Extract and Summarize Bing Copilot Search Results with Gemini AI

This n8n workflow automates the process of extracting search results from Bing Copilot, processing them, and then summarizing the content using Google Gemini AI. It's designed to efficiently gather information from search queries and provide concise summaries.

What it does

This workflow performs the following key steps:

1. Manual Trigger: Initiates the workflow manually, allowing you to start the process on demand.
2. HTTP Request: Sends an HTTP request to an external service (likely a web scraping API like Bright Data, given the directory name context, though not explicitly defined in the JSON) to perform a Bing Copilot search.
3. Edit Fields (Set): Prepares the extracted data for further processing, likely by selecting or renaming relevant fields.
4. If: Checks if the HTTP request was successful and if there are valid results to process.
5. Default Data Loader: If results are found, it loads the raw search result content as a document for AI processing.
6. Recursive Character Text Splitter: Divides the loaded document into smaller, manageable chunks to optimize for AI model input limits.
7. Google Gemini Chat Model: Configures the Google Gemini AI model to be used for summarization.
8. Summarization Chain: Feeds the split text into the Google Gemini model to generate a summary of the search results.
9. Structured Output Parser: Parses the AI-generated summary into a structured format (e.g., JSON) for easier consumption or further actions.
10. Wait: If the initial HTTP request fails or no results are found, the workflow pauses, potentially to prevent excessive retries or to allow for manual intervention.

Prerequisites/Requirements

To use this workflow, you will need:

• n8n Instance: A running n8n instance.
• Google Gemini API Key: Credentials for the Google Gemini AI model.
• Web Scraping Service: An account and API key for a web scraping service capable of interacting with Bing Copilot (e.g., Bright Data, as suggested by the directory name). This is configured within the "HTTP Request" node.

Setup/Usage

1. Import the workflow: Download the provided JSON and import it into your n8n instance.
2. Configure Credentials:
   • Google Gemini Chat Model: Configure your Google Gemini API key in the "Google Gemini Chat Model" node.
   • HTTP Request: Update the "HTTP Request" node with the URL, headers, and body required by your chosen web scraping service (e.g., Bright Data) to perform a Bing Copilot search. Ensure you include your API key or authentication tokens.
3. Customize Search Query: Modify the "HTTP Request" node to define the search query you want to use for Bing Copilot.
4. Execute the workflow: Click "Execute workflow" on the "Manual Trigger" node to run the workflow.
5. Review Results: The summarized search results will be available at the output of the "Structured Output Parser" node. You can then integrate further nodes to store these results (e.g., Google Sheets, database, email).