LangChain "RAG Evaluation" Webinar RAGAS is an open-source evaluation framework for your Retrieval Augmented Generation (RAG) pipelines I'm VERY excited to be doing a webinar with them next week! RAGAS Repo: https://
github.com/explodinggradi
ents/ragas
… Webinar:
CODE
-
RAGAS Framework for RAG Pipeline Evaluation Webinar
By
–
-
Dolly 15k Support Merged for NeurIPS LLM Efficiency Challenge
By
–
If you are working on the NeurIPS LLM Efficiency Challenge, Dolly 15k support is now merged: https://
github.com/Lightning-AI/l
it-gpt/pull/430
… python scripts/prepare_dolly.py
python finetune/lora.py –data_dir data/dolly/ -
LangChain Chat Updates New Pull Request Integration
By
–
always was: https://
github.com/langchain-ai/c
hat-langchain/pull/110
… -
User Feedback Integration for LangSmith Apps with Streamlit
By
–
Feedback is important for improving your apps! Previously we only had examples of logging thumbs up/thumbs down to LangSmith. We've now added examples of user corrections and comments using @streamlit s/o @OhSynap
-
New Package Manager from Mamba Team Released
By
–
a new package manager from the folks who build mamba. worth looking into… https://t.co/5lR1hFRoFr
— Soumith Chintala (@soumithchintala) 16 août 2023a new package manager from the folks who build mamba. worth looking into…
-
Semantic Search with LLMs Course Launch
By
–
We are thrilled to launch the “Semantic Search with LLMs” course in partnership with @DeepLearningAI_ and @AndrewYNg. In this 1 hour hands-on course taught by Jay and Luis, you’ll learn how to combine the power of LLMs and search to build applications using concepts like… https://t.co/mSC3hkLPfa
— Cohere (@cohere) 16 août 2023We are thrilled to launch the “Semantic Search with LLMs” course in partnership with @DeepLearningAI_ and @AndrewYNg
. In this 1 hour hands-on course taught by Jay and Luis, you’ll learn how to combine the power of LLMs and search to build applications using concepts like -
ChatLangChain Improvements: Benchmarking Retrieval and Agent Methods
By
–
ChatLangChain Improvements We're benchmarking a bunch of retrieval and agent methods for our "chat langchain" app! Interact with the new beta version here: …
https://chat-
langchain-mcan-stanfordedu.vercel.app Expect rapid improvements and everything (data, retrieval algorithms, prompts) to be OSS -
Transformer Math 101: GPU Training Optimization Deep Dive
By
–
pod on Transformer Math 101! with @QuentinAnthon15 of @AiEleuther everything you ever wanted to know about the nitty gritty of training and making the gpu go brrrrrrrrrrrr
-
LLM Fallbacks: Chain-Level Prompt Switching Strategy
By
–
Fallbacks Importantly, not just at the LLM level, but at the chain level Why does this matter? Different LLMs need different prompts. If you hit a rate-limit error on OAI and want to switch to Anthropic, you don't just want to retry with the same prompt – you want to switch