Skip to main content

Quickstart

Get started with OpenRAG by loading your knowledge, swapping out your language model, and then chatting with the Langflow API.

Prerequisites​

  • Install and start OpenRAG with the TUI or Docker

Load and chat with your own documents​

  1. In OpenRAG, click Chat. The chat is powered by the OpenRAG OpenSearch Agent. For more information, see Langflow in OpenRAG.
  2. Ask What documents are available to you? The agent responds with a message summarizing the documents that OpenRAG loads by default. Knowledge is stored in OpenSearch. For more information, see OpenSearch in OpenRAG.
  3. To confirm the agent is correct about the default knowledge, click Knowledge. The Knowledge page lists the documents OpenRAG has ingested into the OpenSearch vector database. Click on a document to display the chunks derived from splitting the default documents into the OpenSearch vector database.
  4. To add documents to your knowledge base, click Add Knowledge.
    • Select File to add a single file from your local machine.
    • Select Folder to process an entire folder of documents from your local machine. The default directory is /documents in your OpenRAG directory.
    • Select your cloud storage provider to add knowledge from an OAuth-connected storage provider. For more information, see OAuth ingestion.
  5. Return to the Chat window and ask a question about your loaded data. For example, with a manual about a PC tablet loaded, ask How do I connect this device to WiFi? The agent responds with a message indicating it now has your knowledge as context for answering questions.
  6. Click Function Call: search_documents (tool_call). This log describes how the agent uses tools. This is helpful for troubleshooting when the agent isn't responding as expected.

Swap out the language model to modify agent behavior​

To modify the knowledge ingestion or Agent behavior, click Settings.

In this example, you'll try a different LLM to demonstrate how the Agent's response changes.

  1. To edit the Agent's behavior, click Edit in Langflow. You can more quickly access the Language Model and Agent Instructions fields in this page, but for illustration purposes, navigate to the Langflow visual builder. To revert the flow to its initial state, click Restore flow.

  2. OpenRAG warns you that you're entering Langflow. Click Proceed.

    If Langflow requests login information, enter the LANGFLOW_SUPERUSER and LANGFLOW_SUPERUSER_PASSWORD from the .env file in your OpenRAG directory.

    The OpenRAG OpenSearch Agent flow appears in a new browser window. OpenRAG Open Search Agent Flow

  3. Find the Language Model component, and then change the Model Name field to a different OpenAI model.

  4. Save your flow with Command+S (Mac) or Ctrl+S (Windows).

  5. Return to the OpenRAG browser window, and start a new conversation by clicking in the Conversations tab.

  6. Ask the same question you asked before to see how the response differs between models.

Integrate OpenRAG into your application​

Langflow in OpenRAG includes pre-built flows that you can integrate into your applications using the Langflow API.

The Langflow API accepts Python, TypeScript, or curl requests to run flows and get responses. You can use these flows as-is or modify them to better suit your needs.

In this section, you'll run the OpenRAG OpenSearch Agent flow and get a response using the API.

  1. To navigate to the OpenRAG OpenSearch Agent flow in Langflow, click Settings, and then click Edit in Langflow in the OpenRAG OpenSearch Agent flow.

  2. Create a Langflow API key.

    A Langflow API key is a user-specific token you can use with Langflow. It is only used for sending requests to the Langflow server. It does not access OpenRAG.

    To create a Langflow API key, do the following:

    1. Open Langflow, click your user icon, and then select Settings.
    2. Click Langflow API Keys, and then click Add New.
    3. Name your key, and then click Create API Key.
    4. Copy the API key and store it securely.

  3. Langflow includes code snippets for the request to the Langflow API. To retrieve the code snippet, click Share, and then click API access.

    The default code in the API access pane constructs a request with the Langflow server url, headers, and a payload of request data. The code snippets automatically include the LANGFLOW_SERVER_ADDRESS and FLOW_ID values for the flow.

    import requests
    import os
    import uuid

    api_key = 'LANGFLOW_API_KEY'
    url = "http://LANGFLOW_SERVER_ADDRESS/api/v1/run/FLOW_ID"  # The complete API endpoint URL for this flow

    # Request payload configuration
    payload = {
        "output_type": "chat",
        "input_type": "chat",
        "input_value": "hello world!"
    }
    payload["session_id"] = str(uuid.uuid4())

    headers = {"x-api-key": api_key}

    try:
        # Send API request
        response = requests.request("POST", url, json=payload, headers=headers)
        response.raise_for_status()  # Raise exception for bad status codes

        # Print response
        print(response.text)

    except requests.exceptions.RequestException as e:
        print(f"Error making API request: {e}")
    except ValueError as e:
        print(f"Error parsing response: {e}")

  4. Copy the snippet, paste it in a script file, and then run the script to send the request. If you are using the curl snippet, you can run the command directly in your terminal.

If the request is successful, the response includes many details about the flow run, including the session ID, inputs, outputs, components, durations, and more.

To further explore the API, see: