Skip to main content

Package defining the WayFlow core library and the assistant abstractions.

Project description

🔗 WayFlow Core

PyPI - Version PyPI - License PyPI - Downloads

WayFlow Core is the foundational Python library of the WayFlow ecosystem. It provides the runtime engine, abstractions, and components needed to build powerful AI assistants using Agents, Flows, or hybrid architectures.

WayFlow Core is:

  • 🔧 Flexible — Build assistants using Agents, Flows, or both
  • 🔗 Interoperable — Works with OCI GenAI, OpenAI, Ollama, and other LLM providers
  • 🧩 Composable — Encourages modular, reusable building blocks
  • 🚀 Extensible & Open — Designed for advanced agentic applications

⚡ Quick Install

pip install wayflowcore

(Optional, faster installation using uv)

pip install uv
uv pip install wayflowcore

🧠 Quick Start

1. Initialize an LLM

Initialize a Large Language Model (LLM) of your choice:

OCI Gen AI Open AI Ollama
from wayflowcore.models import OCIGenAIModel

llm = OCIGenAIModel(
model_id="provider.model-id",
service_endpoint="https://url-to-service-endpoint.com",
compartment_id="compartment-id",
auth_type="API_KEY",
)
from wayflowcore.models import OpenAIModel

llm = OpenAIModel(
model_id="model-id",
)
from wayflowcore.models import OllamaModel

llm = OllamaModel(
model_id="model-id",
)

2. Create an Assistant

from wayflowcore.agent import Agent

assistant = Agent(llm=llm)

conversation = assistant.start_conversation()
conversation.append_user_message("I need help regarding my sql query")
conversation.execute()

# get the assistant's response to your query
assistant_answer = conversation.get_last_message()
assistant_answer.content
# I'd be happy to help with your SQL query...

🧩 What You Can Build

WayFlow Core supports a wide range of agentic patterns:

  • 💬 Conversational assistants
  • 🔁 Flow-based assistants with structured sequencing
  • 🤝 Multi-agent systems
  • 🛠️ Tool-calling agents
  • 🧪 Automated code review assistants
  • 📚 Domain-specific knowledge assistants

💁 Contributing

Contributions are welcome! Please refer to the contributor guide located at the root of the repository.


🔐 Security

For responsibly reporting security issues, please refer to the project's security guidelines.


📄 License

WayFlow Core is dual-licensed under:

Project details


Download files

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

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

wayflowcore-25.4.3-py3-none-any.whl (620.6 kB view details)

Uploaded Python 3

File details

Details for the file wayflowcore-25.4.3-py3-none-any.whl.

File metadata

  • Download URL: wayflowcore-25.4.3-py3-none-any.whl
  • Upload date:
  • Size: 620.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for wayflowcore-25.4.3-py3-none-any.whl
Algorithm Hash digest
SHA256 df16c601ad67773b80eb555b41e46a751b208934f57381f0ad52f63e6771a7ed
MD5 5d73cf9ed92157e3039e76af9fe25d5d
BLAKE2b-256 87d402056c725f00431aaf4a5490f041664121b97ac893bee9c291f2f68f369d

See more details on using hashes here.

Supported by

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