█
LastWrite
  • > Curriculum
  • > Pricing
  • > For Educators
  • > About
  • > Contact
Log InGet Started

Questions, concerns, bug reports, or suggestions? We read every message, write to us at [email protected].

More ways to reach us →
LastWrite

Structured computer science lessons for aspiring developers and security professionals.

[email protected]

(201) 785-7951

Mon–Fri, 9 AM–5 PM EST

Learn

  • Curriculum
  • Pricing

Company

  • About
  • For Educators & Schools
  • Contact Us

Legal

  • Terms of Service
  • Privacy Policy
© 2026 LastWrite. All rights reserved.
Curriculum/AI Agents/Low-Code Agents/Memory, Tools, and RAG in Low-Code Agents
60 minIntermediate

Memory, Tools, and RAG in Low-Code Agents

After this lesson, you will be able to: Add persistent memory, web search, code execution, and document retrieval to low-code agents using built-in connectors and vector stores.

By now you've built RAG, multi-agent, and conditional flows on four platforms. This lesson goes deeper on the three power-ups every production agent needs: memory, tools, and RAG, and how to wire them across LangFlow / Flowise / Dify / Relevance.

Prerequisites:Relevance AI: Agent Teams Without Infrastructure

Memory across platforms

All four platforms ship buffer memory (last N messages) and DB-backed memory. LangFlow. ConversationBufferMemory + Astra DB Memory. Flowise. Buffer Memory + Postgres / Redis Memory nodes. Dify, built-in conversation memory + 'Conversation Variables' for cross-turn state. Relevance AI, automatic per-conversation memory; configurable in agent settings.

💡 Tools the agent can call

Built-in tools (web search, calculator, image generation) cover 80% of use cases. Custom tools, every platform supports calling your own HTTP endpoints. Define the OpenAPI spec, attach as tool, the agent reads the description and calls when relevant.

Add a custom tool (Flowise example)

  1. 1

    1. In your chatflow, add a 'Custom Tool'.

  2. 2

    2. Name: 'getUserOrders'. Description: 'Fetches orders for a user. Input: userId (string).'

  3. 3

    3. Code (JavaScript): `return await fetch('https://api.example.com/orders/' + $userId).then(r => r.json())`.

  4. 4

    4. Connect to your Agent. Test: 'What did user 42 order last month?', agent picks the tool by description.

RAG patterns that scale

Naive RAG (embed → retrieve top-K → stuff in prompt) is fine for small docs. Hybrid retrieval, combine semantic search with keyword (BM25) for better recall on rare terms. Re-ranking, retrieve top-50, then a separate model picks the best 5. Multi-query, rephrase the user's query 3 ways, retrieve for each, dedupe. Agentic RAG, the LLM decides what to retrieve and when (not on every turn).

Add hybrid retrieval in LangFlow

  1. 1

    1. Add 'BM25 Retriever' alongside your existing vector retriever.

  2. 2

    2. Add 'Ensemble Retriever' node. Connect both retrievers in.

  3. 3

    3. Set weights: 0.5 / 0.5 (or 0.7 vector / 0.3 BM25, tune per dataset).

  4. 4

    4. Output goes to your prompt as before. Quality on rare-term queries jumps significantly.

Sign in and purchase access to unlock this lesson.

Sign in to purchase
←Relevance AI: Agent Teams Without Infrastructure
Back to Low-Code Agents
Self-Host Flowise via Docker on a VPS→