# AI search

A computing approach that applies artificial intelligence to retrieve, rank, and generate responses from indexed information.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Clipto enables ChatGPT and Claude to search and analyze years of people's meetings and video calls

DevFeed: [Clipto enables ChatGPT and Claude to search and analyze years of people's meetings and video calls](<https://devfeed.tech/articles/clipto-enables-chatgpt-and-claude-to-search-and-analyze-years-of-people-s-meetings-and-video-calls-130451.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/11/12/clipto-enables-chatgpt-and-claude-to-search-and-analyze-years-of-peoples-meetings-and-video-calls/>)

Author: Mike Wheatley

Published: 2026-11-12T14:00:52Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [multimodal-ai](<https://devfeed.tech/topics/multimodal-ai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-assistants](<https://devfeed.tech/tags/ai-assistants.md>), [ai-audio-search](<https://devfeed.tech/tags/ai-audio-search.md>), [ai-chatbot](<https://devfeed.tech/tags/ai-chatbot.md>), [ai-chatbots](<https://devfeed.tech/tags/ai-chatbots.md>), [ai-meeting-insights](<https://devfeed.tech/tags/ai-meeting-insights.md>), [ai-memory](<https://devfeed.tech/tags/ai-memory.md>), [ai-video](<https://devfeed.tech/tags/ai-video.md>), [ai-video-search](<https://devfeed.tech/tags/ai-video-search.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [audio](<https://devfeed.tech/tags/audio.md>), [audio-files](<https://devfeed.tech/tags/audio-files.md>), [building](<https://devfeed.tech/tags/building.md>), [business](<https://devfeed.tech/tags/business.md>), [call](<https://devfeed.tech/tags/call.md>), [chatbots](<https://devfeed.tech/tags/chatbots.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [claude](<https://devfeed.tech/tags/claude.md>), [clipto](<https://devfeed.tech/tags/clipto.md>), [clipto-studio](<https://devfeed.tech/tags/clipto-studio.md>), [data](<https://devfeed.tech/tags/data.md>), [henry-kang](<https://devfeed.tech/tags/henry-kang.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [meetings](<https://devfeed.tech/tags/meetings.md>), [news](<https://devfeed.tech/tags/news.md>), [search](<https://devfeed.tech/tags/search.md>), [speech-data](<https://devfeed.tech/tags/speech-data.md>), [speech-indexing](<https://devfeed.tech/tags/speech-indexing.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>), [video](<https://devfeed.tech/tags/video.md>), [video-call-data](<https://devfeed.tech/tags/video-call-data.md>), [video-call-insights](<https://devfeed.tech/tags/video-call-insights.md>), [video-files](<https://devfeed.tech/tags/video-files.md>)

### AI overview

Clipto Studio is presented as a way for ChatGPT, Claude, and other assistants to search and analyze a user's recorded meetings, calls, and presentations. It connects through the Model Context Protocol and uses proprietary models running locally on Mac and Windows to pre-index speech, speaker voices, facial expressions, and on-screen visuals into searchable metadata. The excerpt says users can query recordings dating back years, locate when a project's scope changed, find recurring customer issues with supporting quotes, or compile highlights from presentations. These are described capabilities and examples; the excerpt does not provide independent performance evidence or implementation details beyond the indexing approach.

### Source excerpt

Artificial intelligence assistants such as ChatGPT and Claude have become essential tools for millions of workers worldwide, helping them compose emails in seconds, generate complex code and draft reports by looking at whatever data that person has access to. But there's one thing that's missing from those chatbots' knowledge. Ask them what was discussed in [...] The post Clipto enables ChatGPT and Claude to search and analyze years of people's meetings and video calls appeared first on SiliconANGLE.

## State Media at Retrieval Time: A Large-Scale Audit of Russian State-Aligned Sources in AI Chatbot Responses

DevFeed: [State Media at Retrieval Time: A Large-Scale Audit of Russian State-Aligned Sources in AI Chatbot Responses](<https://devfeed.tech/articles/state-media-at-retrieval-time-a-large-scale-audit-of-russian-state-aligned-sources-in-ai-chatbot-responses-126167.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.11727>)

Author: Laura Kurek, Elijah Covert, Rafael I Bonilla, Eric Gilbert, Ceren Budak

Published: 2026-11-10T05:00:00Z

Content type: news

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [audit](<https://devfeed.tech/topics/audit.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [audit](<https://devfeed.tech/tags/audit.md>), [chatbot](<https://devfeed.tech/tags/chatbot.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [media](<https://devfeed.tech/tags/media.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [russia](<https://devfeed.tech/tags/russia.md>), [state](<https://devfeed.tech/tags/state.md>)

### AI overview

The audit found Pravda Network articles in 7.3% of 104,997 chatbot responses, with retrieval highly concentrated: You.com, Claude, and Copilot accounted for 94% of those instances. Among frontier models, Claude retrieved some; ChatGPT, Gemini, and Meta AI retrieved none, which the authors suggest may reflect domain filtering. All 11 chatbots retrieved other Russian state-aligned media to some degree. Caveats on surfaced Pravda content varied by platform, from 5.3% to 76.2%, with You.com caveating least. The study also found that 9.92% of sampled headlines used "headline washing," attributing reporting to other, often more credible outlets despite republication from Russian state-aligned media. Results come from a prompt corpus varying headline wording and user skepticism, queried through chatbot web interfaces.

### Source excerpt

arXiv:2611.11727v1 Announce Type: new Abstract: The Pravda Network is a Russian state-aligned media aggregator, with over 110 websites and more than 15 million articles published since 2023. Given its prolific and repetitive output, emerging scholarship argues that the Pravda Network was built to influence AI systems. We conduct a large-scale audit of leading AI chatbots to understand: (1) the retrieval rates of Pravda Network articles, (2) the conditions of retrieval, and (3) whether chatbot responses affirm or caveat this content. We build a 10,000 prompt corpus from sampled Pravda Network headlines varied along two dimensions (headline rewording and user skepticism) and query 11 AI chatbots via the web interface (n=104,997 completed responses). Overall, we find susceptibility to Pravda Network retrieval to be infrequent---appearing in 7.3% of responses---and highly platform dependent---with three chatbots responsible for 94% of retrievals (You.com, Claude, and Copilot). Among the frontier models, Claude is an outlier: ChatGPT, Gemini, and Meta AI retrieved no Pravda Network articles, likely indicative of a domain-level filtering policy. All 11 chatbots, however, retrieved other Russian state-aligned media to some degree (median=13.56% of responses). When Pravda Network articles are surfaced, caveat rates vary widely by platform (from 5.3% to 76.2%), with You.com providing the fewest caveats. We also identify the tactic of headline washing: where 9.92% of sampled Pravda Network headlines attribute their reporting to other, often more credible, media outlets, while the articles themselves are republished from Russian state-aligned media. We discuss headline washing's potential to launder state media as independent reporting. With this audit, we provide a systematic analysis of AI chatbots' susceptibility to Russia's latest attempt to manipulate the information environment.

## Typed-Centrality Grounding for Agentic GraphRAG: A Symbolic Approach for Agentic Reasoning

DevFeed: [Typed-Centrality Grounding for Agentic GraphRAG: A Symbolic Approach for Agentic Reasoning](<https://devfeed.tech/articles/typed-centrality-grounding-for-agentic-graphrag-a-symbolic-approach-for-agentic-reasoning-124679.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.09414>)

Author: Rosario Napoli, Antonio Celesti, Massimo Villari, Maria Fazio

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [context](<https://devfeed.tech/tags/context.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [graphrag](<https://devfeed.tech/tags/graphrag.md>), [grounding](<https://devfeed.tech/tags/grounding.md>), [information-retrieval](<https://devfeed.tech/tags/information-retrieval.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [retrieval-augmented-generation](<https://devfeed.tech/tags/retrieval-augmented-generation.md>), [structured-context](<https://devfeed.tech/tags/structured-context.md>)

### AI overview

The proposed agent-based GraphRAG system adds a symbolic grounding layer to textual similarity: it computes centrality separately for each knowledge graph class, then supplies a symbolic representation to the LLM as a deterministic source. The work reports mathematical validation and a comparison with and without this layer on a real-world POLE (Person, Object, Location, Event) dataset, covering reasoning and information retrieval. The abstract says outputs with the layer were more consistent with context; it provides no quantitative results or implementation details.

### Source excerpt

arXiv:2611.09414v1 Announce Type: new Abstract: Knowledge Graphs (KGs) and Large Language Models (LLMs) represent two approaches for knowledge representation and reasoning over heterogeneous data. Recent research has explored their integration through Graph Retrieval-Augmented Generation (GraphRAG) systems, which use KGs to provide structured context to LLMs. However, existing GraphRAG approaches treat KGs as homogeneous graphs and rely on textual similarity between the input prompt and the context, rather than using it as a source of deterministic knowledge. This work proposes an agent-based GraphRAG system that introduces a symbolic layer to integrate deterministic reasoning alongside text similarities. This approach is based on the definition of typed centralities for KGs, where centrality measures are computed separately for each specific KG's class. This information is used to construct a symbolic representation that is provided to the LLM as a deterministic source. The proposed system was mathematically validated and evaluated on a real-world POLE (Person, Object, Location, Event) dataset, comparing reasoning and information retrieval with and without the symbolic layer. The results indicate that the our approach leads to responses that are more consistent with the context, improving the generated outputs.

## EU Court Advisor Warns Google AI Chatbot May Breach Copyright Rules

DevFeed: [EU Court Advisor Warns Google AI Chatbot May Breach Copyright Rules](<https://devfeed.tech/articles/eu-court-advisor-warns-google-ai-chatbot-may-breach-copyright-rules-115759.md>)

Original publisher: [Read original article](<https://yro.slashdot.org/story/26/11/03/2144244/eu-court-advisor-warns-google-ai-chatbot-may-breach-copyright-rules>)

Author: BeauHD

Published: 2026-11-03T23:00:00Z

Content type: news

Language: en

Sources: [Slashdot](<https://devfeed.tech/sources/slashdot.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>)

Tags: [added](<https://devfeed.tech/tags/added.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-chatbot](<https://devfeed.tech/tags/ai-chatbot.md>), [ai-chatbots](<https://devfeed.tech/tags/ai-chatbots.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [articles](<https://devfeed.tech/tags/articles.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [based](<https://devfeed.tech/tags/based.md>), [but](<https://devfeed.tech/tags/but.md>), [chatbot](<https://devfeed.tech/tags/chatbot.md>), [chatbots](<https://devfeed.tech/tags/chatbots.md>), [company](<https://devfeed.tech/tags/company.md>), [content](<https://devfeed.tech/tags/content.md>), [copyright](<https://devfeed.tech/tags/copyright.md>), [court](<https://devfeed.tech/tags/court.md>), [data](<https://devfeed.tech/tags/data.md>), [data-mining](<https://devfeed.tech/tags/data-mining.md>), [eu](<https://devfeed.tech/tags/eu.md>), [google](<https://devfeed.tech/tags/google.md>), [rules](<https://devfeed.tech/tags/rules.md>)

### AI overview

EU Advocate General Maciej Szpunar said Gemini may infringe publishers' reproduction rights in some circumstances when it accesses articles by circumventing paywalls or other technical barriers, or reproduces their recognizable expression in answers. Copyright protects the article's specific expression, not the mere facts it reports. Szpunar said using protected material to train large language models is permitted under the text and data mining exception; he found no evidence Google used Like Company's articles to train Gemini. His opinion is non-binding, and the EU Court of Justice is expected to rule in the coming months.

### Source excerpt

An adviser to the EU's highest court says Google's Gemini may violate publishers' copyright when it reproduces recognizable portions of their articles or circumvents paywalls and other technical protections to generate answers. Reuters reports: The case before the Luxembourg-based Court of Justice of the European Union pitted Hungarian website operator Like Company against US-based Google's artificial intelligence chatbot Gemini. A ruling against Google, which could force the tech giant to pay fees for the use of such content, could throw a lifeline to online media such as Like Company. They have seen traffic dwindle as news summaries written by AI chatbots like Gemini increasingly replace traditional search engines' results, which include hyperlinks to the media websites. "When an LLM (large language model)-driven chatbot retrieves a publication from a press publisher's website, reuses that publication to generate an answer, and provides that answer to the user, the press publisher's right may be infringed in certain circumstances," Advocate General Maciej Szpunar said. Gemini's answers fall under the publishers' right of reproduction when chatbots access publications by unlawfully "circumventing paywalls or other technical barriers, or when they reuse "the form of expression of that publication in a recognizable manner," he said. Copyright rules do not protect the "mere facts" reported by press publications, but "only the specific form of expression," he added. On the other hand, he said, the use of material protected by copyright to train LLMs -- AI systems that use vast amounts of text to generate human-like responses and summarize information -- is "freely permitted under the text and data mining exception." Szpunar said there was no evidence that Google had used the Hungarian publisher's articles to train Gemini. The court, which follows the majority of its advisers' non-binding opinions, will rule in the coming months. "Google's powerful gatekeeping role in s

## Data-Void Exploits in Web-Searching LLMs

DevFeed: [Data-Void Exploits in Web-Searching LLMs](<https://devfeed.tech/articles/data-void-exploits-in-web-searching-llms-96578.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.30365>)

Author: Michele Guerra, Wuyeh Jobe, Sanjana Nambiar, Christina P\\"opper, Azza Abouzied

Published: 2026-10-23T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [LLM security](<https://devfeed.tech/topics/llm-security.md>), [Adversarial attacks](<https://devfeed.tech/topics/adversarial-attacks.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [adversarial](<https://devfeed.tech/tags/adversarial.md>), [attack-surface](<https://devfeed.tech/tags/attack-surface.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-hc](<https://devfeed.tech/tags/cs-hc.md>), [cs-ir](<https://devfeed.tech/tags/cs-ir.md>), [exploits](<https://devfeed.tech/tags/exploits.md>), [llms](<https://devfeed.tech/tags/llms.md>), [searching](<https://devfeed.tech/tags/searching.md>), [vulnerability](<https://devfeed.tech/tags/vulnerability.md>), [web](<https://devfeed.tech/tags/web.md>)

### AI overview

Data-void exploits can place attacker narratives in web-searching LLM answers even when the attacker controls only one page. In tests varying prompt tone, model, and attacker strategy, visibility, and generative-optimization features, attacker content appeared in responses 31% of the time. Skeptical prompts slightly reduced success and slightly increased warnings or flags; the study found no large success-rate effects from prompt tone or model choice, though smaller effects remain possible. The findings identify strategically placed web content in sparse search spaces as a practical inference-time attack surface.

### Source excerpt

arXiv:2610.30365v1 Announce Type: new Abstract: Web-searching Large Language Models (LLMs) have changed how users seek online information: instead of sifting through ranked lists of links, users read synthesized answers. This shift creates a new LLM vulnerability: a data-void exploit. Disinformers publish their narratives in search spaces where relevant and reliable content is scarce, i.e. data voids, then rely on the LLM's web-search to retrieve and then use, cite, or list those pages in its responses to data-void seeking prompts. Unlike classical search, where users see ranking cues and competing results, LLMs can obscure when an answer relies on sparse, unverified, or adversarial sources. We study this threat by varying the user's prompt tone - skeptical, excited, or neutral - and LLM choice - ChatGPT, Gemini, or Sonar Pro - as well as three attacker controls. The attacker can use one of five known strategies to construct and fill a data void with their narrative, host their content at varying levels of visibility from well-established, indexed domains to less established ones, and include generative-optimization engine features thought to boost citing by web-searching LLMs. We find that data-void exploits can succeed with only a single attacker controlled page. Across all conditions, attacker-content appears in LLM responses 31% of the time. User controls offer limited protection: while skeptical prompts slightly reduce success and slightly increase flagging or warnings in LLM responses, we find no evidence of large effects of prompt tone or model choice on success rates, although smaller effects cannot be ruled out. Overall, our results establish data voids as a practical inference-time attack surface for manipulating web-searching LLMs through strategically placed web content and highlight the urgent need for defenses against such exploits.

## Does Agentic RAG Actually Retrieve Better Evidence? I Tested It on 298 Questions

DevFeed: [Does Agentic RAG Actually Retrieve Better Evidence? I Tested It on 298 Questions](<https://devfeed.tech/articles/does-agentic-rag-actually-retrieve-better-evidence-i-tested-it-on-298-questions-95958.md>)

Original publisher: [Read original article](<https://towardsdatascience.com/does-agentic-rag-actually-retrieve-better-evidence-i-tested-it-on-298-questions/>)

Author: Abdullahi Dattijo

Published: 2026-10-22T15:30:00Z

Content type: news

Language: en

Sources: [Towards Data Science](<https://devfeed.tech/sources/towards-data-science.md>)

Topics: [AI search](<https://devfeed.tech/topics/ai-search.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [A/B Testing](<https://devfeed.tech/topics/a-b-testing.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-rag](<https://devfeed.tech/tags/agentic-rag.md>), [agentic-retrieval](<https://devfeed.tech/tags/agentic-retrieval.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-coding-assistant](<https://devfeed.tech/tags/ai-coding-assistant.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [apache](<https://devfeed.tech/tags/apache.md>), [apache-2-0](<https://devfeed.tech/tags/apache-2-0.md>), [api](<https://devfeed.tech/tags/api.md>), [api-key](<https://devfeed.tech/tags/api-key.md>), [apis](<https://devfeed.tech/tags/apis.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [bootstrap](<https://devfeed.tech/tags/bootstrap.md>), [cache](<https://devfeed.tech/tags/cache.md>), [editor-s-picks](<https://devfeed.tech/tags/editor-s-picks.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [llm-agents](<https://devfeed.tech/tags/llm-agents.md>), [rag](<https://devfeed.tech/tags/rag.md>), [search](<https://devfeed.tech/tags/search.md>)

### AI overview

On 298 questions about 2,000 recent arXiv papers, an agent allowed up to three searches did not clearly improve top-five retrieval over one-shot dense search: it recovered some missed papers but lost others, and the estimated gain was too uncertain to distinguish from no effect. A reranker that rescored the first 50 results improved rank quality, though not top-five recall clearly; it used no language model calls and added about 1.5 seconds on the author's laptop. The agent stopped after one search on about 59% of questions and used all three on about 26%, adding model cost and delay. The test covered retrieval only, used long questions generated from abstracts, one collection, and one agent model and instruction set, so the results may not generalize. The author suggests measuring baseline misses, trying reranking, and inspecting agent rewrites for unsupported added terms.

### Source excerpt

I let an AI agent search again whenever it chose. It found some papers plain search had missed, lost some plain search had found, and gained too little to trust. The post Does Agentic RAG Actually Retrieve Better Evidence? I Tested It on 298 Questions appeared first on Towards Data Science.

## Qdrant 1.20 - Full-Text Search Improvements

DevFeed: [Qdrant 1.20 - Full-Text Search Improvements](<https://devfeed.tech/articles/qdrant-1-20-full-text-search-improvements-95827.md>)

Original publisher: [Read original article](<https://qdrant.tech/blog/qdrant-1.20.x/>)

Author: info@qdrant.tech (Andrey Vasnetsov)

Published: 2026-10-22T01:00:00Z

Content type: release

Language: en

Sources: [Qdrant Blog on Qdrant - Vector Search Engine](<https://devfeed.tech/sources/qdrant-blog-on-qdrant-vector-search-engine.md>)

Topics: [Qdrant](<https://devfeed.tech/topics/qdrant.md>), [search-engines](<https://devfeed.tech/topics/search-engines.md>), [code search](<https://devfeed.tech/topics/code-search.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [quantization](<https://devfeed.tech/topics/quantization.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>)

Tags: [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [bert](<https://devfeed.tech/tags/bert.md>), [bm25](<https://devfeed.tech/tags/bm25.md>), [code](<https://devfeed.tech/tags/code.md>), [code-search](<https://devfeed.tech/tags/code-search.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [faster](<https://devfeed.tech/tags/faster.md>), [fasttext](<https://devfeed.tech/tags/fasttext.md>), [full-text-search](<https://devfeed.tech/tags/full-text-search.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [image-search](<https://devfeed.tech/tags/image-search.md>), [knn-algorithm](<https://devfeed.tech/tags/knn-algorithm.md>), [matching](<https://devfeed.tech/tags/matching.md>), [nested](<https://devfeed.tech/tags/nested.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [payload](<https://devfeed.tech/tags/payload.md>), [qdrant](<https://devfeed.tech/tags/qdrant.md>), [quantization](<https://devfeed.tech/tags/quantization.md>), [recommender-system](<https://devfeed.tech/tags/recommender-system.md>), [saas](<https://devfeed.tech/tags/saas.md>), [search](<https://devfeed.tech/tags/search.md>), [simaes-networks](<https://devfeed.tech/tags/simaes-networks.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [storage](<https://devfeed.tech/tags/storage.md>), [transformer](<https://devfeed.tech/tags/transformer.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>), [vector-search-engine](<https://devfeed.tech/tags/vector-search-engine.md>), [vectors](<https://devfeed.tech/tags/vectors.md>), [version](<https://devfeed.tech/tags/version.md>), [word2vec](<https://devfeed.tech/tags/word2vec.md>)

### AI overview

Qdrant 1.20 adds BM25 ranking directly on full-text indexes, deriving scoring statistics from payload text and allowing query-level tuning without generating embeddings; the new `code` tokenizer splits identifiers on underscores and case changes while retaining full identifiers. Per-element payload indexes can answer nested filters without payload reads when all conditions use indexed fields on the same array; a benchmark on 100,000 points found them 7-38 times faster than regular indexes with payload reads. New `turbo16` and `turbo8` datatypes reduce vector storage: reported tests found `turbo16` matched `float32` recall@10 within 0.001, while `turbo8` approached `float16` recall at half its size. The release also adds `bits8` quantization, memory-tier controls for the ID tracker, and internal cluster authentication by default when API keys are configured. Upgrades require attention to read-only-key clusters and memory tiers for inline storage, whose vectors now follow the HNSW index tier.

### Source excerpt

Qdrant 1.20.0 is out! Let's look at the main features for this version: BM25 on Full-Text Indexes and Code Search: Rank by BM25 straight from your payload text, with no embeddings to generate. Plus, better code search with a new code tokenizer. Faster Nested Filters: A new per-element payload index answers nested filters without reading payloads, making them faster. 16-Bit and 8-Bit TurboQuant: A 16-bit TurboQuant datatype that halves vector storage without accuracy loss, and an 8-bit TurboQuant datatype and quantization option with recall close to float16.

## Otter.ai raises $320M in funding for its AI meeting assistant

DevFeed: [Otter.ai raises $320M in funding for its AI meeting assistant](<https://devfeed.tech/articles/otter-ai-raises-320m-in-funding-for-its-ai-meeting-assistant-91389.md>)

Original publisher: [Read original article](<https://siliconangle.com/2026/10/20/otter-ai-raises-320m-in-funding-for-its-ai-meeting-assistant/>)

Author: Maria Deutscher

Published: 2026-10-20T22:24:09Z

Content type: news

Language: en

Sources: [SiliconANGLE](<https://devfeed.tech/sources/siliconangle.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [hubspot](<https://devfeed.tech/topics/hubspot.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [customer-value-fund](<https://devfeed.tech/tags/customer-value-fund.md>), [funding](<https://devfeed.tech/tags/funding.md>), [funding-round](<https://devfeed.tech/tags/funding-round.md>), [general-catalyst](<https://devfeed.tech/tags/general-catalyst.md>), [investment](<https://devfeed.tech/tags/investment.md>), [meeting-assistant](<https://devfeed.tech/tags/meeting-assistant.md>), [news](<https://devfeed.tech/tags/news.md>), [otter](<https://devfeed.tech/tags/otter.md>), [otter-ai](<https://devfeed.tech/tags/otter-ai.md>), [raises](<https://devfeed.tech/tags/raises.md>), [startup](<https://devfeed.tech/tags/startup.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>), [transcription](<https://devfeed.tech/tags/transcription.md>)

### AI overview

Otter.ai raised $320 million from General Catalyst's Customer Value Fund, which provides sales and marketing financing in exchange for a share of revenue it helps generate rather than an equity stake. Its assistant prepares users for meetings using agenda topics, prior conversations, and data from services such as HubSpot; it also creates speaker-labeled transcripts, incorporates slide and screen-sharing content, and produces summaries with action items. Users can organize and search files, sync them with cloud services, and make them available to chatbots through an MCP server. Role-specific features include sales follow-ups and demo booking, and study guides for teachers. The Enterprise edition adds conversation trend dashboards, expanded access controls, and single sign-on. The company says it has over 40 million users and plans to at least double its enterprise business over the next year by tripling its sales and marketing budget.

### Source excerpt

Otter.ai Inc., the developer of a popular artificial intelligence meeting assistant, today announced that it has raised $320 million in funding. The capital came entirely from General Catalyst's Customer Value Fund. The investment vehicle provides startups with financing for sales and marketing initiatives. General Catalyst doesn't take a stake in portfolio companies, but instead receives [...] The post Otter.ai raises $320M in funding for its AI meeting assistant appeared first on SiliconANGLE.

## From Static Help Content to a RAG-Based Onboarding Agent for Partners

DevFeed: [From Static Help Content to a RAG-Based Onboarding Agent for Partners](<https://devfeed.tech/articles/from-static-help-content-to-a-rag-based-onboarding-agent-for-partners-89968.md>)

Original publisher: [Read original article](<https://booking.ai/from-static-help-content-to-a-rag-based-onboarding-agent-for-partners-f7d5a789c4f7?source=rss----4d265f07defc---4>)

Author: Anastasiia Barchukova

Published: 2026-10-19T09:35:24Z

Content type: article

Language: en

Sources: [Booking.com Data Science](<https://devfeed.tech/sources/booking-com-data-science.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Conversational AI](<https://devfeed.tech/topics/conversational-ai.md>), [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [managing large-scale text data in AI](<https://devfeed.tech/topics/managing-large-scale-text-data-in-ai.md>), [human review](<https://devfeed.tech/topics/human-review.md>)

Tags: [account](<https://devfeed.tech/tags/account.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [backend](<https://devfeed.tech/tags/backend.md>), [booking](<https://devfeed.tech/tags/booking.md>), [business](<https://devfeed.tech/tags/business.md>), [chatbot](<https://devfeed.tech/tags/chatbot.md>), [content](<https://devfeed.tech/tags/content.md>), [context](<https://devfeed.tech/tags/context.md>), [conversational-ai](<https://devfeed.tech/tags/conversational-ai.md>), [featured](<https://devfeed.tech/tags/featured.md>), [help](<https://devfeed.tech/tags/help.md>), [onboarding](<https://devfeed.tech/tags/onboarding.md>), [partner](<https://devfeed.tech/tags/partner.md>), [partners](<https://devfeed.tech/tags/partners.md>), [platform](<https://devfeed.tech/tags/platform.md>), [process](<https://devfeed.tech/tags/process.md>), [quality](<https://devfeed.tech/tags/quality.md>), [questions](<https://devfeed.tech/tags/questions.md>), [rag](<https://devfeed.tech/tags/rag.md>), [responses](<https://devfeed.tech/tags/responses.md>)

### AI overview

Booking.com's onboarding agent improved first-line task handling by fixing retrieval and routing issues rather than changing prompts. Audits found navigation noise, overly small chunks, and irrelevant partner-specific material in the help index; the ingestion process was updated to filter content, refine chunking, and expand retrieved context. The agent also uses separate retrievers for registration guidance and legally restricted questions, which receive pre-approved static answers instead of generated responses. In an online experiment scored across roughly 2,000 conversations, task-completion scores rose 1.33x, with answer relevance, refusal rate, and response reliability also improving. The task-completion measure reflects judge-assessed handling within scope, not confirmed end-to-end resolution; about 15% of older chatbot conversations lacked a required registration-status field and were excluded from the primary comparison.

### Source excerpt

Authors: Anastasiia Barchukova, Antonio Castelli, Artem Alimov, Kate Rasskazimova, Niels Ranzijn, Susanna Agababyan Every property on Booking.com is listed by a partner -- the person or business that owns or manages the place to stay. Some partners are self-managed: they sign up, list their property, and run it entirely on their own, without a dedicated account manager. For them, the registration process -- a multi-step flow where they create an account and describe their property -- is often where they get stuck, due to its length, unfamiliar terminology, and business-critical decisions they must make before they've learned how the platform works. To help self-managed partners get through registration on their own, we built a chatbot that answers their questions as they come up, without needing a human account manager. Our chatbot should therefore be deeply grounded in the context of the registration funnel, while also being capable of managing partner expectations by answering broader questions about the platform and what comes after registration. That is the problem this article is about. It describes the approach behind the next iteration of the solution: an agent embedded directly in the registration flow. By design, the assistant is scoped to answering partners' questions in context, grounded strictly in the partner help center content -- it does not generate free-form responses outside that knowledge base. The system at a glance At a high level, the chatbot sits inside the registration flow, routes requests through a dedicated backend layer, retrieves relevant help-center content, and uses the conversational AI platform to generate grounded responses. Figure 1 illustrates this simplified end-to-end architecture. Figure 1: Simplified architecture of the onboarding chatbot, showing the registration flow, chatbot service, help-content retrieval, response generation, and the feedback loop used to improve quality over time.Diagnosing before touching anything Already i

## Plan or Retrieve First? A Scale Study of Tool Discovery Architectures

DevFeed: [Plan or Retrieve First? A Scale Study of Tool Discovery Architectures](<https://devfeed.tech/articles/plan-or-retrieve-first-a-scale-study-of-tool-discovery-architectures-88212.md>)

Original publisher: [Read original article](<https://machinelearning.apple.com/research/plan-retrieve-tool-discovery>)

Published: 2026-10-15T00:00:00Z

Content type: article

Language: en

Sources: [Apple Machine Learning Research](<https://devfeed.tech/sources/apple-machine-learning-research.md>)

Topics: [AI search](<https://devfeed.tech/topics/ai-search.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>), [Vectors & LLMs](<https://devfeed.tech/topics/vectors-llms.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-agents](<https://devfeed.tech/tags/llm-agents.md>), [planning](<https://devfeed.tech/tags/planning.md>), [queries](<https://devfeed.tech/tags/queries.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [search](<https://devfeed.tech/tags/search.md>)

### AI overview

This paper compares Retrieve-then-Plan and Plan-then-Retrieve approaches for finding APIs for tool-augmented LLM agents. Retrieve-then-Plan performs better for single-tool queries, while Plan-then-Retrieve performs better for multi-tool queries; the latter's added discovery call roughly doubles inference cost. The findings motivate complexity-adaptive routing based on the top retrieval score.

### Source excerpt

Tool-augmented LLM agents discover relevant APIs from large registries before planning execution, yet finite context windows prohibit injecting all tool definitions into a single prompt. The dominant approach, which we term Retrieve-then-Plan (RtP), embeds the user query and retrieves similar tools via approximate nearest-neighbor search. We study an alternative Plan-then-Retrieve (PtR) paradigm in which the LLM first generates Abstract Tool Stubs (hypothesized function signatures describing needed capabilities) which then serve as retrieval queries against the registry. Evaluating on...

## How Tech Startups Can Improve Visibility in AI Search

DevFeed: [How Tech Startups Can Improve Visibility in AI Search](<https://devfeed.tech/articles/from-invisible-to-recomended-how-tech-startups-can-win-ai-search-65587.md>)

Original publisher: [Read original article](<https://hackernoon.com/from-invisible-to-recomended-how-tech-startups-can-win-ai-search?source=rss>)

Author: Nica Furs

Published: 2026-10-06T09:00:03Z

Content type: tutorial

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Search engine optimization (SEO)](<https://devfeed.tech/topics/seo.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [AI interaction best practices](<https://devfeed.tech/topics/ai-interaction-best-practices.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-citation](<https://devfeed.tech/tags/ai-citation.md>), [ai-code-search-indexing](<https://devfeed.tech/tags/ai-code-search-indexing.md>), [ai-recommendations](<https://devfeed.tech/tags/ai-recommendations.md>), [ai-search-optimization](<https://devfeed.tech/tags/ai-search-optimization.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [ai-visibility](<https://devfeed.tech/tags/ai-visibility.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [good-company](<https://devfeed.tech/tags/good-company.md>), [llm-citation-strategy](<https://devfeed.tech/tags/llm-citation-strategy.md>), [strategy](<https://devfeed.tech/tags/strategy.md>)

### AI overview

The article presents a five-step approach for helping tech startups appear in AI search recommendations: analyze category language, map relevant prompts and citation sources, keep brand claims consistent, earn third-party coverage, and track prompt coverage alongside conversion quality. It also provides a 90-day checklist for applying the process.

### Source excerpt

Learn how tech companies can improve AI search visibility through category strategy, third-party coverage, narrative consistency, GEO, and buyer-focused content

## Easily build a knowledge graph from your existing documents with Document Intelligence

DevFeed: [Easily build a knowledge graph from your existing documents with Document Intelligence](<https://devfeed.tech/articles/easily-build-a-knowledge-graph-from-your-existing-documents-with-document-intelligence-65299.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/graph-database/easily-build-a-kg-from-your-existing-documents-with-document-intelligence/>)

Author: corydon baylor

Published: 2026-10-06T07:01:00Z

Content type: release

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [auradb](<https://devfeed.tech/tags/auradb.md>), [connected-data](<https://devfeed.tech/tags/connected-data.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [entity-resolution](<https://devfeed.tech/tags/entity-resolution.md>), [graph-database](<https://devfeed.tech/tags/graph-database.md>), [graph-technology](<https://devfeed.tech/tags/graph-technology.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>), [release](<https://devfeed.tech/tags/release.md>)

### AI overview

Neo4j announces the general availability of Document Intelligence in AuraDB, a service that turns existing documents into knowledge graphs without code. The release adds processing for hundreds of documents per background job, extraction from images and tables, extension of existing graph models, and entity resolution against AuraDB data. An interactive assistant helps users propose and refine graph models; the resulting graph links extracted entities to source passages and stores chunk embeddings for similarity search. API, command-line, and Model Context Protocol access are described as planned extensions.

### Source excerpt

Today, we are announcing the upcoming release to general availability (GA) of Document Intelligence in Neo4j AuraDB on the Free, Professional, and Business Critical tiers. With Document Intelligence, you can build a knowledge graph from existing documents, including plain text... Read more ->

## Judge Dismisses Chegg and Penske Antitrust Lawsuits Targeting Google AI Search

DevFeed: [Judge Dismisses Chegg and Penske Antitrust Lawsuits Targeting Google AI Search](<https://devfeed.tech/articles/judge-dismisses-chegg-and-penske-antitrust-lawsuits-targeting-google-ai-search-64204.md>)

Original publisher: [Read original article](<https://tech.slashdot.org/story/26/10/02/0639218/judge-dismisses-chegg-and-penske-antitrust-lawsuits-targeting-google-ai-search>)

Author: BeauHD

Published: 2026-10-02T17:00:00Z

Content type: news

Language: en

Sources: [Slashdot](<https://devfeed.tech/sources/slashdot.md>)

Topics: [AI search](<https://devfeed.tech/topics/ai-search.md>), [DuckDuckGo](<https://devfeed.tech/topics/duckduckgo.md>), [Google](<https://devfeed.tech/topics/google.md>)

Tags: [ai-overviews](<https://devfeed.tech/tags/ai-overviews.md>), [antitrust](<https://devfeed.tech/tags/antitrust.md>), [chegg](<https://devfeed.tech/tags/chegg.md>), [doj](<https://devfeed.tech/tags/doj.md>), [google](<https://devfeed.tech/tags/google.md>), [google-ai](<https://devfeed.tech/tags/google-ai.md>), [law](<https://devfeed.tech/tags/law.md>), [lawsuit](<https://devfeed.tech/tags/lawsuit.md>), [penske-media](<https://devfeed.tech/tags/penske-media.md>), [running](<https://devfeed.tech/tags/running.md>), [search](<https://devfeed.tech/tags/search.md>)

### AI overview

A federal judge dismissed antitrust lawsuits by Chegg and Penske Media over Google's use of publisher content in AI Overviews and other AI search features. The judge said the publishers had no formal agreement with Google guaranteeing search traffic or compensation. Chegg had argued that Google used educational content to generate AI answers and reduce site traffic; Penske made a similar claim about its publications.

### Source excerpt

A federal judge has dismissed antitrust lawsuits from Chegg and Penske Media accusing Google of harming publishers by using their content in AI Overviews and other AI search features without compensating them or providing a meaningful opt-out. Ars Technica reports: The lawsuits were filed in 2025, and Google requested a dismissal earlier this year. Chegg, an education and learning platform, claimed in its lawsuit that Google illegally scraped its educational content. This allowed Gemini models to essentially recreate that content and reduce the site's traffic. Penske, which owns publications like Rolling Stone and Variety, filed a similar case that alleged lost traffic. Specifically, the publisher claimed it was unfair that sites indexed for organic search would also have their content harvested for AI answers, with no way to opt out. These arguments did not sway the judge, who noted that Google's implicit agreement with websites is not legally relevant. "Plaintiffs have pleaded only that they have an 'expectation' that Google will send them search "traffic if they make their content available for free," wrote Mehta. "But an expectation is not an agreement. It is simply how a general search engine works." Since Google never had a formal arrangement with either Chegg or Penske, antitrust law doesn't apply. And Mehta is aware of the legal issues surrounding search. He also heard the DOJ's long-running search antitrust case against Google, eventually finding that Google violated the law. However, the government didn't get the harsh penalties it wanted in that case. Read more of this story at Slashdot.

## Course teaches how to rebuild YouTube with AI

DevFeed: [Course teaches how to rebuild YouTube with AI](<https://devfeed.tech/articles/last-call-for-enrollment-rebuild-youtube-with-ai-60162.md>)

Original publisher: [Read original article](<https://blog.bytebytego.com/p/last-call-for-enrollment-rebuild>)

Author: ByteByteGo

Published: 2026-09-25T15:02:53Z

Content type: article

Language: en

Sources: [ByteByteGo](<https://devfeed.tech/sources/bytebytego.md>)

Topics: [AI Development](<https://devfeed.tech/topics/ai-development.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [App](<https://devfeed.tech/topics/app.md>), [React](<https://devfeed.tech/topics/react.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [recommendation systems](<https://devfeed.tech/topics/recommendation-systems.md>), [Playwright](<https://devfeed.tech/topics/playwright.md>), [Vercel](<https://devfeed.tech/topics/vercel.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [dashboards](<https://devfeed.tech/topics/dashboards.md>), [Authentication](<https://devfeed.tech/topics/authentication.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-development](<https://devfeed.tech/tags/ai-development.md>), [ai-engineering](<https://devfeed.tech/tags/ai-engineering.md>), [app](<https://devfeed.tech/tags/app.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [dashboard](<https://devfeed.tech/tags/dashboard.md>), [development](<https://devfeed.tech/tags/development.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [playwright](<https://devfeed.tech/tags/playwright.md>), [react](<https://devfeed.tech/tags/react.md>), [recommendation-systems](<https://devfeed.tech/tags/recommendation-systems.md>), [vercel](<https://devfeed.tech/tags/vercel.md>)

### AI overview

A live course teaches participants to scope a YouTube-style MVP, work with coding agents, build React and backend features, add semantic search and related videos, test with Playwright, and deploy to Vercel.

### Source excerpt

Rebuild YouTube with AI, taught by a former YouTube engineer, kicks off on Saturday, September 26. Enrollment closes in 24 hours.

## Building Multi-Tier AI Agent Memory with TypeScript and SQLite-vec

DevFeed: [Building Multi-Tier AI Agent Memory with TypeScript and SQLite-vec](<https://devfeed.tech/articles/building-multi-tier-ai-agent-memory-with-typescript-and-sqlite-vec-59913.md>)

Original publisher: [Read original article](<https://www.sitepoint.com/multi-tier-ai-agent-memory-typescript-sqlite-vec/>)

Author: SitePoint Team

Published: 2026-09-25T14:51:34Z

Content type: tutorial

Language: en

Sources: [SitePoint](<https://devfeed.tech/sources/sitepoint.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [SQLite](<https://devfeed.tech/topics/sqlite.md>), [TypeScript](<https://devfeed.tech/topics/typescript.md>), [Node.js](<https://devfeed.tech/topics/node-js.md>), [Database](<https://devfeed.tech/topics/database.md>), [Local-First](<https://devfeed.tech/topics/local-first.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [Persistence](<https://devfeed.tech/topics/persistence.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [database](<https://devfeed.tech/tags/database.md>), [databases](<https://devfeed.tech/tags/databases.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [guides](<https://devfeed.tech/tags/guides.md>), [local-first](<https://devfeed.tech/tags/local-first.md>), [node-js](<https://devfeed.tech/tags/node-js.md>), [persistence](<https://devfeed.tech/tags/persistence.md>), [programming](<https://devfeed.tech/tags/programming.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [sqlite](<https://devfeed.tech/tags/sqlite.md>), [typescript](<https://devfeed.tech/tags/typescript.md>)

### AI overview

A tutorial for building a local, multi-tier memory system for AI agents with TypeScript, SQLite, better-sqlite3, and sqlite-vec. It implements episodic, semantic, and procedural memory in one database and connects the stores to an agent loop.

### Source excerpt

Architect a tiered local memory system for AI agents using TypeScript, better-sqlite3, and sqlite-vec across episodic, semantic, and procedural stores. Continue reading Building Multi-Tier AI Agent Memory with TypeScript and SQLite-vec on SitePoint.

## Oracle AI Vector Search & Native AI: The Converged Database Era

DevFeed: [Oracle AI Vector Search & Native AI: The Converged Database Era](<https://devfeed.tech/articles/oracle-ai-vector-search-native-ai-the-converged-database-era-59967.md>)

Original publisher: [Read original article](<https://hackernoon.com/oracle-ai-vector-search-and-native-ai-the-converged-database-era?source=rss>)

Author: Arvind Toorpu

Published: 2026-09-25T06:37:25Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Database](<https://devfeed.tech/topics/database.md>), [Oracle Database](<https://devfeed.tech/topics/oracle-database.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [SQL](<https://devfeed.tech/topics/sql.md>), [Transactions](<https://devfeed.tech/topics/transactions.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-vector-search](<https://devfeed.tech/tags/ai-vector-search.md>), [database](<https://devfeed.tech/tags/database.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [indexes](<https://devfeed.tech/tags/indexes.md>), [oracle](<https://devfeed.tech/tags/oracle.md>), [oracle-23ai](<https://devfeed.tech/tags/oracle-23ai.md>), [oracle-26ai](<https://devfeed.tech/tags/oracle-26ai.md>), [oracle-ai-database](<https://devfeed.tech/tags/oracle-ai-database.md>), [oracle-database](<https://devfeed.tech/tags/oracle-database.md>), [oracle-vector-search](<https://devfeed.tech/tags/oracle-vector-search.md>), [queries](<https://devfeed.tech/tags/queries.md>), [rdbms](<https://devfeed.tech/tags/rdbms.md>), [types](<https://devfeed.tech/tags/types.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vector-database](<https://devfeed.tech/tags/vector-database.md>)

### AI overview

The article explains Oracle 23ai's converged database approach, including native VECTOR data types, SQL integration, supported vector formats, dense and sparse vectors, and HNSW and IVF indexing. It presents these capabilities as a way to reduce fragmentation across relational, vector, search, and graph systems.

### Source excerpt

Oracle 23ai brings native VECTOR types, HNSW/IVF indexes, and SELECT AI for natural language queries.

## Jev Uses Typed Decision Models to Route and Filter Retrieval Before Generative AI

DevFeed: [Jev Uses Typed Decision Models to Route and Filter Retrieval Before Generative AI](<https://devfeed.tech/articles/how-jev-can-revolutionize-search-across-domains-and-what-it-would-mean-for-web-search-59962.md>)

Original publisher: [Read original article](<https://hackernoon.com/how-jev-can-revolutionize-search-across-domains-and-what-it-would-mean-for-web-search?source=rss>)

Author: krishna dutt

Published: 2026-09-25T06:36:52Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Computing](<https://devfeed.tech/topics/computing.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-systems](<https://devfeed.tech/tags/ai-systems.md>), [cloud-computing](<https://devfeed.tech/tags/cloud-computing.md>), [genai](<https://devfeed.tech/tags/genai.md>), [genai-for-software-engineering](<https://devfeed.tech/tags/genai-for-software-engineering.md>), [multi-agent-systems](<https://devfeed.tech/tags/multi-agent-systems.md>), [rag](<https://devfeed.tech/tags/rag.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [search](<https://devfeed.tech/tags/search.md>), [software-architecture](<https://devfeed.tech/tags/software-architecture.md>), [software-development](<https://devfeed.tech/tags/software-development.md>), [systems-thinking](<https://devfeed.tech/tags/systems-thinking.md>)

### AI overview

The article presents TypeSafe's Jev as a typed decision engine for making fast, parallel choices, scores, and probabilities before generative AI runs. In a RAG pipeline, Jev can route queries, rank document relevance, filter low-value results, and provide only the strongest context to an LLM.

### Source excerpt

Jev is a decision engine that evaluates typed questions in a single, parallel sweep, spitting out choices, scores, or probabilities.

## For MariaDB, LLMs are the new search engines to win over

DevFeed: [For MariaDB, LLMs are the new search engines to win over](<https://devfeed.tech/articles/for-mariadb-llms-are-the-new-search-engines-to-win-over-59491.md>)

Original publisher: [Read original article](<https://www.theregister.com/databases/2026/09/24/for-mariadb-llms-are-the-new-search-engines-to-win-over/5298104>)

Author: Richard Speed

Published: 2026-09-24T10:00:00Z

Content type: article

Language: en

Sources: [theregister](<https://devfeed.tech/sources/www-theregister-com-articles.md>)

Topics: [MariaDB](<https://devfeed.tech/topics/mariadb.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>)

Tags: [ai-and-ml](<https://devfeed.tech/tags/ai-and-ml.md>), [databases](<https://devfeed.tech/tags/databases.md>), [developers](<https://devfeed.tech/tags/developers.md>), [large-language-model](<https://devfeed.tech/tags/large-language-model.md>), [llms](<https://devfeed.tech/tags/llms.md>), [mariadb](<https://devfeed.tech/tags/mariadb.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [search](<https://devfeed.tech/tags/search.md>)

### AI overview

MariaDB is positioning its vector search capabilities for the rise of large language models, while coding assistants continue directing developers toward other databases.

### Source excerpt

Its vector search is ready, but coding assistants keep pointing developers toward other databases, says the foundation's chairman

## Rescored binary vector search in Neo4j: search more with less memory

DevFeed: [Rescored binary vector search in Neo4j: search more with less memory](<https://devfeed.tech/articles/rescored-binary-vector-search-in-neo4j-search-more-with-less-memory-58774.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/genai/rescored-binary-vector-search-in-neo4j-search-more-with-less-memory/>)

Author: Jocelyn Hoppa

Published: 2026-09-23T11:06:00Z

Content type: article

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [quantization](<https://devfeed.tech/topics/quantization.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [Database](<https://devfeed.tech/topics/database.md>), [Less](<https://devfeed.tech/topics/less.md>)

Tags: [developer](<https://devfeed.tech/tags/developer.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [genai](<https://devfeed.tech/tags/genai.md>), [latency](<https://devfeed.tech/tags/latency.md>), [memory](<https://devfeed.tech/tags/memory.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>), [performance](<https://devfeed.tech/tags/performance.md>), [quantization](<https://devfeed.tech/tags/quantization.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [semantic-search](<https://devfeed.tech/tags/semantic-search.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>)

### AI overview

This article explains how Neo4j's rescored binary quantization reduces the memory required for vector search while maintaining retrieval performance. It describes expanded searches over compressed vectors followed by full-precision rescoring, and outlines available quantization modes in Neo4j 2026.09.

### Source excerpt

As an AI application grows, its embeddings can quickly become one of its largest demands on memory. More documents, finer-grained chunks and richer embedding models all increase the amount of vector data your database needs to search. Keeping retrieval fast... Read more ->

## Vector Search Is Now A Data Type, But The Money Math Has Not Gone Away

DevFeed: [Vector Search Is Now A Data Type, But The Money Math Has Not Gone Away](<https://devfeed.tech/articles/vector-search-is-now-a-data-type-but-the-money-math-has-not-gone-away-58281.md>)

Original publisher: [Read original article](<https://www.nextplatform.com/store/2026/09/22/vector-search-is-now-a-data-type-but-the-money-math-has-not-gone-away/5298393>)

Author: Itamar Syn-Hershko

Published: 2026-09-22T17:06:09Z

Content type: opinion

Language: en

Sources: [The Next Platform: In-depth coverage of high end computing](<https://devfeed.tech/sources/the-next-platform-in-depth-coverage-of-high-end-computing.md>)

Topics: [AI search](<https://devfeed.tech/topics/ai-search.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [elasticsearch](<https://devfeed.tech/topics/elasticsearch.md>), [Database](<https://devfeed.tech/topics/database.md>), [Algorithms](<https://devfeed.tech/topics/algorithms.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ann](<https://devfeed.tech/tags/ann.md>), [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [database](<https://devfeed.tech/tags/database.md>), [elasticsearch](<https://devfeed.tech/tags/elasticsearch.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [hnsw](<https://devfeed.tech/tags/hnsw.md>), [opensearch](<https://devfeed.tech/tags/opensearch.md>), [store](<https://devfeed.tech/tags/store.md>), [vector](<https://devfeed.tech/tags/vector.md>), [vector-database](<https://devfeed.tech/tags/vector-database.md>), [vector-search](<https://devfeed.tech/tags/vector-search.md>)

### AI overview

The article argues that vector search is increasingly implemented as a data type and approximate nearest-neighbor index inside existing databases rather than through separate vector databases. It explains that consolidation reduces operational overhead but does not eliminate the cost of storing, compressing, and keeping embeddings in memory, and it describes the adoption of HNSW across major database and search platforms.

### Source excerpt

For a few years it looked like every AI stack would carry a dedicated vector database next to its pr ...

## Testing RAG Retrieval with Adversarial Failures in Production Document Collections

DevFeed: [Testing RAG Retrieval with Adversarial Failures in Production Document Collections](<https://devfeed.tech/articles/break-your-own-rag-pipeline-before-users-do-58026.md>)

Original publisher: [Read original article](<https://towardsdatascience.com/break-your-own-rag-pipeline-before-users-do/>)

Author: Sara Nobrega

Published: 2026-09-22T15:30:01Z

Content type: article

Language: en

Sources: [Towards Data Science](<https://devfeed.tech/sources/towards-data-science.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [Chaos Engineering](<https://devfeed.tech/topics/chaos-engineering.md>)

Tags: [adversarial](<https://devfeed.tech/tags/adversarial.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-engineer](<https://devfeed.tech/tags/ai-engineer.md>), [articial-intelligence](<https://devfeed.tech/tags/articial-intelligence.md>), [editor-s-picks](<https://devfeed.tech/tags/editor-s-picks.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-evaluation](<https://devfeed.tech/tags/llm-evaluation.md>), [rag](<https://devfeed.tech/tags/rag.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>)

### AI overview

This article demonstrates how to test retrieval-augmented generation systems against realistic document-collection failures. It uses a small retriever and fault injection to expose errors caused by stale documents, OCR mistakes, query typos, and tables split across pages.

### Source excerpt

A small adversarial test set that catches the retrieval failures your evaluation set never will The post Break Your Own RAG Pipeline Before Users Do appeared first on Towards Data Science.

## The AI application your team can actually stand behind

DevFeed: [The AI application your team can actually stand behind](<https://devfeed.tech/articles/the-ai-application-your-team-can-actually-stand-behind-59423.md>)

Original publisher: [Read original article](<https://neo4j.com/blog/genai/the-ai-application-your-team-can-actually-stand-behind/>)

Author: Jocelyn Hoppa

Published: 2026-09-21T18:17:00Z

Content type: article

Language: en

Sources: [Neo4j](<https://devfeed.tech/sources/graph-database-technology-neo4j-blog.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Neo4j](<https://devfeed.tech/topics/neo4j.md>), [Graphs](<https://devfeed.tech/topics/graphs.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [Python](<https://devfeed.tech/topics/python.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [context](<https://devfeed.tech/tags/context.md>), [developer](<https://devfeed.tech/tags/developer.md>), [genai](<https://devfeed.tech/tags/genai.md>), [graphrag](<https://devfeed.tech/tags/graphrag.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [neo4j](<https://devfeed.tech/tags/neo4j.md>), [neo4j-graph-database](<https://devfeed.tech/tags/neo4j-graph-database.md>), [python](<https://devfeed.tech/tags/python.md>), [search](<https://devfeed.tech/tags/search.md>)

### AI overview

This article explains how to build more accurate and auditable generative AI applications by grounding large language model responses in a Neo4j knowledge graph. It describes a structured data layer, feedback loops for measuring answer quality, the Neo4j GraphRAG Python package, and the Needle StarterKit for building chatbot front ends.

### Source excerpt

The demo looked great. Stakeholders were impressed. Then someone asked the chatbot a real question -- and it gave a confident, wrong answer. Now you're fielding emails, your team is manually reviewing outputs, and the question you dread most is the one... Read more ->

## GraphRAG: A Practitioner's Guide to 6 Advanced Architectural Patterns

DevFeed: [GraphRAG: A Practitioner's Guide to 6 Advanced Architectural Patterns](<https://devfeed.tech/articles/graphrag-a-practitioner-s-guide-to-6-advanced-architectural-patterns-56881.md>)

Original publisher: [Read original article](<https://towardsdatascience.com/graphrag-a-practitioners-guide-to-6-advanced-architectural-patterns/>)

Author: Partha Sarkar

Published: 2026-09-20T15:00:01Z

Content type: tutorial

Language: en

Sources: [Towards Data Science](<https://devfeed.tech/sources/towards-data-science.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [Graphs](<https://devfeed.tech/topics/graphs.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [data](<https://devfeed.tech/topics/data.md>), [ner](<https://devfeed.tech/topics/ner.md>)

Tags: [architectures](<https://devfeed.tech/tags/architectures.md>), [editor-s-picks](<https://devfeed.tech/tags/editor-s-picks.md>), [graphrag](<https://devfeed.tech/tags/graphrag.md>), [guide](<https://devfeed.tech/tags/guide.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [llm-engineering](<https://devfeed.tech/tags/llm-engineering.md>), [llm-reasoning](<https://devfeed.tech/tags/llm-reasoning.md>), [practitioner](<https://devfeed.tech/tags/practitioner.md>), [rag](<https://devfeed.tech/tags/rag.md>), [rag-architecture](<https://devfeed.tech/tags/rag-architecture.md>), [retrieval](<https://devfeed.tech/tags/retrieval.md>), [semantic-search](<https://devfeed.tech/tags/semantic-search.md>)

### AI overview

This practitioner-focused guide presents six production-oriented GraphRAG architectural patterns. It explains how combining semantic retrieval with knowledge graphs can address complex queries involving global context, multi-hop reasoning, and cross-document aggregation, and outlines core pipeline components such as information extraction and graph storage.

### Source excerpt

Beyond basic graph retrieval: six production-oriented architectures for combining semantic search, knowledge graphs, and LLM reasoning. The post GraphRAG: A Practitioner's Guide to 6 Advanced Architectural Patterns appeared first on Towards Data Science.

## Selecting a vector store for Amazon Bedrock Knowledge Bases

DevFeed: [Selecting a vector store for Amazon Bedrock Knowledge Bases](<https://devfeed.tech/articles/selecting-a-vector-store-for-amazon-bedrock-knowledge-bases-42134.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/selecting-a-vector-store-for-amazon-bedrock-knowledge-bases/>)

Author: Deepak Dalakoti

Published: 2026-09-17T15:53:13Z

Content type: comparison

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [Amazon S3](<https://devfeed.tech/topics/amazon-s3.md>), [PostgreSQL](<https://devfeed.tech/topics/postgresql.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-knowledge-bases](<https://devfeed.tech/tags/amazon-bedrock-knowledge-bases.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [amazon-s3](<https://devfeed.tech/tags/amazon-s3.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [cost](<https://devfeed.tech/tags/cost.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [performance](<https://devfeed.tech/tags/performance.md>), [pgvector](<https://devfeed.tech/tags/pgvector.md>), [postgresql](<https://devfeed.tech/tags/postgresql.md>), [rag](<https://devfeed.tech/tags/rag.md>), [vector](<https://devfeed.tech/tags/vector.md>)

### AI overview

This comparison explains how to choose a customer-managed vector store for Amazon Bedrock Knowledge Bases RAG applications. It evaluates Amazon OpenSearch Service, Amazon Aurora PostgreSQL with pgvector, and Amazon S3 Vectors across three RAG use cases, focusing on performance, cost, benchmarks, and practical selection criteria.

### Source excerpt

Choosing the right vector store for your Amazon Bedrock Knowledge Bases RAG application affects performance and cost. This post compares Amazon OpenSearch Service, Amazon Aurora PostgreSQL with pgvector, and Amazon S3 Vectors across three RAG use cases, with benchmarks and a practical selection framework.

[Next page](<https://devfeed.tech/topics/ai-search.md?cursor=WyIyMDI2LTA5LTE3VDE1OjUzOjEzKzAwOjAwIiwgImNiMWU0MTNkLWZlYTQtNGFiOC1iMWVkLWE1ODZhMGZiZTZhYyJd>)