Skip to content
NEWMarketplace and the trig8n Agent: sell what you build, and get plans and changes that are tested before you see them. See what is new

Library / RAG & Knowledge Bases

RAG & Knowledge Bases

Embed FTP Files into a Qdrant Vector Database with OpenAI

When you run it, it lists files on an FTP server, splits their text, creates OpenAI embeddings and stores them in Qdrant in batches.

Import it free Sign in to open it

What it does

### Store in Vector DB Node: Qdrant Vector Store Batch Size: 100 Collection: Sends cleaned text chunks to OpenAI to get embeddings (1536 dim for text-embedding-ada-002) #### collection settings in Qdrant cluster PUT /collections/{collection_name} { "vectors": { "size": 1536, "distance": "Cosine" } } Embed Chunks Node: Embeddings OpenAI Pushes the embedded chunks (with metadata) into Qdrant for semantic retrieval.

The steps

  1. Qdrant Vector Store
  2. When clicking ‘Test workflow’
  3. Embeddings OpenAI
  4. Default Data Loader
  5. Character Text Splitter
  6. List all the files
  7. Loop over one item
  8. Downloading item

Similar automations

RAG & Knowledge BasesEmbed Files from FTP into a Qdrant Vector Database10 stepsFiles & Cloud StorageDownload and Upload a File over FTP4 stepsFiles & Cloud StorageMove Files Between an FTP Server and HTTP5 stepsRAG & Knowledge BasesChat with local documents using Ollama and MariaDB Vector cache28 steps