LangChain Changelog

Sign up for our newsletter to stay up to date

Powered by LaunchNotes

Loading...

August 2024

✔️ LangGraph v0.2: Increased customization with new checkpointers

We've released LangGraph v0.2 for increased customization with new checkpointer libraries. LangGraph v0.2 allows you to tailor stateful LangGraph apps to...

🚀 Few-shot examples with LangSmith datasets

LangSmith now supports fast, easy-to-use APIs to find few shot examples from your datasets, which you can use to improve your LLM applications without...

🚀 LangGraph Studio: The first agent IDE

LangGraph Studio offers a new way to develop LLM applications by providing a specialized agent IDE that enables visualization, interaction, and debugging of...

🏃 Trace comparison view & saving custom trace filters

In the runs table in LangSmith, you can now select traces to compare side-by-side. This lets you make direct comparisons to see discrepancies in output...

📊 Define, validate, and update dataset schemas in LangSmith

When building a dataset iteratively for an LLM app, having a defined schema for testing across examples lets you avoid broken code and keep your data clean...

July 2024

✍️ Multiple annotators can review a run in LangSmith

LangSmith's annotation queue now supports allowing multiple people to review an individual run. This makes it easier to coordinate data review across...

🔧 Improved Pydantic 2 support with LangChain tool APIs

LangChain APIs now allow using Pydantic v2 models for BaseTool and StructuredTool . This can enhance type safety, improve code readability, and simplify the...

🗣️ Rate limiting for any chat model

LangChain has a built-in memory rate limiter that can help you avoid exceeding the maximum rate of requests allowed by the chat model provider. You can now...

🔎 Filtering runs within the trace view

You can now filter for runs within the trace view in LangSmith. This is especially helpful for long-running agents, which can produce traces with hundreds,...

🔑 Enhanced Key-Value Search: Matching inputs and outputs

Users can now filter traces or runs by JSON key-value pair in inputs or outputs. This creates a more powerful search experience in LangSmith, as you can...

Powered by LaunchNotes