[Release] langchain-ai/langchain langchain-openai==1.3.5: langchain-openai==1.3.5

langchain-openai version 1.3.5 has been released with support for explicit prompt caching, an optimization feature that reduces API costs and latency by caching prompts. The release includes updates to model profile data and builds upon the previous 1.3.4 version. This enhancement allows developers to leverage OpenAI's prompt caching capabilities directly within LangChain's OpenAI integration.

Key Points

• •Explicit prompt caching support added to langchain-openai for improved performance and cost efficiency
• •Prompt caching reduces redundant API calls by storing and reusing cached prompt data
• •Model profile data refreshed to ensure compatibility with latest OpenAI models
• •Feature enables developers to optimize token usage and reduce latency in LangChain applications
• •Incremental release (1.3.4 → 1.3.5) focusing on performance improvements rather than breaking changes
• •Integration with OpenAI's native prompt caching mechanism for seamless optimization

Workflow Diagram

Concepts