/Adala

Adala: Autonomous DAta (Labeling) Agent framework

Primary LanguagePythonApache License 2.0Apache-2.0

PyPI version Python Version GitHub GitHub Repo stars

Shows Adala logo in light mode and dark mode.

Adala is an Autonomous DAta (Labeling) Agent framework.

Adala offers a robust framework for implementing agents specialized in data processing, with an emphasis on diverse data labeling tasks. These agents are autonomous, meaning they can independently acquire one or more skills through iterative learning. This learning process is influenced by their operating environment, observations, and reflections. Users define the environment by providing a ground truth dataset. Every agent learns and applies its skills in what we refer to as a "runtime", synonymous with LLM.

Training Agent Skill

๐Ÿ“ข Why choose Adala?

  • ๐ŸŒŸ Reliable agents: Agents are built upon a foundation of ground truth data. This ensures consistent and trustworthy results, making Adala a reliable choice for your data processing needs.

  • ๐ŸŽฎ Controllable output: For every skill, you can configure the desired output and set specific constraints with varying degrees of flexibility. Whether you want strict adherence to particular guidelines or more adaptive outputs based on the agent's learning, Adala allows you to tailor results to your exact needs.

  • ๐ŸŽฏ Specialized in data processing: While agents excel in diverse data labeling tasks, they can be customized for a wide range of data processing needs.

  • ๐Ÿง  Autonomous learning: Adala agents aren't just automated; they're intelligent. They iteratively and independently develop skills based on environment, observations, and reflections.

  • โœ… Flexible and extensible runtime: Adala's runtime environment is adaptable. A single skill can be deployed across multiple runtimes, facilitating dynamic scenarios like the student/teacher architecture. Moreover, the openness of framework invites the community to extend and tailor runtimes, ensuring continuous evolution and adaptability to diverse needs.

  • ๐Ÿš€ Easily customizable: Quickly customize and develop agents to address challenges specific to your needs, without facing a steep learning curve.

๐Ÿซต Who is Adala for?

Adala is a versatile framework designed for individuals and professionals in the field of AI and machine learning. Here's who can benefit:

  • ๐Ÿงก AI engineers: Architect and design AI agent systems with modular, interconnected skills. Build production-level agent systems, abstracting low-level ML to Adala and LLMs.
  • ๐Ÿ’ป Machine learning researchers: Experiment with complex problem decomposition and causal reasoning.
  • ๐Ÿ“ˆ Data scientists: Apply agents to preprocess and postprocess your data. Interact with Adala natively through Python notebooks when working with large Dataframes.
  • ๐Ÿซ Educators and students: Use Adala as a teaching tool or as a base for advanced projects and research.

While the roles highlighted above are central, it's pivotal to note that Adala is intricately designed to streamline and elevate the AI development journey, catering to all enthusiasts, irrespective of their specific niche in the field. ๐Ÿฅฐ

๐Ÿ”ŒInstallation

Install Adala:

pip install adala

Adala frequently releases updates. In order to ensure that you are using the most up-to-date version, it is recommended that you install it from GitHub:

pip install git+https://github.com/HumanSignal/Adala.git

Developer installation:

git clone https://github.com/HumanSignal/Adala.git
cd Adala/
poetry install

๐Ÿ“ Prerequisites

Set OPENAI_API_KEY (see instructions here)

export OPENAI_API_KEY='your-openai-api-key'

๐ŸŽฌ Quickstart

In this example we will use Adala as a standalone library directly inside Python notebook.

Click here to see an extended quickstart example.

import pandas as pd

from adala.agents import Agent
from adala.environments import StaticEnvironment
from adala.skills import ClassificationSkill
from adala.runtimes import OpenAIChatRuntime
from rich import print

# Train dataset
train_df = pd.DataFrame([
    ["It was the negative first impressions, and then it started working.", "Positive"],
    ["Not loud enough and doesn't turn on like it should.", "Negative"],
    ["I don't know what to say.", "Neutral"],
    ["Manager was rude, but the most important that mic shows very flat frequency response.", "Positive"],
    ["The phone doesn't seem to accept anything except CBR mp3s.", "Negative"],
    ["I tried it before, I bought this device for my son.", "Neutral"],
], columns=["text", "sentiment"])

# Test dataset
test_df = pd.DataFrame([
    "All three broke within two months of use.",
    "The device worked for a long time, can't say anything bad.",
    "Just a random line of text."
], columns=["text"])

agent = Agent(
    # connect to a dataset
    environment=StaticEnvironment(df=train_df),

    # define a skill
    skills=ClassificationSkill(
        name='sentiment',
        instructions="Label text as positive, negative or neutral.",
        labels={'sentiment': ["Positive", "Negative", "Neutral"]},
        input_template="Text: {text}",
        output_template="Sentiment: {sentiment}"
    ),

    # define all the different runtimes your skills may use
    runtimes = {
        # You can specify your OPENAI API KEY here via `OpenAIRuntime(..., api_key='your-api-key')`
        'openai': OpenAIChatRuntime(model='gpt-3.5-turbo'),
    },
    default_runtime='openai',
    
    # NOTE! If you have access to GPT-4, you can uncomment the lines bellow for better results
#     default_teacher_runtime='openai-gpt4',
#     teacher_runtimes = {
#       'openai-gpt4': OpenAIRuntime(model='gpt-4')
#     }
)

print(agent)
print(agent.skills)

agent.learn(learning_iterations=3, accuracy_threshold=0.95)

print('\n=> Run tests ...')
predictions = agent.run(test_df)
print('\n => Test results:')
print(predictions)

๐Ÿ‘‰ Examples

Skill Description Colab
ClassificationSkill Classify text into a set of predefined labels. Open In Colab
ClassificationSkillWithCoT Classify text into a set of predefined labels, using Chain-of-Thoughts reasoning. Open In Colab
SummarizationSkill Summarize text into a shorter text. Open In Colab
QuestionAnsweringSkill Answer questions based on a given context. Open In Colab
TranslationSkill Translate text from one language to another. Open In Colab
TextGenerationSkill Generate text based on a given prompt. Open In Colab
Skill sets Process complex tasks through a sequence of skills. Open In Colab
OntologyCreator Infer ontology from a set of text examples. Open In Colab
Math reasoning Solve grade-school math problems on GSM8k dataset. Open In Colab

Executing Agent Skill

๐Ÿ—บ Roadmap

  • Low-level skill management (i.e. agent.get_skill("name")) [COMPLETE @niklub]
  • Make every notebook example to run in Google Collab and add a badge into README
  • Extend environment with one more example
  • Multi-task learning (learn multiple skills at once)
  • Calculate and store top line Agent metrics (predictions created, runtime executions, learning loops, etc)
  • Create Named Entity Recognition Skill
  • Command line utility (see the source for this readme for example)
  • REST API to interact with Adala
  • Vision and multi-modal agent skills

๐Ÿคฉ Contributing to Adala

Enhance skills, optimize runtimes, or pioneer new agent types. Whether you're crafting nuanced tasks, refining computational environments, or sculpting specialized agents for unique domains, your contributions will power Adala's evolution. Join us in shaping the future of intelligent systems and making Adala more versatile and impactful for users across the globe.

Read more here.

๐Ÿ’ฌ Support

Do you need help or are you looking to engage with community? Check out Discord channel! Whether you have questions, need clarification, or simply want to discuss topics related to the project, the Discord community is welcoming!