TaskGen - LLM Agentic Framework that Does More, Talks Less: Shared Variables, Memory, Global Context

Subscribers:
5,330
Published on ● Video Link: https://www.youtube.com/watch?v=OWk7moRfTPE



Duration: 1:46:47
602 views
12


Want LLM Agents that focus on doing the task, and not be too verbose with "Thank You" and "I'm sorry"?

TaskGen is the answer for you.

Using StrictJSON at the core to ensure that the functions output in structured JSON with no output key missing, it makes the agents' output more concise.

Problem: Too many possible action paths to solve a task

Solution:
Agent is only allowed to use the constrained function space to select actions to fulfil a task
This helps make generation more targeted and avoids going in cycles

Problem: LLMs do not perform well with long context

Solution:
Agents are only prompted task-specific instructions via selection over memory
Agents are only given functions that are related to tasks. The functions can be programmed to return just a concise statement of what happened and the rest which Agent does not need to know can be put to Shared Variables
Agents can be prompted with Global Context to prime it with important information that carries over across tasks, and so we can remove all the specific history which happened over the previous tasks

Check out all these and more (demos by Brian and I ) in our live discussion session! We will focus on Shared Variables, Memory and Global Context.

~~~~

Part 1: https://www.youtube.com/watch?v=O_XyTT7QGH4

~~~~

0:00 Introduction
1:33 RAG Chatbot by Brian
11:17 Web Browsing Agent by Brian
18:28 AWS Bot by Brian
23:40 Discussion about implementations by Brian
35:28 AI-Powered Shop Assistant by John
50:43 Maze Navigator by John
53:53 TaskGen Introduction
1:00:13 Shared Variables
1:11:31 Memory
1:28:25 Additional/Global Context
1:33:33 Saving and Loading Agents
1:34:28 Discussion

~~~~

AI and ML enthusiast. Likes to think about the essences behind breakthroughs of AI and explain it in a simple and relatable way. Also, I am an avid game creator.

Discord: https://discord.gg/bzp87AHJy5
LinkedIn: https://www.linkedin.com/in/chong-min-tan-94652288/
Online AI blog: https://delvingintotech.wordpress.com/
Twitter: https://twitter.com/johntanchongmin
Try out my games here: https://simmer.io/@chongmin




Other Videos By John Tan Chong Min


2024-07-02TaskGen Conversational Class v2: JARVIS, Psychology Counsellor, Sherlock Holmes Shop Assistant
2024-06-04CodeAct: Code As Action Space of LLM Agents - Pros and Cons
2024-05-28TaskGen Conversation with Dynamic Memory - Math Quizbot, Escape Room Solver, Psychology Counsellor
2024-05-21Integrate ANY Python Function, CodeGen, CrewAI tool, LangChain tool with TaskGen! - v2.3.0
2024-05-11Empirical - Open Source LLM Evaluation UI
2024-05-07TaskGen Ask Me Anything #1
2024-04-29StrictJSON (LLM Output Parser) Ask Me Anything #1
2024-04-22Tutorial #14: Write latex papers with LLMs such as Llama 3!
2024-04-16SORA Deep Dive: Predict patches from text, images or video
2024-04-09OpenAI CLIP Embeddings: Walkthrough + Insights
2024-03-26TaskGen - LLM Agentic Framework that Does More, Talks Less: Shared Variables, Memory, Global Context
2024-03-18CRADLE (Part 2): An AI that can play Red Dead Dedemption 2. Reflection, Memory, Task-based Planning
2024-03-11CRADLE (Part 1) - AI that plays Red Dead Redemption 2. Towards General Computer Control and AGI
2024-03-05TaskGen - A Task-based Agentic Framework using StrictJSON at the core
2024-02-27SymbolicAI / ExtensityAI Paper Overview (Part 2) - Evaluation Benchmark Discussion!
2024-02-20SymbolicAI / ExtensityAI Paper Overview (Part 1) - Key Philosophy Behind the Design - Symbols
2024-02-13Embeddings Walkthrough (Part 2): Context-Dependent Embeddings, Shifting Embedding Space
2024-02-06Embeddings Walkthrough (Part 1) - Bag of Words to word2vec to Transformer contextual embeddings
2024-01-29V* - Better than GPT-4V? Iterative Context Refining for Visual Question Answer!
2024-01-23AutoGen: A Multi-Agent Framework - Overview and Improvements
2024-01-09AppAgent: Using GPT-4V to Navigate a Smartphone!