Scale deal flow with a Pitch Deck AI vision, chatbot and QDrant vector store
Needs changesWhat this workflow does
This AI workflow has 39 nodes and runs manually, when you click “Execute workflow” (plus 3 other triggers). Along the way it connects OpenAI Chat Model, Embeddings OpenAI, Airtable and Vector Store Question Answer and 1 more. It also calls stirlingpdf.io and qdrant:6333 over HTTP.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 3 other triggers).
- Search Pending Rows (Airtable): search
- Get Row (Edit Fields (Set)): sets or maps fields
- Download Deck From Airtable (HTTP Request): calls an HTTP API
- Identify Companies In Question (Information Extractor): extracts structured fields from text with AI, with model: OpenAI Chat Model
- Prequisites Met (If): checks a condition and branches into true / false
- Extract from File: extracts data from a file (binary to propery)
- Ask Questions About Pitchdecks (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 2 tools (Vector Store Tool, Check Pitch Deck Exists); memory: Window Buffer Memory
- Execute Workflow (Execute Sub-workflow): calls another n8n workflow
- Convert to File: converts data to a file (to binary)
- Split PDF into Images (HTTP Request): calls stirlingpdf.io (POST)
…plus 11 more steps. See the full node list below.
Services it uses
HTTP calls to: stirlingpdf.io, qdrant:6333
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Ask Questions About Pitchdecks (v1.6): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Ask Questions About Pitchdecks (v1.6) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (29)
- Manual Trigger
n8n-nodes-base.manualTrigger - Sort
n8n-nodes-base.sort - HTTP Request
n8n-nodes-base.httpRequest - Compression
n8n-nodes-base.compression - Code
n8n-nodes-base.code - Edit Image
n8n-nodes-base.editImage - Aggregate
n8n-nodes-base.aggregate - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Merge
n8n-nodes-base.merge - Airtable
n8n-nodes-base.airtable - Edit Fields (Set)
n8n-nodes-base.set - If
n8n-nodes-base.if - Execute Sub-workflow
n8n-nodes-base.executeWorkflow - No Operation, do nothing
n8n-nodes-base.noOp - Execute Workflow Trigger
n8n-nodes-base.executeWorkflowTrigger - Extract from File
n8n-nodes-base.extractFromFile - Convert to File
n8n-nodes-base.convertToFile - Vector Store Question Answer Tool
@n8n/n8n-nodes-langchain.toolVectorStore - Information Extractor
@n8n/n8n-nodes-langchain.informationExtractor - Airtable Trigger
n8n-nodes-base.airtableTrigger - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Qdrant Vector Store
@n8n/n8n-nodes-langchain.vectorStoreQdrant - AI Agent
@n8n/n8n-nodes-langchain.agent - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Airtable Tool
n8n-nodes-base.airtableTool - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger
From the author
Are you a popular tech startup accelerator (named after a particular higher order function) overwhelmed with 1000s of pitch decks on a daily basis? Wish you could filter through them quickly using AI but the decks are unparseable through conventional means?…