Bear Brown
← All N8N workflows
AI & researchAgentAggregateChat TriggerDocument Default Data LoaderEmbeddings Open Ai

Building RAG Chatbot for Movie Recommendations with Qdrant and Open AI

Configured with Agent, Aggregate, Chat Trigger, Document Default Data Loader, and additional nodes. Review the connections and setup before adapting this template.

Download workflow JSONView files on GitHub ↗25 nodes · MIT
Workflow preview
TriggerWhen clicking ‘Testworkflow’Manual TriggerIntegrationGitHubGithubTransformExtract from FileExtract From FileAI & modelsEmbeddings OpenAIEmbeddings Open AiFiles / mediaDefault Data LoaderDocument Default Data Lo…TransformToken SplitterText Splitter Token Spli…Data storeQdrant Vector StoreVector Store QdrantTriggerWhen chat messagereceivedChat TriggerAI & modelsOpenAI Chat ModelOpenAI Chat ModelSubworkflowCall n8n Workflow ToolTool WorkflowData storeWindow Buffer MemoryMemory Buffer WindowTriggerExecute WorkflowTriggerExecute Workflow TriggerTransformMergeMergeTransformSplit OutSplit OutTransformSplit Out1Split OutTransformMerge1MergeTransformAggregateAggregateAI & modelsAI AgentAgentWeb / APIEmbeddingRecommendation Request…HTTP RequestWeb / APIEmbeddingAnti-Recommendation…HTTP RequestTransformExtracting EmbeddingEdit FieldsTransformExtracting Embedding1Edit FieldsWeb / APICalling QdrantRecommendation APIHTTP RequestWeb / APIRetrieving RecommendedMovies Meta DataHTTP RequestTransformSelecting FieldsRelevant for AgentEdit Fields

Node categories in this workflow

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

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 ‘Test workflow’TriggerManual TriggerSee node parameters
GitHubIntegrationGithubfile / get
Extract from FileTransformExtract From FileSee node parameters
Embeddings OpenAIAI & modelsEmbeddings Open AiSee node parameters
Default Data LoaderFiles / mediaDocument Default Data LoaderSee node parameters
Token SplitterTransformText Splitter Token SplitterSee node parameters
Qdrant Vector StoreData storeVector Store QdrantSee node parameters
When chat message receivedTriggerChat TriggerSee node parameters
OpenAI Chat ModelAI & modelsOpenAI Chat ModelSee node parameters
Call n8n Workflow ToolSubworkflowTool WorkflowSee node parameters
Window Buffer MemoryData storeMemory Buffer WindowSee node parameters
Execute Workflow TriggerTriggerExecute Workflow TriggerSee node parameters
MergeTransformMergeSee node parameters
Split OutTransformSplit OutSee node parameters
Split Out1TransformSplit OutSee node parameters
Merge1TransformMergeSee node parameters
AggregateTransformAggregateSee node parameters
AI AgentAI & modelsAgentSee node parameters
Embedding Recommendation Request with Open AIWeb / APIHTTP RequestPOST
Embedding Anti-Recommendation Request with Open AIWeb / APIHTTP RequestPOST
Extracting EmbeddingTransformEdit FieldsSee node parameters
Extracting Embedding1TransformEdit FieldsSee node parameters
Calling Qdrant Recommendation APIWeb / APIHTTP RequestPOST
Retrieving Recommended Movies Meta DataWeb / APIHTTP RequestPOST
Selecting Fields Relevant for AgentTransformEdit FieldsSee 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

  • githubApi
  • openAiApi
  • qdrantApi

Workflow notes

Sticky Note

Tool, calling Qdrant's recommendation API based on user's request, transformed by AI agent

Sticky Note1

Uploading data (movies and their descriptions) to Qdrant Vector Store

Building RAG Chatbot for Movie Recommendations with Qdrant and Open AI

Building RAG Chatbot for Movie Recommendations with Qdrant and Open AI

Purpose and structure

This folder contains the Building RAG Chatbot for Movie Recommendations with Qdrant and Open AI workflow. Its executable nodes use agent, aggregate, chatTrigger, documentDefaultDataLoader, embeddingsOpenAi, executeWorkflowTrigger, extractFromFile, github, httpRequest, lmChatOpenAi, manualTrigger, memoryBufferWindow, merge, set, splitOut, textSplitterTokenSplitter, toolWorkflow, vectorStoreQdrant. 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 ‘Test workflow’, When chat message received, Execute Workflow Trigger

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/1798_Splitout_GitHub_Create_Webhook.json MIT; preserve source notices.

More in AI & research

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