Google Search Engine Results Page (SERP) Extraction and Summarization with Bright Data

This n8n workflow automates the process of extracting information from Google Search Engine Results Pages (SERPs) using Bright Data and then summarizing and extracting key details from the results using AI.

What it does

This workflow performs the following steps:

1. Manual Trigger: Starts the workflow manually when executed.
2. HTTP Request Tool (Bright Data): Makes an HTTP request to the Bright Data SERP API to fetch Google search results for a specified query. This node is configured as a LangChain tool, allowing the AI Agent to use it.
3. Google Gemini Chat Model: Defines the AI chat model (Google Gemini) that will be used by the AI Agent and Summarization Chain.
4. AI Agent: Utilizes a LangChain AI Agent to intelligently interact with the Bright Data HTTP Request Tool. It can decide when and how to use the tool to get the necessary information based on the prompt.
5. Edit Fields: Transforms the output from the AI Agent, specifically extracting the output field and renaming it to serpResult.
6. Summarization Chain: Takes the extracted serpResult and generates a concise summary of the content using the configured Google Gemini Chat Model.
7. Information Extractor: Parses the summarized content to extract structured information, such as specific entities or data points, based on a defined schema.

Prerequisites/Requirements

• n8n Instance: A running n8n instance.
• Bright Data Account: An active Bright Data account with access to their SERP API. You will need your Bright Data API credentials.
• Google Gemini API Key: An API key for the Google Gemini Chat Model.

Setup/Usage

1. Import the workflow: Import the provided JSON into your n8n instance.
2. Configure Credentials:
   • Bright Data HTTP Request Tool: Set up your Bright Data API credentials within the "HTTP Request Tool" node. This typically involves setting the API endpoint, headers (e.g., Authorization with your Bright Data API key), and any necessary query parameters for the SERP API.
   • Google Gemini Chat Model: Configure your Google Gemini API key in the "Google Gemini Chat Model" node.
3. Customize the Search Query:
   • In the "AI Agent" node, you will need to define the prompt that guides the agent. This prompt should include the search query you want to use for the Bright Data SERP API. For example, "Search Google for 'latest AI trends' and summarize the top results."
4. Define Information Extraction Schema (Optional):
   • If you want to extract specific structured data, configure the "Information Extractor" node with the desired schema. This tells the AI what kind of information to look for and how to format it (e.g., "Extract the title, URL, and a brief description for each search result").
5. Execute the workflow: Click "Execute workflow" in the "Manual Trigger" node to run the workflow.

The workflow will then fetch SERP data, summarize it, and extract structured information, which can then be used for further automation or analysis.