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
AI
-
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! -
Customize Summarization and Question Answering with Custom Prompts
By
–
Customize summarization and question answering The default prompts used for summarization and Question/Answering may not be specific enough for your use case Luckily, you can easily customize them! Here's an example asking them to respond in Italian
-
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
-
AI Captures Human Nuance Through Better Training Data
By
–
“The human touch” is embedded in all the training data these AIs are learning from. As we get better at learning from this data, AI will be able to capture the nuances of human writing. Even today's AIs can come really close if you prompt them well (add direction, angles, etc.)
-
Future of ML: Automation of Repetitive Tasks, Focus on Creativity
By
–
The future of machine learning for companies out there will be much more about creativity and less about repetitive work. Wrangling data, algorithms, and operationalizing models will be fully automated. At @abacusai we've made a lot of progress in that direction!
-
Improving AI Understanding Through Prompt Engineering Techniques
By
–
Yep, jugando con el prompt se puede llegar al resultado. Aún así una señal de que los sistemas actuales aún tienen que mejorar su entendimiento del prompt.