Skip to content

DocSearch Node – Power Your Flows with Context-Driven Search

The DocSearch Node is a Retrieval-Augmented Generation (RAG)-powered component that enhances the real-time discovery and retrieval of information chunks from available resources through an established Search AI app connection. Indexed and high-quality content is fetched from your Sources repository, enabling fast, precise, and context-aware responses to user queries.

Key Capabilities

  • RAG-Powered Search: Combines traditional retrieval (search, databases) with generative LLMs as follows:
    • Retrieval & Pre-processing: Queries indexed content using advanced algorithms, then refines results through tokenization and filtering.
    • Grounded Generation: Integrates refined results with LLMs for accurate and context-rich responses.
  • Seamless SearchAI Integration: Connects to your Search AI App to query indexed documents and return results via the Answer Generation engine.
  • Dynamic Query Support: Supports static and dynamic inputs for flexible, context-aware search automation.
  • Meta Filter Configuration: Use optional meta filters to refine results, or search across all linked documents by default.
  • User Redirection Option: Redirect users to the full Search AI App for a more comprehensive search experience when needed.
  • Precision and Personalization: Delivers context-aware, intent-driven responses aligned to the query, ensuring accurate, relevant, and user-specific outcomes.
  • Flow Integration: Seamlessly connect DocSearch with other nodes to pass queries and process responses.

Common Use Cases

  • Document Retrieval: Retrieve relevant content from indexed sources, such as manuals, policies, or help articles, based on user queries.
  • Contextual Answer Generation: Deliver AI-generated responses grounded in retrieved documents using the RAG framework.
  • Knowledge Base Search: Search internal wikis, technical docs, or training material with support for dynamic inputs and filters.
  • User Query Handling: Accept real-time input queries from other nodes to personalize search results in the workflow context.

Example Use Case

A retail bank uses the DocSearch Node to automate responses to frequently asked questions about loans, accounts, and card services. When a user asks, “What documents are required to apply for a home loan based on my income?”, the node dynamically passes the query to a connected Search AI App, which searches, indexes, and fetches relevant information chunks from internal resources such as loan policy documents, eligibility criteria, and process guidelines. It then returns a precise, context-aware response, reducing call center load and improving self-service efficiency.

How It Works

The DocSearch Node integrates seamlessly into your tool flows, accepting user queries as static text or dynamic variables referencing other node outputs. It connects to a pre-configured Search AI App on the platform to retrieve relevant content from your Sources repository using a Retrieval-Augmented Generation (RAG) framework. You can define meta filters manually or fetch them via the Answer Generation API to generate refined, context-aware responses. The node fully integrates within the canvas and optionally allows redirection to the full Search AI interface.

how doc search works

In this document, you will learn how to add and configure DocSearch Nodes with Search AI connections, set up query inputs and meta filters, handle response outputs, and test the search-driven interactions within your automation flows.

Steps to Add and Configure the Node

Configuring the DocSearch Node consists of the following steps:

  1. Set up a Search AI application and the information source for Agent Platform integration.
  2. Link the Search AI application in Agent Platform.
  3. Add and configure the DocSearch node.
  4. Test the Flow you have built.

Step 1: Set up Search AI App

The integration of Search AI with Agent Platform involves setting up a Search AI application, configuring it for integration, and modifying Agent Platform to interact with Search AI in response to specific conditions or events. Search AI provides REST APIs that enable seamless interaction with any application.

Follow the detailed steps here to complete the configuration.

Note

To receive answers from Search AI, you must enable the Answer Generation option under the API scopes section.

After fetching the Search AI application credentials, configuring the source, and enabling the channel communication via API, you must link the app in Agent Platform.

Steps to integrate Search AI in Agent Platform

  1. Log in to your account and click Autonomous Agents under Agent Platform Modules. import user

  2. Click Settings on the top navigation bar.

  3. Click Integrations on the left navigation menu.

  4. Scroll down to Search AI and click Link an App. link an app

  5. In the Search AI window, provide the required information that you copied from the SearchAI application in Step 1.

  6. Click Test to test the connection.
  7. If the connection is successful, click Confirm. searchai connection form

A success message is displayed and the connection is listed for SearchAI. listed connection

If the connection fails with the following message, check and re-enter the correct Search AI app credentials.

connection failure

Note

Currently, we support connections through Search AI. You must provide "https://platform.kore.ai" for the Search AI URL field.

Step 3: Add and Configure a DocSearch Node

Setting up a DocSearch node in an tool flow involves adding the node at the appropriate location in the flow and configuring various node properties.

Steps to add and configure the node

  1. Log in to your account and click Tools under Agent Platform Modules. access tools

  2. Click the Tools tab on the top navigation bar, and select the tool to which you want to add the node. The Tool Flow page is displayed.

  3. Click Go to flow to edit the in-development version of the flow.

  4. In the flow builder, click DocSearch -> + New DocSearch on the Assets panel. Alternatively, click DocSearch in the bottom panel. add doc search node

  5. To provide a unique name, right-click the node and click Rename since the node is provided a default name.

    rename node

Alternatively, click the node and change the value for Node Name in the configuration panel. node name

  1. Add the input for the Query field to capture the user's search query.

    To accept dynamic inputs, either configure an input variable in the Start node or use the Manage Input Variables feature.

    You can also add plain text for hard-coded inputs like "What does the McKinsey report forecast for Q3 in 2025 based on historic data taken in the past 3 years."

    query field
  2. Select the Search AI connection you set up in Step 2 on the Agent Platform integration page. search ai connection

Note

Use search to look up and select the required connection.

To set up a new connection, click + New Connection. This will redirect you to the Agent Platform Integrations page. Follow the steps mentioned here to complete the integration.

  1. (Optional) Set Meta filters (click the expansion arrow to access the editor) to define rules that will narrow down the search results. For example, if the sources have multiple files, you can define the specific file names to look up in the meta filters code. Learn more. set meta filters

Note

  • If you do not provide any meta filters, the query is applied to all the documents uploaded to that connection.
  • The filters can be a context variable in the flow depending on the builder’s requirement.

Managing Errors

Appropriate canvas-level errors are displayed (in the error log) when you add a new node. You can view and fix the errors by clicking the warning icon.

click run button

Step 4: Test the Flow

To run and test the flow, follow the steps below:

  1. Click the Run Flow button at the top-right corner of the flow builder. click run button

  2. (Optional) Add the value for Input Variable if you have configured it to test the flow in Step 5 of this section. Otherwise, go directly to the next step.

  1. Click Generate Output.
    2. generate output

The Debug window displays the flow log and execution status of each node on the canvas, starting from the Start node to the End node, along with the result shown in the Output window. Learn more about running the tool flow.

Accessing the Output

The answer (extracted chunks) from the node can be accessed via the context variable (key) in the output path. This key is dynamic and depends on the API response. The format is {{context.steps.<<nodename>>.dynamic path}}. For example, it could be context.steps.DocSearch.response.response.answer in one case or context.steps.DocSearch.response.response.response.answer in another. Check the sample response from SearchAI to find the correct key that holds the content. Use that key in your tool flow. You may also need to extract multiple chunks from different keys.