Bear Brown
← All N8N workflows
AI & researchChat TriggerCodeDocument Default Data LoaderEmbeddings Open AiHtml

Insert and retrieve documents

Configured with Chat Trigger, Document Default Data Loader, Embeddings Open Ai, Html, and additional nodes. Review the connections and setup before adapting this template.

Download workflow JSONView files on GitHub ↗20 nodes · MIT
Workflow preview
TriggerWhen clicking "ExecuteWorkflow"Manual TriggerWeb / APIFetch Essay ListHTTP RequestTransformExtract essay namesHtmlTransformSplit out into itemsSplit OutWeb / APIFetch essay textsHTTP RequestTransformLimit to first 3LimitTransformExtract Text OnlyHtmlTransformRecursive CharacterText Splitter1Text Splitter Recursive …TransformGenerate responseEdit FieldsTransformCompose citationsEdit FieldsAI & modelsAnswer the query basedon chunksInformation ExtractorCodePrepare chunksCodeTransformSet max chunks to sendto modelEdit FieldsAI & modelsEmbeddings OpenAI2Embeddings Open AiTriggerWhen chat messagereceivedChat TriggerData storeMilvus Vector Store inretrievalVector Store MilvusData storeMilvus Vector StoreVector Store MilvusAI & modelsEmbeddings OpenAIEmbeddings Open AiFiles / mediaDefault Data LoaderDocument Default Data Lo…AI & modelsOpenAI Chat ModelOpenAI Chat Model

Node categories in this workflow

  • Trigger
  • Web / API
  • Transform
  • AI & models
  • Code
  • Data store
  • Files / media

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
Fetch Essay ListWeb / APIHTTP RequestSee node parameters
Extract essay namesTransformHtmlextractHtmlContent
Split out into itemsTransformSplit OutSee node parameters
Fetch essay textsWeb / APIHTTP RequestSee node parameters
Limit to first 3TransformLimitSee node parameters
Extract Text OnlyTransformHtmlextractHtmlContent
Recursive Character Text Splitter1TransformText Splitter Recursive Character Text SplitterSee node parameters
Generate responseTransformEdit FieldsSee node parameters
Compose citationsTransformEdit FieldsSee node parameters
Answer the query based on chunksAI & modelsInformation ExtractorSee node parameters
Prepare chunksCodeCodeSee node parameters
Set max chunks to send to modelTransformEdit FieldsSee node parameters
Embeddings OpenAI2AI & modelsEmbeddings Open AiSee node parameters
When chat message receivedTriggerChat TriggerSee node parameters
Milvus Vector Store in retrievalData storeVector Store MilvusSee node parameters
Milvus Vector StoreData storeVector Store MilvusSee node parameters
Embeddings OpenAIAI & modelsEmbeddings Open AiSee node parameters
Default Data LoaderFiles / mediaDocument Default Data LoaderSee node parameters
OpenAI Chat ModelAI & modelsOpenAI Chat ModelSee 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

  • milvusApi
  • openAiApi

Workflow notes

Step 1

Step 1

  1. Set up a Milvus server based on this guide. And then create a collection named my_collection.
  2. Click this workflow to load scrape and load Paul Graham essays to Milvus collection.
Step 2

Step 2

Chat and get citations in response

Insert and retrieve documents

Insert and retrieve documents

Purpose and structure

This folder contains the Insert and retrieve documents workflow. Its executable nodes use chatTrigger, code, documentDefaultDataLoader, embeddingsOpenAi, html, httpRequest, informationExtractor, limit, lmChatOpenAi, manualTrigger, set, splitOut, textSplitterRecursiveCharacterTextSplitter, vectorStoreMilvus. 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", When chat message received

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/1495_Splitout_Limit_Import_Webhook.json MIT; preserve source notices.

Canvas section labels

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

  • Scrape latest Paul Graham essays
  • Load into Milvus vector store

More in AI & research

"Hey Siri, Ask Agent" workflow#️⃣Nostr #damus AI Powered Reporting + Gmail + Telegram(G) - Email Classification