AI-powered document chat with Nextcloud files using LangChain and OpenAI
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What to replace before upgrading
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) AI Nextcloud (v1.9) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Community nodes
These come from third-party npm packages. In n8n 3.0 unverified community packages are off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).
n8n-nodes-word2text(DOCX)
Nodes used (14)
- Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - AI Agent
@n8n/n8n-nodes-langchain.agent - Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - Switch
n8n-nodes-base.switch - Aggregate
n8n-nodes-base.aggregate - Edit Fields (Set)
n8n-nodes-base.set - If
n8n-nodes-base.if - Nextcloud
n8n-nodes-base.nextCloud - Code
n8n-nodes-base.code - Call n8n Workflow Tool
@n8n/n8n-nodes-langchain.toolWorkflow - Extract from File
n8n-nodes-base.extractFromFile - Word2text
n8n-nodes-word2text.word2text
What it does
Main Workflow “AI Nextcloud” Entry point: A public chat-trigger greets the user; every incoming chat message starts the flow. AI agent: A LangChain agent (“AI Nextcloud”) uses the configured OpenAI model plus short-term memory to continue the dialogue in context. Purpose: Answers questions about files stored in a Nextcloud folder. The user simply includes the folder path in their question. Tool integration: Calls the sub-workflow “Nextcloud Tool” whenever it needs to read files and pass their text back to the AI. --- Sub-Workflow “Nextcloud Tool” 1. Invocation: Triggered by other workflows with the input parameter path (folder path). 2. File listing: Retrieves every file in the specified folder via the Nextcloud API. 3. Filter: Allows only readable formats (PDF, Markdown, DOCX). 4. Download & text extraction PDF → Text via Extract From File Markdown → Raw text DOCX → Text via community node word2text 5. Aggregation: Combines all extracted text into a single output field and returns it. > Outcome: Each call yields the plain content of every supported file in a Nextcloud folder—providing rich context for the AI agent to answer user questions accurately.