what would you want a langslack to do
@hwchase17
-
Using o1 for Planning in AI Agents with LangGraph
By
–
o1 for a planning step OpenAI just launched API support for o1. What's the best way to use this? I think it's helpful to look at how @unifygtm used o1-preview with LangGraph to build an Account Qualification Agent They used o1-preview for the planning step. They found it to
-
Meta-evaluation frameworks for AI system assessment
By
–
yeah sure you've probably written evals, but have you ever written evals for your evals?
-
Multi-Agent Architecture in Replit Agent with LangGraph
By
–
Multi-agent or single agent? When I interviewed @pirroh (President, @Replit
) he mentioned how they built Replit Agent on LangGraph using a multi-agent architecture "we built a multi agent architecture for what is now very well known in the community… it's important to -
LangGraph works without LangChain using raw OpenAI SDK
By
–
You can use langgraph without LangChain! Can just use the raw OpenAI sdk
-
LangSmith Intro Course Gains Positive User Feedback
By
–
Intro to langsmith course is getting good feedback – check it out https://
m.youtube.com/watch?v=KcGoJP
K-0tY
… -
Production Agent Evolution: Single to Multi-Agent to LangGraph
By
–
Talking to more companies getting serious about putting agents in production, a common trend I'm seeing is: "single agent" -> "multi-agent high level (crewai, autogen)" -> "controllable agent framework (langgraph)" Rexera great example, did a case study here:
-
Custom Memory Systems Superior to General Approaches
By
–
Completely agree with this Bearish on general memory systems, need to be pretty custom
-
LLM Monitoring Evaluation and Prompt Engineering Deep Dive Course
By
–
If you want an in depth course on how to monitor, evaluate, and prompt engineer LLM applications (whether using LangChain or not)… then this is the course for you!
— Harrison Chase (@hwchase17) 11 décembre 2024
~4 hours deep dive into tracing, evals, prompts, monitoring, feedback
👇👇👇 https://t.co/hnKTC4SpdFIf you want an in depth course on how to monitor, evaluate, and prompt engineer LLM applications (whether using LangChain or not)… then this is the course for you! ~4 hours deep dive into tracing, evals, prompts, monitoring, feedback
-
Character AI Tech Lead Discusses 30k QPS Scale Architecture
By
–
Tomorrow night I will be doing a fireside chat with James Groeneveld, a tech lead at Character AI Character AI does over 30k queries per second… one of the few GenAI apps to reach true scale Lots of interesting nuggets to dive into, RSVP! https://
lu.ma/rujejluk