Balance of not putting too much in langchain
CODE
-
LangChat: Customizable LangChain Chatbot Wrapper Specification
By
–
Pretty good spec for langchain chatbot wrapper (langchat?) Let use easily customize LLM used, system message, that’s it Who’s gonna build?
-
Chatbot Configuration: Memory, LLM, and System Message Options
By
–
chatbots is a good one. what (if anything) would you want to configure in a chatbot? memory type? llm? system message?
-

Building a Tree-Structured Parzen Estimator from Scratch
By
–
Building a Tree-Structured Parzen Estimator from Scratch (Kind Of) https://
bit.ly/3XbFTkx #AI #MachineLearning #DeepLearning #LLMs #DataScience -
The Enduring Satisfaction of Merging Code on GitHub
By
–
Something never gets old about pushing the merge button on GitHub.
-

Higher Level LangChain Wrappers for LLM-Powered Applications
By
–
I like this a lot – a higher level wrapper around langchain to make a specific use case (LLM-powered bots over a dataset) easier to create What other use cases deserve higher level wrappers around langchain?
-

Replit Team Hosts Agent Hackathon at AGI House
By
–
The @Replit team is at the AGI House for an agent hackathon. @amasad discussing agents like BabyAGI on Replit
-
OpenAI Gym Unlocks AI Control of Software Products
By
–
I loved this world of bits and OpenAI Gym work. Felt at the time it was poised to unlock the control of software products by AI. Just took a few years more than I thought! https://t.co/EwYX0Kf39E
— Nathan Benaich (@nathanbenaich) 24 juin 2023I loved this world of bits and OpenAI Gym work. Felt at the time it was poised to unlock the control of software products by AI. Just took a few years more than I thought!
-

Train Custom AI Models on Your Knowledge Base
By
–
You can do much better than using a generic AI model to solve your problems. Instead, you can train a model on your knowledge base and get answers to your questions within seconds using @abacusai
’s large language models. -

OpenAI Function Caching Reduces Development Costs
By
–
As @mayowaoshin noted, using @OpenAI functions can be expensive By enabling caching, you can eliminate some costs as you develop Just in time for some weekend hacking