# llm-applications Published articles for llm-applications. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## How LLMs Can Find a Needle in a Haystack DevFeed: [How LLMs Can Find a Needle in a Haystack]() Original publisher: [Read original article]() Author: ByteByteGo Published: 2026-09-16T15:31:42Z Content type: tutorial Language: en Sources: [ByteByteGo]() Topics: [Large Language Model](), [Language models](), [App]() Tags: [article](), [llm](), [llm-applications](), [llms]() ### AI overview This tutorial explains the retrieval problem in LLM applications: finding current, relevant evidence in large collections of private documents. It discusses embeddings, semantic matching, search scope, and changing answers. ### Source excerpt In this article, we are going to look at how LLMs can find a needle in a haystack. ## Prompt Injection Is the Input Bug of the Agent Era DevFeed: [Prompt Injection Is the Input Bug of the Agent Era]() Original publisher: [Read original article]() Author: Eric Roby Published: 2026-07-07T12:02:21Z Content type: opinion Language: en Sources: [Eric Roby]() Topics: [prompt injection](), [Application Security](), [Security](), [SQL](), [trust](), [Large Language Model]() Tags: [ai](), [application-security](), [llm](), [llm-applications](), [prompt-injection](), [security](), [sql](), [trust]() ### AI overview The article compares prompt injection in AI agents with SQL injection. It argues that agents may interpret untrusted content from messages, documents, web pages, emails, RAG data, and tool responses as instructions because language models do not maintain a hard boundary between data and instructions. It frames prompt injection as an application security problem rather than merely a prompt-writing problem. ### Source excerpt SQL injection taught us not to trust raw user input. Agents force the next lesson: don't trust text just because the model can read it. ## From Zero to Hero: Localization-Led Generative AI at Udemy DevFeed: [From Zero to Hero: Localization-Led Generative AI at Udemy]() Original publisher: [Read original article]() Author: Nishanth Gandhidoss Published: 2025-09-22T17:47:18Z Content type: article Language: en Sources: [Udemy Engineering]() Topics: [Localization (l10n)](), [Generative AI](), [Large Language Model](), [datasets]() Tags: [ai](), [features](), [generative-ai](), [generative-ai-tools](), [implementation](), [llm](), [llm-applications](), [machine-learning](), [machine-translation](), [retrieval-augmented-gen](), [techniques](), [translation]() ### AI overview Udemy describes how it localized generative AI features, including Skills Mapping and its in-course AI Assistant, to serve learners in multiple languages. The article compares translation management systems, multilingual LLMs, and hybrid strategies, emphasizing trade-offs among implementation speed, language coverage, fluency, cultural nuance, and domain precision. ### Source excerpt By Nishanth Gandhidoss, Senior Staff Data Scientist @ Udemy Why Multilingual Generative AI Matters Generative AI is rapidly changing how people learn and work, but those gains are only realized when the technology speaks the user's language. Over the past year at Udemy, we prioritized breaking the English-only barrier so our Gen AI features, most critically Skills Mapping and the in-course AI Assistant, could deliver value for learners across the globe. Our approach balanced speed, coverage, and quality, allowing us to move quickly without sacrificing fidelity in markets where nuance matters. Below we describe the localization strategy we adopted, why we made those trade-offs, and the operational practices that made the rollout repeatable, scalable, and quick. Localization Strategies When deciding how to localize a Gen AI product, it is helpful to think of options on a spectrum from low to high complexity. The simplest approach provides broad language coverage fast, while the most involved approach optimizes for fluency, cultural nuance, and domain precision. At Udemy, we researched and organized our work around three primary strategies: a translation management system (TMS) for rapid implementation with broader coverage, a multilingual LLM system (MLS) for high-fidelity experiences, and a hybrid approach to balance reach and quality. As each strategy is introduced below, we briefly explain the industry-standard localization techniques they draw on, with examples, so the differences are clear. Translation Management System (TMS) At the simplest end of the spectrum, we have the TMS approach. With a TMS, the user interacts in their own language, but the AI model itself operates in English input/output. The system first detects the user's input language, say, in Spanish, and sends the input through a machine translation (MT) service that converts it into English. The LLM then generates an English response, and that response is translated back into the user's input lang ## Engineering a Scalable Topic Pipeline: A BERTopic and GenAI Case Study DevFeed: [Engineering a Scalable Topic Pipeline: A BERTopic and GenAI Case Study]() Original publisher: [Read original article]() Author: Saniya Naphade Published: 2025-08-28T06:25:05Z Content type: tutorial Language: en Sources: [GumGum]() Topics: [genai](), [Artificial Intelligence](), [Algorithm](), [data](), [GPU](), [datasets]() Tags: [ai](), [algorithm](), [case-study](), [clustering](), [data](), [datasets](), [engineering](), [genai](), [gpu](), [llm-applications](), [topic-modeling](), [workflow]() ### AI overview GumGum describes a scalable hybrid topic-modeling pipeline that combines deterministic BERTopic clustering with generative AI post-processing. The workflow processes impression data weekly, uses cuML for GPU acceleration, and addresses BERTopic's high outlier rate to recover more topic-related insights. ### Source excerpt Introduction: In a world where trends change in an instant, relying on static taxonomies to target ad campaigns is no longer effective. At GumGum, we face a constant torrent of digital content, ingesting millions of web pages every day. This massive flow of information must be turned into actionable insights, but because trends are dynamic, traditional methods like hard-coded taxonomies and slow hand-labeling are simply not viable at this scale. While large language models (LLMs) can offer some insight, using them at this volume is often cost-prohibitive and can lead to inconsistent results. To solve this, we've developed a lightweight and repeatable hybrid pipeline. This approach combines a deterministic clustering method -- specifically BERTopic¹ -- with a strategic post-processing layer using generative AI. The result is a more efficient and powerful topic modeling workflow that gives us the stability needed for large datasets and provides valuable, human-centric insights. Let's now walk through the key stages of this pipeline, beginning with data preparation. Data preparation The pipeline's first step is a critical data preparation phase built to handle immense scale. We process a comprehensive collection of impression data on a weekly basis to ensure we can capture not only major trends like the Summer Box Office but also the smaller, more nuanced shifts within that topic. For instance, in a given week, the pipeline might detect a specific surge of interest around a new movie's opening weekend, which would be lost in a less frequent processing schedule. This raw data is then thoroughly cleaned and prepared for the next stage, laying the groundwork for accurate and timely topic modeling. Dynamic Topic Modeling With this clean, prepared data, the real work of topic modeling begins. The pipeline then leverages BERTopic¹, a topic modeling algorithm, in conjunction with cuML³ for GPU acceleration, that is both powerful and efficient, and serves as our deterministic co ## Building Data-Aware AI Applications with Heroku AI and LlamaIndex DevFeed: [Building Data-Aware AI Applications with Heroku AI and LlamaIndex]() Original publisher: [Read original article]() Author: Anush DSouza Published: 2025-08-19T15:00:00Z Content type: tutorial Language: en Sources: [Heroku]() Topics: [Heroku](), [Retrieval Augmented Generation (RAG)](), [llamaindex](), [AI Development](), [Large Language Model](), [Model Context Protocol (MCP)]() Tags: [ai](), [building](), [data](), [engineering](), [heroku-ai](), [how-to](), [llamaindex](), [llm-applications](), [managed-inference-and-agents](), [product-features](), [rag]() ### AI overview This tutorial explains how to build retrieval-augmented generation applications that use private data with Heroku AI and LlamaIndex. It describes LlamaIndex's role in orchestrating data ingestion, indexing, retrieval, and LLM context, along with Heroku AI capabilities including managed inference, embeddings, vector search through pgvector, and connections via Model Context Protocol and AppLink. ### Source excerpt Building AI applications that can interact with private data is a common goal for many organizations. The challenge often lies in connecting large language models (LLMs) with proprietary datasets. A combination of Heroku Managed Inference and Agents and LlamaIndex provides an elegant stack for this purpose. This post explores how to use these tools to [...] The post Building Data-Aware AI Applications with Heroku AI and LlamaIndex appeared first on Heroku.