Community PR roundup We get fantastic community PRs to LangChain daily, and we'd like to spotlight 10 Python contributions from the past three weeks! In no particular order, a huge thank you to: (1/n)
SOFTWARE
-
LangChain adds reranking and token counting integrations
By
–
kennethchoe for adding reranking based on @HuggingFace cross encoder models https://
python.langchain.com/docs/integrati
ons/document_transformers/cross_encoder_reranker/
… dmenini and Sukitly for adding token counting to @Anthropic models on @Amazon Bedrock (2/n) -
Meta Aligns PyTorch Compiler Flow on Custom AI Hardware
By
–
+1 to same compiler flow on our chips as mainline PyTorch. At Meta, we don't have a separate copy of PyTorch or Dynamo/Inductor. The source of truth is Github and everything is upstreamed/mainline. Triton's bugs have been going over time, but we liked it as a starting point, and
-
Unified Software Stack Approach for AI Inference Optimization
By
–
we are truly playing out the "uniform software stack" story. As long as you build a triton backend, and you drive down driver/firmware bugs, that is all that's needed. 99% of the user-level papercuts are taken care of.
It also helps that these are targeted for Inference right -
ChatGPT-4 Just Rated My Website’s SEO: Lots of Room for Improvement
By
–
ChatGPT-4 just rated my website's SEO. Lots of room for improvement:
-
Triton Backend Enables AMD Code Generation Support
By
–
Triton can generate anything, as long as you write a Triton backend. As of today, upstream Triton can generate AMD code too.
-
Pfizer Uses Claude on Bedrock for Cancer Treatment Discovery
By
–
One of the world’s premier biopharmaceutical companies, @pfizer
, is using Claude on Amazon Bedrock to aid discovery of potential cancer treatments to achieve breakthroughs for patients faster. -
Simplified Management of Serverless and Dedicated LLM Deployments
By
–
ICYI: Managing #serverelss and dedicated #LLM deployments has never been easier! 🚀
— Predibase by Rubrik (@predibase) 10 avril 2024
😎 see all #deployments and status in one place
🆕 create new dedicated deployments with just a few clicks
🛠️ select the right #GPU for the job and customize autoscalinghttps://t.co/W9hCTKaySr pic.twitter.com/zImeI45nNFICYI: Managing #serverelss and dedicated #LLM deployments has never been easier! see all #deployments and status in one place create new dedicated deployments with just a few clicks select the right #GPU for the job and customize autoscaling https://
pbase.ai/449UUXT -
Raycast partners with Perplexity Pro for Mac users
By
–
We teamed up with Raycast to make knowledge accessible anywhere, anytime on your Mac. New annual Raycast Pro subscribers get Perplexity Pro for free for 3 months, or 6 months if you include the advanced AI add-on.
-
AI Travel Planner Helps Plan Your Next Vacation Quickly
By
–
𝗡𝗲𝘄 𝗦𝗽𝗮𝗰𝗲: 𝘼𝙄 𝙏𝙧𝙖𝙫𝙚𝙡 𝙥𝙡𝙖𝙣𝙣𝙚𝙧 Plan your next vacation in a few minutes! Describe your ideal trip, and it will come up with nice places and recommendations! Try it here