AI & Machine Learning

imagem 13

LangChain Core 1.6.2 Brings Async Tool Support and Key Fixes

Leave a Comment / AI & Machine Learning /

LangChain Core version 1.6.2 has been released, following version 1.6.1. This update introduces a notable enhancement for OpenAI integrations: support for asynchronous tools, allowing developers to define tools that can be awaited within the LangChain tool-calling flow. This makes it easier to build non-blocking applications. The release also includes routine dependency maintenance, updating the mistune […]

LangChain Core 1.6.2 Brings Async Tool Support and Key Fixes Read More »

imagem 8

LangChain-Anthropic 1.7.1 Brings Performance Tuning and Claude Fable 5.1 Support

Leave a Comment / AI & Machine Learning /

The langchain-anthropic library has been updated to version 1.7.1, a minor release that builds on 1.7.0 with targeted improvements for developers working with Anthropic models through LangChain. This update introduces performance optimizations by omitting middleware trace inputs when they are not needed, reducing overhead in tracing pipelines. Users maintaining self-hosted LangChain deployments should notice lighter

LangChain-Anthropic 1.7.1 Brings Performance Tuning and Claude Fable 5.1 Support Read More »

imagem 3

LangChain 1.4.0 Alpha Brings Native MCP Support and Strengthened Middleware

Leave a Comment / AI & Machine Learning /

The LangChain team has shipped a rapid sequence of alpha releases, culminating in langchain 1.4.0a4, with a major focus on native Model Context Protocol (MCP) support and a much more capable agent middleware system. A new langchain.mcp namespace introduces the MCPAdapter, which lets LangChain agents connect to MCP servers built with FastMCP. The adapter now

LangChain 1.4.0 Alpha Brings Native MCP Support and Strengthened Middleware Read More »

imagem 67

Ollama v0.33.2 Restores Dark Mode and Fixes macOS Instance Handling

Leave a Comment / AI & Machine Learning /

Ollama v0.33.2 brings back the app’s ability to follow the system appearance, restoring dark mode support for users who depend on it. The macOS application now correctly hands off to an already-running instance instead of starting a second one, preventing duplicate processes and unnecessary resource usage. Additionally, the Claude Desktop proxy has been fixed so

Ollama v0.33.2 Restores Dark Mode and Fixes macOS Instance Handling Read More »

imagem 65

LangChain MCP Adapter Alpha Connects Any MCP Server to Your Agents

Leave a Comment / AI & Machine Learning /

LangChain is introducing an alpha preview of langchain.mcp, a first-party adapter that converts any MCP server into LangChain tools ready to be passed directly to create_agent. The connection layer is powered by FastMCP, which means all of its client capabilities are available without being re-created behind a more limited interface. pip install “langchain[mcp]==1.4.0a2” Connect With

LangChain MCP Adapter Alpha Connects Any MCP Server to Your Agents Read More »

imagem 63

LangChain Fireworks 1.6.1 Maintenance Release: Reasoning History Fix and Updated Model Profiles

Leave a Comment / AI & Machine Learning /

LangChain Fireworks has published version 1.6.1, a maintenance update following the 1.6.0 release. The headline change is a bug fix that removes reasoning history blocks during conversation processing. This prevents stale or extraneous reasoning content from being carried forward, resulting in cleaner, more reliable chat outputs for self-hosted users. The update also refreshes the model

LangChain Fireworks 1.6.1 Maintenance Release: Reasoning History Fix and Updated Model Profiles Read More »

imagem 60

Transformers v5.16.1 Ships with GLM-5.3-Flash and Backward Compatibility Fixes

Leave a Comment / AI & Machine Learning /

Hugging Face Transformers has released version 5.16.1, a noteworthy update that introduces support for GLM-5.3-Flash, the first natively multimodal model in the GLM-5 series. Alongside this new model, the release includes a pair of small patches aimed at restoring backward compatibility and addressing a security concern. GLM-5.3-Flash: A Leaner, More Capable Multimodal Model GLM-5.3-Flash breaks

Transformers v5.16.1 Ships with GLM-5.3-Flash and Backward Compatibility Fixes Read More »

imagem 57

Transformers v5.16.0 Brings New Models, NVFP4 Quantization, and Long-Context Efficiency

Leave a Comment / AI & Machine Learning /

Hugging Face Transformers v5.16.0 has arrived, introducing several new model architectures alongside a wave of performance and stability improvements. The headline additions include Qwen4-Exp, a hybrid text/multimodal model that combines GatedResidual connections, Qwen Sparse Attention, and Per-Layer Embedding for more efficient long-context inference; GraniteSpeech5, a lightweight ~470M-parameter conformer encoder for fast CTC-based automatic speech recognition;

Transformers v5.16.0 Brings New Models, NVFP4 Quantization, and Long-Context Efficiency Read More »

imagem 54

LangChain 1.3.17: Custom Human-in-the-Loop Rejection Reasons Fixed

Leave a Comment / AI & Machine Learning /

LangChain has released version 1.3.17, moving forward from 1.3.16 with a targeted bug fix and routine maintenance updates. This release is primarily aimed at users who rely on human-in-the-loop workflows. The main change addresses a bug in how custom rejection reasons are framed during human-in-the-loop interactions. Previously, when a human reviewer rejected an action with

LangChain 1.3.17: Custom Human-in-the-Loop Rejection Reasons Fixed Read More »

RSS FEED
RSS FEED