#Reasoning

How Dify Integrates with InfraNodus to Achieve Advanced Q&A and Creative Generation

Dify users can create advanced AI chatbots by integrating InfraNodus. The chatbot not only answers questions but also mines insights and generates new ideas from the knowledge base. InfraNodus can visualize the knowledge base as a knowledge graph, identifying 'structural gaps' in concept connections, and its API generates insight-oriented questions targeting these gaps. Users can seamlessly integrate this capability into Dify applications to initiate conversations, content development, or provide smart prompts for Dify AI agents, thereby embedding enhanced chatbots on websites.

INTELLECT-2: The first globally distributed 32B parameter model for reinforcement learning training.

INTELLECT-2 Released, First to Achieve Global Distributed 32B Parameter Model Reinforcement Learning Training, Anyone Can Contribute Heterogeneous Computing Power Without Permission, Eliminates Communication Bottlenecks Through Asynchronous Reinforcement Learning Paradigm, Supports Heterogeneous Inference Nodes, Inference Nodes Only Need 4×RTX 3090 GPUs to Participate in Training.

Dify MCP Plugin Quick Start Guide: Achieve easy tool calls for AI agents through Zapier

Dify supports integrating over 7000 Zapier applications into AI agents via MCP plugins. Developers can use the MCP SSE plugin to dynamically call external tools or use the Agent Strategy plugin to enable agents to make autonomous decisions on tool calls. The Zapier MCP server provides over 30000 actions, supporting automated tasks like sending emails via Gmail, requiring server endpoint configuration and setting GPT-4o prompts to control calls.

Anthropic research on how to trace the thinking process of the large language model Claude.

Anthropic has published two new papers, constructing an AI microscope to trace the internal mechanisms of the large language model Claude. The research found that Claude has a shared conceptual space when processing multilingual sentences, can plan the output of multiple words in advance, and provide answers that meet user expectations rather than logical reasoning when needed. These findings help understand AI capabilities and ensure its reliability, but current methods still have limitations and need improvement to handle more complex models.

Enhance Dify RAG with InfraNodus: Expand Your LLM Context

InfraNodus enhances Dify RAG by generating an overview of the knowledge base, helping it better understand context and improve the quality of answers to open-ended questions. InfraNodus extracts metadata such as topics, relationships, and blind spots, enhancing RAG prompts to enable LLMs to cover a broader range of important issues. InfraNodus can process data like PDFs and text, and supports API-driven automated insight extraction, significantly improving the structure and accuracy of answers after integration with Dify.

Agora's conversational AI extension has launched on the Dify market platform.

Agora's conversational AI extension, as a plugin, has launched on the Dify market platform, providing developers with real-time voice AI capabilities. The extension supports multiple LLMs, featuring industry-leading speech-to-text and mainstream text-to-speech services, achieving rapid response and global reliability through Agora's low-latency SD-RTN™ technology. Developers can quickly deploy virtual assistants or customer service robots. The Dify market platform now hosts over 120+ plugins, supporting community sharing and local deployment.

Introduction of Dify Agent Node: How workflows achieve 'autonomous reasoning'

Dify has officially launched the Agent Strategy plugin, enabling workflow nodes to delegate steps outside of fixed processes to LLM for autonomous decision-making. The Agent Node serves as the execution unit, managing resources and reasoning processes; Agent Strategy is a pluggable reasoning algorithm module that defines tool usage and problem-solving logic.

DeepSeek releases SYNTHETIC-1: a large-scale distributed synthetic reasoning dataset

TOPLOC: A Local Sensitivity Hashing Scheme for Trusted Verification Inference

TOPLOC detects unauthorized modifications to models, prompts, or computational precision through local sensitivity hashing mechanism, verification speed is 100 times faster than original inference, and submission storage for every 32 new tokens only requires 258 bytes (compared to 262 KB for Llama-3.1-8B-Instruct). This solution maintains robustness across various hardware configurations, GPU types, tensor parallel dimensions, and attention kernel implementations, reducing memory overhead by 1000 times and is suitable for large-scale deployment.

The PRIME-RL algorithm achieves 10 times faster training for the INTELLECT-MATH model through synthetic reasoning data.

Dify has released the Plugins plugin system to modularize component extensions to AI application capabilities.

Dify has launched the Plugins plugin system into Beta, extending AI application functionality through plug-and-play components. Developers can obtain ready-made plugins or build their own on the Dify Marketplace, supporting capabilities such as image processing, audio analysis, text generation, data analysis, logical reasoning, and external integration. The system adopts a decoupled architecture, including five types of components: models, tools, strategies, extensions, and packages, achieving bidirectional communication with Dify's core functionality through custom endpoints.

Dify v0.15.0 Released: Introducing Parent-Child Retrieval to Enhance Knowledge Acquisition

Dify v0.15.0 Launches Parent-Child Retrieval Technology, Achieving Precise Retrieval by Matching Fine-Grained Child Fragments, Combined with Coarse-Grained Parent Fragments to Supplement Context, Improving RAG System's Response Accuracy and Information Richness. This Feature Supports Two Parent Fragment Splitting Modes (Paragraph/Full Text), Allows Users to Edit Parent-Child Fragments Independently and Choose Whether to Regenerate Child Fragments, While Optimizing Fragment Preview Interface to Enhance Low-Code Platform Usability.

Dify v0.14.0 Released: Enhancing AI Workflow Elasticity Through Error Handling

Dify v0.14.0 introduces powerful error handling features, allowing developers to define custom error handling for LLM nodes, HTTP nodes, tool nodes, and code nodes. It prevents process interruptions through strategies like default values and workflow redirection, enhancing the reliability of AI applications.

Dify and Windsurf created a Twitter MBTI analyzer: a no-code journey.

Dify and Windsurf created a Twitter MBTI analyzer, gaining 200,000 visits in the first three days of launch. The project uses Dify to build the backend, analyzes user profiles with Twitter Scraper to generate MBTI reports, and the frontend is developed by Windsurf's Claude-3.5-sonnet assistant. API communication uses HTTP requests, supporting an 8k context window.

INTELLECT-1 Released: The First Global Jointly Trained 10B Parameter Model

INTELLECT-1 is released, the first 10B parameter language model trained through global collaboration, based on the Llama-3 architecture, completing 1T token training on 112 H100 GPUs across 5 countries and 3 continents, with the PRIME framework achieving a 400x reduction in communication bandwidth, 96% computational utilization, supporting sequence lengths of 8192 and a vocabulary of 128256, with the model code and data open-sourced.

How Dify Enhances GPT-Researcher Through Parallel and Advanced Iterative Features

Dify Workflow accelerates GPT-Researcher's research tasks through parallel mode and advanced iterative features, breaking down the problem into 4-6 independent sub-problems, parallel extracting topics to form subheadings, calling the Tavily API to search and analyze results, and finally integrating them into a structured report, significantly shortening research time and isolating error handling.

How Dify.AI empowers this global consumer electronics leader to integrate generative AI

The global consumer electronics leader serving over 100 million users has integrated generative AI into its operations through Dify.AI, bridging the gap between business and technology. Dify.AI's low-code platform allows novice users to quickly utilize mainstream models, expert users to independently customize solutions, and developers to enhance efficiency through component-based workflows. More than 200 AI applications have been created within a month, with 60 in use, reducing user voice analysis time from 8 hours to 3 hours.

Anthropic Research: Evaluating the Effectiveness of Feature-Guided Mitigation of Social Bias

Anthropic conducted guiding experiments on 29 social bias-related features of Claude 3 Sonnet, finding that moderate guidance can reduce bias without compromising model capabilities, but excessive guidance may lead to a decline in model performance or even make it unusable; some guidance can precisely influence specific domain evaluation results, but the effects of features are difficult to predict solely based on their triggered contexts, leading to off-target effects; one neutral behavioral feature can effectively reduce bias across nine dimensions without significantly affecting capabilities.

Dify v0.10.0 released: Supporting file upload functionality.

Dify v0.10.0 released, adding file upload functionality, supporting document, audio, and video files, enabling applications such as Q&A and summary generation, and allowing the creation of AI-driven podcasts through file upload and LLM nodes.

INTELLECT–1 globally distributed training the first 10B parameter model

INTELLECT-1 launches the world's first 10B parameter model distributed training, inviting the public to contribute computing power to advance the open-source AGI process. The training is based on the OpenDiLoCo open-source implementation, extending the 1B parameter scale of DeepMind DiLoCo's method by 10 times, significantly reducing communication frequency (up to 500 times), and lowering bandwidth requirements by 2000 times through quantized pseudo-gradients (int8) and 500-step outer optimizer synchronization.

OpenDiLoCo: An open-source global distributed low-communication training framework

OpenDiLoCo successfully replicated and extended DeepMind's DiLoCo experiment to a 10B parameter model scale, achieving cross-continent, three-country distributed training through Hivemind and PyTorch FSDP, maintaining 90-95% computational resource utilization. The framework is based on the open-source implementation of Hivemind, supporting dynamic resource joining/leaving and fault-tolerant training, significantly reducing communication requirements by 500x while maintaining performance on 1.5B parameter models.

Dify Integrates LangSmith and Langfuse to Enhance LLM Application Observability

Dify version 0.6.12 integrates LangSmith and Langfuse, allowing users to access detailed data of LLM applications through simple configuration, facilitating cost, latency, and quality evaluation. LangSmith provides rich evaluation features, and Langfuse supports open-source hosted architecture, both helping Dify users monitor and optimize LLM application performance.

Prime Intellect Compute platform officially launched: Global GPU resource aggregation and scheduling market

Prime Intellect Compute platform officially launched, aggregating global GPU resources to democratize instant computing. The platform offers a unified resource pool, supporting instant access from single GPU to 512+ GPU clusters. The first batch integrates 12 cloud service providers, with H100 GPUs priced at $1.5-4 per hour.

Dify v0.6.11 released: Integrating Firecrawl to create a top-tier web data knowledge base solution.

Dify v0.6.11 released, integrating Firecrawl as a web data source, generating structured markdown data from websites to enhance knowledge bases, supporting synchronization of web data and embedding vector databases to build RAG applications, providing 500 free page API credit quota, while optimizing workflow collaboration features.

Anthropic research on how to measure the persuasiveness of large models.

Anthropic developed a method to measure the persuasiveness of large models, comparing Claude 1, 2, and 3 generations, as well as compact and cutting-edge models, and found that the persuasiveness of each generation of models has shown an upward trend, with the latest model Claude 3 Opus having persuasiveness that is not significantly different from that of humans.