LCEL We've completely re-written our chains and agents using the new LangChain Expression Language. This ensure better composability, optimised parallel execution, and many other benefits.
OPEN SOURCE
-
LangChain v1.4.10 Release: New Features and Improvements
By
–
1st release in 2024 v1.4.10: Global variables LCEL AstraDB Vectara MMR Langfuse SessionId Improvement on Airtable, Qdrant, PGVector, Milvus, LocalAI
-
LLMLingua: Microsoft Tool on Hugging Face
By
–
HF:
https://huggingface.co/spaces/microsoft/LLMLingua -
Open-Source Developer AI Meetup in San Francisco January 23
By
–
Come to our open-source and local developer AI meetup in SF on Tuesday, January 23rd! https://
lu.ma/devs1 We're co-hosting with our friends from @ollama
, @continuedev
, @langchain
, @huggingface and more. Space is limited, so make sure to register: -
Long Context Encoder Models and Token Processing Optimization Techniques
By
–
anyone know a model that’s out there that’s encoder-only (BERT-like) but supports a really long context length? also what's the most efficient way of processing many tokens like this? i know about enabling FlashAttention & BetterTransformer. what else is out there?
-
LangGraph Official Launch: Building AI Agents Framework
By
–
LangGraph We introduced LangGraph last week, but are excited to launch it more officially today (blog and YouTube series). It includes: Example of replicating the LangChain AgentExecutor
A chat agent executor (aimed specifically at chat models) LangGraph makes it easy -
Open Source Key to Making AI World More Equal
By
–
Among many disagreements, I think this #wef24 GenAI panel agreed that to make the world more equal, open source is essentially valuable. Fun discussion with @ylecun @AndrewYNg @aidangomez @DaphneKoller and always witty moderation by @nxthompson
-
Unsupervised Text Embedding Space Alignment Research Problem
By
–
As an exercise in open science, gonna tweet the research problem I’m stuck on: i want to align two text embedding spaces in an unsupervised way. The motivation is that in my previous vec2text work, we have to know the embedding model and be able to query it. this is fine in
-
Fixing HuggingFace Default Sampling Behavior Without Replacement
By
–
thanks, your curves look a tiny bit different but I believe it; i however have the practical question of why is this happening with the huggingface defaults and how do i make it stop? (i don't want to sample w/ replacement)