespace": "$DISTRIBUTED_CLOUD_NAMESPACE","labels": {},"annotations": {},"description": "","disable": false},"spec": {"domains": ["$PORTKEY_GATEWAY_FQDN"],"https_auto_cert": {"http_redirect": true,"add_hsts": false,"tls_config": {"default_security": {}},"no_mtls": {},"default_header": {},"enable_path_normalize": {},"port": 443,"non_default_loadbalancer": {},"header_transformation_type": {"default_header_transformation": {}},"connection_idle_timeout": 120000,"http_protocol_options": {"http_protocol_enable_v1_v2": {}}},"advertise_on_public_default_vip": {},"default_route_pools": [{"pool": {"tenant": "$DISTRIBUTED_CLOUD_TENANT_ID","namespace": "$DISTRIBUTED_CLOUD_NAMESPACE","name": "$DISTRIBUTED_CLOUD_SERVICE_NAME"},"weight": 1,"priority": 1,"endpoint_subsets": {}}],"origin_server_subset_rule_list": null,"routes": [],"cors_policy": null,"disable_waf": {},"add_location": true,"no_challenge": {},"more_option": {"request_headers_to_add": [{"name": "x-portkey-provider","value": "$PORTKEY_PROVIDER","append": false},{"name": "Authorization","value": "Bearer $PORTKEY_PROVIDER_AUTH_TOKEN","append": false}],"request_headers_to_remove": [],"response_headers_to_add": [],"response_headers_to_remove": [],"max_request_header_size": 60,"buffer_policy": null,"compression_params": null,"custom_errors": {},"javascript_info": null,"jwt": [],"idle_timeout": 30000,"disable_default_error_pages": false,"cookies_to_modify": []},"user_id_client_ip": {},"disable_rate_limit": {},"malicious_user_mitigation": null,"waf_exclusion_rules": [],"data_guard_rules": [],"blocked_clients": [],"trusted_clients": [],"api_protection_rules": null,"ddos_mitigation_rules": [],"service_policies_from_namespace": {},"round_robin": {},"disable_trust_client_ip_headers": {},"disable_ddos_detection": {},"disable_malicious_user_detection": {},"disable_api_discovery": {},"disable_bot_defense": {},"disable_api_definition": {},"disable_ip_reputation": {},"disable_client_side_defense": {},"csrf_policy": null,"graphql_rules": [],"protected_cookies": [],"host_name": "","dns_info": [],"internet_vip_info": [],"system_default_timeouts": {},"jwt_validation": null,"disable_threat_intelligence": {},"l7_ddos_action_default": {},}}'

or use the UI 6. Test the service

curl --request POST \
  --url https://$PORTKEY_GATEWAY_FQDN/v1/chat/completions \
  --header 'content-type: application/json' \
  --data '{"messages": [{"role": "user","content": "Say this might be a test."}],"max_tokens": 20,"model": "gpt-4"}'

in addition to the response headers, you should get a response body like

{
  "id": "chatcmpl-abcde......09876",
  "object": "chat.completion",
  "created": "0123456789",
  "model": "gpt-4-0321",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "This might be a test."
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 6,
    "total_tokens": 20
  },
  "system_fingerprint": null
}

Cloudflare Workers

Clone the Repository

git clone https://github.com/portkey-ai/gateway

Install the NPM Dependencies

cd gateway
npm install

Deploy (using Wrangler CLI)

npm run deploy

NodeJS Server

Clone the Repository

git clone https://github.com/portkey-ai/gateway

Install the NPM Dependencies

cd gateway
npm i
npm run build

Run the Server

node build/start-server.js

Docker

Run using Docker directly:

docker run -d -p 8787:8787 portkeyai/gateway:latest

For more information on the Docker image, check here

Docker Compose

Download Compose File from the Repository:

wget "https://raw.githubusercontent.com/Portkey-AI/gateway/main/docker-compose.yaml"

Run:

docker compose up -d

The service is now running and listening on port 8787