Launching a series of updates to the Assistants API—now with support for up to 10,000 files for knowledge retrieval and more precise tool and token control. Excited to see what you build!
AI
-
Benchmarks vs Real-World AI Efficacy: Narrow Metrics Matter Less
By
–
Or, yes, better data matters. But we always have to remember that 'better' is being assessed via narrow benchmarks that DO NOT speak to efficacy or impact in the "real world"
-
Hacker Terminology: Distinguishing Ethical Hackers from Criminals
By
–
You pretty much stepped in it. Try this naming taxonomy: All hackers are good. Criminals are not hackers, they are criminals. Don't call criminals black hat hackers, call them criminals.
-

Optimize Multiple LLM Calls by Mixing Models for Lower Latency
By
–
Most LLM apps and AI Agents need multiple calls to an LLM, especially a moderately complex LLM app/AI agent. Calling GPT-4 or Claude is impractical and you will soon be in high-latency hell. The optimal way to do this is to mix and match LLMs depending on the latency,
-
LangSmith Evaluations: Unit Tests for LLM Development
By
–
LangSmith Evaluations: Unit Tests
— LangChain (@LangChain) 17 avril 2024
Evaluations can accelerate LLM app development, but it can be challenging to get started. We've kicked off a new video series focused on evaluations in LangSmith.
This is the 10th video in our series that shows how to incorporate unit… pic.twitter.com/nSd8CiuAdRLangSmith Evaluations: Unit Tests Evaluations can accelerate LLM app development, but it can be challenging to get started. We've kicked off a new video series focused on evaluations in LangSmith. This is the 10th video in our series that shows how to incorporate unit
-

Modern Connected Apps Transform Enterprise and Telecom Networks
By
–
Networking’s New Era: Powering Enterprise & Telecoms Transformation With Modern Connected Apps ! Live Now – https://
bit.ly/3x9jmvO Packed with examples from #ElectricVehicles with @halocar_ & @TMobile through to #Microloans & #fraud detection in #banking Plus more -

RAG Fundamentals Tutorial Free on FreeCodeCamp
By
–
RAG From Scratch on FreeCodeCamp We recently released a playlist of videos that explain RAG fundamentals and highlights over a dozen advanced RAG papers / methods. This tutorial is now free on @freeCodeCamp
! Thanks @beaucarnes and team. Video: https://
youtube.com/watch?v=sVcwVQ
RHIc8
… -

Microsoft Cloud Platform Goes Live with 5G and AI Integration
By
–
Absolutely! Thanks for sharing @MyZeroCarbon It's live now at the link below 🙂 https://
bit.ly/3x9jmvO @MSCloud #MSCloud #MSFTPartner #5G #AI #Telco -

LangChain adds token usage tracking for LLM responses
By
–
Token usage tracking We've made it easier to access response metadata returned by LLM providers with a new field on AIMessages! Useful information like token usage for supported models will appear there. Python : https://
python.langchain.com/docs/modules/m
odel_io/chat/token_usage_tracking/
…
JS : https://
js.langchain.com/docs/modules/m
odel_io/chat/token_usage_tracking
… -

Theseus GPU-native query engine benchmarks massive data processing
By
–
Excited to show what our team has been working on over the last 2.5 years: Theseus, our GPU-native query engine! This benchmark compares data queries of different scales — 10TB, 30TB, and 100TB — on Spark (run on CPUs) and Theseus (run on GPUs). Moving the same queries from
