AI agent web search using SearchAPI & LLM

Open on n8n.io

$20/month : Unlimited workflows

2500 executions/month

Try free

THE #1 IN WEB SCRAPING

Scrape any website without limits

Try free

HOSTINGER

Early Deal
DISCOUNT 20%

Self-hosted n8n

Unlimited workflows - from $4.99/mo

Try free

#1 hub for scraping, AI & automation

6000+ actors - $5 credits/mo

Try free

Important notice

This workflow is provided as-is. Please review and test before using in production.

1. Workflow Overview

AI Agent Web Search using SearchApi & LLM Who is this for? This workflow is ideal for anyone conducting online research , including students , researchers , content creators , and professionals ...

Best for

Miscellaneous automation workflows
AI RAG automation workflows
intermediate n8n builders looking for reusable templates

Tools used

@n8n/n8n-nodes-langchain.chattrigger, @n8n/n8n-nodes-langchain.memorybufferwindow, @n8n/n8n-nodes-langchain.agent, n8n-nodes-base.stickynote, @searchapi/n8n-nodes-searchapi.searchapitool, @n8n/n8n-nodes-langchain.lmchatopenai

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Pedro Santos.

Original n8n.io source

1.1 Workflow description

Title: AI agent web search using SearchAPI & LLM
Workflow name: AI agent web search using SearchAPI & LLM

🤖 AI Agent Web Search using SearchApi & LLM

Who is this for?

This workflow is ideal for anyone conducting online research, including students, researchers, content creators, and professionals looking for accurate, up-to-date, and verifiable information. It also serves as an excellent foundation for building more sophisticated AI-driven applications.

What problem does this workflow solve? / Use case

This workflow automates web searches by enabling an AI agent to efficiently retrieve and summarize external, verifiable information, ensuring accuracy through source citations.

What this workflow does

Connects an AI agent node to SearchApi.io as an integrated search tool.
Empowers the AI agent to perform real-time web searches using various SearchApi engines (e.g., Google, Bing).
Allows the AI agent to dynamically determine search parameters based on user interaction, delivering contextually relevant results.
Ensures responses include clearly cited sources for validation and further exploration.

Setup

Install the SearchApi community node:
- Open Settings → Community Nodes inside your self‑hosted n8n instance.
- Fill npm Package Name with @searchapi/n8n-nodes-searchapi.
- Accept the risk prompt, and hit Install.
- It should now appear as a node when you search for it.
API Configuration:
- Set up your SearchApi.io credentials in n8n.
- Add your preferred LLM provider credentials (e.g., OpenRouter API).
Input Requirements:
- Provide the YouTube video ID (e.g., wBuULAoJxok).
Connect LLM Integration:
- Configure the summarization chain with your chosen model and parameters for text splitting.

How to customize this workflow to your needs

Integrate additional nodes to structure or store search results (e.g., saving to databases, Notion, Google Sheets).
Extend chatbot capabilities to integrate with messaging platforms (Slack, Discord) or email notifications.
Adjust search parameters and filters within the AI agent node to tailor information retrieval.

Example Usage

Input: User asks, "What are the latest developments in AI regulation?"
Output: AI retrieves, summarizes, and cites recent, authoritative articles and news sources from the web.

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - When chat message received

Type / Role: @n8n/n8n-nodes-langchain.chatTrigger - chatTrigger
Config choices: Version 1.1

Block 2 - Simple Memory

Type / Role: @n8n/n8n-nodes-langchain.memoryBufferWindow - memoryBufferWindow
Config choices: Version 1.3

Block 3 - AI Agent

Type / Role: @n8n/n8n-nodes-langchain.agent - agent
Config choices: Version 1.8

Block 4 - Sticky Note

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 5 - Sticky Note1

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 6 - SearchApi

Type / Role: @searchapi/n8n-nodes-searchapi.searchApiTool - searchApiTool
Config choices: Version 1

Block 7 - OpenAI Chat Model

Type / Role: @n8n/n8n-nodes-langchain.lmChatOpenAi - lmChatOpenAi
Config choices: Version 1.2

3. Summary Table

Workflow	AI agent web search using SearchAPI & LLM
Complexity	intermediate
Nodes	7
Categories	Miscellaneous, AI RAG
Author	Pedro Santos
Published	02 May 2025

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

Use the JSON export at /data/workflows/3829/3829.json as the source template for this automation.
2. Import the template into n8n

Open n8n, import the downloaded JSON, and review each node before activating the workflow.
3. Configure credentials and variables

Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.
4. Test with sample data

Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.
5. Activate and monitor

Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Download workflow JSON Original n8n.io source Miscellaneous workflows AI RAG workflows

Frequently asked questions

What does AI agent web search using SearchAPI & LLM do?

AI Agent Web Search using SearchApi & LLM Who is this for? This workflow is ideal for anyone conducting online research , including students , researchers , content creators , and professionals ...

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your Miscellaneous, AI RAG use case.

Pedro Santos

2 workflows

Nodes

@n8n/n8n-nodes-langchain.chattrigger @n8n/n8n-nodes-langchain.memorybufferwindow @n8n/n8n-nodes-langchain.agent n8n-nodes-base.stickynote @searchapi/n8n-nodes-searchapi.searchapitool @n8n/n8n-nodes-langchain.lmchatopenai

Complexity

intermediate

Published 02 May 2025

Likes 0

View on n8n.io Download Workflow

Install path: /data/workflows/3829/3829.json

Share Your Workflow

Have a useful automation to share? Publish it and help the community.

Submit Your Template How to Submit

Related Workflows

Predict airport queue wait times and email alerts with OpenAI and SendGrid

## Quick Overview This workflow accepts traveler flight details via webhook or runs every 5 minutes, predicts airport queue wait times with a custom JavaScript model, generates an alert message using OpenAI, emails the traveler via SendGrid, and logs the prediction to Google Sheets. ## How it works 1. Receives a POST request to a webhook with traveler/flight details or runs on a 5-minute schedule. 2. Normalizes the incoming data into a consistent context (flight, airport/terminal, traveler contact details, and live queue inputs). 3. Waits briefly to throttle processing, then calculates predicted security, immigration, and boarding wait times plus risk flags and an optimal arrival time. 4. Sends the prediction to OpenAI to generate a short, traveler-friendly alert message. 5. Formats the final alert payload (alert level, email subject/body) and prepares a row for tracking. 6. Sends the alert email through the SendGrid Mail Send API and appends the prediction record to a Google Sheets tab. ## Setup 1. Configure the webhook URL in the system that submits traveler requests (POST to `/airport-queue-check`) or enable the schedule trigger for proactive runs. 2. Add OpenAI credentials and select the chat model used to generate the traveler message. 3. Add Google Sheets OAuth2 credentials and replace `YOUR_SHEET_ID` and the target range (for example, `Predictions!A1:append`) in the Google Sheets request URL. 4. Add your SendGrid API key by replacing `YOUR_SENDGRID_API_KEY` in the Authorization header, and update the sender/recipient fields (including ensuring `travelerEmail` is provided by the trigger payload).

View

Send transactional SMS with the OVHcloud SMS API

## Quick overview This workflow manually triggers an HTTP request to the OVHcloud SMS API, signing it with your OVH application credentials to send a transactional SMS to a specified phone number. ## How it works 1. Runs when you manually execute the workflow. 2. Sets the OVHcloud API credentials, SMS service name, sender, and target API region. 3. Defines the SMS recipient number and message text to send. 4. Generates the OVHcloud request URL, JSON body, timestamp, and SHA1-based X-Ovh-Signature headers. 5. Sends a POST request to the OVHcloud endpoint `/sms/{serviceName}/jobs` to create an SMS sending job. ## Setup 1. Create OVHcloud API application credentials (Application Key and Application Secret) and a Consumer Key with SMS permissions. 2. Replace the placeholder values for `APPLICATION_KEY`, `APPLICATION_SECRET`, `CONSUMER_KEY`, `SMS_SERVICE_NAME`, `SMS_SENDER`, and `OVH_REGION`. 3. Update the `receiver` (E.164 format) and `message` fields with the SMS details you want to send, and ensure your OVHcloud SMS account has available credits. ## Requirements - OVH account - SMS credits (API account)

View

Tutor English chat messages using OpenRouter with Postgres memory and log to Supabase

## Quick overview This workflow receives English practice messages via a webhook, uses an OpenRouter chat model with Postgres-backed conversation memory to generate tutoring feedback, logs the exchange to Supabase, and returns the tutor’s reply as a JSON response. ## How it works 1. Receives a POST webhook request containing a `user_id` and `message`. 2. Extracts and standardizes the incoming fields so the workflow has clean `user_id` and `message` values. 3. Sends the message to an AI English tutor powered by OpenRouter, using Postgres chat memory keyed by `user_id` to maintain per-student context. 4. Logs the tutor output to a Supabase `conversations` table along with the user identifier and original message. 5. Returns a JSON response to the caller containing the tutor’s reply. ## Setup 1. Add an OpenRouter API credential and (optionally) choose a different model in the OpenRouter chat model configuration. 2. Add Postgres credentials and ensure the database is reachable from n8n so chat memory can persist sessions by `user_id`. 3. Add Supabase credentials and create a `conversations` table, then confirm the mapped columns (`user_id`, `role`, `message`) match your schema. 4. Copy the webhook URL from n8n and configure your app to POST a JSON body with `user_id` and `message` to that endpoint.

View

Need Custom Automation?

Get help designing a custom n8n workflow that connects your stack and fits your process.

AI agent web search using SearchAPI & LLM

Workflow preview

Important notice

1. Workflow Overview

Best for

Tools used

Source and attribution

1.1 Workflow description

🤖 AI Agent Web Search using SearchApi & LLM

Who is this for?

What problem does this workflow solve? / Use case

What this workflow does

Setup

How to customize this workflow to your needs

Example Usage

1.2 Logical Blocks

2. Block-by-Block Analysis

Block 1 - When chat message received

Block 2 - Simple Memory

Block 3 - AI Agent

Block 4 - Sticky Note

Block 5 - Sticky Note1

Block 6 - SearchApi

Block 7 - OpenAI Chat Model

3. Summary Table

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

2. Import the template into n8n

3. Configure credentials and variables

4. Test with sample data

5. Activate and monitor

5. General Notes & Resources

Frequently asked questions