π Versioned docs and better structure for LangChain v0.2
Weβve updated our docs for LangChain v0.2 to be separated into: LangChain v0.2 docs walkthrough Check out the new docs in Python and JavaScript , then give...
π LangChain v0.2: Improving the stability and security of the `langchain` package
With the release of LangChain v0.2 , weβve decoupled the langchain package from langchain-community to improve the stability and security of langchain . With...
π Pairwise Evaluations in LangSmith
For LLM use cases like text generation or chat (where there may not be a single "correct" answer), picking a preferred response with pairwise evaluation can...
π οΈ Personal prompts are now separate from LangChain Hub
Your organization's prompts are now separate from the LangChain Hub. This lets you organize and pull existing prompts by their commit versions β so you can...
π LangSmith is now GDPR compliant
LangSmith β our unified developer platform for building, testing, and monitoring LLM applications β is now GDPR compliant. Security and compliance are...
πRole Based Access Control (RBAC) for enterprise customers
Admins can now assign roles to users in their organization with RBAC in LangSmith . Create/edit custom roles with granular permissions to determine who can...
π Regression testing in LangSmith
Regression testing, hotkeys, and more in LangSmith Check out our video walkthrough and blog to learn more! We also have a few new additional updates in...
βοΈ Standardized Tool Calling in LangChain
You can now create agents that work with any tool calling model. Our new standardized tool calling interface allows you to switch between different LLM...
π Version-controlled prompts & running prompts over datasets in LangSmith
Version-controlled prompts, running prompts over datasets, and more in LangSmith Itβs been a little over 1 month since we GAβd LangSmith, and weβre so...
π Auto-rendering graph, conditional entry points, and more in LangGraph
Auto-rendering, conditional entry points, and more for LangGraph We've made several improvements to LangGraph over the past few weeks: