[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:adala":3},"\u003Cp>\u003Ca href=\"https:\u002F\u002Fbadge.fury.io\u002Fpy\u002Fadala\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fbadge.fury.io\u002Fpy\u002Fadala.svg\" alt=\"PyPI version\" \u002F>\u003C\u002Fa>\n\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fsupported_python_version_-3.8%20%7C%203.9%20%7C%203.10%20%7C%203.11-blue\" alt=\"Python Version\" \u002F>\n\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002FHumanSignal\u002FAdala\" alt=\"GitHub\" \u002F>\n\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002FHumanSignal\u002FAdala\" alt=\"GitHub Repo stars\" \u002F>\n\u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FQBtgTbXTgU\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fdiscord\u002F1166330284300570624?label=Discord&logo=discord\" alt=\"\" \u002F>\u003C\u002Fa>\u003C\u002Fp>\n\u003Cpicture>\n  \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"\u002Fdocs\u002Fsrc\u002Fimg\u002Flogo-dark-mode.png\">\u003C\u002Fsource>\n  \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"\u002Fdocs\u002Fsrc\u002Fimg\u002Flogo.png\">\u003C\u002Fsource>\n  \u003Cimg alt=\"Shows Adala logo in light mode and dark mode.\" src=\"\u002Fdocs\u002Fsrc\u002Fimg\u002Flogo.png\" width=\"275\" \u002F>\n\u003C\u002Fpicture>\u003Cp>Adala is an \u003Cstrong>A\u003C\u002Fstrong>utonomous \u003Cstrong>DA\u003C\u002Fstrong>ta (\u003Cstrong>L\u003C\u002Fstrong>abeling) \u003Cstrong>A\u003C\u002Fstrong>gent framework.\u003C\u002Fp>\n\u003Cp>Adala offers a robust framework for implementing agents specialized in data processing, with an emphasis on\ndiverse data labeling tasks. These agents are autonomous, meaning they can independently acquire one or more skills\nthrough iterative learning. This learning process is influenced by their operating environment, observations, and\nreflections. Users define the environment by providing a ground truth dataset. Every agent learns and applies its skills\nin what we refer to as a \"runtime\", synonymous with LLM.\u003C\u002Fp>\n\u003Cp>\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002FHumanSignal\u002Fadala\u002FHEAD\u002Fdocs\u002Fsrc\u002Fimg\u002Ftraining-agents-skill.png\" alt=\"Training Agent Skill\" title=\"Training Agent Skill\" \u002F>\u003C\u002Fp>\n\u003Ch2>📢 Why choose Adala?\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>\u003Cp>🌟 \u003Cstrong>Reliable agents\u003C\u002Fstrong>: Agents are built upon a foundation of ground\ntruth data. This ensures consistent and trustworthy results, making Adala a\nreliable choice for your data processing needs.\u003C\u002Fp>\n\u003C\u002Fli>\n\u003Cli>\u003Cp>🎮 \u003Cstrong>Controllable output\u003C\u002Fstrong>: For every skill, you can configure the\ndesired output and set specific constraints with varying degrees of\nflexibility. Whether you want strict adherence to particular\nguidelines or more adaptive outputs based on the agent's learning,\nAdala allows you to tailor results to your exact needs.\u003C\u002Fp>\n\u003C\u002Fli>\n\u003Cli>\u003Cp>🎯 \u003Cstrong>Specialized in data processing\u003C\u002Fstrong>: While agents excel in diverse\ndata labeling tasks, they can be customized for a wide range of data\nprocessing needs.\u003C\u002Fp>\n\u003C\u002Fli>\n\u003Cli>\u003Cp>🧠 \u003Cstrong>Autonomous learning\u003C\u002Fstrong>: Adala agents aren't just automated;\nthey're intelligent. They iteratively and independently develop\nskills based on environment, observations, and reflections.\u003C\u002Fp>\n\u003C\u002Fli>\n\u003Cli>\u003Cp>✅ \u003Cstrong>Flexible and extensible runtime\u003C\u002Fstrong>: Adala's runtime environment is\nadaptable. A single skill can be deployed across multiple runtimes,\nfacilitating dynamic scenarios like the student\u002Fteacher\narchitecture. Moreover, the openness of framework invites the\ncommunity to extend and tailor runtimes, ensuring continuous\nevolution and adaptability to diverse needs.\u003C\u002Fp>\n\u003C\u002Fli>\n\u003Cli>\u003Cp>🚀 \u003Cstrong>Easily customizable\u003C\u002Fstrong>: Quickly customize and develop agents to address\nchallenges specific to your needs, without facing a steep learning curve.\u003C\u002Fp>\n\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2>🫵 Who is Adala for?\u003C\u002Fh2>\n\u003Cp>Adala is a versatile framework designed for individuals and professionals in the field of AI and machine learning. Here's who can benefit:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>🧡 \u003Cstrong>AI engineers:\u003C\u002Fstrong> Architect and design AI agent systems with modular, interconnected skills. Build production-level agent systems, abstracting low-level ML to Adala and LLMs.\u003C\u002Fli>\n\u003Cli>💻 \u003Cstrong>Machine learning researchers:\u003C\u002Fstrong> Experiment with complex problem decomposition and causal reasoning.\u003C\u002Fli>\n\u003Cli>📈 \u003Cstrong>Data scientists:\u003C\u002Fstrong> Apply agents to preprocess and postprocess your data. Interact with Adala natively through Python notebooks when working with large Dataframes.\u003C\u002Fli>\n\u003Cli>🏫 \u003Cstrong>Educators and students:\u003C\u002Fstrong> Use Adala as a teaching tool or as a base for advanced projects and research.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>While the roles highlighted above are central, it's pivotal to note that \u003C\u002Fp>\n",1784240406334]