https://
x.com/hwchase17/stat
us/1836790660063510701
… gave a shout out in blog! I'm bullish on templates and want to make them successful. what ideas/advice would you have for this?
@hwchase17
-
Making AI Templates Successful: Ideas and Strategy
By
–
-
Three Cognitive Architecture Templates Launch: ReAct, RAG, Data Enrichment
By
–
we're launching a small number (3) of templates for common cognitive architectures
— Harrison Chase (@hwchase17) 19 septembre 2024
these are configurable (choose LLM/vector store of your choice)
Starting with:
– ReAct agent
– RAG chatbot
– data enrichment (research) agent
What should we add next? https://t.co/bqOclMrhUNwe're launching a small number (3) of templates for common cognitive architectures these are configurable (choose LLM/vector store of your choice) Starting with:
– ReAct agent
– RAG chatbot
– data enrichment (research) agent What should we add next? -
Pydantic 2 upgrade completed after version 1 EOL
By
–
Have finally upgraded to Pydantic 2! We know this could potentially be a big change – we held off for a while but now Pydantic 1 is EOL so we figured the time is right This is the ONLY change in this release, wanted to keep it really focused an minimize disruption
-
Human in the Loop: A Believer’s Perspective on AI Safety
By
–
Not tested rigorously but I’m a bigger believer in human in the loop
-
LangGraph Cloud Deployment Options and Infrastructure Choices
By
–
Probably not for the langgraph cloud deployment. We’ll have guides for other options (fastapi, etc). We also have a “bring your own cloud” approach where it’s deployed on your infrastructure (similar to databricks). Would that work?
-
Langgraph Migration Guide for AI Agents Recommended
By
–
Yes recommending Langgraph. We won’t remove the agents (so as not to break people’s flows) but will work on detailed migration guides
-
Integrating o1 Model into Agentic Systems
By
–
Langgraph* But yes – I’m super excited about plugging o1 into some agentic systems!
-
API Limitations: Streaming and Function Calling Still Missing
By
–
yeah needs a lot of things (streaming, function calling, system message). im sure theyre working on it but feels like the apis of 2022 lol
-
O1 Models Drive Multi-Agent Compound AI Systems Forward
By
–
perhaps counter-intuitively, i think models like o1 will actually make "compound ai"/"multi-agent" systems MORE prevalent a lot of ideas of how to use o1 boil down to using it as just one part of a larger, more complex "cognitive architecture", with multiple other LLM calls