Skip to main content
Version: 1.10.x

Langflow TypeScript client

The Langflow TypeScript client allows your TypeScript applications to programmatically interact with the Langflow API.

For the client code repository, see langflow-client-ts.

For the npm package, see @datastax/langflow-client.

Install the Langflow TypeScript package​

To install the Langflow typescript client package, use one of the following commands:

npm install @datastax/langflow-client

Initialize the Langflow TypeScript client​

  1. Import the client into your code.

    import { LangflowClient } from "@datastax/langflow-client";

  2. Initialize a LangflowClient object to interact with your server:

    const baseUrl = "BASE_URL";
    const apiKey = "API_KEY";
    const client = new LangflowClient({ baseUrl, apiKey });

    Replace BASE_URL and API_KEY with values from your deployment. The default Langflow base URL is http://localhost:7860. To create an API key, see API keys and authentication.

Connect to your server and get responses​

  1. With your Langflow client initialized, test the connection by calling your Langflow server.

    The following example runs a flow (runFlow) by sending the flow ID and a chat input string:

    import { LangflowClient } from "@datastax/langflow-client";

    const baseUrl = "http://localhost:7860";
    const client = new LangflowClient({ baseUrl });

    async function runFlow() {
        const flowId = "aa5a238b-02c0-4f03-bc5c-cc3a83335cdf";
        const flow = client.flow(flowId);
        const input = "Is anyone there?";

        const response = await flow.run(input);
        console.log(response);
    }

    runFlow().catch(console.error);

    Replace the following:

    • baseUrl: The URL of your Langflow server.
    • flowId: The ID of the flow you want to run.
    • input: The chat input message you want to send to trigger the flow. This is only valid for flows with a Chat Input component.

  2. Review the result to confirm that the client connected to your Langflow server.

    The following example shows the response from a well-formed runFlow request that reached the Langflow server and successfully started the flow:

    FlowResponse {
      sessionId: 'aa5a238b-02c0-4f03-bc5c-cc3a83335cdf',
      outputs: [ { inputs: [Object], outputs: [Array] } ]
    }

    In this case, the response includes a sessionID that is a unique identifier for the client-server session and an outputs array that contains information about the flow run.

  3. Optional: If you want to get full response objects from the server, change console.log to stringify the returned JSON object:

    console.log(JSON.stringify(response, null, 2));

    The exact structure of the returned inputs and outputs objects depends on the components and configuration of your flow.

  4. Optional: If you want the response to include only the chat message from the Chat Output component, change console.log to use the chatOutputText convenience function:

    console.log(response.chatOutputText());

Use advanced TypeScript client features​

The TypeScript client can do more than just connect to your server and run a flow.

This example builds on the quickstart with additional features for interacting with Langflow:

  1. Pass tweaks as an object with the request. Tweaks are programmatic run-time overrides for component settings.

    This example changes the LLM used by a language model component in a flow::

    const tweaks = { model_name: "gpt-4o-mini" };

  2. Pass a session ID with the request to separate the conversation from other flow runs, and to be able to continue this conversation by calling the same session ID in the future:

    const session_id = "aa5a238b-02c0-4f03-bc5c-cc3a83335cdf";

  3. Instead of calling run on the Flow object, call stream with the same arguments to get a streaming response:

    const response = await client.flow(flowId).stream(input);

    for await (const event of response) {
      console.log(event);
    }

    The response is a ReadableStream of objects. For more information on streaming Langflow responses, see the /run endpoint.

  4. Run the modified TypeScript application to run the flow with tweaks, session_id, and streaming:

    import { LangflowClient } from "@datastax/langflow-client";

    const baseUrl = "http://localhost:7860";
    const client = new LangflowClient({ baseUrl });

    async function runFlow() {
        const flowId = "aa5a238b-02c0-4f03-bc5c-cc3a83335cdf";
        const input = "Is anyone there?";
        const tweaks = { model_name: "gpt-4o-mini" };
        const session_id = "test-session";

        const response = await client.flow(flowId).stream(input, {
            session_id,
            tweaks,
          });

        for await (const event of response) {
            console.log(event);
        }

    }
    runFlow().catch(console.error);

    Replace the following:

    • baseUrl: The URL of your Langflow server.
    • flowId: The ID of the flow you want to run.
    • input: The chat input message you want to send to trigger the flow, assuming the flow has a Chat Input component.
    • tweaks: Any tweak modifiers to apply to the flow run. This example changes the LLM used by a component in the flow.
    • session_id: Pass a custom session ID. If omitted or empty, the flow ID is the default session ID.
    Result

    With streaming enabled, the response includes the flow metatadata and timestamped events for flow activity. For example:

    {
      event: 'add_message',
      data: {
        timestamp: '2025-05-23 15:52:48 UTC',
        sender: 'User',
        sender_name: 'User',
        session_id: 'test-session',
        text: 'Is anyone there?',
        files: [],
        error: false,
        edit: false,
        properties: {
          text_color: '',
          background_color: '',
          edited: false,
          source: [Object],
          icon: '',
          allow_markdown: false,
          positive_feedback: null,
          state: 'complete',
          targets: []
        },
        category: 'message',
        content_blocks: [],
        id: '7f096715-3f2d-4d84-88d6-5e2f76bf3fbe',
        flow_id: 'aa5a238b-02c0-4f03-bc5c-cc3a83335cdf',
        duration: null
      }
    }
    {
      event: 'token',
      data: {
        chunk: 'Absolutely',
        id: 'c5a99314-6b23-488b-84e2-038aa3e87fb5',
        timestamp: '2025-05-23 15:52:48 UTC'
      }
    }
    {
      event: 'token',
      data: {
        chunk: ',',
        id: 'c5a99314-6b23-488b-84e2-038aa3e87fb5',
        timestamp: '2025-05-23 15:52:48 UTC'
      }
    }
    {
      event: 'token',
      data: {
        chunk: " I'm",
        id: 'c5a99314-6b23-488b-84e2-038aa3e87fb5',
        timestamp: '2025-05-23 15:52:48 UTC'
      }
    }
    {
      event: 'token',
      data: {
        chunk: ' here',
        id: 'c5a99314-6b23-488b-84e2-038aa3e87fb5',
        timestamp: '2025-05-23 15:52:48 UTC'
      }
    }

    // this response is abbreviated

    {
      event: 'end',
      data: { result: { session_id: 'test-session', outputs: [Array] } }
    }

Retrieve Langflow logs with the TypeScript client​

To retrieve Langflow logs, you must enable log retrieval on your Langflow server by including the following values in your Langflow .env file:

LANGFLOW_ENABLE_LOG_RETRIEVAL=True
LANGFLOW_LOG_RETRIEVER_BUFFER_SIZE=10000
LANGFLOW_LOG_LEVEL=DEBUG

The following example script starts streaming logs in the background, and then runs a flow so you can monitor the flow run:

import { LangflowClient } from "@datastax/langflow-client";

const baseUrl = "http://localhost:7863";
const flowId = "86f0bf45-0544-4e88-b0b1-8e622da7a7f0";

async function runFlow(client: LangflowClient) {
    const input = "Is anyone there?";
    const response = await client.flow(flowId).run(input);
    console.log('Flow response:', response);
}

async function main() {
    const client = new LangflowClient({ baseUrl: baseUrl });

    // Start streaming logs
    console.log('Starting log stream...');
    for await (const log of await client.logs.stream()) {
        console.log('Log:', log);
    }

    // Run the flow
    await runFlow(client);

}

main().catch(console.error);

Replace the following:

  • baseUrl: The URL of your Langflow server.
  • flowId: The ID of the flow you want to run.
  • input: The chat input message you want to send to trigger the flow, assuming the flow has a Chat Input component.

Logs begin streaming indefinitely, and the flow runs once.

Result

The following example result is truncated for readability, but you can follow the messages to see how the flow instantiates its components, configures its model, and processes the outputs.

The FlowResponse object, at the end of the stream, is returned to the client with the flow result in the outputs array.

Starting log stream...
Log: Log {
  timestamp: 2025-05-30T11:49:16.006Z,
  message: '2025-05-30T07:49:16.006127-0400 DEBUG Instantiating ChatInput of type component\n'
}
Log: Log {
  timestamp: 2025-05-30T11:49:16.029Z,
  message: '2025-05-30T07:49:16.029957-0400 DEBUG Instantiating Prompt of type component\n'
}
Log: Log {
  timestamp: 2025-05-30T11:49:16.049Z,
  message: '2025-05-30T07:49:16.049520-0400 DEBUG Instantiating ChatOutput of type component\n'
}
Log: Log {
  timestamp: 2025-05-30T11:49:16.069Z,
  message: '2025-05-30T07:49:16.069359-0400 DEBUG Instantiating OpenAIModel of type component\n'
}
Log: Log {
  timestamp: 2025-05-30T11:49:16.086Z,
  message: "2025-05-30T07:49:16.086426-0400 DEBUG Running layer 0 with 2 tasks, ['ChatInput-xjucM', 'Prompt-I3pxU']\n"
}
Log: Log {
  timestamp: 2025-05-30T11:49:16.101Z,
  message: '2025-05-30T07:49:16.101766-0400 DEBUG Building Chat Input\n'
}
Log: Log {
  timestamp: 2025-05-30T11:49:16.113Z,
  message: '2025-05-30T07:49:16.113343-0400 DEBUG Building Prompt\n'
}
Log: Log {
  timestamp: 2025-05-30T11:49:16.131Z,
  message: '2025-05-30T07:49:16.131423-0400 DEBUG Logged vertex build: 6bd9fe9c-5eea-4f05-a96d-f6de9dc77e3c\n'
}
Log: Log {
  timestamp: 2025-05-30T11:49:16.143Z,
  message: '2025-05-30T07:49:16.143295-0400 DEBUG Logged vertex build: 39c68ec9-3859-4fff-9b14-80b3271f8fbf\n'
}
Log: Log {
  timestamp: 2025-05-30T11:49:16.188Z,
  message: "2025-05-30T07:49:16.188730-0400 DEBUG Running layer 1 with 1 tasks, ['OpenAIModel-RtlZm']\n"
}
Log: Log {
  timestamp: 2025-05-30T11:49:16.201Z,
  message: '2025-05-30T07:49:16.201946-0400 DEBUG Building OpenAI\n'
}
Log: Log {
  timestamp: 2025-05-30T11:49:16.216Z,
  message: '2025-05-30T07:49:16.216622-0400 INFO Model name: gpt-4.1-mini\n'
}
Flow response: FlowResponse {
  sessionId: '86f0bf45-0544-4e88-b0b1-8e622da7a7f0',
  outputs: [ { inputs: [Object], outputs: [Array] } ]
}
Log: Log {
  timestamp: 2025-05-30T11:49:18.094Z,
  message: `2025-05-30T07:49:18.094364-0400 DEBUG Vertex OpenAIModel-RtlZm, result: <langflow.graph.utils.UnbuiltResult object at 0x364d24dd0>, object: {'text_output': "Hey there! I'm here and ready to help you build something awesome with AI. What are you thinking about creating today?"}\n`
}

For more information, see Logs endpoints.

Was this page helpful?

Support
Search