LangChain has announced a series of new features and updates aimed at enhancing user experience across its various platforms, including LangSmith, LangGraph, and its generative UI applications, according to LangChain Blog.
LangChain Enhancements
LangChain has introduced the capability to build generative UI applications using LangChain JavaScript/TypeScript, Next.js, and Python. This feature allows users to leverage streaming agent events and tool calls to pick pre-built components, enhancing chatbot interactivity. Detailed tutorials and a Next.js template repo are available for users to get started.
Additionally, LangChain’s chatbot, Chat LangChain, now allows users to view and continue previous chats, thanks to LangGraph’s backend support.
LangSmith Updates
LangSmith has rolled out new Workspaces to improve collaboration and organization. These Workspaces enable admins to add users and grant permissions on resources within specific Workspaces, streamlining workflows for large enterprises.
The Playground feature in LangSmith has been updated to allow users to start from scratch rather than a trace or a prompt. This new tab in the sidebar simplifies prompt creation and experimentation.
LangSmith has also introduced variable mapping for online evaluator prompts, enabling customizable inputs based on recent runs. Moreover, the platform now supports data retention-based pricing, allowing users to choose shorter data retention periods for cost savings.
LangGraph Developments
LangGraph has partnered with Andrew Ng (DeepLearning) and Rotem Weiss (Tavily co-founder) to offer a free course on building advanced AI agents. The course covers implementing persistence, agentic search, and human-in-the-loop functionalities.
LangGraph also supports several new integrations, including:
Meta’s Llama 3 agents with new code recipes and video tutorials.MistralAI’s codestral model and completions LLM, which now supports passing a suffix to prompts for improved results.NVIDIA’s NIM microservices API for deploying LangChain applications on NVIDIA accelerated infrastructure.Nomic Embed Vision for multimodal RAG, allowing for image and text embedding and synthesis.Couchbase vector store integration for flexible search capabilities.
LangChain has also been recognized by Databricks as their GenAI Partner of the Year and included in their State of AI Data Report.
Community and Learning Resources
LangChain continues to support its community with various meetups and learning resources. Upcoming events include:
June 18: Berkeley LLM meetup in San Francisco.June 26: LangChain and Elastic NYC meetup.
For those interested in building practical applications, LangChain offers several tutorials and resources, including:
A step-by-step guide to building an AI research assistant agent with memory and knowledge management.Insights on RAG pipelines for enhancing search accuracy and relevance.Projects on AI-powered voice assistants and the latest Whisper models for voice input and transcription.Basic tutorials on building LangChain chatbots and managing chat history.
LangChain encourages users to explore these new features and integrations to enhance their AI applications. More details and updates can be found on the LangChain blog and their YouTube channel.
Image source: Shutterstock
