reag 0.0.5

ReAG SDK - Reasoning Augmented Generation framework for Python

🎓 ReAG Python SDK

Installation

1. Ensure Python 3.9+ is installed.
2. Install using pip or poetry:

   pip install reag
   # or
   poetry add reag
   

Quick Start

from reag.client import ReagClient, Document

async with ReagClient(
      model="ollama/deepseek-r1:7b",
      model_kwargs={"api_base": "http://localhost:11434"}
   ) as client:
        docs = [
            Document(
                name="Superagent",
                content="Superagent is a workspace for AI-agents that learn, perform work, and collaborate.",
                metadata={
                    "url": "https://superagent.sh",
                    "source": "web",
                },
            ),
        ]
        response = await client.query("What is Superagent?", documents=docs)

API Reference

Initialization

Initialize the client by providing required configuration options:

client = new ReagClient(
  model: "gpt-4o-mini", // LiteLLM model name
  system: Optional[str] // Optional system prompt
  batchSize: Optional[Number] // Optional batch size
  schema: Optional[BaseModel] // Optional Pydantic schema
);

Document Structure

Documents should follow this structure:

document = Document(
    name="Superagent",
    content="Superagent is a workspace for AI-agents that learn, perform work, and collaborate.",
    metadata={
        "url": "https://superagent.sh",
        "source": "web",
    },
)

Querying

Query documents with optional filters:

docs = [
    Document(
        name="Superagent",
        content="Superagent is a workspace for AI-agents that learn, perform work, and collaborate.",
        metadata={
            "url": "https://superagent.sh",
            "source": "web",
            "id": "sa-1",
        },
    ),
    Document(
        name="Superagent",
        content="Superagent is a workspace for AI-agents that learn, perform work, and collaborate.",
        metadata={
            "url": "https://superagent.sh",
            "source": "web",
            "id": "sa-2",
        },
    ),
]
options = {"filter": [{"key": "id", "value": "sa-1", "operator": "equals"}]}
response = await client.query(
    "What is Superagent?", documents=docs, options=options
)

Response structure:

content: str
reasoning: str
is_irrelevant: bool
document: Document

Example filters:

• Filter by metadata field:

  options = {"filter": [{"key": "id", "value": "sa-1", "operator": "equals"}]}
  

• Filter by numeric values:

  options = {
    "filter": [{"key": "version", "value": 2, "operator": "greaterThanOrEqual"}]
  }
  

Contributing

We welcome contributions from the community. Please refer to the CONTRIBUTING.md file for guidelines on reporting issues, suggesting improvements, and submitting pull requests.

License

This project is licensed under the MIT License.

Additional Resources

• ReAG Blog Post - A deep dive into ReAG.

Contact

For support or inquiries, please contact:

• Create Issue
• X: @superagent_ai