OpenAI workflows
459 results — 93 downloadable workflow files, 366 source-linked n8n references
GitHub Repo RAG Chat Agent
Indexes GitHub files into a Qdrant vector store, then answers chat queries via an OpenAI agent using retrieval and memory.
Zendesk Support RAG Agent
On chat message, an OpenAI agent retrieves knowledge from Qdrant and Google Drive to draft Zendesk ticket replies.
Website RAG Agent With Milvus
On chat message, scrapes web pages, embeds them into Milvus with OpenAI, and answers via a retrieval agent.
MCP Qdrant Document Ingestion
Exposes an MCP tool that ingests and chunks documents into Qdrant using OpenAI embeddings for retrieval.
OpenAI Milvus RAG Chatbot
On a chat message, embeds scraped web content into Milvus with OpenAI and answers questions via retrieval QA.
OpenAI + Google Drive AI Workflow — Zendesk
On a chat message, an OpenAI agent answers using a Qdrant knowledge base built from Google Drive files and creates Zendesk tickets.
Hacker News Insight Extractor
On manual run, fetches Hacker News items, embeds them into Qdrant, and uses OpenAI to extract structured data into Google Sheets.
HTML Scrape Embedding Extractor
On manual run, scrapes and splits HTML content, embeds it into Qdrant, and uses OpenAI to extract details into Google Sheets.
Document Embedding Extraction Pipeline
On trigger, loads and splits documents, embeds them into Qdrant, then uses OpenAI to extract fields and log them to Google Sheets.
Slack — Google Drive
On a Slack message, an AI agent answers from Qdrant-indexed Google Drive docs using OpenAI and Anthropic, replying in Slack.
RAG & Genai App with WordPress Content — OpenAI
On a webhook query, answers from WordPress content embedded into a Supabase vector store, using OpenAI and Postgres chat memory.
RAG & Genai App with WordPress Content
On a webhook query, answers from WordPress content embedded into a Supabase vector store, using OpenAI and Postgres chat memory.
FTP Document Embedding To Qdrant
On manual trigger, loads files from FTP, embeds them with OpenAI, and stores the vectors in Qdrant in batches.
Drive Document Vector Indexer
On manual run, loads and edits Google Drive files, then embeds documents with OpenAI into an in-memory vector store.
Structured Drive RAG Pipeline
On a chat message, embeds Google Drive documents into Pinecone and returns structured OpenAI answers.
Chat with GitHub Openapi Specification Using RAG (Pinecone and OpenAI)
On chat message, answers questions about a GitHub OpenAPI spec using an OpenAI agent over a Pinecone vector store.
Drive Docs Pinecone Chatbot
Loads Google Drive docs, embeds them into Pinecone, and answers chat questions with OpenAI retrieval QA.
Workflow Retrieval QA
On manual run, retrieves context from a source workflow and answers the query using OpenAI retrieval QA.
Drive Document RAG With OpenAI
On manual run, loads Google Drive files, splits and embeds them into an in-memory vector store, and answers queries with OpenAI.
Drive Information Extraction Agent
On chat message, embeds Google Drive documents into Pinecone and extracts structured information with OpenAI.
Drive Document RAG Agent
On chat message, embeds Google Drive documents into Pinecone and answers via an OpenAI agent over the vector store.
OpenAI Retrieval QA Chain
On manual trigger, answers questions via an OpenAI retrieval-QA chain backed by a workflow retriever.
Limit with Textsplittertokensplitter
On a Notion update or chat, embeds documents into Supabase and answers questions with OpenAI retrieval-augmented generation.
Google Docs — Google Sheets
On manual trigger, answers queries via a Gemini and OpenAI agent over a Pinecone vector store built from Google Docs, Sheets, and Drive.