missed this great thread as well. Prompts are implementation detail – don't leak them, and don't blindly slap them on all the textboxes!
CODE
-
Happy Birthday Linus Torvalds, Father of Linux
By
–
Happy birthday to Linus Torvalds, the father of #Linux: http://
tcrn.ch/2hXs1H1 -
Memory Support Now Works with Multiple Chain Inputs
By
–
Memory support for chains with multi inputs Previously, memory only worked if there was single input This meant it couldn't work in cases like question/answering, where you passed in multiple inputs (documents and a question) Now it can: https://
langchain.readthedocs.io/en/latest/exam
ples/memory/adding_memory_chain_multiple_inputs.html
… -
SerpAPI Wrapper Gains Sports and Knowledge Graph Results
By
–
Add sports & knowledge graph results to SerpAPI wrapper When working on http://
howdoi.ai, @brunotorious noticed that results for sports were not found, due to parsing of SerpAPI results. So he fixed it! See screenshots for before and after https://
x.com/brunotorious/s
tatus/1607088382521507841?s=20&t=ar8qq203aMD2Hxs3yuNYRQ
… -
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
… -
Developer pushing 300 daily git commits to repository
By
–
me pushing to git 300 times per daypic.twitter.com/K9UpBQAM5H
— @levelsio (@levelsio) 28 décembre 2022me pushing to git 300 times per day
-
OT Too Low Level: Codex Better for Code Refactoring
By
–
OT is way too low level man. too much structure to have to rebuild when codex can already do entire coherent code blocks of refactoring
-
Training ResNets Without Batchnorm: Achieving Strong Results
By
–
Pretty amazing that we can get such good results even without batchnorm — and not using a proper resnet init like Fixup either! Maybe I should try lsuv with batchnorm-free resnet sometime…
