Classic software wisdom is to focus on one problem at a time. However, I often find it more productive to focus on many interrelated problems. When you get stuck on one, you can do something productive on another one — and often unstick the original by noticing the connections.
CODE
-
Stanford NLP Textbook January 2023 Release
By
–
Here's the Jan '23 release of draft chapters for Speech and Language Processing. This is just a bug-fixing and chapter-refactoring release, to modernize the structure for teaching/learning. Best wishes from Jim and me for a healthy and happy New Year! https://
web.stanford.edu/~jurafsky/slp3/ -
Question Answering on GitHub Repositories with LangChain
By
–
This is another great example of question answering over specific data (in this case a GitHub repo) Also we need to look into getting the `langchain` handle
-
Feature Platforms Maturation: MLOps Stack Evolution
By
–
The last few years saw the maturation of a core component of the MLOps stack: feature platforms. This post discusses the evolution of feature platforms & the design decisions / functionality to speed up feature engineering. Feedback always appreciated! https://
huyenchip.com/2023/01/08/sel
f-serve-feature-platforms.html
… -
LangChain Improves Documentation for Existing AI Functionality
By
–
This functionality was already in LangChain (h/t @johnjnay for pushing to get it in in the first place) We've just improved documentation GREATLY around this capability, since it was a bit hidden s/o to people in the discord for making me realize we lacked documentation here
-
LangChain Recursive Character Text Splitting Example Notebook
By
–
Check out example notebook: https://
langchain.readthedocs.io/en/latest/modu
les/utils/combine_docs_examples/textsplitter.html#recursive-character-text-splitting
… Shout out to @krrish_dh and others in the discord for helping ideate + test! -
LangChain Question Answering Examples and LLM Applications
By
–
Check out example notebooks: https://
langchain.readthedocs.io/en/latest/modu
les/chains/combine_docs_examples/question_answering.html
… Shout out to @johnjnay
, @BruceHammer
, and others in the discord for helping to ideate + test John's already started to use it in some more awesome work on llm-lobbyist: -
Recursive Text Splitter for Improved Chunk Processing
By
–
Recursive Text Splitter The previous text splitter only split on a single character This one recursively splits chunks on different types of characters, until all chunks are below the desired size
-
LangChain 0.0.59 Adds Map-Rerank Chain and Text Splitting
By
–
New LangChain version makes it easier than ever to combine LLMs with your own data Brand new map-rerank chain
Recursive Text Splitter
Customize summarization and question answering `pip install langchain==0.0.59` -
Map-Rerank Chain for Enhanced Question Answering Systems
By
–
Brand new map-rerank chain This chain can be used for question answering. It maps over documents, trying to both (a) answer a question, (b) assign a score to how good the answer is It then picks the answer with the highest score