AI Briefing#langchain
The latest AI and developer news about #langchain, with the original source and a short summary.
The latest AI and developer news about #langchain, with the original source and a short summary.
LangSmith now supports OpenTelemetry, standardizing tracing for LLM applications and providing unified observability.
LangChain has released OpenEvals, an open-source framework that helps evaluate the performance of LLM and agent applications.
AI21 Labs has released a Jamba-based long-context course with DeepLearning.AI.
LangChain has released its annual report covering 2024 AI development trends and LLM infrastructure usage.
The LangChain team has released the Promptim library, which automatically improves prompts based on datasets and evaluation metrics.
Replit has launched 'Replit Guides', which supports learning technology and building applications.
Hugging Face and LangChain have partnered to release the `langchain-huggingface` package, which supports the latest features.
This introduces how to build cost-efficient enterprise RAG applications and their architecture using Intel Gaudi 2 and Xeon CPUs.
LangSmith has launched improved regression testing features that allow precise comparison and analysis of performance changes in LLM applications.
LangSmith, LangChain's LLM DevOps platform, has launched as an Azure Kubernetes Application through Azure Marketplace.
We benchmark the problem of handling high-cardinality categorical values that arises during LLM-based query analysis, and its solutions.
AI21 released open-source Python SDK v2.0, simplifying the developer experience.
Open-source LLMs like Mixtral have reached a level where they can perform ReAct-style agent workflows.
Introduces how to build and deploy a production-grade RAG application by combining Pinecone Serverless, LangServe, and LangSmith.
High-performance vector database **Qdrant** has launched a **Replit** template to help developers implement RAG and streamline onboarding.
CrewAI is a modular library built on LangChain that orchestrates and manages collaboration among multiple AI agents.
LangChain analyzed LangSmith data to reveal 2023 trends in LLM application development and testing.
Replit has unveiled 9 AI templates to help businesses quickly integrate the latest AI tools.
LangChain has released 4 new testing environments that measure the tool use and function calling performance of LLM agents.
LangChain has launched a dataset and results sharing feature in LangSmith to help developers easily compare and validate LLM architectures.
LangChain unveiled a new LangSmith feature that lets you compare multiple test run results side by side for evaluating LLM applications.
This introduces a process for systematically evaluating and comparing the performance of fine-tuned open source models using LangSmith.
According to Replit's data analysis, AI projects grew 34x year-over-year, with OpenAI holding more than 80% of the market.
It argues that prompts are closer to **design**, like web design, than to writing.