Coding agents issue dozens of context-fetch calls per task across multi-file, evolving repos. Most embedding models were never trained for that.
📢 Introducing voyage-code-4 — trained on retrieval patterns from real issue-fixing pull requests. 32K context.
📈voyage-code-4 outperforms Cohere Embed v4 and Gemini Embedding 2 by an average of 28.25% and 31.03% on agentic code retrieval
Get started with voyage-code-4:
embedding — A list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
Coding agents issue many context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → fetches per task, so an embeddingA list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.Full definition → model trained on that access pattern rather than generic text search changes what actually lands in the AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition →'s context.
