@hwchase17

–

31 August 2023 15h11

For most chains you should be able to pass ‘return_intermediate_steps=True’

31 August 2023

LangSmith Monitoring: Tracking App Usage and User Experience

By

–

30 August 2023 19h56

We launched monitoring in LangSmith today I've mainly been using for two use cases: Track usage – are people actually using my app? / Track feedback – are changes I introduced leading to a better user experience? Can you spot when we upgraded our app to use an agent?

Fine-tune Models to Replace GPT-4 Using LangSmith Data

By

–

30 August 2023 19h29

This is really useful for finetuning models to replace GPT-4 at particular points in your system Log all data flowing through your app to LangSmith Export with some filter (all runs, all runs with positive feedback, etc) to a dataset Finetune a model on this data!

Llama2 Powers Fun Application on Anyscale Compute

By

–

30 August 2023 19h24

This is very fun! And – really cool that this is powered by Llama2 on @anyscalecompute

JavaScript retrieval method support advances

By

–

30 August 2023 19h02

Excited to see support for this retrieval method make its way to JS!

Greg Kamradt’s Podcast Host Speaking Style Mimicking Method Webinar

By

–

30 August 2023 17h00

Very excited to hear @GregKamradt
's method for mimicing a podcast host's speaking style Join us in an hour for what should be a very fun webinar! https://
crowdcast.io/c/lzafugqtyata

LangSmith Platform Visual Overview Guide

By

–

29 August 2023 19h57

This is an amazing visual overview of the langsmith platform!

29 August 2023

LangChain Batch Interface Concurrency Optimization Guide

By

–

29 August 2023 2h19

you can use the `.batch` interface (see here: https://
python.langchain.com/docs/guides/ex
pression_language/interface#batch
…) and set `max_concurrency` to determine the max concurrency (see example of that here: https://
python.langchain.com/docs/modules/d
ata_connection/retrievers/multi_vector#summary
…)