LangChain turns two! Forever grateful to everyone who has been a part of this journey LangChain has changed a TON from the open source side project it started as. I wanted to take this time to reflect on the evolution Thank you for being a part
@hwchase17
-
Managing LLM Prompts Across Cross-Functional Teams
By
–
We commonly see that teams building LLM apps are getting more and more cross functional
— Harrison Chase (@hwchase17) 24 octobre 2024
A lot of their collaboration happens on the prompts!
Having a way to properly tag prompts makes it easier to pull new versions into code, but allow them live and be managed outside https://t.co/PCRCpnOvcDWe commonly see that teams building LLM apps are getting more and more cross functional A lot of their collaboration happens on the prompts! Having a way to properly tag prompts makes it easier to pull new versions into code, but allow them live and be managed outside
-
LangSmith Adds Side-by-Side Trace Comparison with Prompt Highlighting
By
–
no more opening up two LangSmith windows side by side!
— Harrison Chase (@hwchase17) 23 octobre 2024
easily compare traces to see where the differ… including some nice highlighting of prompt differences https://t.co/xSbh7J4k4Wno more opening up two LangSmith windows side by side! easily compare traces to see where the differ… including some nice highlighting of prompt differences
-
CopilotKit and LangGraph Integration for Agent UX
By
–
i've been talking a bunch about UX for agents, and copilotkit is working on just that!!
— Harrison Chase (@hwchase17) 22 octobre 2024
excited to seamlessly integrate with them for their launch
langgraph + copilotkit = a delightful combo https://t.co/PxAfOfHU9Hi've been talking a bunch about UX for agents, and copilotkit is working on just that!! excited to seamlessly integrate with them for their launch langgraph + copilotkit = a delightful combo
-
Testing LLM Consistency with Edge Case Generation
By
–
This was a fun weekend project! Generate edge cases with a pretty simple algorithm: 1. Generate two questions that are asking the same thing but worded differently
2. Run those questions through the LLM application
3. Compare the answers – if different, you know one is wrong -
Canvas UI functionality enhancement launched this week
By
–
Some basic functionality added Sets the stage for more interesting stuff coming later this week If you haven't played around with the canvas style UX, I'd recommend checking it out
-
OpenAI Canvas collaboration tool now available open source
By
–
I'm bullish on the "canvas" experience that OpenAI launched a week ago It's a great way to "collaborate" with AI & should be in more applications We made a version you can try for free: https://
open-canvas-lc.vercel.app Open source code here: https://
github.com/langchain-ai/o
pen-canvas
… More features soon -
Memory functionality for agents in LangGraph explained
By
–
I wrote some thoughts on memory for agents! We released a bunch of new functionality for memory in LangGraph, and in doing so we thought hard about what memory actually means, and was is useful today Some highlights Memory is application specific The best memory today
-
Chat LangChain Improved with New Cognitive Architecture
By
–
Improved Chat LangChain We have a new and improved Chat LangChain experience! The new version has a new cognitive architecture (uses a research subagent) and slicker UI Open source as always Check it out https://
chat.langchain.com -
Evaluators Defined in Code Now Manageable in UI
By
–
A much requested feature – evaluators defined in code and managed in the UI! Makes it easier to iterate on online and offline evaluations