Skip to main content

A flexible agent library.

Project description

Language agent experimentation made easy.

codecov License: MIT

Agential provides clear implementations of popular LLM-based agents across a variety of reasoning/decision-making and language agent benchmarks, making it easy for researchers to evaluate and compare different agents.

🤔 Getting Started

First, install the library with pip:

pip install agential

Next, let's query the ReActAgent!

from agential.llm.llm import LLM
from agential.cog.react.agent import ReActAgent

question = 'Who was once considered the best kick boxer in the world, however he has been involved in a number of controversies relating to his "unsportsmanlike conducts" in the sport and crimes of violence outside of the ring?'

llm = LLM("gpt-3.5-turbo")
agent = ReActAgent(llm=llm, benchmark="hotpotqa")
out = agent.generate(question=question)

🙏 Acknowledgement

😀 Contributing

If you want to contribute, please check the contributing.md for guidelines! Please check out the project document timeline on Notion and reach out to us if you have any questions!

😶‍🌫️ Contact Us!

If you have any questions or suggestions, please feel free to reach out to tuvincent0106@gmail.com!

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agential-0.2.1.tar.gz (220.2 kB view details)

Uploaded Source

Built Distribution

agential-0.2.1-py3-none-any.whl (303.9 kB view details)

Uploaded Python 3

File details

Details for the file agential-0.2.1.tar.gz.

File metadata

  • Download URL: agential-0.2.1.tar.gz
  • Upload date:
  • Size: 220.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.11.5 Windows/10

File hashes

Hashes for agential-0.2.1.tar.gz
Algorithm Hash digest
SHA256 04db4f12a526fe1f826137f271bbcbe72d6c18d213587604cf47055d07bc1122
MD5 b1960bf4e72c0a887830e56480ddc129
BLAKE2b-256 e14444e989c913ae38783bb04ca9b850661b89c30a0d607130fb7e6ba4df632f

See more details on using hashes here.

File details

Details for the file agential-0.2.1-py3-none-any.whl.

File metadata

  • Download URL: agential-0.2.1-py3-none-any.whl
  • Upload date:
  • Size: 303.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.11.5 Windows/10

File hashes

Hashes for agential-0.2.1-py3-none-any.whl
Algorithm Hash digest
SHA256 d419e0c6068ee6aa8bfb3026527b17c4c83961cda808d2bb62b30959f495a5d5
MD5 485b6e9198ed9ec6f899c3f69698511a
BLAKE2b-256 bcde45d8923f3d35a5385677f7886d630a00ab2c946c071a389a7412ef9d2400

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page