Continuing down the LangChain

LangChain provides a Pythonic framework for writing LLM powered applications, e.g. tools for asking questions re knowledge bases, personal assistants, chatbots, etc. Given it provides a toolkint to implement “smart” apps, I wanted to go through the motions of implementing something simple + useful.

I started wiring LangChain to my org files and emails but I wasn’t able to fully take it through it’s paces. While most of my organized thoughts are in the org files, there doesn’t seem to be an unstructured parser for it. This means all of the semantic structure (headings, tags, linnks, etc) is lost in raw text parsing & splitting. Solution-wise, should be easy enough to convert the org files to HTML which unstructured will devour happily. Email have their own problem, namely persisting the Chroma vectorstore index because it takes a while to index my tens of thousands of emails. Should also be easy enough with LangChain, but I’m still learning the API calls to pull it off.

Watched F1 Australia (ye olde Melbourne’s Prince Albert Park) qualifying at EBJ’s. Supermax to pole, but Merc two and three. Where are you at Ferrari? The race starts at 10p PT tomorrow, overlapping with a house (?) show. I’m looking forward to unashamedly watching the race during the show.

Got some exercise in too, back and biceps. The pullups were rough (gaining weight quicker than strength =D ), but the rest of the workout I could feel improvement. The barbell felt great for deadlift, more control of the movement allowed me to push.

It’s the end of March, so I hit an [arbitrary] milestone: a full month of lifting. Improvements in weights have been consistent, so for next month I want to keep the cadence and start to play with other workout plans. More to come.