LangChain Changelog

Sign up for our newsletter to stay up to date

Powered by LaunchNotes

Loading...

July 2024

🪝 Webhook notifications for run rules

We now allow for the configuration of headers per webhook URL (stored in an encrypted format). When you add a webhook URL on an automation action in...

⚓ Enhanced state management & retries in LangGraph Python

For the LangGraph Python library, we've added:

🛝 Build prompts faster and compare in LangSmith Playground

No more juggling tabs or context-switching — you can now compare multiple prompts and model configurations side-by-side in LangSmith's Playground. Build,...

🇪🇺 EU Data Residency for LangSmith

We're excited to offer EU data residency to LangSmith customers on all plan tiers, at no extra cost. You can now choose to host your data in the EU (instead...

💬 Improved message handling, checkpointing of pending writes, and metadata rendering

We've made several improvements to the open-source LangGraph library:

LangGraph LangGraph Platform

🧵 Improved thread management and batch processing

We've made a few new improvements to LangGraph Cloud:

🔒 LangSmith is now SOC 2 Type II compliant

We're excited to announce that LangSmith — our unified developer platform for building, testing and monitoring LLM applications — is now SOC 2 Type II...

June 2024

LangGraph LangGraph Platform

☁ 🚀 LangGraph Cloud: Deploy at scale, monitor carefully, iterate boldly

LangGraph Cloud is now in closed beta, offering scalable, fault-tolerant deployment for LangGraph agents. Deploy in one-click and get an integrated tracing &...

🔁 Self-improving LLM evaluators in LangSmith

Using an “ LLM-as-a-Judge ” is a popular way to grade outputs from LLM applications. This involves passing the generated output to a separate LLM and asking...

✂️ Trim messages with transformer utils

Processing LangChain messages is now easier in both Python and JavaScript with our new message transformers. The new trim_messages util in LangChain covers a...

Powered by LaunchNotes