Webtagr - Technology News Summarizer

Voyage-3.5: Next-Gen Embedding Models with Superior Cost-Performance

2025-05-24

Voyage AI launched Voyage-3.5 and Voyage-3.5-lite, its next-generation embedding models. These maintain the same size as their predecessors but deliver significant improvements in retrieval quality at a lower cost. Compared to OpenAI's v3-large, Voyage-3.5 and Voyage-3.5-lite show 8.26% and 6.34% better retrieval quality, respectively, while costing 2.2x and 6.5x less. Supporting multiple embedding dimensions and quantization options via Matryoshka learning and quantization-aware training, they drastically reduce vector database costs while maintaining superior accuracy.

Benchmarking Code Retrieval: Challenges and Voyage AI's Approach

2025-02-03

Modern coding assistants heavily rely on code retrieval, but existing evaluation methods fall short. Voyage AI's research highlights issues with current datasets, including noisy labels, lack of deep algorithmic reasoning assessment, and data contamination, leading to unreliable model evaluations. To address this, Voyage AI proposes two methods for creating high-quality code retrieval datasets: repurposing question-answer datasets and leveraging GitHub repositories and issues/tickets. Voyage AI also built its internal benchmarking suite, encompassing multiple programming languages, various QA datasets, and domain-specific benchmarks, evaluating several code embedding models. Voyage-code-3 emerged as the top performer.

Voyage-code-3: More Accurate Code Retrieval with Lower Costs

2025-01-14

Voyage AI unveiled Voyage-code-3, a next-generation code retrieval embedding model surpassing OpenAI-v3-large and CodeSage-large by an average of 13.80% and 16.81% across 32 datasets. Leveraging Matryoshka learning and quantization (int8 and binary), Voyage-code-3 dramatically reduces storage and search costs with minimal impact on retrieval quality. Supporting 2048, 1024, 512, and 256-dimensional embeddings and various quantization formats, it boasts a 32K token context length. Trained on a massive, diverse code corpus, Voyage-code-3 excels in code retrieval, particularly handling algorithmic reasoning and nuanced syntax, and has been rigorously evaluated for robustness and accuracy.