• DATA
  • INDEX
  • SYNC
  • HUMAN

How to update vector stores with your AI

Connect FlowiseAI to your agent once. From then on, you can feed new information directly into your RAG pipelines through your chat window.

Ask AI about this page

Short answer

How can I add new data to my FlowiseAI RAG pipelines?

You can push new text or documents into your vector store by asking your agent to perform an upsert. This adds the new information to your existing knowledge base so your agent can use it immediately. You'll see how the data moves through the pipeline below.

The results.

Where your data lands.

The AI handles the heavy lifting of processing and storing your new information.

DATA

New knowledge added

The AI takes the raw text or files you provide and pushes them into your vector database. Your RAG pipeline stays updated without manual uploads.

INDEX

Vector store updated

The information is embedded and indexed. This ensures your agent can find the new data during future retrieval steps.

SYNC

Immediate availability

Once the process finishes, the new data is live. You can start asking questions about the new content right away.

HUMAN

Review required

The AI cannot verify if the data you provided is factually correct. You need to check the source material before sending it.

The workflow

What your AI does when the data arrives.

Your agent acts as the bridge between your chat interface and your FlowiseAI vector store.

  1. Receive input

    Your agent receives the new document or raw text snippet you paste into the chat.

    upsert_vector_data

  2. Process data

    The agent prepares the incoming information for storage in your specific vector database.

    upsert_vector_data

  3. Update store

    The tool pushes the processed data into your FlowiseAI RAG pipeline.

    upsert_vector_data

  4. Confirm success

    The agent tells you once the data is successfully indexed and ready for retrieval.

    upsert_vector_data

Try it

Copy these to start.

Use these prompts to trigger the data update process.

Starting points

These are opening lines, not scripts. Replace the bracketed text with your actual document content or specific data.

FlowiseAI Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_lh0zyPoJJj1xxwGDq27KDGRA6H9DV4YmiVFcM13z/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — FlowiseAI capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "flowiseai-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_lh0zyPoJJj1xxwGDq27KDGRA6H9DV4YmiVFcM13z/mcp"
    }
  }
}
Copy into chat04

  • Upsert this text into my FlowiseAI vector store: [paste text here]

  • Add the information from the attached document to my RAG pipeline.

  • Update my vector store with this new data: [paste data]

  • Please run an upsert for this new project documentation.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect FlowiseAI once, then ask.

One link, login stays encrypted on our side, and the full walkthrough lives on the Connector page.

Connect FlowiseAI to your AI

FAQ

How the update process behaves

  • 01

    Can the AI delete old documents from my vector store?

    No. This connector only supports adding or updating data through the upsert tool. It cannot delete existing records.

  • 02

    Does the AI automatically know which vector store to use?

    The AI uses the connection you established. You should specify the target store in your prompt if you have multiple pipelines.

  • 03

    Can I upload a whole folder at once?

    No. The AI processes the data you send through the chat interface.

  • 04

    Will this change my existing FlowiseAI workflow settings?

    No. The tool only interacts with the vector data. It does not modify your FlowiseAI graph or node configurations.

  • 05

    Can the AI fix errors in my source documents?

    No. The AI only pushes the data you provide. It does not edit or correct your original files.

  • More questions about FlowiseAI? See everything the FlowiseAI Connector can do

Connect FlowiseAI to Claude, Cursor, ChatGPT & more