LangflowUnclaimed profile

Low-code visual builder for AI agents and RAG apps — drag-and-drop flows you ship as APIs or MCP servers.

Task: Automating WorkflowsUse case: Build and deploy ai agents and rag applications with low code visual flowsModels: llama-3.2, openai, anthropic

0.0

based on 0 reviews

Claim this Agent

Are you the vendor?

reviews

Building the picture

Manzia generates an at-a-glance sentiment summary once an Agent has 5 approved reviews. This Agent has 0.

Video tutorials

Official tutorial

Community tutorials

Summarized from 2 community tutorials · July 2026

What you need

Access: Free tier
API key: Bring your own
Runs on: Web app · CLI · Self-hosted
You’ll need: Python 3.10+ (for local install)
OpenAI API key (or other LLM provider)
Vector database account e.g. Astra DB
Sample PDF/document for RAG demo
Skill level: Some setup — keys, settings, or a connected account
Setup time: about 20 minutes

Worth knowing: OpenAI API keys now require funding the account with a few dollars before calls work, and the app returns no valid answer on the very first query until the vector store finishes indexing.

Summarized from 2 community tutorials · July 2026

Highlights

Visual drag-and-drop flow builderWire together pre-built components (chat input/output, prompt template, memory, LLM) on a canvas to build an AI app without writing code.
PDF-based RAG chatbotLoads a PDF, splits it into chunks, embeds and stores it in a vector database, then retrieves relevant context to answer user questions.
Per-user chat memoryStores conversation history keyed by a session/user name so different users get separate, remembered chat histories.
Swappable LLM and vector-store providersAny model node (OpenAI, local Ollama, HuggingFace, etc.) or vector store can be swapped in without rebuilding the rest of the flow.
Import/export flows as JSONEntire flow definitions can be exported and re-imported as JSON files to share or reuse projects.

Summarized from 2 community tutorials · July 2026