Adala
GPT-HTN-Planner
Adala | GPT-HTN-Planner | |
---|---|---|
5 | 1 | |
732 | 30 | |
8.7% | - | |
9.1 | 4.9 | |
7 days ago | 2 months ago | |
Python | Python | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Adala
-
Ask HN: Are you using a GPT to prompt-engineer another GPT?
We recently open sourced an agent framework [1] for automating data processing and labeling where the prompt is refined trough iterations (i.e. automatic prompt tuning). We tested it on the Math reasoning dataset GSM8k and where able to improve the baseline accuracy (GPT4) by 45% -> 74% using 25 labeled examples (I'll put the notebook and blog post linked below [2][3]). Results are definitively very interesting, if not surprising with some skills, and we see more and more of our open source users and customers showing interested in the framework for automating labeling / having it as a data processing / labeling copilot.
[1] https://github.com/HumanSignal/Adala
[2] https://github.com/HumanSignal/Adala/blob/master/examples/gs...
[3] https://labelstud.io/blog/mastering-math-reasoning-with-adal...
- Adala: Autonomous Data Agent Framework
- Show HN: Adala framework – Applying LLM skills to various data processing tasks
-
Adala: Reliable Open Source Agent Framework for Data Processing
We have just open sourced Adala - a robust framework for implementing agents that specialize in advanced data processing tasks, starting with data labeling and generation.
- Show HN: Adala – Autonomous Data (Labeling) Agent
GPT-HTN-Planner
-
Can LLMs Reason and Plan?
"Plan" means a lot of things.
There has been some research in applying GPT-4 to Hierarchical Task Networks (HTN), one means of doing computerized semi-automated/automated planning of a complex task as a tree of less and less complex tasks [1].
There are other types of planning. Automated planning works better as there are more defined the tasks in a plan, less ambiguity in dependencies, more separate between the tasks. The OP article touches on that, noting LLMs are good at extracting planning knowledge but not good in their experience at creating executable plans. This is why I think the hybrid approach is best, using an LLM to inform and tweak other planning tools in order to create an executable plan.
[1] https://github.com/DaemonIB/GPT-HTN-Planner
What are some alternatives?
langroid - Harness LLMs with Multi-Agent Programming
Interactive-LLM-Powered-NPCs - Interactive LLM Powered NPCs, is an open-source project that completely transforms your interaction with non-player characters (NPCs) in any game! 🎮🤖🚀
agents-aea - A framework for autonomous economic agent (AEA) development
awesome-ai-agents - A list of AI autonomous agents
DemoGPT - Create 🦜️🔗 LangChain apps by just using prompts🌟 Star to support our work! | 只需使用句子即可创建 LangChain 应用程序。 给个star支持我们的工作吧!
AgentPilot - A framework to create, manage, and chat with AI agents + Multi agent chat, branching chat and multiple API providers
evadb - Database system for AI-powered apps
Auto-GPT - An experimental open-source attempt to make GPT-4 fully autonomous. [Moved to: https://github.com/Significant-Gravitas/AutoGPT]
micro-gpt - MiniAGI is a minimal general-purpose autonomous agent based on GPT-3.5 / GPT-4. Can analyze stock prices, perform network security tests, create art, and order pizza. [Moved to: https://github.com/muellerberndt/mini-agi]
automata - Automata: The Future is Self-Written