quraite 0.1.1

This project provides adaptors and methods to integrate with the Quraite platform

Quraite Python SDK

The Quraite Python SDK provides adapters and methods to integrate AI agent frameworks with the Quraite platform. It offers a unified interface for different agent frameworks, automatic tracing and observability, and easy local server setup with tunneling capabilities.

Features

• 🔌 Framework Adapters: Support for multiple AI agent frameworks (LangGraph, Pydantic AI, Agno, Google ADK, OpenAI Agents, Smolagents, AWS Bedrock, Flowise, Langflow, N8n, and more)
• 📊 Automatic Tracing: Built-in OpenTelemetry-based tracing for agent execution, tool calls, and performance metrics
• 🚀 Local Server: Easy-to-use local server with optional tunneling (Cloudflare/ngrok) for public access
• 📦 Standardized Schema: Unified message and response formats across all frameworks
• 🔍 Observability: Track token usage, costs, latency, and model information for each agent invocation

Installation

Basic Installation

pip install quraite

Framework-Specific Installation

Install with optional dependencies for specific frameworks:

# LangGraph
pip install 'quraite[langgraph]'

# Pydantic AI
pip install 'quraite[pydantic-ai]'

# Agno
pip install 'quraite[agno]'

# Google ADK
pip install 'quraite[google-adk]'

# OpenAI Agents
pip install 'quraite[openai-agents]'

# Smolagents
pip install 'quraite[smolagents]'

# AWS Bedrock
pip install 'quraite[bedrock]'

# Multiple frameworks
pip install 'quraite[langgraph,pydantic-ai,agno]'

Quick Start

Example: LangGraph Agent with Local Server

Pass your compiled LangGraph agent to the adapter and expose it as an HTTP API:

import uvicorn
from dotenv import load_dotenv
from openinference.instrumentation import TracerProvider
from openinference.instrumentation.langchain import LangChainInstrumentor

from quraite.adapters import LanggraphAdapter
from quraite.serve.local_agent import LocalAgentServer
from quraite.tracing.span_exporter import QuraiteInMemorySpanExporter
from quraite.tracing.span_processor import QuraiteSimpleSpanProcessor

load_dotenv()

# Set up tracing (optional)
tracer_provider = TracerProvider()
quraite_span_exporter = QuraiteInMemorySpanExporter()
quraite_span_processor = QuraiteSimpleSpanProcessor(quraite_span_exporter)
tracer_provider.add_span_processor(quraite_span_processor)
LangChainInstrumentor().instrument(tracer_provider=tracer_provider)

# Your compiled LangGraph agent (created elsewhere)
# agent = create_agent(...)

# Wrap with Quraite adapter
adapter = LanggraphAdapter(
    agent_graph=agent,  # Pass your compiled LangGraph agent here
    tracer_provider=tracer_provider,  # Optional: for tracing
)

# Create and start server with Cloudflare tunnel
server = LocalAgentServer(
    wrapped_agent=adapter,
    agent_id="your-agent-id",  # Optional: for Quraite platform integration
)

app = server.create_app(
    port=8080,
    host="0.0.0.0",
    tunnel="cloudflare",  # Options: "cloudflare", "ngrok", or "none"
)

if __name__ == "__main__":
    uvicorn.run("local_server:app", host="0.0.0.0", port=8080)

The server exposes:

• GET / - Health check endpoint
• POST /v1/agents/completions - Agent invocation endpoint

When using tunnel="cloudflare" or tunnel="ngrok", your agent will be publicly accessible via the generated URL.

Supported Frameworks

Framework	Adapter	Installation
LangGraph	LanggraphAdapter	pip install 'quraite[langgraph]'
Pydantic AI	PydanticAIAdapter	pip install 'quraite[pydantic-ai]'
Agno	AgnoAdapter	pip install 'quraite[agno]'
Google ADK	GoogleADKAdapter	pip install 'quraite[google-adk]'
OpenAI Agents	OpenaiAgentsAdapter	pip install 'quraite[openai-agents]'
Smolagents	SmolagentsAdapter	pip install 'quraite[smolagents]'
AWS Bedrock	BedrockAgentsAdapter	pip install 'quraite[bedrock]'
Flowise	FlowiseAdapter	Included in base package
Langflow	LangflowAdapter	Included in base package
N8n	N8nAdapter	Included in base package
HTTP	HttpAdapter	Included in base package
LangGraph Server	LanggraphServerAdapter	pip install 'quraite[langgraph]'

Core Concepts

Adapters

Adapters provide a unified interface (BaseAdapter) for different agent frameworks. Each adapter:

• Converts framework-specific agents to a standard interface
• Handles message format conversion
• Supports optional tracing integration
• Provides async invocation via ainvoke()

Tracing

The SDK includes built-in OpenTelemetry-based tracing that captures:

• Agent Trajectory: Complete conversation flow with all messages
• Tool Calls: Tool invocations with inputs and outputs
• Performance Metrics: Token usage, costs, latency
• Model Information: Model name and provider details

To enable tracing:

from openinference.instrumentation import TracerProvider
from quraite.tracing.span_exporter import QuraiteInMemorySpanExporter
from quraite.tracing.span_processor import QuraiteSimpleSpanProcessor

tracer_provider = TracerProvider()
quraite_span_exporter = QuraiteInMemorySpanExporter()
quraite_span_processor = QuraiteSimpleSpanProcessor(quraite_span_exporter)
tracer_provider.add_span_processor(quraite_span_processor)

# Instrument your framework (example for LangChain)
from openinference.instrumentation.langchain import LangChainInstrumentor
LangChainInstrumentor().instrument(tracer_provider=tracer_provider)

Message Schema

The SDK uses a standardized message format:

from quraite.schema.message import (
    UserMessage,
    AssistantMessage,
    ToolMessage,
    SystemMessage,
    MessageContentText,
    ToolCall,
)

# User message
user_msg = UserMessage(
    content=[MessageContentText(text="Hello, world!")]
)

# Assistant message with tool calls
assistant_msg = AssistantMessage(
    content=[MessageContentText(text="I'll calculate that for you.")],
    tool_calls=[
        ToolCall(
            id="call_123",
            name="add",
            arguments={"a": 10, "b": 5}
        )
    ]
)

# Tool message
tool_msg = ToolMessage(
    tool_call_id="call_123",
    content=[MessageContentText(text="15")]
)

Response Format

Agent invocations return an AgentInvocationResponse:

from quraite.schema.response import AgentInvocationResponse

response: AgentInvocationResponse = await adapter.ainvoke(
    input=[user_msg],
    session_id="session-123"
)

# Access trajectory (list of messages)
trajectory = response.agent_trajectory

# Access trace (if tracing enabled)
trace = response.agent_trace

# Access final response text
final_response = response.agent_final_response

Examples

The repository includes comprehensive examples for each supported framework:

• langgraph_calculator_agent - LangGraph calculator agent
• pydantic_calculator_agent - Pydantic AI calculator agent
• agno_calculator_agent - Agno calculator agent
• google_adk_weather_agent - Google ADK weather agent
• openai_flight_booking_agent - OpenAI Agents flight booking
• smolagents_sql_agent - Smolagents SQL agent
• bedrock_restaurant_support_agent - AWS Bedrock agent
• And more...

Each example includes:

• Agent implementation
• Adapter setup
• Local server configuration
• Environment variable examples

API Reference

BaseAdapter

All adapters inherit from BaseAdapter:

from quraite.adapters.base import BaseAdapter

class MyAdapter(BaseAdapter):
    async def ainvoke(
        self,
        input: List[AgentMessage],
        session_id: str | None,
    ) -> AgentInvocationResponse:
        # Implementation
        pass

LocalAgentServer

Create a local HTTP server for your agent:

from quraite.serve.local_agent import LocalAgentServer

server = LocalAgentServer(
    wrapped_agent=adapter,
    agent_id="optional-agent-id",
)

app = server.create_app(
    port=8080,
    host="0.0.0.0",
    tunnel="cloudflare",  # or "ngrok" or "none"
)

Development

Setup

# Clone the repository
git clone https://github.com/innowhyte/quraite-python.git
cd quraite-python

# Install dependencies
pip install -e ".[dev,test]"

Running Tests

pytest

Building

make build

Publishing

# Update version
make update-version v=0.4.0

# Build
make build

# Publish to Test PyPI
make publish
# Enter username as "__token__" and then enter your API key

Requirements

• Python 3.10+
• See pyproject.toml for full dependency list

License

See LICENSE file for details.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Support

For issues, questions, or contributions, please visit the Quraite platform or open an issue on GitHub.

Changelog

See the repository's commit history for detailed changes.