



const { OpenAI } = require('openai');
const main = async () => {
const api = new OpenAI({ apiKey: '', baseURL: 'https://api.ai.cc/v1' });
const text = 'Your text string goes here';
const response = await api.embeddings.create({
input: text,
model: 'voyage-large-2-instruct',
});
const embedding = response.data[0].embedding;
console.log(embedding);
};
main();
import json
from openai import OpenAI
def main():
client = OpenAI(
base_url="https://api.ai.cc/v1",
api_key="",
)
text = "Your text string goes here"
response = client.embeddings.create(input=text, model="voyage-large-2-instruct")
embedding = response.data[0].embedding
print(json.dumps(embedding, indent=2))
main()
-
AI Playground

Test all API models in the sandbox environment before you integrate.
We provide more than 300 models to integrate into your app.


Product Detail
🚀 Introducing Voyage Large 2 Instruct: A Cutting-Edge Text Embedding Model
Discover the power of Voyage Large 2 Instruct, an advanced instruction-tuned, general-purpose text embedding model developed by Voyage AI. Released in May 2024 as Version 2.0, this model is engineered to deliver unparalleled performance across a range of natural language processing tasks, including clustering, classification, and retrieval.
It stands out by consistently achieving top rankings on the Massive Text Embedding Benchmark (MTEB), affirming its position as a leader in text understanding and representation.
✨ Key Features & Capabilities
- Instruction Tuning: Enhanced performance across diverse tasks through specialized instruction fine-tuning.
- Task Optimization: Specifically optimized for critical NLP functions like text clustering, classification, and information retrieval.
- Benchmark Excellence: Consistently achieves high performance on MTEB benchmarks, often ranking first.
- Extended Context: Features a robust 16K context window for deeper understanding and processing of longer texts.
💡 Intended Use Cases for Voyage Large 2 Instruct
Voyage Large 2 Instruct is ideal for developers and businesses seeking high-quality text embeddings in various applications:
- Advanced Text Retrieval & Search: Powering intelligent search engines and recommendation systems.
- Efficient Text Classification & Clustering: Organizing and categorizing large volumes of text data with high accuracy.
- Sophisticated Reranking Tasks: Improving the relevance and order of search results or document lists.
While primarily supporting English, the model can be adapted for other languages through specific tuning processes.
⚙️ Technical Deep Dive
Understanding the foundation of Voyage Large 2 Instruct reveals its sophisticated design:
Architecture:
Built upon a robust transformer architecture, Voyage Large 2 Instruct leverages a proven framework known for its efficiency, scalability, and effectiveness in modern natural language processing tasks.
Training Data:
The model's exceptional performance stems from training on a diverse and extensive dataset, comprising millions of text samples from various domains and sources. This comprehensive training ensures strong generalization capabilities and mitigates potential biases across different applications.
The sheer scale of the training data contributes significantly to the model's comprehensive understanding of linguistic nuances and complex topics.
📊 Performance at a Glance
Voyage Large 2 Instruct is engineered for peak performance:

- Accuracy: Demonstrates superior accuracy across various NLP tasks, consistently outperforming many competitors in classification and retrieval benchmarks.
- Speed: Optimized for an excellent balance between processing speed and accuracy, making it suitable for real-time applications where efficiency is key.
- Robustness: Exhibits strong generalization capabilities, handling diverse inputs and adapting effectively across different topics and languages, a direct benefit of its extensive training.
🚀 Getting Started with Voyage Large 2 Instruct
Ready to integrate this powerful model into your projects? Get immediate access:
➡️ Sign In to Access 📞 Schedule a Consultation
Code Samples:
For implementation details and example code, refer to the following snippet:
Ethical Guidelines:
Voyage Large 2 Instruct is developed with a strong commitment to ethical AI principles. Efforts are continuously made to minimize biases and promote fair use. Developers are strongly encouraged to conduct thorough assessments within their specific application contexts to ensure ethical deployment and address any potential concerns.
License Type:
The model is available under a commercial license. This permits both commercial and non-commercial applications, subject to the detailed terms and conditions provided by Voyage AI.
❓ Frequently Asked Questions (FAQ)
Q: What is Voyage Large 2 Instruct?
A: Voyage Large 2 Instruct is an advanced, instruction-tuned text embedding model by Voyage AI, optimized for tasks like text clustering, classification, and retrieval. It consistently excels on MTEB benchmarks.
Q: What makes it stand out from other text embedding models?
A: Its key differentiators include specialized instruction tuning for superior task performance, a generous 16K context window, and top-tier rankings on MTEB, showcasing its high accuracy and robustness.
Q: What are the primary use cases for this model?
A: It is ideally suited for text retrieval, sophisticated search applications, efficient text classification, robust clustering, and advanced reranking tasks where high-quality semantic representations are crucial.
Q: Does Voyage Large 2 Instruct support multiple languages?
A: The model primarily supports English. However, its versatile architecture allows for effective adaptation and fine-tuning to support other languages as needed.
Q: How can I access Voyage Large 2 Instruct?
A: You can gain immediate access by signing in on the AI.CC platform. Additionally, you can schedule a personalized call with Voyage AI to discuss specific use cases, integration strategies, and potential solutions.
Learn how you can transformyour company with AICC APIs



Log in