# Retrieval-Augmented Generation A language-generation approach that retrieves documents as additional context. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Glyph: A Multi-Strategy Agentic System for Column Description and Sensitivity-Ontology Tagging of Enterprise Data Catalogs DevFeed: [Glyph: A Multi-Strategy Agentic System for Column Description and Sensitivity-Ontology Tagging of Enterprise Data Catalogs]() Original publisher: [Read original article]() Published: 2026-09-16T00:00:00Z Content type: article Language: en Sources: [Apple Machine Learning Research]() Topics: [data](), [Large Language Model](), [Code](), [Retrieval-Augmented Generation](), [Access Control](), [Graphs](), [GitHub]() Tags: [agents](), [classification](), [code](), [data](), [documentation](), [governance](), [production](), [provenance](), [retrieval](), [vector-database]() ### AI overview Glyph is a production system for generating column descriptions and assigning sensitivity-ontology labels in enterprise data catalogs. It uses cooperating LLM agents, source-code-grounded retrieval, parallel tagging strategies, vector-based metadata matching, and ranked-output fusion to support auditable cataloging. ### Source excerpt Enterprise data lakes accumulate tables faster than human stewards can document or classify them, leaving columns with missing descriptions and unassigned governance labels. This documentation debt undermines data discovery, access control, and regulatory compliance. We present Glyph, a production system that frames two coupled problems, column description generation and column type annotation for data classification, as cooperating LLM agents orchestrated as stateful graphs. The Descriptor grounds generation in the pipeline source code that produces each column, retrieved on demand from an... ## Seagate and WD AI Storage Research Finds Enterprises Rank Storage Above Compute as the AI Bottleneck DevFeed: [Seagate and WD AI Storage Research Finds Enterprises Rank Storage Above Compute as the AI Bottleneck]() Original publisher: [Read original article]() Author: Lyle Smith Published: 2026-09-15T17:23:54Z Content type: news Language: en Sources: [StorageReview.com]() Topics: [Data Infrastructure](), [AI Infrastructure](), [idc](), [Inference](), [Retrieval-Augmented Generation](), [synthetic-data]() Tags: [ai](), [compute](), [data-infrastructure](), [datasets](), [enterprise](), [genai](), [hdd](), [idc](), [inference](), [reports](), [research](), [retrieval](), [storage](), [synthetic-data]() ### AI overview Seagate and WD published separate studies indicating that AI is increasing enterprise storage requirements and extending data retention. Although their headline percentages differ because they asked different questions, both reports point to storage becoming a larger part of AI infrastructure planning alongside growing archive and retrieval needs. ### Source excerpt Seagate and WD published separate AI storage studies within days of each other; the headline numbers: Seagate says 99% of enterprises expect AI to increase their storage requirements over the next three years, while WD's IDC research puts the comparable figure at 74%. Read the fine print, and both reports land in the same directional The post Seagate and WD AI Storage Research Finds Enterprises Rank Storage Above Compute as the AI Bottleneck appeared first on StorageReview.com. ## Build a support chatbot with Appwrite Functions and VectorsDB DevFeed: [Build a support chatbot with Appwrite Functions and VectorsDB]() Original publisher: [Read original article]() Author: Atharva Deosthale Published: 2026-09-10T00:00:00Z Content type: tutorial Language: en Sources: [Appwrite Blog]() Topics: [Appwrite](), [Chat Bot](), [Retrieval-Augmented Generation](), [Embeddings](), [React](), [SDKs](), [Node.js]() Tags: [api](), [build](), [chat](), [deploy](), [embedding](), [functions](), [node-js](), [rag](), [react](), [retrieval](), [support](), [tutorials]() ### AI overview This tutorial builds Harbor Help, a support chatbot for a fictional project-management product. It uses Appwrite VectorsDB to store help-center article embeddings, an Appwrite Function to retrieve relevant excerpts and generate answers through OpenRouter, and Appwrite Sites to host a React interface. The chatbot uses retrieval-augmented generation and can refuse questions outside the help center. ### Source excerpt Seed a help center, retrieve relevant articles with VectorsDB, and answer customer questions through an Appwrite Function. Deploy the chat interface on Appwrite Sites. ## Deploying a RAG Chatbot with Shared State and Storage Across Replicas DevFeed: [Deploying a RAG Chatbot with Shared State and Storage Across Replicas]() Original publisher: [Read original article]() Author: Avi Chawla Published: 2026-09-01T21:11:23Z Content type: tutorial Language: en Sources: [Daily Dose of Data Science]() Topics: [Retrieval-Augmented Generation](), [Kubernetes](), [Terraform](), [FastAPI](), [LangChain](), [Python]() Tags: [fastapi](), [github](), [persistence](), [pgvector](), [python](), [rag](), [retrieval](), [terraform]() ### AI overview The article explains why a RAG chatbot that works locally can lose vector indexes, conversation history, and documents when deployed across multiple replicas. It recommends shared persistence for embeddings, checkpointed conversation state, and shared object storage, with examples using Postgres, pgvector, LangGraph, and object storage. ### Source excerpt + a popular LLM interview question. ## When LLM judges agree, should we believe them? DevFeed: [When LLM judges agree, should we believe them?]() Original publisher: [Read original article]() Author: Krishna Balasubramanian; Sasha Podkopaev Published: 2026-08-26T17:10:40Z Content type: article Language: en Sources: [Amazon Science homepage]() Topics: [Large Language Model](), [Retrieval-Augmented Generation](), [Ising](), [benchmark overfitting machine learning](), [Network](), [AI, ML & Data Engineering]() Tags: [conversational-ai](), [evaluation](), [ising](), [large-language-models-llms](), [llm](), [machine-learning](), [metrics](), [retrieval](), [retrieval-augmented-generation]() ### AI overview The article examines whether agreement among LLM judges is trustworthy when their outputs may be correlated. It presents a dependence-aware aggregation method based on Ising models that discounts shared blind spots and outperforms historical-accuracy-weighted majority voting on three tasks. ### Source excerpt Discounting the opinions of LLM judges with highly correlated outputs ensures that panels of judges reflect a true diversity of perspectives. ## GraphRAG: How AI Answers Questions Hidden Across Many Documents DevFeed: [GraphRAG: How AI Answers Questions Hidden Across Many Documents]() Original publisher: [Read original article]() Author: ByteByteGo Published: 2026-08-19T15:31:18Z Content type: tutorial Language: en Sources: [ByteByteGo]() Topics: [Graphs](), [Retrieval-Augmented Generation](), [Artificial Intelligence]() Tags: [graphs](), [knowledge-graphs](), [rag](), [retrieval-augmented-generation](), [search]() ### AI overview This tutorial explains how GraphRAG addresses questions whose answers emerge from patterns across an entire document collection, contrasting it with standard RAG, which is designed to retrieve information from specific documents. ### Source excerpt GraphRAG was designed to handle the second kind of questions, and we are going to learn more about it in this article. ## Building the AI Retrieval Infrastructure Behind 20 Billion+ Vectors at HubSpot DevFeed: [Building the AI Retrieval Infrastructure Behind 20 Billion+ Vectors at HubSpot]() Original publisher: [Read original article]() Author: Oleg Tereshin & Xin Liu Published: 2026-06-25T18:17:44Z Content type: article Language: en Sources: [HubSpot]() Topics: [Qdrant](), [AI search](), [Artificial Intelligence](), [Embeddings](), [Retrieval-Augmented Generation](), [Open Source](), [systems](), [quantization]() Tags: [ai](), [embeddings](), [engineering](), [latency](), [open-source](), [quantization](), [rag](), [retrieval](), [search](), [vector-database](), [vectors]() ### AI overview HubSpot describes how it built VaaS, a centralized vector storage and search platform using Qdrant, to support semantic search across tens of billions of vectors and many use cases. ### Source excerpt Discover how HubSpot built a scalable AI retrieval infrastructure, managing over 20 billion vectors with Qdrant, to enhance semantic search and support diverse applications. ## Doximity Ask DevFeed: [Doximity Ask]() Original publisher: [Read original article]() Author: Doximity Published: 2026-06-23T09:30:00Z Content type: article Language: en Sources: [Doximity]() Topics: [Artificial Intelligence](), [Retrieval-Augmented Generation](), [Hallucination detection]() Tags: [agentic](), [ai](), [grounding](), [hallucinations](), [retrieval-augmented-generation](), [review](), [verification]() ### AI overview The article explains how Doximity Ask approaches reliability in clinical AI. It describes a HIPAA-compliant clinical reference platform that combines retrieval-augmented generation, validated tools, a reasoning model, citation-grounded responses, automated verification, physician-authored evaluation, and production monitoring. It argues that reliability is a system property spanning retrieval, ranking, reasoning, tool use, verification, and evaluation. ### Source excerpt Medical AI has attracted confident claims: perfect scores, no hallucinations, a system that gracefully declines whenever the evidence runs out. But are these dimensions the right way to think about a tool that physicians use to make real-world decisions? For clinical AI, reliability is not just a question of whether an answer is correct. It is also a question of whether a physician can understand where the answer came from, evaluate the supporting evidence, and identify situations where uncertainty remains. How Doximity Ask Answers Clinical Questions Few domains face stakes as high as medical AI, where system performance can directly influence patient outcomes, clinical workflows, and healthcare professionals' decisions. Clinical reference requires traceable grounding, numerically exact doses and scores, and explicit handling of situations in which the available evidence is insufficient to support an answer. At the same time, healthcare providers often work under significant time constraints and have exceptionally high expectations for the performance and reliability of AI systems. Doximity Ask is a HIPAA compliant composite clinical reference platform for question answering at the point of care. It combines retrieval-augmented generation over a physician-governed evidence library, multi-turn agentic tool use through a fixed registry of validated calculators and structured lookups, and a post-trained reasoning model that orchestrates retrieval, tool calls, and citation-grounded generation. Automated verifiers, physician-authored rubrics, and in-product physician review form one evaluation loop that grades releases, defines training rewards, and monitors production. Reliability Is A System Property Over 150 health systems have purchased the Doximity Clinical AI Suite including 8 of the top 20 hospitals in the country, therefore reliability is paramount. The reliability of a clinical AI system depends on more than the capabilities of its underlying language model. Pro ## Adding embeddings/RAG support to the Koog-based AI agent in Confetti DevFeed: [Adding embeddings/RAG support to the Koog-based AI agent in Confetti]() Original publisher: [Read original article]() Published: 2026-05-25T23:00:00Z Content type: tutorial Language: en Sources: [John O'Reilly]() Topics: [AI Agent](), [Embeddings](), [Retrieval-Augmented Generation](), [multiplatform](), [Kotlin](), [GraphQL]() Tags: [agent](), [ai-agent](), [compose-multiplatform](), [embeddings](), [graphql](), [kotlin](), [rag]() ### AI overview This tutorial explains how to add semantic search to the Koog-based AI agent in the Confetti Compose Multiplatform sample. It uses embeddings and retrieval-augmented generation to find related conference sessions even when query wording differs from session titles or descriptions. ### Source excerpt Recently I started looking at reworking the recommendation feature in the Confetti Compose Multiplatform sample (which uses Apollo Kotlin to consume a GraphQL API serving data for various conferences). The new implementation uses a Koog AIAgent with a ToolRegistry that includes session and speaker tools, giving the LLM on-demand access to the conference data it needs. ## Ambient Associative Memory DevFeed: [Ambient Associative Memory]() Original publisher: [Read original article]() Published: 2026-05-17T00:00:00Z Content type: article Language: en Sources: [Tim Kellogg]() Topics: [Retrieval-Augmented Generation](), [context]() Tags: [agent](), [embedding](), [memory](), [models](), [performance](), [prompt](), [rag](), [tokens](), [vector]() ### AI overview The article describes an ambient associative memory system for agents that queries an index on every tool call and injects brief excerpts from relevant past memories. It uses late-interaction, multi-vector embeddings to identify highly relevant tokens rather than returning entire document chunks, aiming to surface prior lessons without intentional searching or a growing rules list. ### Source excerpt Most agent memory waits to be queried. Ambient memory runs on every tool call -- past lessons surface on their own, no rules list required. ## Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context -- Best Sub-100M Retrieval Quality DevFeed: [Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context -- Best Sub-100M Retrieval Quality]() Original publisher: [Read original article]() Author: Radu Florian; Parul Awasthy; Aashka Trivedi; Madison Lee Published: 2026-05-14T18:55:01Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Embeddings](), [Benchmark](), [Retrieval-Augmented Generation](), [AI search](), [LangChain](), [Code]() Tags: [apache](), [benchmark](), [embeddings](), [frameworks](), [langchain](), [llamaindex](), [model](), [retrieval]() ### AI overview Granite Embedding Multilingual R2 introduces two Apache 2.0 multilingual embedding models: a compact 97M-parameter model and a 311M full-size model. They support more than 200 languages, 32K-token contexts, code retrieval across nine programming languages, and integration with popular retrieval frameworks. ### Source excerpt Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context -- Best Sub-100M Retrieval Quality TL;DR: Two new Apache 2.0 multilingual embedding models built on ModernBERT -- a 97M-parameter compact model that beats every open sub-100M multilingual embedder on MTEB Multilingual Retrieval (60.3), and a 311M full-size model that scores 65.2 on MTEB Multilingual Retrieval (#2 among open models under 500M parameters) with Matryoshka support. ## Pricing AI Chat Apps for Sustainable Margins DevFeed: [Pricing AI Chat Apps for Sustainable Margins]() Original publisher: [Read original article]() Author: Ayush Agarwal Published: 2026-05-14T00:00:00Z Content type: tutorial Language: en Sources: [Dodo Payments Blog]() Topics: [AI Chat](), [App](), [Large Language Model](), [Software as a service](), [Retrieval-Augmented Generation]() Tags: [ai](), [app](), [chat](), [cost](), [how-to](), [llm](), [pricing](), [rag](), [retrieval](), [saas](), [subscription](), [token](), [unit-economics](), [usage-based-billing](), [variable](), [volume]() ### AI overview This practical guide explains how to price AI chat applications when model costs vary with token usage. It covers unit economics, hidden infrastructure and retrieval costs, and usage-based billing approaches intended to align customer charges with consumption. ### Source excerpt A practical guide to pricing AI chat apps for positive margins. Cover token costs, hidden infrastructure spend, and a step by step framework for usage based billing. ## Building an Agent with RAG, Tool Calling, Memory, and Feedback DevFeed: [Building an Agent with RAG, Tool Calling, Memory, and Feedback]() Original publisher: [Read original article]() Author: hi@swizec.com (Swizec Teller) Published: 2026-05-05T00:00:00Z Content type: opinion Language: en Sources: [Swizec Teller]() Topics: [Retrieval-Augmented Generation](), [Large Language Model](), [Tool]() Tags: [agent](), [memory](), [rag]() ### AI overview The author outlines four components for an agent used in internal tooling and processes: retrieval-augmented generation (RAG), tool calling, memory, and a feedback loop. The article describes using tools to retrieve external data and returning results to an LLM's context, while noting that long prompts may require memory-management techniques. ### Source excerpt I've been digging into agents for internal tooling and processes. Looking for how to scale without drowning in manual work. Here's what I found ## Razorpay Oncall Agent: From 30-Minute Investigations to 90-Second AI Analysis DevFeed: [Razorpay Oncall Agent: From 30-Minute Investigations to 90-Second AI Analysis]() Original publisher: [Read original article]() Author: Anuj Gupta Published: 2026-04-29T06:56:11Z Content type: article Language: en Sources: [Razorpay Engineering - Medium]() Topics: [Artificial Intelligence](), [Langgraph](), [incident](), [SRE](), [observability](), [Large Language Model](), [Retrieval-Augmented Generation]() Tags: [agent](), [ai](), [incident](), [langgraph](), [logs](), [metrics](), [observability](), [retrieval-augmented-generation](), [sre]() ### AI overview Razorpay describes building a multi-agent AI system to automate production incident investigations. The Oncall Agent uses LangGraph, an LLM, alerting tools, and two retrieval-augmented generation systems containing architecture, dependency, and diagnostic runbook context. ### Source excerpt Our on-call engineers were spending 30 minutes investigating every production alert. Here's what happened when we automated it. At 3 AM, alerts don't care about your sleep schedule. When our payment infrastructure threw an error last month, our on-call engineer spent 32 minutes jumping between six different monitoring systems before understanding what was broken. One tool for metrics. Another for logs. Third tool for pod health. And multiple more for infrastructure, deployment history and database health. By the time they identified the root cause (a bad deployment), payment failures had already impacted customers for nearly 40 minutes. This wasn't their fault. They followed our runbook perfectly. The problem was that no single system could tell them "here's what's wrong and why." They had to manually connect dots across disconnected observability tools. That's when we asked ourselves: what if AI could do this investigation for us? The Metric Nobody Optimizes For The SRE world talks endlessly about Mean Time to Detect (how fast you catch problems) and Mean Time to Resolve (how fast you fix them). But there's a critical phase hiding between them: Mean Time to Investigate. MTTI is the gap from "we know it's broken" to "we know what to fix." At Razorpay, this phase was consuming 20-40 minutes per incident. With 15-20 incidents weekly, that's 6-8 hours of engineering time spent doing repetitive investigative work. Worse, the quality was inconsistent. Senior engineers knew exactly which systems to check for payment alerts. Junior engineers sometimes checked irrelevant dashboards or missed critical correlations. The investigation depended entirely on who was on-call that night. What We Built (And Why It Works) Razorpay Oncall Agent is a multi-agent AI system that automates incident investigation. The architecture is built on LangGraph, a framework for creating stateful workflows with conditional logic, and uses LLM as the reasoning engine. Here's how the components work t ## How NASA and Chainguard used AI to support secure, compliant Artemis mission readiness DevFeed: [How NASA and Chainguard used AI to support secure, compliant Artemis mission readiness]() Original publisher: [Read original article]() Author: Dimension Published: 2026-04-17T00:00:00Z Content type: article Language: en Sources: [Chainguard: Unchained]() Topics: [Artificial Intelligence](), [chainguard](), [data](), [Retrieval-Augmented Generation](), [Model Context Protocol (MCP)](), [datasets](), [cloud-infrastructure](), [User Experience](), [Scalability](), [Grafana]() Tags: [ai](), [ai-in-space](), [artemis-2](), [artemis-ii](), [automated](), [chainguard](), [chainguard-containers](), [compliance](), [data](), [embeddings](), [fedramp](), [mcp](), [pipelines](), [retrieval](), [safety](), [scalability](), [space](), [user-experience]() ### AI overview The article describes how NASA and MRI Technologies partnered with Chainguard to build a secure, continuously compliant software foundation for Artemis and Habitable Worlds Observatory missions. It discusses attempts to use retrieval-augmented generation and MCP with mixed-format safety data, while highlighting unresolved data-fidelity and traceability challenges. ### Source excerpt How NASA Artemis used AI and Chainguard to enable secure, compliant software and faster mission readiness in high-stakes environments. ## Agent Development with CockroachDB using the LangChain Framework DevFeed: [Agent Development with CockroachDB using the LangChain Framework]() Original publisher: [Read original article]() Author: David Bressler Published: 2026-02-26T00:00:00Z Content type: release Language: en Sources: [Cockroach Labs]() Topics: [CockroachDB](), [LangChain](), [agentic AI applications](), [Orchestration](), [Python](), [Databases](), [Retrieval-Augmented Generation]() Tags: [agentic-ai-applications](), [cockroachdb](), [langchain](), [orchestration](), [pgvector](), [postgresql](), [python](), [retrieval-augmented-generation]() ### AI overview CockroachDB describes its integration with LangChain for building production-oriented agentic AI applications in Python. The integration supports CockroachDB as a vector source and helps connect language models with CockroachDB data for retrieval and other multi-step application workflows. ### Source excerpt Recently we launched an integration with LangChain, the most popular orchestration framework for developing applications with large language models, to simplify development of production-ready agentic AI applications with CockroachDB. This integration provides out-of-the-box support for CockroachDB as a vector source for any LangChain user using LangChain Python. ## Building AI Agent Applications: Lessons on Model Size, Context, MCP, and RAG DevFeed: [Building AI Agent Applications: Lessons on Model Size, Context, MCP, and RAG]() Original publisher: [Read original article]() Author: Mai Lubega Published: 2026-02-16T00:00:00Z Content type: tutorial Language: en Sources: [Deliveroo]() Topics: [AI Agent](), [Large Language Model](), [Model Context Protocol](), [Retrieval-Augmented Generation](), [Ollama](), [Go Language]() Tags: [ai](), [ai-agent](), [go](), [llms](), [mcp](), [ollama](), [rag](), [software]() ### AI overview This tutorial shares lessons from an Ardan Labs workshop on building AI agent applications. It covers using smaller local models with Ollama, managing conversation context, generating vector embeddings, building RAG applications, and creating an MCP client and server. ### Source excerpt LLMs, MCPs, RAG. There are lots of acronyms in the AI space, but what do they all mean? Dear reader, despite being a software engineer who works in the machine learning space, I confess there was a time I wasn't really sure. Fortunately, with the financial support of Deliveroo's Women-in-Tech Employee Resource Group, I took the Ardan Labs Building AI-Powered Applications in Go workshop that helped me understand what's really going on behind the chat interface and where software engineering meets LLM-based applications. We went through a series of modules to incrementally build a RAG (Retrieval-Augmented Generation) AI Agent application. I started with generating vector embeddings from text and eventually built an MCP Client & Server able to process image and text input and respond to simple queries, after which I felt I understood the new AI landscape much, much better. For my dearest gentle reader, I'm happy to share these three takeaways from the course: Size Matters Full-size language models are very large and can require several hundred gigabytes of memory to run, certainly much more than is available on a personal laptop. To work around this constraint, we used Ollama -- an open-source project that provides smaller, more size-efficient LLM models - that can be run locally. In the real world, some applications get around this problem by sending data directly to OpenAI/Anthropic's APIs. They don't have to host any models locally, just send and receive data (subject to usage tier and API limits, of course). But applications that need a model to run locally for proprietary reasons will have to manage the infrastructure themselves -- which usually involves a very spicy cloud bill or a server in the corner that doubles as a space heater. Don't Lose the Plot (Manage your Context) Think of Context as the LLM's short-term memory. When we chat with an AI, we don't just send the current question; we send the entire conversation history, system instructions, and any retrieve ## Building AI Search on Heroku DevFeed: [Building AI Search on Heroku]() Original publisher: [Read original article]() Author: Anush DSouza Published: 2026-01-29T17:50:08Z Content type: tutorial Language: en Sources: [Heroku]() Topics: [Heroku](), [AI search](), [Retrieval-Augmented Generation](), [Claude]() Tags: [ai](), [ai-search](), [building](), [engineering](), [heroku](), [heroku-ai](), [managed-inference-and-agents](), [news](), [pgvector](), [rag](), [retrieval](), [retrieval-augmented-generation](), [search](), [vector-search]() ### AI overview This article presents a Heroku reference architecture for production-grade enterprise AI search using two-stage retrieval. It combines vector search with semantic reranking so documents are scored for whether they answer the query, then uses Claude to generate an answer. ### Source excerpt If you've built a RAG (Retrieval Augmented Generation) system, you've probably hit this wall: your vector search returns 20 documents that are semantically similar to the query, but half of them don't actually answer it. A user asks "how do I handle authentication errors?" and gets back documentation about authentication, errors, and error handling in [...] The post Building AI Search on Heroku appeared first on Heroku. ## Optimize Search Precision with Reranking on Heroku AI DevFeed: [Optimize Search Precision with Reranking on Heroku AI]() Original publisher: [Read original article]() Author: Anush DSouza Published: 2026-01-15T16:00:48Z Content type: release Language: en Sources: [Heroku]() Topics: [Heroku](), [Inference](), [Retrieval-Augmented Generation](), [model-deployment](), [amazon](), [cohere]() Tags: [ai](), [api](), [availability](), [heroku](), [heroku-ai](), [inference](), [managed-inference-and-agents](), [news](), [rag](), [retrieval-augmented-generation]() ### AI overview Heroku announces general availability of reranking models in Heroku Managed Inference and Agents, with support for Cohere Rerank 3.5 and Amazon Rerank 1.0. The article explains how semantic reranking can improve RAG pipelines by filtering documents for query relevance and reducing noise and token costs. ### Source excerpt Today, we are announcing the general availability of reranking models on Heroku Managed Inference and Agents, featuring support for Cohere Rerank 3.5 and Amazon Rerank 1.0. Semantic reranking models score documents based on their relevance to a specific query. Unlike keyword search or vector similarity, rerank models understand nuanced semantic relationships to identify the most [...] The post Optimize Search Precision with Reranking on Heroku AI appeared first on Heroku. ## Building AI-powered apps with Angular and Gemini DevFeed: [Building AI-powered apps with Angular and Gemini]() Original publisher: [Read original article]() Author: Armen Vardanyan Published: 2025-09-29T09:27:51Z Content type: tutorial Language: en Sources: [Daniel Glejzner]() Topics: [Angular](), [AI Development](), [API](), [AI Models](), [multimodal](), [Retrieval-Augmented Generation]() Tags: [ai](), [angular](), [api](), [articles](), [getting-started](), [multimodal]() ### AI overview This introductory tutorial series explains how Angular developers can build AI-powered applications with the Gemini API. It outlines topics including API requests and configuration, embeddings, retrieval-augmented generation, multimodal capabilities, and agentic AI applications. ### Source excerpt Like it or not, we live in the age of AI, and it can be both exciting and frustrating. On one hand, AI can help us unlock almost unlimited capabilities for the apps we build; if in the past, tasks like image recognition or text classification could be a dealbreaker ## Welcome EmbeddingGemma, Google's new efficient embedding model DevFeed: [Welcome EmbeddingGemma, Google's new efficient embedding model]() Original publisher: [Read original article]() Author: Tom Aarsen; Joshua; Alvaro Bartolome; Aritra Roy Gosthipaty; Pedro Cuenca; Sergio Paniego Published: 2025-09-04T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Embeddings](), [sentence-transformers](), [Artificial Intelligence](), [Google](), [Retrieval-Augmented Generation](), [Open Source](), [transformers.js](), [Inference](), [onnx](), [dataset](), [LangChain](), [llamaindex]() Tags: [artificial-intelligence](), [benchmark](), [community](), [embedding](), [google](), [guide](), [langchain](), [llamaindex](), [nlp](), [on-device](), [onnx](), [open-source](), [rag](), [sentence-transformers](), [transformers-js]() ### AI overview Google introduces EmbeddingGemma, a compact multilingual embedding model designed for fast, efficient on-device use. The article covers its architecture, training, multilingual capabilities, benchmark performance, framework integrations, and domain fine-tuning for retrieval applications. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Evaluating GPT-5 for hallucination handling in RAG applications DevFeed: [Evaluating GPT-5 for hallucination handling in RAG applications]() Original publisher: [Read original article]() Author: Pamela Fox (noreply@blogger.com) Published: 2025-08-11T18:40:00Z Content type: opinion Language: en Sources: [Pamela Fox]() Topics: [Retrieval-Augmented Generation](), [Artificial Intelligence](), [OpenAI](), [SDKs](), [Azure](), [Ground truth / benchmark quality]() Tags: [ai](), [azure](), [evaluation](), [gpt](), [hallucinations](), [llm](), [models](), [openai](), [rag](), [sdk]() ### AI overview The article evaluates GPT-5 models in an Azure AI Foundry RAG template. It reports that GPT-5 identified when the source documents lacked enough information to answer a question, and describes broader bulk evaluations using the azure-ai-evaluations SDK across 50 question-and-answer pairs. ### Source excerpt OpenAI released the GPT-5 model family today, with an emphasis on accurate tool calling and reduced hallucinations. For those of us working on RAG (Retrieval-Augmented Generation), it's particularly exciting to see a model specifically trained to reduce hallucination. There are five variants in the family: gpt-5 gpt-5-mini gpt-5-nano gpt-5-chat: Not a reasoning model, optimized for chat applications gpt-5-pro: Only available in ChatGPT, not via the API As soon as GPT-5 models were available in Azure AI Foundry, I deployed them and evaluated them inside our popular open source RAG template. I was immediately impressed - not by the model's ability to answer a question, but by it's ability to admit it could not answer a question! You see, we have one test question for our sample data (HR documents for a fictional company's) that sounds like it should be an easy question: "What does a Product Manager do?" But, if you actually look at the company documents, there's no job description for "Product Manager", only related jobs like "Senior Manager of Product Management". Every other model, including the reasoning models, has still pretended that it could answer that question. For example, here's a response from o4-mini: However, the gpt-5 model realizes that it doesn't have the information necessary, and responds that it cannot answer the question: As I always say: I would much rather have an LLM admit that it doesn't have enough information instead of making up an answer. Bulk evaluation But that's just a single question! What we really need to know is whether the GPT-5 models will generally do a better job across the board, on a wide range of questions. So I ran bulk evaluations using the azure-ai-evaluations SDK, checking my favorite metrics: groundedness (LLM-judged), relevance (LLM-judged), and citation_match (regex based off ground truth citations). I didn't bother evaluating gpt-5-nano, as I did some quick manual tests and wasn't impressed enough - plus, we've never ## Codestral Embed DevFeed: [Codestral Embed]() Original publisher: [Read original article]() Published: 2025-05-28T12:00:00Z Content type: article Language: en Sources: [Mistral AI Blog]() Topics: [Embeddings](), [Retrieval-Augmented Generation](), [AI-assisted coding](), [code-completion](), [AI search](), [coding]() Tags: [code-completion](), [code-search](), [coding](), [cost](), [developer](), [embeddings](), [performance](), [retrieval-augmented-generation]() ### AI overview Mistral releases Codestral Embed, an embedding model specialized for code retrieval. The article presents benchmark results, configurable embedding dimensions and precisions, and trade-offs between retrieval quality and storage cost. It highlights applications including retrieval-augmented generation, semantic code search, similarity search, duplicate detection, clustering, and code analytics. ### Source excerpt The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models. ## How to Make a RAG Application With LangChain4j DevFeed: [How to Make a RAG Application With LangChain4j]() Original publisher: [Read original article]() Author: Tim Kelly Published: 2025-05-03T12:00:00Z Content type: tutorial Language: en Sources: [Nic Raboy]() Topics: [Retrieval-Augmented Generation](), [Databases](), [Development](), [Embeddings](), [Java](), [Library](), [MongoDB](), [AI Development](), [Chat Bot]() Tags: [ai](), [artificial-intelligence](), [chatbots](), [database](), [embeddings](), [how-to](), [java](), [langchain4j](), [library](), [mongodb](), [rag]() ### AI overview This tutorial explains how to build a retrieval-augmented generation Q&A chatbot with LangChain4j. It describes retrieving data from MongoDB Atlas, storing documents as vector embeddings, and using the retrieved data to augment LLM prompts. ### Source excerpt Retrieval-augmented generation, or RAG, introduces some serious capabilities to your large language models (LLMs). These applications can answer questions about your specific corpus of knowledge, whil... The post How to Make a RAG Application With LangChain4j appeared first on DEV. [Next page]()