Integrate ANY Python Function, CodeGen, CrewAI tool, LangChain tool with TaskGen! - v2.3.0

Subscribers:
5,330
Published on ● Video Link: https://www.youtube.com/watch?v=irVj2NS7gas



Duration: 1:18:29
300 views
11


In this session, I show how to use LangChain tools, CrewAI tools, your own tools for a very flexible Agent in TaskGen!

Spent 2 months creating a very versatile prompt that works with memory / plug and play functions. So, this is a showcase for TaskGen v2.3.0!

Why TaskGen? Most existing Agentic frameworks use free-text conversation as the base for Agentic interactions. TaskGen uses StrictJSON, a type-based JSON parser and more, to ensure correct output at each intermediate step, allowing for Chain of Thought and other sequential generation in a structured manner.

We will be showing how to generate games, essays, scrape web pages and many more with TaskGen equipped with the right tools.

It's really easy 🙂

TaskGen Repo: https://github.com/simbianai/taskgen

~~~

0:00 Introduction
2:12 Interfacing LLMs with TaskGen
4:55 Interfacing Functions with TaskGen
19:53 Interfacing Functions with Agents
25:23 Logic for Selecting Next Subtask
34:05 Multi-step Function Showcase
38:23 Integrating with Crew.AI tools (WebScraper, PDF Query)
47:59 Integrating with LangChain Structured Tools
49:10 Integrating with LangChain Community Tools (Wikipedia, DuckDuckGo, Python REPL)
50:00 TaskGen Custom Tools: Code generator, executor, debugger, Webpage Parser
57:48 TaskGen CodeGen Showcase
1:04:38 Integrating with LlamaIndex Structured Tools
1:05:19 PyGame Creator with Agents
1:09:19 Essay Writer with Agents
1:13:13 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


2024-09-06TaskGen: Co-create the best open-sourced LLM Agentic Framework together!
2024-08-21AriGraph (Part 2) - Knowledge Graph Construction and Retrieval Details
2024-08-13alphaXiv - Share Ideas, Build Collective Understanding, Interact with ANY open sourced paper authors
2024-07-30AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents
2024-07-23NeoPlanner - Continually Learning Planning Agent for Large Environments guided by LLMs
2024-07-17Intelligence = Sampling + Filtering
2024-07-12Michael Hodel: Reverse Engineering the Abstraction and Reasoning Corpus
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