animuz-core 0.1.0

Core shared utilities for Animuz RAG system - LLM clients, pipelines, vector DB, and document ingestion

animuz-core

Core shared utilities for Animuz RAG (Retrieval-Augmented Generation) system.

Features

• LLM Clients: OpenAI, Anthropic Claude, Ollama
• RAG Pipelines: Simple and Agentic RAG implementations
• Vector Database: Qdrant integration with hybrid search
• Embedding Clients: Multiple embedding providers (Modal, S3, SageMaker)
• Document Ingestion: Azure Document Intelligence, Unstructured, custom parsers
• CloudWatch Logging: Structured logging with watchtower

Installation

pip install animuz-core

Or with uv (faster):

uv pip install animuz-core

Usage

from animuz_core.genai import OpenAIAgentClient
from animuz_core.pipelines import AgenticRAG
from animuz_core.vectordb import QdrantDBClient

# Initialize LLM client
agent = OpenAIAgentClient(tools={})

# Use RAG pipeline
pipeline = AgenticRAG(...)
result = await pipeline.run(query="What is RAG?")

Development

Install in editable mode:

pip install -e .

Run tests:

pytest tests/

License

MIT