like you want to add memory to plan-and-execute agent?
@hwchase17
-
LangChain Plan and Execute Agent Documentation
By
–
Python Docs: https://
python.langchain.com/en/latest/modu
les/agents/plan_and_execute.html
… JS/TS Docs: https://
js.langchain.com/docs/modules/a
gents/agents/examples/plan_and_execute_agent
… Blog: -
New experimental feature added to core library for community feedback
By
–
We think this is a really promising direction, so we're adding it to the core library But we also think there is a lot of work to do here, so we're adding it to the experimental module as we rapidly iterate In that vein, would love all thoughts/community contributions!
-
LangChain Agents Enhance Focus on Complex Task
By
–
Up until now, agents in LangChain have followed the algorithm of: – take user input
– think about action to take
– take action and observe response
– repeat until done This is great for simple tasks, but for more complex tasks we've noticed the agent losing focus -
Two-step planning improves language model task performance
By
–
To fix this, we're separating the planning and execution into two steps: – plan what to do
– execute on each step This usually leads to more calls to the language model… but helps it stay on track for more complex tasks -
BabyAGI and Plan-and-Solve Pattern Recognition in AI
By
–
We first noticed this pattern in @yoheinakajima
's BabyAGI project, and then more recently saw it in the Plan-and-Solve paper Paper: https://
arxiv.org/abs/2305.04091
Code: -
LangChain Introduces Plan-and-Execute Agents for Complex Tasks
By
–
Plan-and-Execute Agents Inspired by BabyAGI and the recent Plan-and-Solve paper, we're introducing a new type of @langchain agent We think these are better for more complex tasks, at the cost of more calls to the LLM Blog: https://
blog.langchain.dev/plan-and-execu
te-agents/
… -
LangChain Question Answering Instructions Tutorial
By
–
try these instructions? https://
python.langchain.com/en/latest/use_
cases/question_answering.html
… -
New Agent Executor Inspired by Plan-and-Solve and BabyAGI
By
–
Working on a new type of agent executor, taking inspiration from the "Plan-and-Solve" paper and @yoheinakajima
's BabyAGI Will pitch @DivGarg9 @devstein64 @sjwhitmore tomorrow during our "Agents in Production" webinar and get their thoughts! Webinar link: -
Feature Store Insights from ML Experts
By
–
Big big thanks to @willpienaar @mikedelbalso and @simba_khadder for their thoughts on this! They know far more about feature stores than I do