RAG with PDF as source
Configured with Agent, Chain Retrieval Qa, Chat Trigger, Document Default Data Loader, and additional nodes. Review the connections and setup before adapting this template.
Node categories in this workflow
- Messaging
- Code
- Transform
- AI & models
- Files / media
- Web / API
- Routing
- Data store
- Trigger
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.
| Node | Category | Type | Operation |
|---|---|---|---|
| Send message | Messaging | Slack | See node parameters |
| Execute JavaScript | Code | Code | See node parameters |
| Recursive Character Text Splitter | Transform | Text Splitter Recursive Character Text Splitter | See node parameters |
| Embeddings OpenAI | AI & models | Embeddings Open Ai | See node parameters |
| Default Data Loader | Files / media | Document Default Data Loader | See node parameters |
| OpenAI Chat Model | AI & models | OpenAI Chat Model | See node parameters |
| Embeddings OpenAI2 | AI & models | Embeddings Open Ai | See node parameters |
| Vector Store Retriever | AI & models | Retriever Vector Store | See node parameters |
| Download PDF | Web / API | HTTP Request | See node parameters |
| PDFs to download | Routing | No Op | See node parameters |
| Read Pinecone Vector Store | Data store | Vector Store Pinecone | See node parameters |
| Question and Answer Chain | AI & models | Chain Retrieval Qa | See node parameters |
| Anthropic Chat Model | AI & models | Anthropic Chat Model | See node parameters |
| Get calendar availability | Web / API | Tool Http Request | POST |
| Appointment booking agent | AI & models | Agent | See node parameters |
| Window Buffer Memory | Data store | Memory Buffer Window | See node parameters |
| Insert into Pinecone vector store | Data store | Vector Store Pinecone | See node parameters |
| Book appointment | Web / API | Tool Http Request | POST |
| When chat message received | Trigger | Chat Trigger | See node parameters |
| OpenAI Chat Model1 | AI & models | OpenAI Chat Model | See node parameters |
| Add automation label | Messaging | Gmail | addLabels |
| On new email to nathan's inbox | Trigger | Gmail Trigger | See node parameters |
| Add music label | Messaging | Gmail | addLabels |
| Assign label with AI | AI & models | Text Classifier | See node parameters |
| Webhook | Trigger | Webhook | See node parameters |
| Whether email contains n8n | Routing | If | See node parameters |
Setup
- Download the JSON and import it into an isolated n8n instance. Leave the workflow inactive.
- Connect your own credentials through n8n’s credential store. Replace
REPLACE_WITH_*values with your resource identifiers. - Inspect API destinations, Code nodes, database queries, file paths, and outbound actions.
- 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
None declared. HTTP requests and Code nodes may still need configuration.
Workflow notes
Sticky Note2
PDFs to download
BTC Whitepaper + metadata
A. Load PDF into Pinecone
A. Load PDF into Pinecone
Download the PDF, then text embeddings into Pincecone
B. Chat with PDF
B. Chat with PDF
Use GPT4o to chat with Pinecone index
Sticky Note1
Sticky Note8
BTC Whitepaper references
Connect with me or explore this demo 👇
Connect with me or explore this demo 👇
Explore 100+ AI Workflow templates on n8n.io
Explore 100+ AI Workflow templates on n8n.io
Ask a question in our community (13k+ members)
Ask a question in our community (13k+ members)
RAG with PDF as source
RAG with PDF as source
Purpose and structure
This folder contains the RAG with PDF as source workflow. Its executable nodes use agent, chainRetrievalQa, chatTrigger, code, documentDefaultDataLoader, embeddingsOpenAi, gmail, gmailTrigger, httpRequest, if, lmChatAnthropic, lmChatOpenAi, memoryBufferWindow, noOp, retrieverVectorStore, slack, textClassifier, textSplitterRecursiveCharacterTextSplitter, toolHttpRequest, vectorStorePinecone, webhook. 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 chat message received, On new email to nathan's inbox, Webhook
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/Code/0548_Code_Webhook_Create_Webhook.json MIT; preserve source notices.
Canvas section labels
These name areas of the original canvas; they do not include explanatory instructions.
- What is n8n?
- Example #2
- Example #3
- Example #1
- Thank you and happy flowgramming 🤘