Skip to main content

ReXia.AI: An advanced AI framework for agentic processes

Project description

ReXia.AI

ReXia.AI is an advanced AI framework designed to integrate various language models, tools, and workflows for complex task solving and analysis. It provides a flexible and extensible platform for building AI-powered applications and agents.

Table of Contents

Update v0.1.3

  • Improved handling of JSON responses
  • Removed LLMWare and Huggingface LLM types, they're still useable, just provide an OpenAI compatibile endpoint for them.
  • Added 'PerplexityLite' example.
  • resolved a minor bug with working memory in that messages added more recently to the list were being passed further down in the prompt. This was causing the LLM to think the oldest message was the most recent.

Features

  • Support for multiple language models
  • Extensible workflow system
  • Built-in memory management
  • Integration with various external tools and APIs
  • Customizable agents for specific tasks

Installation

To install ReXia.AI, you can use pip:

pip install rexia-ai

Additionally, you need to install either PyTorch or TensorFlow, depending on your preference:

For PyTorch:

pip install torch

For TensorFlow:

pip install tensorflow

Quick Start

Here's a simple example to get you started with ReXia.AI:

from rexia_ai.agent import Agent
from rexia_ai.workflows import SimpleToolWorkflow
from rexia_ai.memory import WorkingMemory
from rexia_ai.llm import RexiaAIOpenAI

# Initialize the language model
llm = RexiaAIOpenAI(
    base_url="https://api.openai.com/v1",
    model="gpt-3.5-turbo",
    temperature=0.7,
    api_key="your-openai-api-key"
)

# Create an Agent instance
agent = Agent(
    llm=llm,
    task="Summarize the latest news on AI advancements",
    workflow=SimpleToolWorkflow,
    memory=WorkingMemory(),
    verbose=True
)

# Run the agent
result = agent.invoke()
print(result)

Documentation

Detailed documentation for each component can be found in the docs folder:

Tools

ReXia.AI comes with several built-in tools:

License

This project is licensed under the Apache License 2.0. See the LICENSE file for details.

Contact

For any questions, issues, or suggestions, please open an issue on our GitHub repository.

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

rexia_ai-0.1.5.tar.gz (28.9 kB view details)

Uploaded Source

Built Distribution

rexia_ai-0.1.5-py3-none-any.whl (39.4 kB view details)

Uploaded Python 3

File details

Details for the file rexia_ai-0.1.5.tar.gz.

File metadata

  • Download URL: rexia_ai-0.1.5.tar.gz
  • Upload date:
  • Size: 28.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.0 CPython/3.11.9

File hashes

Hashes for rexia_ai-0.1.5.tar.gz
Algorithm Hash digest
SHA256 7f77b61d8b1c960228d2b5a69a96007e925f05b868ee9fb8386283592e8397c9
MD5 c4e0eaa382930590d84ffd83464564ec
BLAKE2b-256 9f0b5ca9ec4ffd91b208afa6d2b59b9abe042fba96774f3fb6e856baa78e04b3

See more details on using hashes here.

File details

Details for the file rexia_ai-0.1.5-py3-none-any.whl.

File metadata

  • Download URL: rexia_ai-0.1.5-py3-none-any.whl
  • Upload date:
  • Size: 39.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.0 CPython/3.11.9

File hashes

Hashes for rexia_ai-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 cc8ac98bbba40078292515aa25d77eea3c4d1548b6298b6f13e2aded052480c2
MD5 22524ff5bfa0f7c1368f9e77d347e601
BLAKE2b-256 7621243793eb75bb3e15c7dbc863124f75e1f001d8a0607ca6a81994cf358df3

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