docs: Simplify LGP quickstarts (#4678)

- Change quickstarts to use `new-langgraph-project`, which doesn't require API keys for Anthropic, Tavily, etc.
2026-08-17 21:25:46 +02:00 · 2025-05-13 11:47:48 -07:00
parent 4534d174f4 a7faae6b54
commit 2b8c295898
10 changed files with 16 additions and 42 deletions
@@ -9,20 +9,11 @@ Before you begin, ensure you have the following:
 - A [GitHub account](https://github.com/)
 - A [LangSmith account](https://smith.langchain.com/) – free to sign up

-This quickstart uses the [pre-built Python ReAct agent template](https://github.com/langchain-ai/react-agent), which requires the following:
-
- An API key for [Anthropic](https://console.anthropic.com/)
- An API key for [Tavily](https://app.tavily.com/)
-
-!!! note
-
-    If you want to use a scaffold application that doesn't require API keys, use the [New LangGraph Project](https://github.com/langchain-ai/new-langgraph-project) template instead.
-
 ## 1. Create a repository on GitHub

-To deploy a LangGraph application to **LangGraph Platform**, your application code must reside in a GitHub repository. Both public and private repositories are supported. For this quickstart, use the [pre-built Python ReAct agent template](https://github.com/langchain-ai/react-agent) for your application:
+To deploy an application to **LangGraph Platform**, your application code must reside in a GitHub repository. Both public and private repositories are supported. For this quickstart, use the [`new-langgraph-project` template](https://github.com/langchain-ai/react-agent) for your application:

-1. Go to the [ReAct Agent](https://github.com/langchain-ai/react-agent) repository.
+1. Go to the [`new-langgraph-project` repository](https://github.com/langchain-ai/new-langgraph-project) or [`new-langgraphjs-project` template](https://github.com/langchain-ai/new-langgraphjs-project).
 1. Click the `Fork` button in the top right corner to fork the repository to your GitHub account.
 1. Click **Create fork**. 

@@ -30,14 +21,9 @@ To deploy a LangGraph application to **LangGraph Platform**, your application co

 1. Log in to [LangSmith](https://smith.langchain.com/).
 1. In the left sidebar, select **LangGraph Platform**.
-1. Click the **+ New Deployment** button. A modal will open where you can fill in the required fields.
+1. Click the **+ New Deployment** button. A pane will open where you can fill in the required fields.
 1. If you are a first time user or adding a private repository that has not been previously connected, click the **Import from GitHub** button and follow the instructions to connect your GitHub account.
-1. Select your ReAct Agent repository.
-1. In the **Environment Variables** section, set the following secrets:
-    
-    - **ANTHROPIC_API_KEY**: Get an API key from [Anthropic](https://console.anthropic.com/).
-    - **TAVILY_API_KEY**: Get an API key on the [Tavily website](https://app.tavily.com/).
-
+1. Select your New LangGraph Project repository.
 1. Click **Submit** to deploy.

    This may take about 15 minutes to complete. You can check the status in the **Deployment details** view.
@@ -52,7 +38,7 @@ Once your application is deployed:
    LangGraph Studio will open to display your graph.

    <figure markdown="1">
-    [![image](deployment/img/09_langgraph_studio.png){: style="max-height:400px"}](deployment/img/09_langgraph_studio.png)
+    [![image](deployment/img/langgraph_studio.png){: style="max-height:400px"}](deployment/img/langgraph_studio.png)
    <figcaption>
        Sample graph run in LangGraph Studio.
    </figcaption>
@@ -129,7 +115,7 @@ You can now test the API:
            print("\n\n")
        ```

-=== "Javascript SDK"
+=== "JavaScript SDK"

    1. Install the LangGraph JS SDK

@@ -185,7 +171,7 @@ You can now test the API:
    ```


-## Next Steps
+## Next steps

 Congratulations! You have deployed an application using LangGraph Platform.

@@ -8,15 +8,6 @@ Before you begin, ensure you have the following:

 - An API key for [LangSmith](https://smith.langchain.com/settings) - free to sign up

-This quickstart uses the [pre-built Python ReAct agent template](https://github.com/langchain-ai/react-agent), which requires the following:
-
- An API key for [Anthropic](https://console.anthropic.com/)
- An API key for [Tavily](https://app.tavily.com/)
-
-!!! note
-
-    If you want to use a scaffold application that doesn't require API keys, use the [New LangGraph Project](https://github.com/langchain-ai/new-langgraph-project) template instead.
-
 ## 1. Install the LangGraph CLI

 ```bash
@@ -27,18 +18,18 @@ pip install --upgrade "langgraph-cli[inmem]"

 ## 2. Create a LangGraph app 🌱 

-Create a new app from the `react-agent` template. This template is a simple agent that can be flexibly extended to many tools.
+Create a new app from the [`new-langgraph-project` template](https://github.com/langchain-ai/new-langgraph-project) or [`new-langgraphjs-project` template](https://github.com/langchain-ai/new-langgraphjs-project). This template demonstrates a simple chatbot that maintains chat memory, which allows for coherent conversations across multiple interactions.

-=== "Python Server"
+=== "Python server"

    ```shell
-    langgraph new path/to/your/app --template react-agent-python 
+    langgraph new path/to/your/app --template new-langgraph-project 
    ```

-=== "Node Server"
+=== "Node server"

    ```shell
-    langgraph new path/to/your/app --template react-agent-js
+    langgraph new path/to/your/app --template new-langgraphjs-project 
    ```

 !!! tip "Additional templates"
@@ -69,21 +60,18 @@ You will find a `.env.example` in the root of your new LangGraph app. Create a `

 ```bash
 LANGSMITH_API_KEY=lsv2...
-TAVILY_API_KEY=tvly-...
-ANTHROPIC_API_KEY=sk-
 ```

 ## 5. Launch LangGraph Server 🚀 

 Start the LangGraph API server locally:

-=== "Python Server"
+=== "Python server"

    ```shell
    langgraph dev
    ```
-
-=== "Node Server"
+=== "Node server"

    ```shell
    npx @langchain/langgraph-cli dev
@@ -187,7 +175,7 @@ For a LangGraph Server running on a custom host/port, update the baseURL paramet
            print(chunk.data)
            print("\n\n")
        ```
-
+        
 === "Javascript SDK"

    1. Install the LangGraph JS SDK:
@@ -244,7 +232,7 @@ For a LangGraph Server running on a custom host/port, update the baseURL paramet
        }" 
    ```

-## Next Steps
+## Next steps

 Now that you have a LangGraph app running locally, take your journey further by exploring deployment and advanced features: