You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: src/langsmith/authentication-methods.mdx
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -21,7 +21,7 @@ Enterprise customers can configure [SAML SSO](/langsmith/user-management) and [S
21
21
22
22
## Self-Hosted
23
23
24
-
Self-hosted customers have more control over how their users can login to LangSmith. For more in-depth coverage of configuration options, see [the self-hosting docs](/langsmith/architectural-overview) and [Helm chart](https://github.com/langchain-ai/helm/tree/main/charts/langsmith).
24
+
Self-hosted customers have more control over how their users can login to LangSmith. For more in-depth coverage of configuration options, see [the self-hosting docs](/langsmith/self-hosted) and [Helm chart](https://github.com/langchain-ai/helm/tree/main/charts/langsmith).
Copy file name to clipboardExpand all lines: src/langsmith/cli.mdx
+43-22Lines changed: 43 additions & 22 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -3,31 +3,52 @@ title: LangGraph CLI
3
3
sidebarTitle: CLI
4
4
---
5
5
6
-
The LangGraph command line interface includes commands to build and run a LangSmith Platform API server locally in [Docker](https://www.docker.com/). For development and testing, you can use the CLI to deploy a local API server.
6
+
**LangGraph CLI** is a command-line tool for building and running the [LangGraph API server](/langsmith/langgraph-server) locally. The resulting server exposes all API endpoints for runs, threads, assistants, etc., and includes supporting services such as a managed database for checkpointing and storage.
7
7
8
8
## Installation
9
9
10
-
1. Ensure that Docker is installed (e.g. `docker --version`).
11
-
2. Install the CLI package:
12
-
<Tabs>
13
-
<Tabtitle="Python">
14
-
```bash
15
-
pip install langgraph-cli
16
-
```
17
-
</Tab>
18
-
<Tabtitle="JS">
19
-
```bash
20
-
npx @langchain/langgraph-cli
21
-
22
-
# Install globally, will be available as `langgraphjs`
23
-
npm install -g @langchain/langgraph-cli
24
-
```
25
-
</Tab>
26
-
</Tabs>
27
-
3. Run the command `langgraph --help` or `npx @langchain/langgraph-cli --help` to confirm that the CLI is working correctly.
28
-
29
-
<aid="configuration-file"></a>
30
-
## Configuration File
10
+
1. Ensure Docker is installed (e.g., `docker --version`).
11
+
1. Install the CLI:
12
+
13
+
<CodeGroup>
14
+
```bash [Python (pip)]
15
+
pip install langgraph-cli
16
+
```
17
+
```bash Homebrew
18
+
brew install langgraph-cli
19
+
```
20
+
```bash JavaScript
21
+
# Use latest on demand
22
+
npx @langchain/langgraph-cli
23
+
24
+
# Or install globally (available as `langgraphjs`)
25
+
npm install -g @langchain/langgraph-cli
26
+
```
27
+
</CodeGroup>
28
+
29
+
1. Verify the install
30
+
31
+
<CodeGroup>
32
+
```bash [Python (pip)]
33
+
langgraph --help
34
+
```
35
+
```bash JavaScript
36
+
npx @langchain/langgraph-cli --help
37
+
```
38
+
</CodeGroup>
39
+
40
+
### Quick commands
41
+
42
+
| Command | What it does |
43
+
| --- | --- |
44
+
|[`langgraph dev`](#dev)| Starts a lightweight local dev server (no Docker required), ideal for rapid testing. |
45
+
|[`langgraph build`](#build)| Builds a Docker image of your LangGraph API server for deployment. |
46
+
|[`langgraph dockerfile`](#dockerfile)| Emits a Dockerfile derived from your config for custom builds. |
47
+
|[`langgraph up`](#up)| Starts the LangGraph API server locally in Docker. Requires Docker running; LangSmith API key for local dev; license for production. |
48
+
49
+
For JS, use `npx @langchain/langgraph-cli <command>` (or `langgraphjs` if installed globally).
50
+
51
+
## Configuration file
31
52
32
53
The LangGraph CLI requires a JSON configuration file that follows this [schema](https://raw.githubusercontent.com/langchain-ai/langgraph/refs/heads/main/libs/cli/schemas/schema.json). It contains the following properties:
Copy file name to clipboardExpand all lines: src/langsmith/cloud-architecture-and-scalability.mdx
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -6,7 +6,7 @@ sidebarTitle: Cloud architecture and scalability
6
6
<Note>
7
7
This section is only relevant for the cloud-managed LangSmith services available at [https://smith.langchain.com](https://smith.langchain.com) and [https://eu.smith.langchain.com](https://eu.smith.langchain.com).
8
8
9
-
For information on the self-hosted LangSmith solution, please refer to the [self-hosted documentation](/langsmith/architectural-overview).
9
+
For information on the self-hosted LangSmith solution, please refer to the [self-hosted documentation](/langsmith/self-hosted).
10
10
</Note>
11
11
12
12
LangSmith is deployed on Google Cloud Platform (GCP) and is designed to be highly scalable. Many customers run production workloads on LangSmith for both LLM application observability and evaluation.
When running the self-hosted [LangSmith Platform with agent deployment](/langsmith/deploy-self-hosted-full-platform), your installation includes several key components. Together these tools and services provide a complete solution for building, deploying, and managing graphs (including agentic applications) in your own infrastructure:
7
7
8
8
-[LangGraph Server](/langsmith/langgraph-server): Defines an opinionated API and runtime for deploying graphs and agents. Handles execution, state management, and persistence so you can focus on building logic rather than server infrastructure.
9
-
-[LangGraph CLI](/langsmith/langgraph-cli): A command-line interface to build, package, and interact with graphs locally and prepare them for deployment.
9
+
-[LangGraph CLI](/langsmith/cli): A command-line interface to build, package, and interact with graphs locally and prepare them for deployment.
10
10
-[Studio](/langsmith/langgraph-studio): A specialized IDE for visualization, interaction, and debugging. Connects to a local LangGraph Server for developing and testing your graph.
11
11
-[Python/JS SDK](/langsmith/sdk): The Python/JS SDK provides a programmatic way to interact with deployed graphs and agents from your applications.
12
12
-[Remote Graph](/langsmith/use-remote-graph): Allows you to interact with a deployed graph as though it were running locally.
Copy file name to clipboardExpand all lines: src/langsmith/data-storage-and-privacy.mdx
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -6,7 +6,7 @@ This document describes how data is processed in the LangGraph CLI and the LangG
6
6
7
7
## CLI
8
8
9
-
LangGraph **CLI** is the command-line interface for building and running LangGraph applications; see the [CLI guide](/langsmith/langgraph-cli) to learn more.
9
+
LangGraph **CLI** is the command-line interface for building and running LangGraph applications; see the [CLI guide](/langsmith/cli) to learn more.
10
10
11
11
By default, calls to most CLI commands log a single analytics event upon invocation. This helps us better prioritize improvements to the CLI experience. Each telemetry event contains the calling process's OS, OS version, Python version, the CLI version, the command name (`dev`, `up`, `run`, etc.), and booleans representing whether a flag was passed to the command. You can see the full analytics logic [here](https://github.com/langchain-ai/langgraph/blob/main/libs/cli/langgraph-cli/analytics.py).
Copy file name to clipboardExpand all lines: src/langsmith/deploy-hybrid.mdx
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -13,8 +13,8 @@ The Hybrid deployment option requires an [Enterprise](/langsmith/plans) plan.
13
13
14
14
## Prerequisites
15
15
16
-
1. Use the [LangGraph CLI](/langsmith/langgraph-cli) to [test your application locally](/langsmith/local-server).
17
-
2. Use the [LangGraph CLI](/langsmith/langgraph-cli) to build a Docker image (i.e. `langgraph build`) and push it to a registry your Kubernetes cluster or Amazon ECS cluster has access to.
16
+
1. Use the [LangGraph CLI](/langsmith/cli) to [test your application locally](/langsmith/local-server).
17
+
2. Use the [LangGraph CLI](/langsmith/cli) to build a Docker image (i.e. `langgraph build`) and push it to a registry your Kubernetes cluster or Amazon ECS cluster has access to.
Copy file name to clipboardExpand all lines: src/langsmith/deploy-self-hosted-full-platform.mdx
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -15,8 +15,8 @@ Self-hosting LangSmith Platform with agent deployment requires an [Enterprise](/
15
15
16
16
1. You are using Kubernetes.
17
17
2. You have an instance of [self-hosted LangSmith Platform](/langsmith/kubernetes) running.
18
-
3. Use the [LangGraph CLI](/langsmith/langgraph-cli) to [test your application locally](/langsmith/local-server).
19
-
4. Use the [LangGraph CLI](/langsmith/langgraph-cli) to build a Docker image (i.e. `langgraph build`) and push it to a registry your Kubernetes cluster has access to.
18
+
3. Use the [LangGraph CLI](/langsmith/cli) to [test your application locally](/langsmith/local-server).
19
+
4. Use the [LangGraph CLI](/langsmith/cli) to build a Docker image (i.e. `langgraph build`) and push it to a registry your Kubernetes cluster has access to.
Copy file name to clipboardExpand all lines: src/langsmith/deploy-standalone-server.mdx
+3-3Lines changed: 3 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -8,8 +8,8 @@ Before setting up standalone servers, review the [self-hosting overview page](/l
8
8
9
9
## Prerequisites
10
10
11
-
1. Use the [LangGraph CLI](/langsmith/langgraph-cli) to [test your application locally](/langsmith/local-server).
12
-
2. Use the [LangGraph CLI](/langsmith/langgraph-cli) to build a Docker image (i.e. `langgraph build`).
11
+
1. Use the [LangGraph CLI](/langsmith/cli) to [test your application locally](/langsmith/local-server).
12
+
2. Use the [LangGraph CLI](/langsmith/cli) to build a Docker image (i.e. `langgraph build`).
13
13
3. The following environment variables are needed for a data plane deployment.
14
14
1.`REDIS_URI`: Connection details to a Redis instance. Redis will be used as a pub-sub broker to enable streaming real time output from background runs. The value of `REDIS_URI` must be a valid [Redis connection URI](https://redis-py.readthedocs.io/en/stable/connections.html#redis.Redis.from_url).
15
15
<Note>
@@ -27,7 +27,7 @@ Before setting up standalone servers, review the [self-hosting overview page](/l
27
27
</Note>
28
28
3.`LANGSMITH_API_KEY`: LangSmith API key.
29
29
4.`LANGGRAPH_CLOUD_LICENSE_KEY`: LangSmith Platform license key. This will be used to authenticate ONCE at server start up.
30
-
5.`LANGSMITH_ENDPOINT`: To send traces to a [self-hosted LangSmith](/langsmith/architectural-overview) instance, set `LANGSMITH_ENDPOINT` to the hostname of the self-hosted LangSmith instance.
30
+
5.`LANGSMITH_ENDPOINT`: To send traces to a [self-hosted LangSmith](/langsmith/self-hosted) instance, set `LANGSMITH_ENDPOINT` to the hostname of the self-hosted LangSmith instance.
31
31
4. Egress to `https://beacon.langchain.com` from your network. This is required for license verification and usage reporting if not running in air-gapped mode. See the [Egress documentation](/langsmith/egress-metrics-metadata) for more details.
0 commit comments