Skip to main content

Unit Tests

EAGLE Logo

Enhanced Agents for Generative Language Excellence

Do que se trata este projeto?

Esse projeto implementa a visão do framework CoALA (Cognitive Architectures for Language Agents) no contexto do LangGraph, com agentes, ferramentas e estratégias de integração multiagentes para servirem de exemplo para novas implementações.

Instalação

Pré-requisitos (considerando o uso do Conda para gerenciar o ambiente python)

  • Miniforge 3: O Miniforge é uma distribuição mínima do conda, que é um gerenciador de pacotes e ambientes virtuais. Ele será usado para criar um ambiente virtual para instalar as dependências do projeto.

Criando o ambiente virtual

  1. Uma vez instalado o Conda, abra o terminal e digite o seguinte comando:
conda create -n eagle python=3.10
  1. Após a criação do ambiente, ative-o com o comando:
conda activate eagle
  1. Instale a versão mais recente do Poetry com o comando:
pip install poetry==1.8.5
  1. Instale as dependências do projeto com o comando:
poetry install

Testes

Para executar os testes, execute os seguintes passos:

  1. Ative o ambiente virtual com o comando:
conda activate eagle
  1. Copie o arquivo sample.test.env para .test.env e preencha as variáveis de ambiente com as informações necessárias para o seu amnbiente de testes.
cp sample.test.env .test.env

Ponto de Atenção

Os testes e exemplos dos notebooks estão baseados nos modelos AzureChatOpenAI para os LLMs e AzureOpenAIEmbeddings para os embeddings. Caso seja necessário utilizar outros nomes de modelos, tipos ou ajustar as relações com as variáveis de ambiente, essas alterações podem ser feitas na pasta tests/models.

Exemplos de uso das funcionalidades

A pasta notebooks contém exemplos de uso das ferramentas. Para executar os exemplos:

  1. Ative o ambiente virtual com o comando:
conda activate eagle
  1. Ative a extensão de widgets do jupyter com o comando:
jupyter nbextension enable --py widgetsnbextension
  1. Ative o jupyter lab com o comando:
jupyter lab
  1. Abra o browser e execute os notebooks da pasta notebooks.

Metadata

Release files for dev-tools-eagle-thompsonp17 0.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for dev-tools-eagle-thompsonp17 0.0.1
File Size Uploaded Provenance Actions
dev_tools_eagle_thompsonp17-0.0.1.tar.gz 152.0 kB Without provenance Details for dev_tools_eagle_thompsonp17-0.0.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for dev-tools-eagle-thompsonp17 0.0.1
File Interpreter ABI Platform Actions
dev_tools_eagle_thompsonp17-0.0.1-py3-none-any.whl Python 3 none any Details for dev_tools_eagle_thompsonp17-0.0.1-py3-none-any.whl

Total release size: 374.8 kB

Release files / dev_tools_eagle_thompsonp17-0.0.1.tar.gz

Download URL dev_tools_eagle_thompsonp17-0.0.1.tar.gz
Size 152.0 kB
Tags Source
SHA-256 checksum
How to use checksums
d7c652e198e40e5963df25ed87d1aa29ae37fa656cc2c1f27da7156ebb47e4ce
BLAKE2b-256 checksum
How to use checksums
83f199c68f5c18682a4259cded76459360e3d5c47fd87a4a280786963dc92400
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/2.2.1 CPython/3.11.13 Linux/5.15.167.4-microsoft-standard-WSL2

Release files / dev_tools_eagle_thompsonp17-0.0.1-py3-none-any.whl

Download URL dev_tools_eagle_thompsonp17-0.0.1-py3-none-any.whl
Size 222.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
fa01fa5e1a42ae78e57a8f756da7fe729a8de2983ac6261e3af9d7a3ab86e9af
BLAKE2b-256 checksum
How to use checksums
f69cd5b532ee9140d08e69b82a6d379c59290d2625ede4917c61b2e9e7a31295
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/2.2.1 CPython/3.11.13 Linux/5.15.167.4-microsoft-standard-WSL2

Security for dev-tools-eagle-thompsonp17 0.0.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.0.1 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page