@n8n-as-code/skills 2.2.1-next.151 → 2.2.1

package/dist/assets/n8n-docs-complete.json

@@ -1,5 +1,5 @@
 {
-  "generatedAt": "2026-05-21T21:20:28.554Z",
+  "generatedAt": "2026-05-21T21:34:02.863Z",
   "version": "1.0.0",
   "sourceUrl": "https://docs.n8n.io/llms.txt",
   "totalPages": 1284,
@@ -17906,7 +17906,7 @@
       "nodeName": null,
       "nodeType": null,
       "content": {
-        "markdown": "# Hosting n8n on Google Kubernetes Engine\n\nGoogle Cloud offers several options suitable for hosting n8n, including Cloud Run (optimized for running containers), Compute Engine (VMs), and Kubernetes Engine (containers running with Kubernetes).\n\nThis guide uses the Google Kubernetes Engine (GKE) as the hosting option. If you want to use Cloud Run, refer to [these instructions](../google-cloud-run/).\n\nMost of the steps in this guide use the Google Cloud UI, but you can also use the [gcloud command line tool](https://cloud.google.com/sdk/gcloud/) instead to undertake all the steps.\n\n## Prerequisites\n\n- The [gcloud command line tool](https://cloud.google.com/sdk/gcloud/)\n- The [gke-gcloud-auth-plugin](https://cloud.google.com/blog/products/containers-kubernetes/kubectl-auth-changes-in-gke) (install the gcloud CLI first)\n\nSelf-hosting knowledge prerequisites\n\nSelf-hosting n8n requires technical knowledge, including:\n\n- Setting up and configuring servers and containers\n- Managing application resources and scaling\n- Securing servers and applications\n- Configuring n8n\n\nn8n recommends self-hosting for expert users. Mistakes can lead to data loss, security issues, and downtime. If you aren't experienced at managing servers, n8n recommends [n8n Cloud](https://n8n.io/cloud/).\n\nStable and Beta versions\n\nn8n releases a new minor version most weeks. The `stable` version is for production use. `beta` is the most recent release. The `beta` version may be unstable. To report issues, use the [forum](https://community.n8n.io/c/questions/12).\n\nCurrent `stable`: 2.21.5 Current `beta`: 2.22.0\n\n## Create project\n\nGCP encourages you to create projects to logically organize resources and configuration. Create a new project for your n8n deployment from your Google Cloud Console: select the project dropdown menu and then the **NEW PROJECT** button. Then select the newly created project. As you follow the other steps in this guide, make sure you have the correct project selected.\n\n## Enable the Kubernetes Engine API\n\nGKE isn't enabled by default. Search for \"Kubernetes\" in the top search bar and select \"Kubernetes Engine\" from the results.\n\nSelect **ENABLE** to enable the Kubernetes Engine API for this project.\n\n## Create a cluster\n\nFrom the [GKE service page](https://console.cloud.google.com/kubernetes/list/overview), select **Clusters** > **CREATE**. Make sure you select the \"Standard\" cluster option, n8n doesn't work with an \"Autopilot\" cluster. You can leave the cluster configuration on defaults unless there's anything specifically you need to change, such as location.\n\n## Set Kubectl context\n\nThe rest of the steps in this guide require you to set the GCP instance as the Kubectl context. You can find the connection details for a cluster instance by opening its details page and selecting **CONNECT**. The displayed code snippet shows a connection string for the gcloud CLI tool. Paste and run the code snippet in the gcloud CLI to change your local Kubernetes settings to use the new gcloud cluster.\n\n## Clone configuration repository\n\nKubernetes and n8n require a series of configuration files. You can clone these from [this repository](https://github.com/n8n-io/n8n-hosting) locally. The following steps explain the file configuration and how to add your information.\n\nClone the repository with the following command:\n\n```\ngit clone https://github.com/n8n-io/n8n-hosting.git\n```\n\nAnd change directory:\n\n```\ncd n8n-hosting/kubernetes\n```\n\n## Configure Postgres\n\nFor larger scale n8n deployments, Postgres provides a more robust database backend than SQLite.\n\n### Create a volume for persistent storage\n\nTo maintain data between pod restarts, the Postgres deployment needs a persistent volume. Running Postgres on GCP requires a specific Kubernetes Storage Class. You can read [this guide](https://cloud.google.com/architecture/deploying-highly-available-postgresql-with-gke) for specifics, but the `storage.yaml` manifest creates it for you. You may want to change the regions to create the storage in under the `allowedTopologies` > `matchedLabelExpressions` > `values` key. By default, they're set to `us-central`.\n\n```\n…\nallowedTopologies:\n  - matchLabelExpressions:\n      - key: failure-domain.beta.kubernetes.io/zone\n        values:\n          - us-central1-b\n          - us-central1-c\n```\n\n### Postgres environment variables\n\nPostgres needs some environment variables set to pass to the application running in the containers.\n\nThe example `postgres-secret.yaml` file contains placeholders you need to replace with your own values. Postgres will use these details when creating the database..\n\nThe `postgres-deployment.yaml` manifest then uses the values from this manifest file to send to the application pods.\n\n## Configure n8n\n\n### Create a volume for file storage\n\nWhile not essential for running n8n, using persistent volumes is required for:\n\n- Using nodes that interact with files, such as the binary data node.\n- If you want to persist [manual n8n encryption keys](../../../configuration/environment-variables/deployment/) between restarts. This saves a file containing the key into file storage during startup.\n\nThe `n8n-claim0-persistentvolumeclaim.yaml` manifest creates this, and the n8n Deployment mounts that claim in the `volumes` section of the `n8n-deployment.yaml` manifest.\n\n```\n…\nvolumes:\n  - name: n8n-claim0\n    persistentVolumeClaim:\n      claimName: n8n-claim0\n…\n```\n\n### Pod resources\n\n[Kubernetes lets you](https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/) optionally specify the minimum resources application containers need and the limits they can run to. The example YAML files cloned above contain the following in the `resources` section of the `n8n-deployment.yaml` and `postgres-deployment.yaml` files:\n\n```\n��\nresources:\n  requests:\n    memory: \"250Mi\"\n  limits:\n    memory: \"500Mi\"\n…\n```\n\nThis defines a minimum of 250mb per container, a maximum of 500mb, and lets Kubernetes handle CPU. You can change these values to match your own needs. As a guide, here are the resources values for the n8n cloud offerings:\n\n- **Start**: 320mb RAM, 10 millicore CPU burstable\n- **Pro (10k executions)**: 640mb RAM, 20 millicore CPU burstable\n- **Pro (50k executions)**: 1280mb RAM, 80 millicore CPU burstable\n\n### Optional: Environment variables\n\nYou can configure n8n settings and behaviors using environment variables.\n\nCreate an `n8n-secret.yaml` file. Refer to [Environment variables](../../../configuration/environment-variables/) for n8n environment variables details.\n\n## Deployments\n\nThe two deployment manifests (`n8n-deployment.yaml` and `postgres-deployment.yaml`) define the n8n and Postgres applications to Kubernetes.\n\nThe manifests define the following:\n\n- Send the environment variables defined to each application pod\n- Define the container image to use\n- Set resource consumption limits with the `resources` object\n- The `volumes` defined earlier and `volumeMounts` to define the path in the container to mount volumes.\n- Scaling and restart policies. The example manifests define one instance of each pod. You should change this to meet your needs.\n\n## Services\n\nThe two service manifests (`postgres-service.yaml` and `n8n-service.yaml`) expose the services to the outside world using the Kubernetes load balancer using ports 5432 and 5678 respectively.\n\n## Send to Kubernetes cluster\n\nSend all the manifests to the cluster with the following command:\n\n```\nkubectl apply -f .\n```\n\nNamespace error\n\nYou may see an error message about not finding an \"n8n\" namespace as that resources isn't ready yet. You can run the same command again, or apply the namespace manifest first with the following command:\n\n```\nkubectl apply -f namespace.yaml\n```\n\n## Set up DNS\n\nn8n typically operates on a subdomain. Create a DNS record with your provider for the subdomain and point it to the IP address of the n8n service. Find the IP address of the n8n service from the **Services & Ingress** menu item of the cluster you want to use under the **Endpoints** column.\n\nGKE and IP addresses\n\n[Read this GKE tutorial](https://cloud.google.com/kubernetes-engine/docs/tutorials/configuring-domain-name-static-ip#configuring_your_domain_name_records) for more details on how reserved IP addresses work with GKE and Kubernetes resources.\n\n## Delete resources\n\nRemove the resources created by the manifests with the following command:\n\n```\nkubectl delete -f .\n```\n\n## Next steps\n\n- Learn more about [configuring](../../../configuration/environment-variables/) and [scaling](../../../scaling/overview/) n8n.\n- Or explore using n8n: try the [Quickstarts](../../../../try-it-out/).\n",
+        "markdown": "# Hosting n8n on Google Kubernetes Engine\n\nGoogle Cloud offers several options suitable for hosting n8n, including Cloud Run (optimized for running containers), Compute Engine (VMs), and Kubernetes Engine (containers running with Kubernetes).\n\nThis guide uses the Google Kubernetes Engine (GKE) as the hosting option. If you want to use Cloud Run, refer to [these instructions](../google-cloud-run/).\n\nMost of the steps in this guide use the Google Cloud UI, but you can also use the [gcloud command line tool](https://cloud.google.com/sdk/gcloud/) instead to undertake all the steps.\n\n## Prerequisites\n\n- The [gcloud command line tool](https://cloud.google.com/sdk/gcloud/)\n- The [gke-gcloud-auth-plugin](https://cloud.google.com/blog/products/containers-kubernetes/kubectl-auth-changes-in-gke) (install the gcloud CLI first)\n\nSelf-hosting knowledge prerequisites\n\nSelf-hosting n8n requires technical knowledge, including:\n\n- Setting up and configuring servers and containers\n- Managing application resources and scaling\n- Securing servers and applications\n- Configuring n8n\n\nn8n recommends self-hosting for expert users. Mistakes can lead to data loss, security issues, and downtime. If you aren't experienced at managing servers, n8n recommends [n8n Cloud](https://n8n.io/cloud/).\n\nStable and Beta versions\n\nn8n releases a new minor version most weeks. The `stable` version is for production use. `beta` is the most recent release. The `beta` version may be unstable. To report issues, use the [forum](https://community.n8n.io/c/questions/12).\n\nCurrent `stable`: 2.21.5 Current `beta`: 2.22.0\n\n## Create project\n\nGCP encourages you to create projects to logically organize resources and configuration. Create a new project for your n8n deployment from your Google Cloud Console: select the project dropdown menu and then the **NEW PROJECT** button. Then select the newly created project. As you follow the other steps in this guide, make sure you have the correct project selected.\n\n## Enable the Kubernetes Engine API\n\nGKE isn't enabled by default. Search for \"Kubernetes\" in the top search bar and select \"Kubernetes Engine\" from the results.\n\nSelect **ENABLE** to enable the Kubernetes Engine API for this project.\n\n## Create a cluster\n\nFrom the [GKE service page](https://console.cloud.google.com/kubernetes/list/overview), select **Clusters** > **CREATE**. Make sure you select the \"Standard\" cluster option, n8n doesn't work with an \"Autopilot\" cluster. You can leave the cluster configuration on defaults unless there's anything specifically you need to change, such as location.\n\n## Set Kubectl context\n\nThe rest of the steps in this guide require you to set the GCP instance as the Kubectl context. You can find the connection details for a cluster instance by opening its details page and selecting **CONNECT**. The displayed code snippet shows a connection string for the gcloud CLI tool. Paste and run the code snippet in the gcloud CLI to change your local Kubernetes settings to use the new gcloud cluster.\n\n## Clone configuration repository\n\nKubernetes and n8n require a series of configuration files. You can clone these from [this repository](https://github.com/n8n-io/n8n-hosting) locally. The following steps explain the file configuration and how to add your information.\n\nClone the repository with the following command:\n\n```\ngit clone https://github.com/n8n-io/n8n-hosting.git\n```\n\nAnd change directory:\n\n```\ncd n8n-hosting/kubernetes\n```\n\n## Configure Postgres\n\nFor larger scale n8n deployments, Postgres provides a more robust database backend than SQLite.\n\n### Create a volume for persistent storage\n\nTo maintain data between pod restarts, the Postgres deployment needs a persistent volume. Running Postgres on GCP requires a specific Kubernetes Storage Class. You can read [this guide](https://cloud.google.com/architecture/deploying-highly-available-postgresql-with-gke) for specifics, but the `storage.yaml` manifest creates it for you. You may want to change the regions to create the storage in under the `allowedTopologies` > `matchedLabelExpressions` > `values` key. By default, they're set to `us-central`.\n\n```\n…\nallowedTopologies:\n  - matchLabelExpressions:\n      - key: failure-domain.beta.kubernetes.io/zone\n        values:\n          - us-central1-b\n          - us-central1-c\n```\n\n### Postgres environment variables\n\nPostgres needs some environment variables set to pass to the application running in the containers.\n\nThe example `postgres-secret.yaml` file contains placeholders you need to replace with your own values. Postgres will use these details when creating the database..\n\nThe `postgres-deployment.yaml` manifest then uses the values from this manifest file to send to the application pods.\n\n## Configure n8n\n\n### Create a volume for file storage\n\nWhile not essential for running n8n, using persistent volumes is required for:\n\n- Using nodes that interact with files, such as the binary data node.\n- If you want to persist [manual n8n encryption keys](../../../configuration/environment-variables/deployment/) between restarts. This saves a file containing the key into file storage during startup.\n\nThe `n8n-claim0-persistentvolumeclaim.yaml` manifest creates this, and the n8n Deployment mounts that claim in the `volumes` section of the `n8n-deployment.yaml` manifest.\n\n```\n…\nvolumes:\n  - name: n8n-claim0\n    persistentVolumeClaim:\n      claimName: n8n-claim0\n…\n```\n\n### Pod resources\n\n[Kubernetes lets you](https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/) optionally specify the minimum resources application containers need and the limits they can run to. The example YAML files cloned above contain the following in the `resources` section of the `n8n-deployment.yaml` and `postgres-deployment.yaml` files:\n\n```\n…\nresources:\n  requests:\n    memory: \"250Mi\"\n  limits:\n    memory: \"500Mi\"\n…\n```\n\nThis defines a minimum of 250mb per container, a maximum of 500mb, and lets Kubernetes handle CPU. You can change these values to match your own needs. As a guide, here are the resources values for the n8n cloud offerings:\n\n- **Start**: 320mb RAM, 10 millicore CPU burstable\n- **Pro (10k executions)**: 640mb RAM, 20 millicore CPU burstable\n- **Pro (50k executions)**: 1280mb RAM, 80 millicore CPU burstable\n\n### Optional: Environment variables\n\nYou can configure n8n settings and behaviors using environment variables.\n\nCreate an `n8n-secret.yaml` file. Refer to [Environment variables](../../../configuration/environment-variables/) for n8n environment variables details.\n\n## Deployments\n\nThe two deployment manifests (`n8n-deployment.yaml` and `postgres-deployment.yaml`) define the n8n and Postgres applications to Kubernetes.\n\nThe manifests define the following:\n\n- Send the environment variables defined to each application pod\n- Define the container image to use\n- Set resource consumption limits with the `resources` object\n- The `volumes` defined earlier and `volumeMounts` to define the path in the container to mount volumes.\n- Scaling and restart policies. The example manifests define one instance of each pod. You should change this to meet your needs.\n\n## Services\n\nThe two service manifests (`postgres-service.yaml` and `n8n-service.yaml`) expose the services to the outside world using the Kubernetes load balancer using ports 5432 and 5678 respectively.\n\n## Send to Kubernetes cluster\n\nSend all the manifests to the cluster with the following command:\n\n```\nkubectl apply -f .\n```\n\nNamespace error\n\nYou may see an error message about not finding an \"n8n\" namespace as that resources isn't ready yet. You can run the same command again, or apply the namespace manifest first with the following command:\n\n```\nkubectl apply -f namespace.yaml\n```\n\n## Set up DNS\n\nn8n typically operates on a subdomain. Create a DNS record with your provider for the subdomain and point it to the IP address of the n8n service. Find the IP address of the n8n service from the **Services & Ingress** menu item of the cluster you want to use under the **Endpoints** column.\n\nGKE and IP addresses\n\n[Read this GKE tutorial](https://cloud.google.com/kubernetes-engine/docs/tutorials/configuring-domain-name-static-ip#configuring_your_domain_name_records) for more details on how reserved IP addresses work with GKE and Kubernetes resources.\n\n## Delete resources\n\nRemove the resources created by the manifests with the following command:\n\n```\nkubectl delete -f .\n```\n\n## Next steps\n\n- Learn more about [configuring](../../../configuration/environment-variables/) and [scaling](../../../scaling/overview/) n8n.\n- Or explore using n8n: try the [Quickstarts](../../../../try-it-out/).\n",
         "excerpt": "# Hosting n8n on Google Kubernetes Engine  Google Cloud offers several options suitable for hosting n8n, including Cloud Run (optimized for running containers), Compute Engine (VMs), and Kubernetes Engine (containers running with Kubernetes).  This guide uses the Google Kubernetes Engine (GKE) as the hosting option. If you want to use Cloud Run, refer to [these instructions](../google-cloud-run/).  Most of the steps in this guide use the Google Cloud UI, but you can also use the [gcloud command...",
         "sections": [
           {
@@ -17954,11 +17954,11 @@
         "codeExamples": 8,
         "complexity": "intermediate",
         "readingTime": "6 min",
-        "contentLength": 8655,
+        "contentLength": 8654,
         "relatedPages": []
       },
       "searchIndex": {
-        "fullText": "google kubernetes engine # hosting n8n on google kubernetes engine\n\ngoogle cloud offers several options suitable for hosting n8n, including cloud run (optimized for running containers), compute engine (vms), and kubernetes engine (containers running with kubernetes).\n\nthis guide uses the google kubernetes engine (gke) as the hosting option. if you want to use cloud run, refer to [these instructions](../google-cloud-run/).\n\nmost of the steps in this guide use the google cloud ui, but you can also use the [gcloud command line tool](https://cloud.google.com/sdk/gcloud/) instead to undertake all the steps.\n\n## prerequisites\n\n- the [gcloud command line tool](https://cloud.google.com/sdk/gcloud/)\n- the [gke-gcloud-auth-plugin](https://cloud.google.com/blog/products/containers-kubernetes/kubectl-auth-changes-in-gke) (install the gcloud cli first)\n\nself-hosting knowledge prerequisites\n\nself-hosting n8n requires technical knowledge, including:\n\n- setting up and configuring servers and containers\n- managing application resources and scaling\n- securing servers and applications\n- configuring n8n\n\nn8n recommends self-hosting for expert users. mistakes can lead to data loss, security issues, and downtime. if you aren't experienced at managing servers, n8n recommends [n8n cloud](https://n8n.io/cloud/).\n\nstable and beta versions\n\nn8n releases a new minor version most weeks. the `stable` version is for production use. `beta` is the most recent release. the `beta` version may be unstable. to report issues, use the [forum](https://community.n8n.io/c/questions/12).\n\ncurrent `stable`: 2.21.5 current `beta`: 2.22.0\n\n## create project\n\ngcp encourages you to create projects to logically organize resources and configuration. create a new project for your n8n deployment from your google cloud console: select the project dropdown menu and then the **new project** button. then select the newly created project. as you follow the other steps in this guide, make sure you have the correct project selected.\n\n## enable the kubernetes engine api\n\ngke isn't enabled by default. search for \"kubernetes\" in the top search bar and select \"kubernetes engine\" from the results.\n\nselect **enable** to enable the kubernetes engine api for this project.\n\n## create a cluster\n\nfrom the [gke service page](https://console.cloud.google.com/kubernetes/list/overview), select **clusters** > **create**. make sure you select the \"standard\" cluster option, n8n doesn't work with an \"autopilot\" cluster. you can leave the cluster configuration on defaults unless there's anything specifically you need to change, such as location.\n\n## set kubectl context\n\nthe rest of the steps in this guide require you to set the gcp instance as the kubectl context. you can find the connection details for a cluster instance by opening its details page and selecting **connect**. the displayed code snippet shows a connection string for the gcloud cli tool. paste and run the code snippet in the gcloud cli to change your local kubernetes settings to use the new gcloud cluster.\n\n## clone configuration repository\n\nkubernetes and n8n require a series of configuration files. you can clone these from [this repository](https://github.com/n8n-io/n8n-hosting) locally. the following steps explain the file configuration and how to add your information.\n\nclone the repository with the following command:\n\n```\ngit clone https://github.com/n8n-io/n8n-hosting.git\n```\n\nand change directory:\n\n```\ncd n8n-hosting/kubernetes\n```\n\n## configure postgres\n\nfor larger scale n8n deployments, postgres provides a more robust database backend than sqlite.\n\n### create a volume for persistent storage\n\nto maintain data between pod restarts, the postgres deployment needs a persistent volume. running postgres on gcp requires a specific kubernetes storage class. you can read [this guide](https://cloud.google.com/architecture/deploying-highly-available-postgresql-with-gke) for specifics, but the `storage.yaml` manifest creates it for you. you may want to change the regions to create the storage in under the `allowedtopologies` > `matchedlabelexpressions` > `values` key. by default, they're set to `us-central`.\n\n```\n…\nallowedtopologies:\n  - matchlabelexpressions:\n      - key: failure-domain.beta.kubernetes.io/zone\n        values:\n          - us-central1-b\n          - us-central1-c\n```\n\n### postgres environment variables\n\npostgres needs some environment variables set to pass to the application running in the containers.\n\nthe example `postgres-secret.yaml` file contains placeholders you need to replace with your own values. postgres will use these details when creating the database..\n\nthe `postgres-deployment.yaml` manifest then uses the values from this manifest file to send to the application pods.\n\n## configure n8n\n\n### create a volume for file storage\n\nwhile not essential for running n8n, using persistent volumes is required for:\n\n- using nodes that interact with files, such as the binary data node.\n- if you want to persist [manual n8n encryption keys](../../../configuration/environment-variables/deployment/) between restarts. this saves a file containing the key into file storage during startup.\n\nthe `n8n-claim0-persistentvolumeclaim.yaml` manifest creates this, and the n8n deployment mounts that claim in the `volumes` section of the `n8n-deployment.yaml` manifest.\n\n```\n…\nvolumes:\n  - name: n8n-claim0\n    persistentvolumeclaim:\n      claimname: n8n-claim0\n…\n```\n\n### pod resources\n\n[kubernetes lets you](https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/) optionally specify the minimum resources application containers need and the limits they can run to. the example yaml files cloned above contain the following in the `resources` section of the `n8n-deployment.yaml` and `postgres-deployment.yaml` files:\n\n```\n��\nresources:\n  requests:\n    memory: \"250mi\"\n  limits:\n    memory: \"500mi\"\n…\n```\n\nthis defines a minimum of 250mb per container, a maximum of 500mb, and lets kubernetes handle cpu. you can change these values to match your own needs. as a guide, here are the resources values for the n8n cloud offerings:\n\n- **start**: 320mb ram, 10 millicore cpu burstable\n- **pro (10k executions)**: 640mb ram, 20 millicore cpu burstable\n- **pro (50k executions)**: 1280mb ram, 80 millicore cpu burstable\n\n### optional: environment variables\n\nyou can configure n8n settings and behaviors using environment variables.\n\ncreate an `n8n-secret.yaml` file. refer to [environment variables](../../../configuration/environment-variables/) for n8n environment variables details.\n\n## deployments\n\nthe two deployment manifests (`n8n-deployment.yaml` and `postgres-deployment.yaml`) define the n8n and postgres applications to kubernetes.\n\nthe manifests define the following:\n\n- send the environment variables defined to each application pod\n- define the container image to use\n- set resource consumption limits with the `resources` object\n- the `volumes` defined earlier and `volumemounts` to define the path in the container to mount volumes.\n- scaling and restart policies. the example manifests define one instance of each pod. you should change this to meet your needs.\n\n## services\n\nthe two service manifests (`postgres-service.yaml` and `n8n-service.yaml`) expose the services to the outside world using the kubernetes load balancer using ports 5432 and 5678 respectively.\n\n## send to kubernetes cluster\n\nsend all the manifests to the cluster with the following command:\n\n```\nkubectl apply -f .\n```\n\nnamespace error\n\nyou may see an error message about not finding an \"n8n\" namespace as that resources isn't ready yet. you can run the same command again, or apply the namespace manifest first with the following command:\n\n```\nkubectl apply -f namespace.yaml\n```\n\n## set up dns\n\nn8n typically operates on a subdomain. create a dns record with your provider for the subdomain and point it to the ip address of the n8n service. find the ip address of the n8n service from the **services & ingress** menu item of the cluster you want to use under the **endpoints** column.\n\ngke and ip addresses\n\n[read this gke tutorial](https://cloud.google.com/kubernetes-engine/docs/tutorials/configuring-domain-name-static-ip#configuring_your_domain_name_records) for more details on how reserved ip addresses work with gke and kubernetes resources.\n\n## delete resources\n\nremove the resources created by the manifests with the following command:\n\n```\nkubectl delete -f .\n```\n\n## next steps\n\n- learn more about [configuring](../../../configuration/environment-variables/) and [scaling](../../../scaling/overview/) n8n.\n- or explore using n8n: try the [quickstarts](../../../../try-it-out/).\n hosting n8n on google kubernetes engine",
+        "fullText": "google kubernetes engine # hosting n8n on google kubernetes engine\n\ngoogle cloud offers several options suitable for hosting n8n, including cloud run (optimized for running containers), compute engine (vms), and kubernetes engine (containers running with kubernetes).\n\nthis guide uses the google kubernetes engine (gke) as the hosting option. if you want to use cloud run, refer to [these instructions](../google-cloud-run/).\n\nmost of the steps in this guide use the google cloud ui, but you can also use the [gcloud command line tool](https://cloud.google.com/sdk/gcloud/) instead to undertake all the steps.\n\n## prerequisites\n\n- the [gcloud command line tool](https://cloud.google.com/sdk/gcloud/)\n- the [gke-gcloud-auth-plugin](https://cloud.google.com/blog/products/containers-kubernetes/kubectl-auth-changes-in-gke) (install the gcloud cli first)\n\nself-hosting knowledge prerequisites\n\nself-hosting n8n requires technical knowledge, including:\n\n- setting up and configuring servers and containers\n- managing application resources and scaling\n- securing servers and applications\n- configuring n8n\n\nn8n recommends self-hosting for expert users. mistakes can lead to data loss, security issues, and downtime. if you aren't experienced at managing servers, n8n recommends [n8n cloud](https://n8n.io/cloud/).\n\nstable and beta versions\n\nn8n releases a new minor version most weeks. the `stable` version is for production use. `beta` is the most recent release. the `beta` version may be unstable. to report issues, use the [forum](https://community.n8n.io/c/questions/12).\n\ncurrent `stable`: 2.21.5 current `beta`: 2.22.0\n\n## create project\n\ngcp encourages you to create projects to logically organize resources and configuration. create a new project for your n8n deployment from your google cloud console: select the project dropdown menu and then the **new project** button. then select the newly created project. as you follow the other steps in this guide, make sure you have the correct project selected.\n\n## enable the kubernetes engine api\n\ngke isn't enabled by default. search for \"kubernetes\" in the top search bar and select \"kubernetes engine\" from the results.\n\nselect **enable** to enable the kubernetes engine api for this project.\n\n## create a cluster\n\nfrom the [gke service page](https://console.cloud.google.com/kubernetes/list/overview), select **clusters** > **create**. make sure you select the \"standard\" cluster option, n8n doesn't work with an \"autopilot\" cluster. you can leave the cluster configuration on defaults unless there's anything specifically you need to change, such as location.\n\n## set kubectl context\n\nthe rest of the steps in this guide require you to set the gcp instance as the kubectl context. you can find the connection details for a cluster instance by opening its details page and selecting **connect**. the displayed code snippet shows a connection string for the gcloud cli tool. paste and run the code snippet in the gcloud cli to change your local kubernetes settings to use the new gcloud cluster.\n\n## clone configuration repository\n\nkubernetes and n8n require a series of configuration files. you can clone these from [this repository](https://github.com/n8n-io/n8n-hosting) locally. the following steps explain the file configuration and how to add your information.\n\nclone the repository with the following command:\n\n```\ngit clone https://github.com/n8n-io/n8n-hosting.git\n```\n\nand change directory:\n\n```\ncd n8n-hosting/kubernetes\n```\n\n## configure postgres\n\nfor larger scale n8n deployments, postgres provides a more robust database backend than sqlite.\n\n### create a volume for persistent storage\n\nto maintain data between pod restarts, the postgres deployment needs a persistent volume. running postgres on gcp requires a specific kubernetes storage class. you can read [this guide](https://cloud.google.com/architecture/deploying-highly-available-postgresql-with-gke) for specifics, but the `storage.yaml` manifest creates it for you. you may want to change the regions to create the storage in under the `allowedtopologies` > `matchedlabelexpressions` > `values` key. by default, they're set to `us-central`.\n\n```\n…\nallowedtopologies:\n  - matchlabelexpressions:\n      - key: failure-domain.beta.kubernetes.io/zone\n        values:\n          - us-central1-b\n          - us-central1-c\n```\n\n### postgres environment variables\n\npostgres needs some environment variables set to pass to the application running in the containers.\n\nthe example `postgres-secret.yaml` file contains placeholders you need to replace with your own values. postgres will use these details when creating the database..\n\nthe `postgres-deployment.yaml` manifest then uses the values from this manifest file to send to the application pods.\n\n## configure n8n\n\n### create a volume for file storage\n\nwhile not essential for running n8n, using persistent volumes is required for:\n\n- using nodes that interact with files, such as the binary data node.\n- if you want to persist [manual n8n encryption keys](../../../configuration/environment-variables/deployment/) between restarts. this saves a file containing the key into file storage during startup.\n\nthe `n8n-claim0-persistentvolumeclaim.yaml` manifest creates this, and the n8n deployment mounts that claim in the `volumes` section of the `n8n-deployment.yaml` manifest.\n\n```\n…\nvolumes:\n  - name: n8n-claim0\n    persistentvolumeclaim:\n      claimname: n8n-claim0\n…\n```\n\n### pod resources\n\n[kubernetes lets you](https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/) optionally specify the minimum resources application containers need and the limits they can run to. the example yaml files cloned above contain the following in the `resources` section of the `n8n-deployment.yaml` and `postgres-deployment.yaml` files:\n\n```\n…\nresources:\n  requests:\n    memory: \"250mi\"\n  limits:\n    memory: \"500mi\"\n…\n```\n\nthis defines a minimum of 250mb per container, a maximum of 500mb, and lets kubernetes handle cpu. you can change these values to match your own needs. as a guide, here are the resources values for the n8n cloud offerings:\n\n- **start**: 320mb ram, 10 millicore cpu burstable\n- **pro (10k executions)**: 640mb ram, 20 millicore cpu burstable\n- **pro (50k executions)**: 1280mb ram, 80 millicore cpu burstable\n\n### optional: environment variables\n\nyou can configure n8n settings and behaviors using environment variables.\n\ncreate an `n8n-secret.yaml` file. refer to [environment variables](../../../configuration/environment-variables/) for n8n environment variables details.\n\n## deployments\n\nthe two deployment manifests (`n8n-deployment.yaml` and `postgres-deployment.yaml`) define the n8n and postgres applications to kubernetes.\n\nthe manifests define the following:\n\n- send the environment variables defined to each application pod\n- define the container image to use\n- set resource consumption limits with the `resources` object\n- the `volumes` defined earlier and `volumemounts` to define the path in the container to mount volumes.\n- scaling and restart policies. the example manifests define one instance of each pod. you should change this to meet your needs.\n\n## services\n\nthe two service manifests (`postgres-service.yaml` and `n8n-service.yaml`) expose the services to the outside world using the kubernetes load balancer using ports 5432 and 5678 respectively.\n\n## send to kubernetes cluster\n\nsend all the manifests to the cluster with the following command:\n\n```\nkubectl apply -f .\n```\n\nnamespace error\n\nyou may see an error message about not finding an \"n8n\" namespace as that resources isn't ready yet. you can run the same command again, or apply the namespace manifest first with the following command:\n\n```\nkubectl apply -f namespace.yaml\n```\n\n## set up dns\n\nn8n typically operates on a subdomain. create a dns record with your provider for the subdomain and point it to the ip address of the n8n service. find the ip address of the n8n service from the **services & ingress** menu item of the cluster you want to use under the **endpoints** column.\n\ngke and ip addresses\n\n[read this gke tutorial](https://cloud.google.com/kubernetes-engine/docs/tutorials/configuring-domain-name-static-ip#configuring_your_domain_name_records) for more details on how reserved ip addresses work with gke and kubernetes resources.\n\n## delete resources\n\nremove the resources created by the manifests with the following command:\n\n```\nkubectl delete -f .\n```\n\n## next steps\n\n- learn more about [configuring](../../../configuration/environment-variables/) and [scaling](../../../scaling/overview/) n8n.\n- or explore using n8n: try the [quickstarts](../../../../try-it-out/).\n hosting n8n on google kubernetes engine",
         "importantTerms": [
           "kubernetes",
           "cloud",
@@ -51493,132 +51493,6 @@
     },
     {
       "id": "page-0649",
-      "title": "OpenAI Chat Model",
-      "url": "https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatopenai/index.md",
-      "urlPath": "integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatopenai/index.md",
-      "category": "cluster-nodes",
-      "subcategory": null,
-      "nodeName": null,
-      "nodeType": null,
-      "content": {
-        "markdown": "# OpenAI Chat Model node\n\nUse the OpenAI Chat Model node to use OpenAI's chat models with conversational [agents](../../../../../glossary/#ai-agent).\n\nOn this page, you'll find the node parameters for the OpenAI Chat Model node and links to more resources.\n\nCredentials\n\nYou can find authentication information for this node [here](../../../credentials/openai/).\n\nParameter resolution in sub-nodes\n\nSub-nodes behave differently to other nodes when processing multiple items using an expression.\n\nMost nodes, including root nodes, take any number of items as input, process these items, and output the results. You can use expressions to refer to input items, and the node resolves the expression for each item in turn. For example, given an input of five `name` values, the expression `{{ $json.name }}` resolves to each name in turn.\n\nIn sub-nodes, the expression always resolves to the first item. For example, given an input of five `name` values, the expression `{{ $json.name }}` always resolves to the first name.\n\n## Node parameters\n\n### Model\n\nSelect the model to use to generate the completion.\n\nn8n dynamically loads models from OpenAI, and you'll only see the models available to your account.\n\n### Use Responses API\n\nOpenAI provides two endpoints for generating output from a model:\n\n- **Chat Completions**: The Chat Completions API endpoint generates a model response from a list of messages that comprise a conversation. The API requires the user to handle conversation state manually, for example by adding a [Simple Memory](../n8n-nodes-langchain.memorybufferwindow/) subnode. For new projects, OpenAI recommends to use the Responses API.\n- **Responses**: The Responses API is an agentic loop, allowing the model to call multiple built-in tools within the span of one API request. It also supports persistent conversations by passing a `conversation_id`.\n\nToggle to **Use Responses API** if you want the model to generate output using the Responses API. Otherwise, the OpenAI Chat Model node will default to using the Chat Completions API.\n\nRefer to the OpenAI documentation for a [comparison of the Chat Completions and Responses APIs](https://platform.openai.com/docs/guides/migrate-to-responses).\n\n### Built-in Tools\n\nThe OpenAI Responses API provides a range of [built-in tools](https://platform.openai.com/docs/guides/tools) to enrich the model's response. Toggle to **Use Responses API** if you want the model to have access to the following built-in tools:\n\n- **Web Search**: Allows models to search the web for the latest information before generating a response.\n- **File Search**: Allow models to search your knowledgebase from previously uploaded files for relevant information before generating a response. Refer to the [OpenAI documentation](https://platform.openai.com/docs/guides/tools-file-search) for more information.\n- **Code Interpreter**: Allows models to write and run Python code in a sandboxed environment.\n\nUse with AI Agent node\n\nBuilt-in tools are only supported when using the OpenAI Chat Model node in combination with the AI Agent node. Built-in tools aren't available when using the OpenAI Chat Model node in combination with a Basic LLM Chain node, for example.\n\n## Node options\n\nUse these options to further refine the node's behavior. The following options are available whether you use the Responses API to generate model output or not.\n\n### Frequency Penalty\n\nUse this option to control the chances of the model repeating itself. Higher values reduce the chance of the model repeating itself.\n\n### Maximum Number of Tokens\n\nEnter the maximum number of tokens used, which sets the completion length.\n\n### Presence Penalty\n\nUse this option to control the chances of the model talking about new topics. Higher values increase the chance of the model talking about new topics.\n\n### Sampling Temperature\n\nUse this option to control the randomness of the sampling process. A higher temperature creates more diverse sampling, but increases the risk of hallucinations.\n\n### Timeout\n\nEnter the maximum request time in milliseconds.\n\n### Max Retries\n\nEnter the maximum number of times to retry a request.\n\n### Top P\n\nUse this option to set the probability the completion should use. Use a lower value to ignore less probable options.\n\n## Additional node options (Responses API only)\n\nThe following, additional options are available when toggling to **Use Responses API**.\n\n### Conversation ID\n\nThe conversation that this response belongs to. Input items and output items from this response are automatically added to this conversation after this response completes.\n\n### Prompt Cache Key\n\nUse this key for caching similar requests to optimize cache hit rates.\n\n### Safety Identifier\n\nApply an identifier to track users who may violate usage policies.\n\n### Service Tier\n\nSelect the service tier that fits your needs: Auto, Flex, Default, or Priority.\n\n### Metadata\n\nA set of key-value pairs for storing structured information. You can attach up to 16 pairs to an object, which is useful for adding custom data that can be used for searching by the API or in the dashboard.\n\n### Top Logprobs\n\nDefine an integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability.\n\n### Output Format\n\nChoose a response format: Text, JSON Schema, or JSON Object. Use of JSON Schema is recommended, if you want to receive data in JSON format.\n\n### Prompt\n\nConfigure the prompt filled with a unique ID, its version, and substitutable variables. Prompts are configured through the OpenAI dashboard.\n\n## Templates and examples\n\n**AI agent chat**\n\nby n8n Team\n\n[View template details](https://n8n.io/workflows/1954-ai-agent-chat/)\n\n**Building Your First WhatsApp Chatbot**\n\nby Jimleuk\n\n[View template details](https://n8n.io/workflows/2465-building-your-first-whatsapp-chatbot/)\n\n**Angie, personal AI assistant with Telegram voice and text**\n\nby Derek Cheung\n\n[View template details](https://n8n.io/workflows/2462-angie-personal-ai-assistant-with-telegram-voice-and-text/)\n\n[Browse OpenAI Chat Model integration templates](https://n8n.io/integrations/openai-chat-model/), or [search all templates](https://n8n.io/workflows/)\n\n## Related resources\n\nRefer to [LangChains's OpenAI documentation](https://js.langchain.com/docs/integrations/chat/openai/) for more information about the service.\n\nRefer to [OpenAI documentation](https://platform.openai.com/docs/api-reference/responses/create) for more information about the parameters.\n\nView n8n's [Advanced AI](../../../../../advanced-ai/) documentation.\n\n## Common issues\n\nFor common questions or issues and suggested solutions, refer to [Common issues](common-issues/).\n",
-        "excerpt": "# OpenAI Chat Model node  Use the OpenAI Chat Model node to use OpenAI's chat models with conversational [agents](../../../../../glossary/#ai-agent).  On this page, you'll find the node parameters for the OpenAI Chat Model node and links to more resources.  Credentials  You can find authentication information for this node [here](../../../credentials/openai/).  Parameter resolution in sub-nodes  Sub-nodes behave differently to other nodes when processing multiple items using an expression.  Most...",
-        "sections": [
-          {
-            "title": "OpenAI Chat Model node",
-            "level": 1,
-            "content": "Use the OpenAI Chat Model node to use OpenAI's chat models with conversational [agents](../../../../../glossary/#ai-agent).\n\nOn this page, you'll find the node parameters for the OpenAI Chat Model node and links to more resources.\n\nCredentials\n\nYou can find authentication information for this node [here](../../../credentials/openai/).\n\nParameter resolution in sub-nodes\n\nSub-nodes behave differently to other nodes when processing multiple items using an expression.\n\nMost nodes, including root nodes, take any number of items as input, process these items, and output the results. You can use expressions to refer to input items, and the node resolves the expression for each item in turn. For example, given an input of five `name` values, the expression `{{ $json.name }}` resolves to each name in turn.\n\nIn sub-nodes, the expression always resolves to the first item. For example, given an input of five `name` values, the expression `{{ $json.name }}` always resolves to the first name."
-          }
-        ]
-      },
-      "metadata": {
-        "keywords": [
-          "openai",
-          "chat",
-          "model",
-          "node",
-          "parameters",
-          "responses",
-          "built",
-          "tools",
-          "options",
-          "frequency",
-          "penalty",
-          "maximum",
-          "number",
-          "tokens",
-          "presence",
-          "sampling",
-          "temperature",
-          "timeout",
-          "retries",
-          "additional",
-          "(responses",
-          "only)",
-          "conversation",
-          "prompt",
-          "cache",
-          "safety",
-          "identifier",
-          "service",
-          "tier",
-          "metadata",
-          "logprobs",
-          "output",
-          "format",
-          "templates",
-          "examples",
-          "related",
-          "resources",
-          "common",
-          "issues"
-        ],
-        "useCases": [],
-        "operations": [],
-        "codeExamples": 0,
-        "complexity": "intermediate",
-        "readingTime": "5 min",
-        "contentLength": 6718,
-        "relatedPages": []
-      },
-      "searchIndex": {
-        "fullText": "openai chat model # openai chat model node\n\nuse the openai chat model node to use openai's chat models with conversational [agents](../../../../../glossary/#ai-agent).\n\non this page, you'll find the node parameters for the openai chat model node and links to more resources.\n\ncredentials\n\nyou can find authentication information for this node [here](../../../credentials/openai/).\n\nparameter resolution in sub-nodes\n\nsub-nodes behave differently to other nodes when processing multiple items using an expression.\n\nmost nodes, including root nodes, take any number of items as input, process these items, and output the results. you can use expressions to refer to input items, and the node resolves the expression for each item in turn. for example, given an input of five `name` values, the expression `{{ $json.name }}` resolves to each name in turn.\n\nin sub-nodes, the expression always resolves to the first item. for example, given an input of five `name` values, the expression `{{ $json.name }}` always resolves to the first name.\n\n## node parameters\n\n### model\n\nselect the model to use to generate the completion.\n\nn8n dynamically loads models from openai, and you'll only see the models available to your account.\n\n### use responses api\n\nopenai provides two endpoints for generating output from a model:\n\n- **chat completions**: the chat completions api endpoint generates a model response from a list of messages that comprise a conversation. the api requires the user to handle conversation state manually, for example by adding a [simple memory](../n8n-nodes-langchain.memorybufferwindow/) subnode. for new projects, openai recommends to use the responses api.\n- **responses**: the responses api is an agentic loop, allowing the model to call multiple built-in tools within the span of one api request. it also supports persistent conversations by passing a `conversation_id`.\n\ntoggle to **use responses api** if you want the model to generate output using the responses api. otherwise, the openai chat model node will default to using the chat completions api.\n\nrefer to the openai documentation for a [comparison of the chat completions and responses apis](https://platform.openai.com/docs/guides/migrate-to-responses).\n\n### built-in tools\n\nthe openai responses api provides a range of [built-in tools](https://platform.openai.com/docs/guides/tools) to enrich the model's response. toggle to **use responses api** if you want the model to have access to the following built-in tools:\n\n- **web search**: allows models to search the web for the latest information before generating a response.\n- **file search**: allow models to search your knowledgebase from previously uploaded files for relevant information before generating a response. refer to the [openai documentation](https://platform.openai.com/docs/guides/tools-file-search) for more information.\n- **code interpreter**: allows models to write and run python code in a sandboxed environment.\n\nuse with ai agent node\n\nbuilt-in tools are only supported when using the openai chat model node in combination with the ai agent node. built-in tools aren't available when using the openai chat model node in combination with a basic llm chain node, for example.\n\n## node options\n\nuse these options to further refine the node's behavior. the following options are available whether you use the responses api to generate model output or not.\n\n### frequency penalty\n\nuse this option to control the chances of the model repeating itself. higher values reduce the chance of the model repeating itself.\n\n### maximum number of tokens\n\nenter the maximum number of tokens used, which sets the completion length.\n\n### presence penalty\n\nuse this option to control the chances of the model talking about new topics. higher values increase the chance of the model talking about new topics.\n\n### sampling temperature\n\nuse this option to control the randomness of the sampling process. a higher temperature creates more diverse sampling, but increases the risk of hallucinations.\n\n### timeout\n\nenter the maximum request time in milliseconds.\n\n### max retries\n\nenter the maximum number of times to retry a request.\n\n### top p\n\nuse this option to set the probability the completion should use. use a lower value to ignore less probable options.\n\n## additional node options (responses api only)\n\nthe following, additional options are available when toggling to **use responses api**.\n\n### conversation id\n\nthe conversation that this response belongs to. input items and output items from this response are automatically added to this conversation after this response completes.\n\n### prompt cache key\n\nuse this key for caching similar requests to optimize cache hit rates.\n\n### safety identifier\n\napply an identifier to track users who may violate usage policies.\n\n### service tier\n\nselect the service tier that fits your needs: auto, flex, default, or priority.\n\n### metadata\n\na set of key-value pairs for storing structured information. you can attach up to 16 pairs to an object, which is useful for adding custom data that can be used for searching by the api or in the dashboard.\n\n### top logprobs\n\ndefine an integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability.\n\n### output format\n\nchoose a response format: text, json schema, or json object. use of json schema is recommended, if you want to receive data in json format.\n\n### prompt\n\nconfigure the prompt filled with a unique id, its version, and substitutable variables. prompts are configured through the openai dashboard.\n\n## templates and examples\n\n**ai agent chat**\n\nby n8n team\n\n[view template details](https://n8n.io/workflows/1954-ai-agent-chat/)\n\n**building your first whatsapp chatbot**\n\nby jimleuk\n\n[view template details](https://n8n.io/workflows/2465-building-your-first-whatsapp-chatbot/)\n\n**angie, personal ai assistant with telegram voice and text**\n\nby derek cheung\n\n[view template details](https://n8n.io/workflows/2462-angie-personal-ai-assistant-with-telegram-voice-and-text/)\n\n[browse openai chat model integration templates](https://n8n.io/integrations/openai-chat-model/), or [search all templates](https://n8n.io/workflows/)\n\n## related resources\n\nrefer to [langchains's openai documentation](https://js.langchain.com/docs/integrations/chat/openai/) for more information about the service.\n\nrefer to [openai documentation](https://platform.openai.com/docs/api-reference/responses/create) for more information about the parameters.\n\nview n8n's [advanced ai](../../../../../advanced-ai/) documentation.\n\n## common issues\n\nfor common questions or issues and suggested solutions, refer to [common issues](common-issues/).\n openai chat model node",
-        "importantTerms": [
-          "openai",
-          "model",
-          "chat",
-          "node",
-          "responses",
-          "this",
-          "https",
-          "with",
-          "response",
-          "tools",
-          "information",
-          "nodes",
-          "models",
-          "items",
-          "output",
-          "refer",
-          "name",
-          "json",
-          "built",
-          "search",
-          "options",
-          "agent",
-          "more",
-          "using",
-          "expression",
-          "number",
-          "input",
-          "from",
-          "your",
-          "conversation",
-          "documentation",
-          "docs",
-          "when",
-          "resolves",
-          "each",
-          "example",
-          "values",
-          "first",
-          "available",
-          "completions",
-          "that",
-          "platform",
-          "option",
-          "maximum",
-          "about",
-          "view",
-          "workflows",
-          "common",
-          "issues",
-          "parameters"
-        ]
-      }
-    },
-    {
-      "id": "page-0650",
       "title": "Common issues",
       "url": "https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatopenai/common-issues/index.md",
       "urlPath": "integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatopenai/common-issues/index.md",
@@ -51724,7 +51598,7 @@
       }
     },
     {
-      "id": "page-0651",
+      "id": "page-0650",
       "title": "Ollama Model",
       "url": "https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmollama/index.md",
       "urlPath": "integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmollama/index.md",
@@ -51807,6 +51681,132 @@
         ]
       }
     },
+    {
+      "id": "page-0651",
+      "title": "OpenAI Chat Model",
+      "url": "https://docs.n8n.io/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatopenai/index.md",
+      "urlPath": "integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatopenai/index.md",
+      "category": "cluster-nodes",
+      "subcategory": null,
+      "nodeName": null,
+      "nodeType": null,
+      "content": {
+        "markdown": "# OpenAI Chat Model node\n\nUse the OpenAI Chat Model node to use OpenAI's chat models with conversational [agents](../../../../../glossary/#ai-agent).\n\nOn this page, you'll find the node parameters for the OpenAI Chat Model node and links to more resources.\n\nCredentials\n\nYou can find authentication information for this node [here](../../../credentials/openai/).\n\nParameter resolution in sub-nodes\n\nSub-nodes behave differently to other nodes when processing multiple items using an expression.\n\nMost nodes, including root nodes, take any number of items as input, process these items, and output the results. You can use expressions to refer to input items, and the node resolves the expression for each item in turn. For example, given an input of five `name` values, the expression `{{ $json.name }}` resolves to each name in turn.\n\nIn sub-nodes, the expression always resolves to the first item. For example, given an input of five `name` values, the expression `{{ $json.name }}` always resolves to the first name.\n\n## Node parameters\n\n### Model\n\nSelect the model to use to generate the completion.\n\nn8n dynamically loads models from OpenAI, and you'll only see the models available to your account.\n\n### Use Responses API\n\nOpenAI provides two endpoints for generating output from a model:\n\n- **Chat Completions**: The Chat Completions API endpoint generates a model response from a list of messages that comprise a conversation. The API requires the user to handle conversation state manually, for example by adding a [Simple Memory](../n8n-nodes-langchain.memorybufferwindow/) subnode. For new projects, OpenAI recommends to use the Responses API.\n- **Responses**: The Responses API is an agentic loop, allowing the model to call multiple built-in tools within the span of one API request. It also supports persistent conversations by passing a `conversation_id`.\n\nToggle to **Use Responses API** if you want the model to generate output using the Responses API. Otherwise, the OpenAI Chat Model node will default to using the Chat Completions API.\n\nRefer to the OpenAI documentation for a [comparison of the Chat Completions and Responses APIs](https://platform.openai.com/docs/guides/migrate-to-responses).\n\n### Built-in Tools\n\nThe OpenAI Responses API provides a range of [built-in tools](https://platform.openai.com/docs/guides/tools) to enrich the model's response. Toggle to **Use Responses API** if you want the model to have access to the following built-in tools:\n\n- **Web Search**: Allows models to search the web for the latest information before generating a response.\n- **File Search**: Allow models to search your knowledgebase from previously uploaded files for relevant information before generating a response. Refer to the [OpenAI documentation](https://platform.openai.com/docs/guides/tools-file-search) for more information.\n- **Code Interpreter**: Allows models to write and run Python code in a sandboxed environment.\n\nUse with AI Agent node\n\nBuilt-in tools are only supported when using the OpenAI Chat Model node in combination with the AI Agent node. Built-in tools aren't available when using the OpenAI Chat Model node in combination with a Basic LLM Chain node, for example.\n\n## Node options\n\nUse these options to further refine the node's behavior. The following options are available whether you use the Responses API to generate model output or not.\n\n### Frequency Penalty\n\nUse this option to control the chances of the model repeating itself. Higher values reduce the chance of the model repeating itself.\n\n### Maximum Number of Tokens\n\nEnter the maximum number of tokens used, which sets the completion length.\n\n### Presence Penalty\n\nUse this option to control the chances of the model talking about new topics. Higher values increase the chance of the model talking about new topics.\n\n### Sampling Temperature\n\nUse this option to control the randomness of the sampling process. A higher temperature creates more diverse sampling, but increases the risk of hallucinations.\n\n### Timeout\n\nEnter the maximum request time in milliseconds.\n\n### Max Retries\n\nEnter the maximum number of times to retry a request.\n\n### Top P\n\nUse this option to set the probability the completion should use. Use a lower value to ignore less probable options.\n\n## Additional node options (Responses API only)\n\nThe following, additional options are available when toggling to **Use Responses API**.\n\n### Conversation ID\n\nThe conversation that this response belongs to. Input items and output items from this response are automatically added to this conversation after this response completes.\n\n### Prompt Cache Key\n\nUse this key for caching similar requests to optimize cache hit rates.\n\n### Safety Identifier\n\nApply an identifier to track users who may violate usage policies.\n\n### Service Tier\n\nSelect the service tier that fits your needs: Auto, Flex, Default, or Priority.\n\n### Metadata\n\nA set of key-value pairs for storing structured information. You can attach up to 16 pairs to an object, which is useful for adding custom data that can be used for searching by the API or in the dashboard.\n\n### Top Logprobs\n\nDefine an integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability.\n\n### Output Format\n\nChoose a response format: Text, JSON Schema, or JSON Object. Use of JSON Schema is recommended, if you want to receive data in JSON format.\n\n### Prompt\n\nConfigure the prompt filled with a unique ID, its version, and substitutable variables. Prompts are configured through the OpenAI dashboard.\n\n## Templates and examples\n\n**AI agent chat**\n\nby n8n Team\n\n[View template details](https://n8n.io/workflows/1954-ai-agent-chat/)\n\n**Building Your First WhatsApp Chatbot**\n\nby Jimleuk\n\n[View template details](https://n8n.io/workflows/2465-building-your-first-whatsapp-chatbot/)\n\n**Angie, personal AI assistant with Telegram voice and text**\n\nby Derek Cheung\n\n[View template details](https://n8n.io/workflows/2462-angie-personal-ai-assistant-with-telegram-voice-and-text/)\n\n[Browse OpenAI Chat Model integration templates](https://n8n.io/integrations/openai-chat-model/), or [search all templates](https://n8n.io/workflows/)\n\n## Related resources\n\nRefer to [LangChains's OpenAI documentation](https://js.langchain.com/docs/integrations/chat/openai/) for more information about the service.\n\nRefer to [OpenAI documentation](https://platform.openai.com/docs/api-reference/responses/create) for more information about the parameters.\n\nView n8n's [Advanced AI](../../../../../advanced-ai/) documentation.\n\n## Common issues\n\nFor common questions or issues and suggested solutions, refer to [Common issues](common-issues/).\n",
+        "excerpt": "# OpenAI Chat Model node  Use the OpenAI Chat Model node to use OpenAI's chat models with conversational [agents](../../../../../glossary/#ai-agent).  On this page, you'll find the node parameters for the OpenAI Chat Model node and links to more resources.  Credentials  You can find authentication information for this node [here](../../../credentials/openai/).  Parameter resolution in sub-nodes  Sub-nodes behave differently to other nodes when processing multiple items using an expression.  Most...",
+        "sections": [
+          {
+            "title": "OpenAI Chat Model node",
+            "level": 1,
+            "content": "Use the OpenAI Chat Model node to use OpenAI's chat models with conversational [agents](../../../../../glossary/#ai-agent).\n\nOn this page, you'll find the node parameters for the OpenAI Chat Model node and links to more resources.\n\nCredentials\n\nYou can find authentication information for this node [here](../../../credentials/openai/).\n\nParameter resolution in sub-nodes\n\nSub-nodes behave differently to other nodes when processing multiple items using an expression.\n\nMost nodes, including root nodes, take any number of items as input, process these items, and output the results. You can use expressions to refer to input items, and the node resolves the expression for each item in turn. For example, given an input of five `name` values, the expression `{{ $json.name }}` resolves to each name in turn.\n\nIn sub-nodes, the expression always resolves to the first item. For example, given an input of five `name` values, the expression `{{ $json.name }}` always resolves to the first name."
+          }
+        ]
+      },
+      "metadata": {
+        "keywords": [
+          "openai",
+          "chat",
+          "model",
+          "node",
+          "parameters",
+          "responses",
+          "built",
+          "tools",
+          "options",
+          "frequency",
+          "penalty",
+          "maximum",
+          "number",
+          "tokens",
+          "presence",
+          "sampling",
+          "temperature",
+          "timeout",
+          "retries",
+          "additional",
+          "(responses",
+          "only)",
+          "conversation",
+          "prompt",
+          "cache",
+          "safety",
+          "identifier",
+          "service",
+          "tier",
+          "metadata",
+          "logprobs",
+          "output",
+          "format",
+          "templates",
+          "examples",
+          "related",
+          "resources",
+          "common",
+          "issues"
+        ],
+        "useCases": [],
+        "operations": [],
+        "codeExamples": 0,
+        "complexity": "intermediate",
+        "readingTime": "5 min",
+        "contentLength": 6718,
+        "relatedPages": []
+      },
+      "searchIndex": {
+        "fullText": "openai chat model # openai chat model node\n\nuse the openai chat model node to use openai's chat models with conversational [agents](../../../../../glossary/#ai-agent).\n\non this page, you'll find the node parameters for the openai chat model node and links to more resources.\n\ncredentials\n\nyou can find authentication information for this node [here](../../../credentials/openai/).\n\nparameter resolution in sub-nodes\n\nsub-nodes behave differently to other nodes when processing multiple items using an expression.\n\nmost nodes, including root nodes, take any number of items as input, process these items, and output the results. you can use expressions to refer to input items, and the node resolves the expression for each item in turn. for example, given an input of five `name` values, the expression `{{ $json.name }}` resolves to each name in turn.\n\nin sub-nodes, the expression always resolves to the first item. for example, given an input of five `name` values, the expression `{{ $json.name }}` always resolves to the first name.\n\n## node parameters\n\n### model\n\nselect the model to use to generate the completion.\n\nn8n dynamically loads models from openai, and you'll only see the models available to your account.\n\n### use responses api\n\nopenai provides two endpoints for generating output from a model:\n\n- **chat completions**: the chat completions api endpoint generates a model response from a list of messages that comprise a conversation. the api requires the user to handle conversation state manually, for example by adding a [simple memory](../n8n-nodes-langchain.memorybufferwindow/) subnode. for new projects, openai recommends to use the responses api.\n- **responses**: the responses api is an agentic loop, allowing the model to call multiple built-in tools within the span of one api request. it also supports persistent conversations by passing a `conversation_id`.\n\ntoggle to **use responses api** if you want the model to generate output using the responses api. otherwise, the openai chat model node will default to using the chat completions api.\n\nrefer to the openai documentation for a [comparison of the chat completions and responses apis](https://platform.openai.com/docs/guides/migrate-to-responses).\n\n### built-in tools\n\nthe openai responses api provides a range of [built-in tools](https://platform.openai.com/docs/guides/tools) to enrich the model's response. toggle to **use responses api** if you want the model to have access to the following built-in tools:\n\n- **web search**: allows models to search the web for the latest information before generating a response.\n- **file search**: allow models to search your knowledgebase from previously uploaded files for relevant information before generating a response. refer to the [openai documentation](https://platform.openai.com/docs/guides/tools-file-search) for more information.\n- **code interpreter**: allows models to write and run python code in a sandboxed environment.\n\nuse with ai agent node\n\nbuilt-in tools are only supported when using the openai chat model node in combination with the ai agent node. built-in tools aren't available when using the openai chat model node in combination with a basic llm chain node, for example.\n\n## node options\n\nuse these options to further refine the node's behavior. the following options are available whether you use the responses api to generate model output or not.\n\n### frequency penalty\n\nuse this option to control the chances of the model repeating itself. higher values reduce the chance of the model repeating itself.\n\n### maximum number of tokens\n\nenter the maximum number of tokens used, which sets the completion length.\n\n### presence penalty\n\nuse this option to control the chances of the model talking about new topics. higher values increase the chance of the model talking about new topics.\n\n### sampling temperature\n\nuse this option to control the randomness of the sampling process. a higher temperature creates more diverse sampling, but increases the risk of hallucinations.\n\n### timeout\n\nenter the maximum request time in milliseconds.\n\n### max retries\n\nenter the maximum number of times to retry a request.\n\n### top p\n\nuse this option to set the probability the completion should use. use a lower value to ignore less probable options.\n\n## additional node options (responses api only)\n\nthe following, additional options are available when toggling to **use responses api**.\n\n### conversation id\n\nthe conversation that this response belongs to. input items and output items from this response are automatically added to this conversation after this response completes.\n\n### prompt cache key\n\nuse this key for caching similar requests to optimize cache hit rates.\n\n### safety identifier\n\napply an identifier to track users who may violate usage policies.\n\n### service tier\n\nselect the service tier that fits your needs: auto, flex, default, or priority.\n\n### metadata\n\na set of key-value pairs for storing structured information. you can attach up to 16 pairs to an object, which is useful for adding custom data that can be used for searching by the api or in the dashboard.\n\n### top logprobs\n\ndefine an integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability.\n\n### output format\n\nchoose a response format: text, json schema, or json object. use of json schema is recommended, if you want to receive data in json format.\n\n### prompt\n\nconfigure the prompt filled with a unique id, its version, and substitutable variables. prompts are configured through the openai dashboard.\n\n## templates and examples\n\n**ai agent chat**\n\nby n8n team\n\n[view template details](https://n8n.io/workflows/1954-ai-agent-chat/)\n\n**building your first whatsapp chatbot**\n\nby jimleuk\n\n[view template details](https://n8n.io/workflows/2465-building-your-first-whatsapp-chatbot/)\n\n**angie, personal ai assistant with telegram voice and text**\n\nby derek cheung\n\n[view template details](https://n8n.io/workflows/2462-angie-personal-ai-assistant-with-telegram-voice-and-text/)\n\n[browse openai chat model integration templates](https://n8n.io/integrations/openai-chat-model/), or [search all templates](https://n8n.io/workflows/)\n\n## related resources\n\nrefer to [langchains's openai documentation](https://js.langchain.com/docs/integrations/chat/openai/) for more information about the service.\n\nrefer to [openai documentation](https://platform.openai.com/docs/api-reference/responses/create) for more information about the parameters.\n\nview n8n's [advanced ai](../../../../../advanced-ai/) documentation.\n\n## common issues\n\nfor common questions or issues and suggested solutions, refer to [common issues](common-issues/).\n openai chat model node",
+        "importantTerms": [
+          "openai",
+          "model",
+          "chat",
+          "node",
+          "responses",
+          "this",
+          "https",
+          "with",
+          "response",
+          "tools",
+          "information",
+          "nodes",
+          "models",
+          "items",
+          "output",
+          "refer",
+          "name",
+          "json",
+          "built",
+          "search",
+          "options",
+          "agent",
+          "more",
+          "using",
+          "expression",
+          "number",
+          "input",
+          "from",
+          "your",
+          "conversation",
+          "documentation",
+          "docs",
+          "when",
+          "resolves",
+          "each",
+          "example",
+          "values",
+          "first",
+          "available",
+          "completions",
+          "that",
+          "platform",
+          "option",
+          "maximum",
+          "about",
+          "view",
+          "workflows",
+          "common",
+          "issues",
+          "parameters"
+        ]
+      }
+    },
     {
       "id": "page-0652",
       "title": "Common issues",
@@ -96224,7 +96224,7 @@
         "page-0542",
         "page-0546",
         "page-0638",
-        "page-0650",
+        "page-0649",
         "page-0681",
         "page-0725",
         "page-0726",
@@ -96487,7 +96487,7 @@
         "page-0519",
         "page-0538",
         "page-0546",
-        "page-0650",
+        "page-0649",
         "page-0656",
         "page-0665",
         "page-0675",
@@ -97790,7 +97790,7 @@
         "page-0543",
         "page-0546",
         "page-0566",
-        "page-0650",
+        "page-0649",
         "page-0726",
         "page-1047",
         "page-1048",
@@ -99686,7 +99686,7 @@
         "page-0567",
         "page-0568",
         "page-0647",
-        "page-0651",
+        "page-0650",
         "page-0922",
         "page-1041",
         "page-1223",
@@ -100110,7 +100110,7 @@
         "page-0640",
         "page-0641",
         "page-0647",
-        "page-0649",
+        "page-0650",
         "page-0651",
         "page-0659",
         "page-0661",
@@ -101055,7 +101055,7 @@
         "page-0647",
         "page-0648",
         "page-0649",
-        "page-0650",
+        "page-0651",
         "page-0713",
         "page-0734",
         "page-0735",
@@ -101804,7 +101804,7 @@
         "page-0645",
         "page-0646",
         "page-0647",
-        "page-0649",
+        "page-0650",
         "page-0651",
         "page-0653",
         "page-0655",
@@ -102357,7 +102357,7 @@
         "page-0645",
         "page-0646",
         "page-0647",
-        "page-0649",
+        "page-0650",
         "page-0651",
         "page-0653",
         "page-0655",
@@ -103113,7 +103113,7 @@
         "page-0645",
         "page-0646",
         "page-0647",
-        "page-0649",
+        "page-0650",
         "page-0651",
         "page-0653",
         "page-0655",
@@ -103371,7 +103371,7 @@
         "page-0579",
         "page-0582",
         "page-0635",
-        "page-0649",
+        "page-0651",
         "page-1226"
       ],
       "step": [
@@ -103447,7 +103447,7 @@
         "page-0578",
         "page-0579",
         "page-0581",
-        "page-0649"
+        "page-0651"
       ],
       "best": [
         "page-0020",
@@ -104274,7 +104274,7 @@
         "page-0645",
         "page-0646",
         "page-0647",
-        "page-0649",
+        "page-0650",
         "page-0651",
         "page-0653",
         "page-0655",
@@ -104669,7 +104669,7 @@
         "page-0579",
         "page-0625",
         "page-0626",
-        "page-0649",
+        "page-0651",
         "page-0655",
         "page-0656",
         "page-0661",
@@ -104746,7 +104746,7 @@
         "page-0567",
         "page-0568",
         "page-0647",
-        "page-0651",
+        "page-0650",
         "page-0734",
         "page-0813",
         "page-0922",
@@ -105261,7 +105261,7 @@
         "page-0241",
         "page-0550",
         "page-0556",
-        "page-0649",
+        "page-0651",
         "page-0717",
         "page-1182",
         "page-1225",
@@ -105348,7 +105348,7 @@
         "page-0508",
         "page-0542",
         "page-0546",
-        "page-0650",
+        "page-0649",
         "page-0670",
         "page-0702",
         "page-0714",
@@ -106341,7 +106341,7 @@
         "page-0424",
         "page-0504",
         "page-0546",
-        "page-0650",
+        "page-0649",
         "page-0717",
         "page-0726"
       ],
@@ -106384,7 +106384,7 @@
         "page-0577",
         "page-0578",
         "page-0579",
-        "page-0649",
+        "page-0651",
         "page-1177",
         "page-1180"
       ],
@@ -106668,7 +106668,7 @@
         "page-0611",
         "page-0612",
         "page-0624",
-        "page-0649",
+        "page-0651",
         "page-0676",
         "page-0683",
         "page-0708",
@@ -106904,7 +106904,7 @@
         "page-0224",
         "page-0558",
         "page-0648",
-        "page-0650",
+        "page-0649",
         "page-0652",
         "page-0656",
         "page-1223"
@@ -108430,7 +108430,7 @@
         "page-0569",
         "page-0570",
         "page-0571",
-        "page-0650",
+        "page-0649",
         "page-0691",
         "page-0726",
         "page-1187"
@@ -109089,7 +109089,7 @@
         "page-0610",
         "page-0611",
         "page-0612",
-        "page-0649",
+        "page-0651",
         "page-0725",
         "page-1266"
       ],
@@ -109173,7 +109173,7 @@
         "page-0504",
         "page-0546",
         "page-0649",
-        "page-0650",
+        "page-0651",
         "page-0726",
         "page-0795",
         "page-0849",
@@ -110122,7 +110122,7 @@
         "page-0610",
         "page-0611",
         "page-0612",
-        "page-0649"
+        "page-0651"
       ],
       "kept": [
         "page-0211"
@@ -110171,7 +110171,7 @@
         "page-0611",
         "page-0612",
         "page-0615",
-        "page-0649"
+        "page-0651"
       ],
       "traces": [
         "page-0213"
@@ -110312,7 +110312,7 @@
         "page-0610",
         "page-0611",
         "page-0612",
-        "page-0649",
+        "page-0651",
         "page-0656",
         "page-0665",
         "page-0668",
@@ -110514,7 +110514,7 @@
         "page-0567",
         "page-0568",
         "page-0647",
-        "page-0651"
+        "page-0650"
       ],
       "what’s": [
         "page-0237"
@@ -112310,7 +112310,7 @@
       "receiving": [
         "page-0504",
         "page-0546",
-        "page-0650",
+        "page-0649",
         "page-0726"
       ],
       "discord": [
@@ -112370,7 +112370,7 @@
         "page-0508",
         "page-0542",
         "page-0546",
-        "page-0650",
+        "page-0649",
         "page-0726"
       ],
       "draft": [
@@ -112615,7 +112615,7 @@
       "additional": [
         "page-0536",
         "page-0540",
-        "page-0649",
+        "page-0651",
         "page-1062",
         "page-1197",
         "page-1226"
@@ -112697,7 +112697,7 @@
         "page-0596",
         "page-0600",
         "page-0649",
-        "page-0650",
+        "page-0651",
         "page-0756",
         "page-0925",
         "page-1226"
@@ -112715,11 +112715,11 @@
       ],
       "insufficient": [
         "page-0546",
-        "page-0650"
+        "page-0649"
       ],
       "quota": [
         "page-0546",
-        "page-0650"
+        "page-0649"
       ],
       "referenced": [
         "page-0546"
@@ -112729,7 +112729,7 @@
       ],
       "conversation": [
         "page-0547",
-        "page-0649"
+        "page-0651"
       ],
       "classify": [
         "page-0550"
@@ -112809,7 +112809,7 @@
         "page-0611",
         "page-0612",
         "page-0615",
-        "page-0649"
+        "page-0651"
       ],
       "iterative": [
         "page-0558"
@@ -113008,7 +113008,7 @@
       ],
       "safety": [
         "page-0562",
-        "page-0649"
+        "page-0651"
       ],
       "milvus": [
         "page-0563",
@@ -113167,7 +113167,7 @@
       ],
       "responses": [
         "page-0581",
-        "page-0649",
+        "page-0651",
         "page-0696",
         "page-0731",
         "page-1205",
@@ -113217,7 +113217,7 @@
         "page-0595",
         "page-0647",
         "page-0648",
-        "page-0651",
+        "page-0650",
         "page-0652",
         "page-0922",
         "page-1226"
@@ -113233,7 +113233,7 @@
         "page-0611",
         "page-0612",
         "page-0615",
-        "page-0649"
+        "page-0651"
       ],
       "penalty": [
         "page-0602",
@@ -113242,7 +113242,7 @@
         "page-0611",
         "page-0612",
         "page-0615",
-        "page-0649"
+        "page-0651"
       ],
       "tokens": [
         "page-0602",
@@ -113251,7 +113251,7 @@
         "page-0611",
         "page-0612",
         "page-0615",
-        "page-0649",
+        "page-0651",
         "page-0886"
       ],
       "presence": [
@@ -113261,14 +113261,14 @@
         "page-0611",
         "page-0612",
         "page-0615",
-        "page-0649"
+        "page-0651"
       ],
       "retries": [
         "page-0602",
         "page-0610",
         "page-0611",
         "page-0612",
-        "page-0649"
+        "page-0651"
       ],
       "groq": [
         "page-0605",
@@ -113410,22 +113410,22 @@
         "page-0652"
       ],
       "(responses": [
-        "page-0649"
+        "page-0651"
       ],
       "only)": [
-        "page-0649"
+        "page-0651"
       ],
       "cache": [
-        "page-0649"
+        "page-0651"
       ],
       "identifier": [
-        "page-0649"
+        "page-0651"
       ],
       "tier": [
-        "page-0649"
+        "page-0651"
       ],
       "logprobs": [
-        "page-0649"
+        "page-0651"
       ],
       "intermediary": [
         "page-0656"