kamiwaza 0.1.1

Python client library for the Kamiwaza AI Infrastructure Platform

Kamiwaza Python SDK

Python client library for interacting with the Kamiwaza AI Infrastructure Platform. This SDK provides a type-safe interface to all Kamiwaza API endpoints with built-in authentication, error handling, and resource management.

Installation

pip install kamiwaza-client

Quick Start

from kamiwaza_client import KamiwazaClient

# Initialize the client for local development
client = KamiwazaClient("http://localhost:7777/api/")

Examples

The /examples directory contains Jupyter notebooks demonstrating various use cases:

1. Model Download and Deployment - Shows how to download and deploy a model using the SDK
2. Structured Data Extraction - Demonstrates how to use deployed models for data processing and standardization

More examples coming soon!

Service Overview

Service	Description	Documentation
client.models	Model management	Models Service
client.serving	Model deployment	Serving Service
client.vectordb	Vector database	VectorDB Service
client.catalog	Data management	Catalog Service
client.embedding	Text processing	Embedding Service
client.retrieval	Search	Retrieval Service
client.ingestion	Data pipeline	Ingestion Service
client.cluster	Infrastructure	Cluster Service
client.lab	Lab environments	Lab Service
client.auth	Security	Auth Service
client.activity	Monitoring	Activity Service

Batch Operations

Many services support batch operations for better performance:

# Batch embedding
chunks = embedder.chunk_text(text, max_length=500)
embeddings = embedder.embed_chunks(chunks, batch_size=32)

# Batch vector insertion
client.vectordb.insert(vectors, metadata, batch_size=1000)

---

The Kamiwaza SDK is actively being developed with new features, examples, and documentation being added regularly. Stay tuned for updates including additional example notebooks, enhanced documentation, and expanded functionality across all services. For the latest updates and feature releases, keep an eye on this repository.