Moorcheh - Information-Theoretical Memory for AI Agents/Apps/Assistants

📊 Download Statistics

📚 Repositories

🔌 Integrations

💡 Use Cases

🚀 Getting Started

📦 Install the SDK:

pip install moorcheh-sdk

🚀 Quick Start Example:

import os
from moorcheh_sdk import MoorchehClient

# Initialize client
client = MoorchehClient(api_key=os.getenv("MOORCHEH_API_KEY"))

# Create namespace and upload documents
client.create_namespace("my-rag", "text")
client.upload_documents("my-rag", [
    {"id": "doc1", "text": "Your content...", "metadata": {}}
])

# Get AI-powered answers
answer = client.get_generative_answer(
    namespace="my-rag",
    query="Your question here"
)
print(answer["answer"])

🛠️ Complete toolkit for Python developers:

• Namespace management (text/vector)
• Document and vector ingestion
• Advanced semantic search with filtering
• Built-in RAG system support
• Generative AI integration
• Comprehensive error handling

Why Moorcheh.ai?

Moorcheh.ai delivers ultra-fast, highly accurate semantic search powered by cutting-edge information theory principles. Our enterprise platform enables developers to build production-ready RAG systems and AI chatbots with unprecedented search accuracy and performance.

🧮 Information-Theoretical Foundation

• ITS (Information-Theoretical Similarity) Scoring: Our proprietary algorithm goes beyond traditional cosine similarity, providing more nuanced and contextually aware search results
• Mathematical Precision: Built on solid information theory foundations for consistent, explainable results
• Superior Accuracy: Outperforms traditional vector databases in semantic understanding and relevance

🏢 Enterprise-Ready Features

• Scalable Architecture: Handle enterprise workloads with confidence
• Multi-Modal Support: Text and vector embeddings in unified namespaces
• Production Monitoring: Built-in analytics and performance metrics