Skip to main content
ZICQ

Topics RAG in Practice

RAG in Practice

Retrieval-Augmented Generation from principles to engineering: chunking, vector search, reranking, hybrid retrieval, and production evaluation.

· Aug 20, 2026 #RAG#retrieval-augmented generation#vector search#hybrid search#reranking · 30 / 224 articles

News · 2026-09-13

LlamaIndex and OpenLLM Collaborate to Build Intelligent Query-Response Systems: Seamlessly Integrate Open-Source LLMs wi

LlamaIndex and OpenLLM have partnered to introduce an intelligent query-response system that seamlessly integrates open-source large language models (LLMs) with users' private data. This system leverages OpenLLM for deploying and fine-tuning open-source models and utilizes LlamaIndex to manage and retrieve domain-specific private data, enabling efficient, secure, and customized AI applications. Developers can use this combination to build intelligent query systems that understand and respond to

News · 2026-09-13

LlamaIndex Releases Advanced RAG Techniques: Optimization for Retrieval and Generation

LlamaIndex has released a comprehensive guide on advanced RAG (Retrieval-Augmented Generation) techniques, covering retrieval optimization, generation strategies, and practical recipes to help developers build high-performance RAG systems. Inspired by recent research, the guide provides detailed methodologies ranging from basic to advanced, such as chunk-size optimization and structured external knowledge construction, aiming to enhance RAG performance in complex scenarios.

News · 2026-09-13

LlamaIndex Releases Query Pipelines: A Declarative API for Building Advanced RAG DAG Workflows

LlamaIndex has introduced Query Pipelines, a new declarative API designed to help developers orchestrate query workflows ranging from simple to advanced, including RAG (Retrieval-Augmented Generation) and structured data extraction scenarios. This feature allows users to build complex DAG (Directed Acyclic Graph) computational graphs, reduce boilerplate code, and enhance workflow readability and maintainability. Query Pipelines supports callback integration, serialization, and caching, providing

News · 2026-09-13

LlamaIndex Launches LlamaParse: A Cutting-Edge OCR Solution for Accurate Document Parsing and RAG

LlamaIndex has launched LlamaParse, a state-of-the-art OCR (Optical Character Recognition) platform designed to deliver the highest accuracy in parsing and extracting information from complex documents while optimizing for cost-efficiency. Positioned at the 'Pareto frontier' of cost and accuracy, LlamaParse aims to significantly enhance the performance of RAG (Retrieval-Augmented Generation) systems by providing more precise and reliable document processing capabilities. This release underscores

News · 2026-09-13

LlamaIndex and Activeloop Launch Free Advanced RAG Certification Course

LlamaIndex and Activeloop have launched a free Advanced RAG (Retrieval-Augmented Generation) Certification Course designed to equip AI practitioners with skills for production-grade AI applications. The course includes over 40 lessons and 7 hands-on projects, covering multimodal AI applications, legal, healthcare, finance, and more. It offers a free extended trial of the Deep Lake database and is led by LlamaIndex CEO Jerry Liu, aiming to enhance learners' practical abilities in applying RAG tec

News · 2026-09-13

LlamaIndex Releases Multi-Tenancy RAG System: Enhancing Data Security and Privacy

LlamaIndex has launched a Multi-Tenancy RAG (Retrieval-Augmented Generation) system that ensures user data isolation through metadata filtering. This system allows multiple users to interact with the RAG pipeline independently, ensuring that queries only retrieve information relevant to the querying user. By preventing unauthorized cross-referencing of private data, the system enhances data security and privacy, making it suitable for applications dealing with sensitive information.

News · 2026-09-13

LlamaIndex Releases Slackbot with Qdrant: Enabling Conversational Learning and Q&A

LlamaIndex has released a Slackbot powered by Qdrant that listens to conversations, learns from them, and answers questions based on the knowledge within a Slack workspace. Integrated with Render, the bot leverages incremental RAG (Retrieval-Augmented Generation) techniques, enabling users to efficiently build and deploy intelligent conversational systems. This release highlights LlamaIndex's ongoing innovation in AI application development, providing developers with powerful new tools.

News · 2026-09-13

LlamaIndex Releases No-Code RAG Command-Line Tool: Streamlining AI Application Development

LlamaIndex has launched the LlamaIndex-CLI, a no-code RAG (Retrieval-Augmented Generation) command-line tool designed to help developers build RAG applications without writing code. The tool facilitates local file ingestion, querying, and conversational search through simple terminal commands, leveraging the OpenAI API for generating accurate responses. It also supports customization with various LLM models and advanced query techniques, providing developers with a flexible and efficient solutio

News · 2026-09-13

LlamaIndex Releases LlamaParse JSON: Enhancing Complex Document Processing and RAG Pipeline Development

LlamaIndex has launched LlamaParse JSON, a tool designed to convert PDF content into structured data, simplifying the processing of complex documents such as PDFs containing images, text, and tables. By integrating with multimodal models like Claude-3 Opus, this feature significantly enhances the efficiency of RAG (Retrieval-Augmented Generation) pipeline development, providing developers with a more efficient and accurate document parsing solution.

News · 2026-09-13

LlamaIndex Launches Agentic RAG Architecture: Revolutionizing Multi-Agent RAG Systems

LlamaIndex has introduced Agentic RAG, a novel architecture designed to enhance the scalability and intelligence of RAG (Retrieval-Augmented Generation) systems through multi-agent collaboration. This approach divides large document sets into subsets managed by individual agents, enabling efficient document management and retrieval. A top-level agent orchestrates the process using Chain-of-Thought and reranking mechanisms to optimize user query responses. This innovation provides a more powerful

News · 2026-09-13

LlamaIndex Introduces Alpha Tuning for Enhanced Hybrid Search in RAG

LlamaIndex has introduced a novel Alpha Tuning technique for optimizing hybrid search in Retrieval-Augmented Generation (RAG) applications. By fine-tuning the Alpha parameter, which balances the weight between keyword-based (BM25) and vector search methods, developers can achieve more precise retrieval results tailored to various user query types. The blog post provides a comprehensive guide on implementing Alpha Tuning using the Weaviate vector database, along with evaluation metrics such as Hi

News · 2026-09-13

LlamaIndex Releases RAGArch: A No-Code Tool for One-Click RAG Pipeline Generation

LlamaIndex has launched RAGArch, a no-code tool designed to streamline the process of building, testing, and deploying Retrieval-Augmented Generation (RAG) pipelines. The tool offers an intuitive interface, supports various language models, embedding models, and vector databases, and allows for one-click Python code generation, enabling developers to create customized RAG solutions efficiently. This release highlights LlamaIndex's ongoing innovation in automating AI application development workf

News · 2026-09-13

LlamaIndex Releases Latest Newsletter: Introducing Self-RAG and Multi-Modal RAG Solutions

LlamaIndex has released its latest newsletter, announcing the launch of Self-RAG, a dynamic retrieval tool, and integration with FlowiseAI for enhanced no-code RAG application development. The newsletter also highlights a RAG guide developed in collaboration with MistralAI, TypeScript-based agent development tools, and the integration of DeepEval for improved RAG evaluation. These updates demonstrate LlamaIndex's ongoing innovation in multi-modal AI applications, developer tools, and intelligent

News · 2026-09-13

LlamaIndex Releases TypeScript-Based LLM Agents for Building Data-Driven Autonomous Systems

LlamaIndex has launched its TypeScript-based LLM Agents (LlamaIndex.TS), empowering developers to build autonomous systems capable of reasoning and acting on user data. The tool supports function calling APIs for integrating various utilities and offers intelligent question-answering capabilities for personal or private datasets. Developers can leverage these features to create agents ranging from simple calculations to complex document processing, thereby enhancing the automation and efficiency

News · 2026-09-12

LlamaIndex Launches GenAI-Powered ADU Planning Tool: Revolutionizing Home Development

LlamaIndex has launched a GenAI-driven Accessory Dwelling Unit (ADU) planning tool designed to streamline the home development process. By automating building code research and site analysis, the tool connects users with local builders and generates viable floor plans, significantly reducing the complexity of planning and enhancing development efficiency. This innovation marks a breakthrough application of AI in residential construction, offering a new approach to addressing global housing short

News · 2026-09-12

LlamaIndex Launches LlamaParse JSON Mode: Enhancing Complex Document Processing and RAG Pipeline Development

LlamaIndex has recently launched the LlamaParse JSON Mode, a tool designed to convert PDF content into structured data, aiming to simplify the processing of complex documents such as PDFs containing images, text, and tables. By integrating with multimodal models like Claude-3 Opus, this feature significantly enhances the efficiency of RAG (Retrieval-Augmented Generation) pipeline development, providing developers with more efficient and accurate document parsing solutions. Additionally, LlamaInd

News · 2026-09-12

LlamaIndex Releases LlamaIndex-Networks: Building RAG Networks for Cross-System Knowledge Querying

LlamaIndex has released its latest extension library, LlamaIndex-Networks, designed to build networks of RAG (Retrieval-Augmented Generation) systems. This library enables data suppliers to provide knowledge through external data sources and allows developers to connect multiple RAG systems with just a few lines of code, creating more intelligent and efficient knowledge query engines. This innovation opens up new possibilities for RAG marketplaces, data sharing, and cross-organizational knowledg

News · 2026-09-12

LlamaIndex Explores New Long-Context RAG Architectures: Addressing Multimodal Data and Complex Task Challenges

LlamaIndex delves into the evolution of Long-Context RAG (Retrieval-Augmented Generation) architectures, analyzing the impact of long-context LLMs like Gemini 1.5 Pro on existing RAG technologies. The article highlights that while long-context LLMs simplify certain aspects of RAG, such as document chunking and cross-document reasoning, they also introduce new challenges, including difficulties in parsing complex tables and charts and longer response times. To address these, LlamaIndex proposes n

News · 2026-09-12

LlamaIndex Launches neThing.xyz: Optimizing Text-to-CAD with RAG for 3D Generative AI

The LlamaIndex team has launched neThing.xyz, a platform that leverages Retrieval-Augmented Generation (RAG) to optimize the text-to-CAD workflow in 3D generative AI. By training a code generation AI on domain-specific languages for CAD, neThing.xyz converts natural language instructions into CAD model code, significantly improving the efficiency and accuracy of 3D modeling while reducing API costs by 80%. This innovation provides engineers with a smarter and more efficient tool for 3D design, s

News · 2026-09-12

LlamaIndex and DeepLearningAI Launch 'Building Agentic RAG' Course: Enhancing Skills in Complex Document Processing and

LlamaIndex has announced a new course in collaboration with DeepLearningAI titled 'Building Agentic RAG,' designed to teach developers how to build research assistants capable of reasoning across multiple documents and answering complex questions. The course covers setting up basic functions, integrating advanced features like local and remote LLMs, and steering AI agents with human feedback. Additionally, LlamaIndex introduced day-zero support for GPT-4o, Llama3 cookbooks, and a TypeScript agen

News · 2026-09-12

LlamaIndex Releases LlamaParse JSON Mode: Enhancing Complex Document Processing and RAG Pipeline Development

LlamaIndex has launched LlamaParse JSON Mode, a tool designed to transform PDF content into structured data, simplifying the development of RAG (Retrieval-Augmented Generation) pipelines for complex documents that include images, text, and tables. This feature, integrated with multimodal models like Claude-3 Opus, enhances the efficiency and accuracy of document processing. Additionally, LlamaIndex introduced a hierarchical code splitting technique to improve code comprehension and supports vide

News · 2026-09-12

LlamaIndex Integrates Microsoft Presidio: Enhancing PII Detection in RAG Pipelines

LlamaIndex has announced the integration of Microsoft’s open-source privacy-preserving tool, Presidio, to enhance PII (Personally Identifiable Information) detection and anonymization within RAG (Retrieval-Augmented Generation) pipelines. This integration allows developers to automatically identify and mask sensitive information during data processing, ensuring AI applications comply with privacy regulations and protect user data. The collaboration provides AI developers with a robust privacy pr

News · 2026-09-12

LlamaIndex Integrates UpTrain for Enhanced RAG Pipeline Evaluation

LlamaIndex has integrated with UpTrain, an open-source LLM evaluation framework, to enhance the evaluation capabilities of RAG (Retrieval-Augmented Generation) pipelines. This integration offers comprehensive assessments for both basic and advanced RAG applications, covering query engines, sub-question handling, and reranking modules. UpTrain's features, such as local data processing and customizable evaluator LLMs, ensure data security while providing root cause analysis and model improvement r

News · 2026-09-12

LlamaIndex Integrates Langfuse for One-Click Open Source RAG Observability

LlamaIndex has announced a deep integration with Langfuse, offering developers a one-click solution for RAG (Retrieval-Augmented Generation) observability. This integration allows users to trace latency, cost, and session details with just two lines of code, leveraging Langfuse's capabilities for session grouping, prompt management, and evaluation to optimize complex application performance. This collaboration simplifies the debugging and optimization of RAG applications, providing developers wi

News · 2026-09-12

LlamaIndex Open-Sources LlamaFile: A Tool for Building Local Private Research Assistants

LlamaIndex, in collaboration with Mozilla, has open-sourced LlamaFile, a tool that enables users to run large language models (LLMs) locally on their laptops. This approach ensures data privacy and allows for offline usage without relying on cloud services or third-party platforms. LlamaFile supports various open-source models and integrates with LlamaIndex's RAG (Retrieval-Augmented Generation) capabilities, providing developers with an efficient and privacy-preserving AI application solution.

News · 2026-09-12

MyMagic AI and LlamaIndex Integration: Enabling Efficient Batch Inference and RAG Pipeline Integration

MyMagic AI has announced a deep integration with LlamaIndex, enabling efficient batch inference for large-scale data processing and seamless integration with LlamaIndex's RAG (Retrieval-Augmented Generation) pipeline. This feature allows users to leverage various open-source LLMs (such as Llama 70B, Mistral 7B, etc.) for tasks like data extraction, classification, and sentiment analysis, streamlining complex data processing workflows and enhancing AI application development efficiency.

News · 2026-09-12

LlamaIndex Integrates with PostgresML: Streamlining RAG Architecture for Enhanced Performance

LlamaIndex has announced its integration with PostgresML, introducing the PostgresML Managed Index. This integration unifies document storage, splitting, embedding, and retrieval into a single system, significantly streamlining the Retrieval-Augmented Generation (RAG) application architecture. By reducing the number of network calls, LlamaIndex users can achieve faster, more reliable, and easier-to-manage RAG workflows. Additionally, the solution leverages open-source models for transparency and

News · 2026-09-12

LlamaIndex Releases Property Graph Index: A Major Upgrade for Knowledge Graph Construction and Querying

LlamaIndex has launched the Property Graph Index, a powerful toolkit for building and querying knowledge graphs (KGs). This toolkit enhances graph searches with vector capabilities, improving retrieval efficiency for KGs, particularly in graph stores lacking native vector support. Additionally, LlamaParse now supports spreadsheet parsing, transforming complex Excel files into LLM-friendly tables to optimize RAG (Retrieval-Augmented Generation) pipeline performance. These updates highlight LlamaI

News · 2026-09-12

LlamaIndex and PostgresML Collaborate to Enhance Vector Search Reranking for Improved RAG Accuracy

LlamaIndex and PostgresML have introduced a cross-encoder-based vector search reranking approach to enhance the accuracy of Retrieval-Augmented Generation (RAG) systems. This method directly compares query-result pairs for similarity, addressing the limitations of traditional semantic search in handling new content. Although computationally expensive, it excels at reranking smaller datasets, significantly improving the relevance of search results and providing developers with a more precise sear

News · 2026-09-12

LlamaIndex Launches LlamaParse and LlamaExtract: New Tools for Agentic OCR and Structured Data Extraction

LlamaIndex has launched LlamaParse and LlamaExtract, two new tools designed to enhance AI agent capabilities in parsing complex documents and extracting structured data. LlamaParse focuses on agentic OCR, optimizing document understanding through a two-stage processing approach. LlamaExtract offers managed services for structured data extraction, supporting asynchronous operations and streaming, and integrates with Pydantic for real-time JSON output visualization. These tools provide developers