AI Agent Builder Bootcamp: Flowise, LangFlow, RAG & more!

Install Flowise locally or on cloud by setting up Node.js and using npx flowise start, or opt for Flowise cloud; compare self-hosting and cloud, and review the free plan limits.

install Flowise with docker using docker compose up or by building the docker image and running it in a container, then access it at localhost:3000 with initialization logs.

Navigate the Flow Wise interface to manage chat flows, agent flows, executions, and tools, credentials, variables, API keys, and document stores, enabling rapid prototyping and production AI applications.

Explore flow wise nodes and connections to build sophisticated AI applications—from simple chat flows to complex multi-agent systems—using Lang chain, Lama index, embeddings, document loaders, and tools.

Learn to create your first simple Flowise workflow to build a chatbot using a chat model, buffer memory, a chat prompt template, and a conversation chain powered by Google Gemini.

Create a no-code reusable naming workflow in Flowise by connecting a language model, a prompt template, and an LM chain to generate company names from product descriptions.

Learn to build a two-path, parallel multi-prompt chain that processes data with a data performer and a data scientist, turning analysis into executive insights.

Build a multi-tool conversational agent in Flowise that uses the chat anthropic (Claude), Serp API, and a calculator, with buffer memory and an orchestrator to handle complex queries.

Flowise training teaches building a no-code document retrieval system that uploads documents, extracts text, and answers questions with chat model, file reader, chat prompt template, conversational chain, and buffer memory.

Build a retrieval augmented generation chatbot by loading documents with a file loader and splitting text into 1000-character chunks with 200-character overlap for embeddings and vector storage.

Chunk text into manageable pieces, convert them into embeddings, and store them in an in-memory vector store to enable retrieval-based question answering for a rag chatbot.

Build a Rag chatbot that answers questions about your documents by using a conversational retrieval Q&A chain with Flowise nodes, memory, a vector store, and a Chat Mistral AI model.

Embed your flowwise chatbot into websites and apps using four integration options, including html and react variants, with auto-generated embed codes for smooth deployment.

Expose your flow as an API endpoint using Python and the requests library to post JSON payloads to the flow wise pipelines API, then test with Streamlit.

Learn to share your Flowise chatbot playground by publishing a direct link, using embedding options, and customizing title, colors, and welcome messages, then test responses via API calls.

Build a no-code text summarization workflow that converts documents and YouTube transcripts into concise, search engine optimized summaries using Anthropic Claude, with memory, prompt engineering, and a chat model.

Explore conditional logic in Flowise using if else to route conversations through specialized ai paths, building a chatbot that analyzes inputs and selects appropriate responses.

Build a no-code, multi-agent portfolio management system with a ai brain and three specialists—portfolio manager, financial analyst, risk manager—coordinated by a supervisor to gather real-time data and provide investment recommendations.

Automate lead outreach with a multi-agent workflow where a supervisor coordinates a researcher and a sales writer to research leads and craft personalized emails, leveraging Google generative ai.

Learn the branch out to merge in pattern for ai automation, using parallel processing with four agents and a chat model; design start, sequential, and end nodes to merge insights.

Explore Flowise Agent V2, an architectural evolution that replaces v1 with explicit workflow, orchestration, and native core flow components, enabling no-code generation, editing, and validation of ai agents.

Build a multi-agent AI research system using flows to generate a detailed paper from a simple prompt. The setup includes a topic enhancer, three specialized agents, and a paper generator.

Develop ai-powered email reply agent in a no-code workflow that drafts professional responses, routes them for human approval, and uses Google search and date tools for context.

Learn to build a multi-agent no-code AI workflow using iterations. Chaining Google, Gemini, and Mistral models creates a pipeline with start nodes and iteration containers.

Build a no-code, multi-agent financial research pipeline with a planner, a search agent, and a writer agent to autonomously turn web findings into professional reports.

Explore agentic rag with Flowise v2 in a no-code platform, featuring query validation, relevance assessment, vector retrieval, and iterative self-improvement to generate accurate responses.

Build the core workflow in flowise by configuring a start node, query validator, and conditional routing with a chatgpt model; then add a generator and retriever for vector database testing.

Connect a database retriever to an AI related document store, load PDFs with a file loader, and upsert embeddings for fast retrieval using a flow state query.

Finalize the no-code agent workflow by wiring the start, query and response generators, a vector retriever, relevance checks, and a regeneration loop, then validate and test end-to-end.