Novita AI & DeepSearcher: Quick Start

DeepSearcher is an open-source solution designed to transform private data search and reasoning by integrating cutting-edge large language models (LLMs) with vector databases such as Milvus. With support for LLMs and embedding models from Novita AI, this powerful configuration delivers unmatched accuracy and efficiency in private data search.

This step-by-step guide will walk you through how to quickly and easily configure Novita AI with DeepSearcher.

​

How to use DeepSearcher with Novita

Step 1: Follow the example in examples/basic_example.py .

Step 2: Add the following code below the line config = Configuration() :

config.set_provider_config("llm", "NOVITA", {"model": "deepseek/deepseek-r1-turbo"})
config.set_provider_config("embedding", "NovitaEmbedding", {"model": "baai/bge-m3"})

Step 3: Run examples/basic_example.py to execute the integration.

You’ll get the following results：