Automated research report generation with AI, Wiki, Search & Gmail/Telegram
Needs changesWhat this workflow does
This AI workflow has 25 nodes and runs when another workflow calls it (plus 1 other trigger). Along the way it connects OpenAI Chat Model, HTTP Request, Google Sheets and Gmail and 2 more. It also calls api.pdfshift.io over HTTP.
How it runs
Trigger: When another workflow calls it (plus 1 other trigger).
- Input Validation (Code): runs custom JavaScript code
- Query Refiner (AI Agent): runs an AI agent, with model: OpenAI Chat Model; output parser: Structured Output Parser
- Research AI Agent (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 4 tools (SerpApi, Wikipedia, Search News, Google Search Web); memory: Simple Memory
- Parse Research Output (Code): runs custom JavaScript code
- Split Out: splits a list into separate items
- Merge Split Items (Code): runs custom JavaScript code
- Aggregate: combines items into one
- Store Research Metadata (Google Sheets): append
- Generate PDF HTML (Code): runs custom JavaScript code
- Convert HTML to PDF (HTTP Request): calls api.pdfshift.io (POST)
…plus 5 more steps. See the full node list below.
Services it uses
HTTP calls to: api.pdfshift.io
Before you upgrade to n8n 3.0
2 things in this workflow are removed in n8n 3.0. Fix them before you upgrade:
- HTTP Request Tool (legacy) in Search News, Wikipedia, Google Search Web…: replace with HTTP Request node connected to the AI Agent's Tool input.
- AI Agent v1 (old agent modes) in Query Refiner (v1.8), Research AI Agent (v1.8): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| HTTP Request Tool (legacy) Search News, Wikipedia, Google Search Web, SerpApi | HTTP Request node connected to the AI Agent's Tool input |
| AI Agent v1 (old agent modes) Query Refiner (v1.8), Research AI Agent (v1.8) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (16)
- OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - HTTP Request Tool
@n8n/n8n-nodes-langchain.toolHttpRequest - AI Agent
@n8n/n8n-nodes-langchain.agent - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Split Out
n8n-nodes-base.splitOut - Code
n8n-nodes-base.code - Google Sheets
n8n-nodes-base.googleSheets - HTTP Request
n8n-nodes-base.httpRequest - Aggregate
n8n-nodes-base.aggregate - Gmail
n8n-nodes-base.gmail - Manual Trigger
n8n-nodes-base.manualTrigger - Telegram
n8n-nodes-base.telegram - Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - Google Drive
n8n-nodes-base.googleDrive - If
n8n-nodes-base.if
From the author
Automated Research Report Generation with OpenAI, Wikipedia, Google Search, Gmail/Telegram and PDF Output --- Description What Problem Does This Solve? 🛠️ This workflow automates the process of generating professional research reports for researchers,…