← All N8N workflows
AI & researchAgentChain SummarizationCodeDocument Default Data LoaderGmail

Chunk the transcript into several parts, and refine-summarize it

Configured with Agent, Chain Summarization, Document Default Data Loader, Gmail, and additional nodes. Review the connections and setup before adapting this template.

Workflow preview
TriggerWhen clicking "ExecuteWorkflow"Manual TriggerFiles / mediaDefault Data LoaderDocument Default Data Lo…AI & modelsOpenAI Chat ModelOpenAI Chat ModelAI & modelsAI AgentAgentIntegrationWikipediaTool WikipediaCodePodcast EpisodeTranscriptCodeAI & modelsSummarize TranscriptChain SummarizationTransformRecursive CharacterText SplitterText Splitter Recursive …AI & modelsExtract Topics &QuestionsInformation ExtractorAI & modelsOpenAI Chat Model3OpenAI Chat ModelTransformTopicsSplit OutAI & modelsOpenAI Chat Model1OpenAI Chat ModelCodeFormat topic text &titleCodeMessagingSend DigestGmail

Node categories in this workflow

  • Trigger
  • Files / media
  • AI & models
  • Integration
  • Code
  • Transform
  • Messaging

Icons describe general node roles, inferred from node types. Inspect the parameters for the configured action.

Drag to pan; use + and − to zoom. Reconstructed from the exported node positions; nothing runs here. Dashed lines represent non-main connections. Full node names and notes appear below.

How it works

The exported workflow contains the following configured nodes. Their connections are shown above; inspect the JSON for the complete logic, expressions, and external actions.

Workflow node names, types, and operations
NodeCategoryTypeOperation
When clicking "Execute Workflow"TriggerManual TriggerSee node parameters
Default Data LoaderFiles / mediaDocument Default Data LoaderSee node parameters
OpenAI Chat ModelAI & modelsOpenAI Chat ModelSee node parameters
AI AgentAI & modelsAgentSee node parameters
WikipediaIntegrationTool WikipediaSee node parameters
Podcast Episode TranscriptCodeCodeSee node parameters
Summarize TranscriptAI & modelsChain SummarizationSee node parameters
Recursive Character Text SplitterTransformText Splitter Recursive Character Text SplitterSee node parameters
Extract Topics & QuestionsAI & modelsInformation ExtractorSee node parameters
OpenAI Chat Model3AI & modelsOpenAI Chat ModelSee node parameters
TopicsTransformSplit OutSee node parameters
OpenAI Chat Model1AI & modelsOpenAI Chat ModelSee node parameters
Format topic text & titleCodeCodeSee node parameters
Send DigestMessagingGmailSee node parameters

Setup

  1. Download the JSON and import it into an isolated n8n instance. Leave the workflow inactive.
  2. Connect your own credentials through n8n’s credential store. Replace REPLACE_WITH_* values with your resource identifiers.
  3. Inspect API destinations, Code nodes, database queries, file paths, and outbound actions.
  4. Run with synthetic data and harmless destinations. Enable triggers only after checking the actual outputs.

Requirements

An n8n instance with the listed node types and compatible versions. Service-connected workflows may require accounts, credentials, or paid APIs.

Credential types declared in the source

  • gmailOAuth2
  • openAiApi

Workflow notes

Chunk the transcript into several parts, and refine-summarize it

Chunk the transcript into several parts, and refine-summarize it

Purpose and structure

This folder contains the Chunk the transcript into several parts, and refine-summarize it workflow. Its executable nodes use agent, chainSummarization, code, documentDefaultDataLoader, gmail, informationExtractor, lmChatOpenAi, manualTrigger, splitOut, textSplitterRecursiveCharacterTextSplitter, toolWikipedia. The table and connection map below are derived from the JSON, not an inferred guarantee of behavior.

Setup

Import inactive. Configure your own credentials and replace REPLACE_WITH_* values. Review external destinations and Code nodes before running.

Entry points

When clicking "Execute Workflow"

Verification

Sanitized source candidate; not runtime-tested. This overview is generated from node metadata. Read the folder README for the connection map, credential types, and license.

Attribution

https://github.com/Zie619/n8n-workflows/blob/94007c1445d9258a7da116646b79473e7c7c3282/workflows/Splitout/0322_Splitout_Code_Send_Triggered.json MIT; preserve source notices.

Canvas section labels

These name areas of the original canvas; they do not include explanatory instructions.

  • Chunk the transcript into several parts, and refine-summarize it
  • Generate Questions and Topics from the summary and make sure the response follows required schema.
  • Ask Agent to research and explain each topic using Wikipedia
  • Format as HTML and send via Gmail

More in AI & research