See these docs for a quickstart for this utility: https://
langchain.readthedocs.io/en/latest/exam
ples/chains/google_search.html
… But, probably more importantly, see these docs for a guide on how to load it as a tool that you can use with an agent: https://
langchain.readthedocs.io/en/latest/exam
ples/agents/search_tools.html
…
AGENTS
-
LangChain Quickstart: Google Search Integration with Agents
By
–
-
Teaching children politeness to AI prevents behavioral problems
By
–
A study showed that kids raised with Alexa who were allowed to treat her badly were more likely to have behavioral problems later on. Even if you don’t have to, I think we should continue to be nice to AIs so we don’t condition ourselves in ways we don’t expect
-
New max_iterations parameter to control agent iterations
By
–
So glad you asked! there's now a max_iterations parameter you can use to cap the number of iterations an agent takes A bit brute force, but better than nothing
-
LangChain v0.052 Adds Watch Mode Tests Agent Security
By
–
v0.052 Add watch mode for tests – @nfcampos Add schema property to SQL DB class – @diwanksingh Propagate verbose flag to combine-document chains – @parth_29 Add max_iterations kwarg to agent executor, in part to stop attacks like the below
-
LangChain Agents Max Iterations Parameter Implementation
By
–
To expand on the last point, previously agents were allowed to potentially loop forever, whether caused maliciously or not Now you can specify a max_iterations parameter, which stops it after that many iterations https://
langchain.readthedocs.io/en/latest/exam
ples/agents/max_iterations.html
… -
LangChain v0.0.51 Release: Enhanced Tools, Memory, and Documentation
By
–
v0.0.51 Unify return types for intermediate steps – h/t @johnjnay Add sports & knowledge graph results to SerpAPI wrapper – @brunotorious Document improvements: @eltociear @samcwl Making tools editable – h/t @brunotorious Memory support for chains with multi inputs
-
Making Tools Editable: Customize Tool Descriptions for Better Agent Performance
By
–
Making tools editable When loading tools, they come with default descriptions. Sometimes, as @brunotorious pointed out, you may want to edit their descriptions in order to get them to work better with agents Now you can: https://
langchain.readthedocs.io/en/latest/exam
ples/agents/custom_tools.html#Modify-existing-tools
… -
Beyond Copilot: The Next Evolution in AI Developer Experience
By
–
The Big Question in AI-driven developer experience: What's after Copilot? Everyone is convinced this is "just" the beginning but can't articulate what the next killer form factor will be. Increasingly convinced next step change won't be from optimal stuffing context windows
-
Integrating True AGI with Robotics: A Trivial Challenge Ahead
By
–
Should be trivial to hook up true AGI to a robot…