Ragflow
PulseAugur coverage of Ragflow — every cluster mentioning Ragflow across labs, papers, and developer communities, ranked by signal.
- 2026-11-09 product_launch Ragflow released version 1.0.0 with a rewritten engine in Go, Agentic Chat, and a queue system change. source
4 day(s) with sentiment data
-
Ragflow v1.0.0: Engine rewritten in Go, adds Agentic Chat, switches queue to NATS
Ragflow has released version 1.0.0, featuring a significant rewrite of its engine in the Go programming language. This update results in approximately 10x smaller image sizes and faster startup times. Additionally, Ragf…
-
RAGFlow integrates CloudGPU models including DeepSeek, Kimi, and GLM
The RAGFlow application has integrated CloudGPU as a new model provider, allowing users to access various chat models including DeepSeek V4.1 Flash, Kimi, GLM, and MiniMax. This integration, merged into RAGFlow's main b…
-
LLM Agents' Memory Systems Face New Benchmarks for Safety and Efficiency
Recent research explores vulnerabilities and improvements in Large Language Model (LLM) agent memory systems. Studies highlight how memory formation can be susceptible to poisoning, leading to unreliable agent behavior …
-
RAGFlow performance issues resolved with dual-index and normalization fixes
A developer encountered significant performance issues while integrating RAGFlow into an agent memory pipeline, specifically with PostgreSQL's pgvector. High concurrency led to HNSW index lock contention and improper em…
-
2026 RAG Frameworks: LlamaIndex, LangChain, Haystack, DSPy, RAGFlow Compared
As of 2026, Retrieval-Augmented Generation (RAG) frameworks have become standard for LLM applications, with several prominent options available. LlamaIndex excels in document RAG with advanced parsing and workflows, whi…
-
Galahad memory layer makes LLM reading a one-time cost
Researchers have developed Galahad, a novel memory layer designed to make large language model (LLM) reading a one-time cost, significantly improving efficiency in LLM serving. Galahad addresses the issue of stateless s…
-
New RAG test checks for conflicting data and source citation accuracy
A new five-minute manual test has been proposed to evaluate the reliability of Retrieval-Augmented Generation (RAG) assistants, particularly focusing on their ability to handle conflicting information and cite sources a…
-
RAGFlow: Open-source tool for LLM document integration
RAGFlow is an open-source tool designed to implement the Retrieval-Augmented Generation (RAG) method, which addresses common Large Language Model (LLM) issues like hallucinations and outdated knowledge. This approach al…
-
Top AI Tools for 2026: Open-Source, Local, and General Use
Several articles highlight top AI tools for 2026, focusing on different categories. One piece details essential open-source tools for local use, including Ollama for chat models, Open WebUI for an interface, RAGflow for…
-
RAG frameworks: Production challenges and open-source solutions
Two articles discuss the practical challenges and solutions for deploying Retrieval-Augmented Generation (RAG) systems. The first highlights RAGFlow as a mature open-source tool for building production-ready assistants,…
-
Structured Parsing Boosts Dense Retrieval Performance in LLM RAG
A study comparing document parsing strategies for retrieval-augmented generation (RAG) found that structured parsing significantly benefits dense retrieval more than traditional BM25 methods. When using dense retrieval,…
-
Chinese PDF parser DeepDoc shows mixed results on Japanese documents
A technical evaluation of RAGFlow's DeepDoc, an open-source document parser from China, revealed a critical flaw when processing Japanese PDFs. The parser systematically misreads the Japanese era name character 令 as 今 o…
-
AI infrastructure startups launch tools for agents, DevOps, security, and healthcare
Several startups are launching AI-powered tools aimed at improving infrastructure and developer productivity. Trigger.dev offers an open-source platform for building reliable AI agents and workflows, utilizing snapshott…