# querying

Published articles for querying.

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

## What Is Tool Calling? How LLMs and AI Agents Take Action

DevFeed: [What Is Tool Calling? How LLMs and AI Agents Take Action](<https://devfeed.tech/articles/what-is-tool-calling-how-llms-and-ai-agents-take-action-145886.md>)

Original publisher: [Read original article](<https://montecarlo.ai/blog-what-is-tool-calling>)

Author: Virna Sekuj

Published: 2026-11-19T16:58:24Z

Content type: article

Language: en

Sources: [Monte Carlo](<https://devfeed.tech/sources/monte-carlo.md>)

Topics: [function calling](<https://devfeed.tech/topics/function-calling.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [API](<https://devfeed.tech/topics/api.md>), [Tool](<https://devfeed.tech/topics/tool.md>)

Tags: [2023](<https://devfeed.tech/tags/2023.md>), [2026](<https://devfeed.tech/tags/2026.md>), [actions](<https://devfeed.tech/tags/actions.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-behavior](<https://devfeed.tech/tags/agent-behavior.md>), [agent-frameworks](<https://devfeed.tech/tags/agent-frameworks.md>), [agent-trust](<https://devfeed.tech/tags/agent-trust.md>), [agent-trust-glossary](<https://devfeed.tech/tags/agent-trust-glossary.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [api](<https://devfeed.tech/tags/api.md>), [database](<https://devfeed.tech/tags/database.md>), [function](<https://devfeed.tech/tags/function.md>), [function-calling](<https://devfeed.tech/tags/function-calling.md>), [glossary](<https://devfeed.tech/tags/glossary.md>), [large-language-model](<https://devfeed.tech/tags/large-language-model.md>), [llm-tool-calling](<https://devfeed.tech/tags/llm-tool-calling.md>), [llms](<https://devfeed.tech/tags/llms.md>), [querying](<https://devfeed.tech/tags/querying.md>), [searching](<https://devfeed.tech/tags/searching.md>), [structured](<https://devfeed.tech/tags/structured.md>), [tool-calling](<https://devfeed.tech/tags/tool-calling.md>), [tool-calling-examples](<https://devfeed.tech/tags/tool-calling-examples.md>), [tool-calling-vs-mcp](<https://devfeed.tech/tags/tool-calling-vs-mcp.md>), [tool-use-ai-agents](<https://devfeed.tech/tags/tool-use-ai-agents.md>), [uses](<https://devfeed.tech/tags/uses.md>)

### AI overview

Tool calling lets an LLM request an action by returning a structured tool name and arguments; the application validates and executes the request, sends back the result, and the model uses it to answer or make another call. Function calling and tool use are alternate names for the same mechanism. MCP standardizes how compatible applications discover and connect to tools; it builds on tool calling rather than replacing it. Calls can fail through wrong tool choice, bad arguments, skipped checks, retries, mishandled errors, changed responses, or unintended access, often without obvious errors. The text recommends tracing each call and its result, validating arguments and permissions before execution, watching for unexpected patterns and loops, tracking cost and latency, monitoring the underlying data, and limiting or requiring approval for high-impact actions.

### Source excerpt

Tool calling, also called function calling, is how a large language model asks an application to run a function, such as querying a database, calling an API, or searching documents, and then uses the result in its answer. The model doesn't run the tool itself. It produces a structured request naming the tool and its arguments, the application executes it, and the result goes back to the model.

## ProvCards: Artifact-Oriented Provenance for Heterogeneous Scientific Workflows

DevFeed: [ProvCards: Artifact-Oriented Provenance for Heterogeneous Scientific Workflows](<https://devfeed.tech/articles/provcards-artifact-oriented-provenance-for-heterogeneous-scientific-workflows-142291.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24894>)

Author: Tanja Auge, Marinus Holitschke, Meike Klettke

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>)

Topics: [reproducibility](<https://devfeed.tech/topics/reproducibility.md>), [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [RDF (Resource Description Framework)](<https://devfeed.tech/topics/rdf.md>)

Tags: [cs-db](<https://devfeed.tech/tags/cs-db.md>), [data-processing](<https://devfeed.tech/tags/data-processing.md>), [provenance](<https://devfeed.tech/tags/provenance.md>), [querying](<https://devfeed.tech/tags/querying.md>), [reproducibility](<https://devfeed.tech/tags/reproducibility.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

ProvCards captures workflow provenance as portable artifacts grounded in the W3C PROV Data Model. Components can independently create, exchange, reuse, and compose cards without relying on a particular workflow system or centralized execution context. ProvDecks group related cards while preserving their identities; derived ProvGraphs support reconstruction, querying, visualization, and analysis. A graph-based implementation evaluated in a scientific data-processing workflow demonstrated component-level capture, cross-component composition, and reconstruction. The evidence is limited to the abstract and does not specify comparative performance or broader evaluation results.

### Source excerpt

arXiv:2611.24894v1 Announce Type: new Abstract: Reproducibility in scientific workflows is hindered by heterogeneous components and execution environments, as well as fragmented provenance capture. Although existing approaches offer established semantics and workflow-specific solutions, provenance remains difficult to capture, exchange, and compose across workflow boundaries. We present ProvCards, an artifact-oriented approach that treats provenance as a first-class artifact grounded in the W3C PROV Data Model. Individual workflow components can generate cards that are stored, exchanged, reused, and composed independently of any workflow system or centralized execution context. ProvDecks group related cards into portable scopes while preserving their identities. ProvGraphs provide derived views for provenance reconstruction, querying, visualization, and analysis. Together, these representations support coherent, task-specific provenance views across heterogeneous components, facilitating traceability, reuse, and reproducibility. We implement ProvCards using a graph-based infrastructure and evaluate them in a scientific data-processing workflow. The results demonstrate independent provenance capture at the component level, composition across component boundaries, and reconstruction for querying and analysis. ProvCards provide a portable, composable, and incrementally extensible foundation for provenance management in heterogeneous scientific workflows.

## Asking but Missing: Decision Coverage in Natural-Language Data Querying

DevFeed: [Asking but Missing: Decision Coverage in Natural-Language Data Querying](<https://devfeed.tech/articles/asking-but-missing-decision-coverage-in-natural-language-data-querying-142199.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23864>)

Author: Hangle Hu, Chenyu Hou, Bin Cao, Jing Fan, Wei Luo

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

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

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>)

Tags: [code-generation](<https://devfeed.tech/tags/code-generation.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [data](<https://devfeed.tech/tags/data.md>), [decision](<https://devfeed.tech/tags/decision.md>), [errors](<https://devfeed.tech/tags/errors.md>), [execution](<https://devfeed.tech/tags/execution.md>), [framework](<https://devfeed.tech/tags/framework.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [querying](<https://devfeed.tech/tags/querying.md>)

### AI overview

The study finds that natural-language data querying models often fail to recognize when a question needs clarification, silently choosing an interpretation that can produce incorrect code. It calls this Underspecified Decision Completion (UDC) and introduces Grounded Code Generation (GCG), which separately diagnoses whether unresolved decisions were identified, resolved using evidence, and translated into executable code. Evaluation of 12 models on BIRD-Pandas found that answering clarification questions consistently improves execution accuracy, but substantial errors remain; the key difficulty appears to be deciding which questions to ask.

### Source excerpt

arXiv:2611.23864v1 Announce Type: cross Abstract: Large language models are increasingly used to translate natural language questions about structured data into executable programs. A fundamental challenge is recognizing when a question admits multiple computational interpretations and identifying the decisions needed to resolve them. We investigate whether language models recognize these unresolved decisions before generating code, or silently adopt assumptions that may lead to incorrect results. We refer to the latter behavior as Underspecified Decision Completion (UDC). To distinguish different causes of UDC, we introduce Grounded Code Generation (GCG), a diagnostic protocol that separates the identification of unresolved decisions, their resolution using evidence, and their translation into executable code. By examining each stage separately, we can determine where the decisions responsible for incorrect results were first missed or mishandled. We evaluate this framework on BIRD-Pandas with twelve models. The results show that answering clarification questions consistently improves execution accuracy, yet substantial errors remain. Our findings suggest that the main difficulty lies not in answering clarification questions, but in recognizing which questions need to be asked in the first place.

## Build2SPARQL: A Large-Scale Text-to-SPARQL Benchmark Dataset for Building Knowledge Graph Querying

DevFeed: [Build2SPARQL: A Large-Scale Text-to-SPARQL Benchmark Dataset for Building Knowledge Graph Querying](<https://devfeed.tech/articles/build2sparql-a-large-scale-text-to-sparql-benchmark-dataset-for-building-knowledge-graph-querying-137288.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.00224>)

Author: Wooyoung Jung

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

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

Topics: [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [AI for SQL query generation](<https://devfeed.tech/topics/ai-for-sql-query-generation.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [база знаний](<https://devfeed.tech/topics/tag-c51cc4bf76e5.md>)

Tags: [automation](<https://devfeed.tech/tags/automation.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmark-dataset](<https://devfeed.tech/tags/benchmark-dataset.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [building](<https://devfeed.tech/tags/building.md>), [building-automation](<https://devfeed.tech/tags/building-automation.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [generate](<https://devfeed.tech/tags/generate.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graphs](<https://devfeed.tech/tags/graphs.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [language](<https://devfeed.tech/tags/language.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [ontologies](<https://devfeed.tech/tags/ontologies.md>), [querying](<https://devfeed.tech/tags/querying.md>)

### AI overview

Build2SPARQL addresses the shortage of natural-language/SPARQL benchmarks for building knowledge graphs with a pipeline that generates and validates queries through graph traversal, leaving language models to phrase the questions. Across 201 Brick and ASHRAE 223P graphs, it produced 6,136 executable queries and 30,680 questions covering six query-pattern families and five vocabulary registers. Two raters assessed 300 questions, finding 98.8% semantic fidelity and naturalness and 84.0% operational plausibility. In evaluations of three open-weight models, retrieval-augmented three-shot prompting raised exact-match accuracy from 0.2-20% zero-shot to 56-65%. These figures describe the benchmark and reported evaluation; the excerpt does not establish broader deployment performance.

### Source excerpt

arXiv:2610.00224v2 Announce Type: replace Abstract: Building automation systems are increasingly represented as semantic knowledge graphs (KGs) using ontologies such as Brick and ASHRAE 223P, creating a machine-readable substrate for artificial-intelligence applications. One promising application is translating natural-language questions into SPARQL (text-to-SPARQL), which would let building operators query these graphs through language agents, but progress is limited by the scarcity of large natural-language/SPARQL benchmarks. This paper presents Build2SPARQL, a large-scale benchmark for building KGs generated by a KG-grounded pipeline: SPARQL queries are produced and validated entirely by graph-traversal code, while large language models generate only the natural-language questions, keeping query correctness independent of model behavior. The pipeline mines six query-pattern families -- linear chains, branching, UNION, aggregation, OPTIONAL, and attribute-filtered -- and phrases each query across five vocabulary registers. Applied to 201 building KGs (180 Brick, 21 ASHRAE 223P), it yields 6,136 executable SPARQL queries and 30,680 questions. A two-rater human validation of 300 questions found 98.8% semantic fidelity, 98.8% naturalness, and 84.0% operational plausibility. A retrieval-augmented evaluation across three open-weight language models raised exact-match accuracy from 0.2-20% (zero-shot) to 56-65% (three-shot retrieved).

## How Are Companies Handling AI Governance in Practice?

DevFeed: [How Are Companies Handling AI Governance in Practice?](<https://devfeed.tech/articles/how-are-companies-handling-ai-governance-in-practice-133240.md>)

Original publisher: [Read original article](<https://www.starburst.io/blog/how-are-companies-handling-ai-governance-in-practice>)

Published: 2026-11-13T05:00:24Z

Content type: article

Language: en

Sources: [Starburst Data](<https://devfeed.tech/sources/starburst-data.md>)

Topics: [ai-governance](<https://devfeed.tech/topics/ai-governance.md>), [Sovereign AI](<https://devfeed.tech/topics/sovereign-ai.md>)

Tags: [access-controls](<https://devfeed.tech/tags/access-controls.md>), [act](<https://devfeed.tech/tags/act.md>), [added](<https://devfeed.tech/tags/added.md>), [adoption](<https://devfeed.tech/tags/adoption.md>), [after](<https://devfeed.tech/tags/after.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-application](<https://devfeed.tech/tags/ai-application.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [ai-projects](<https://devfeed.tech/tags/ai-projects.md>), [ai-prompts](<https://devfeed.tech/tags/ai-prompts.md>), [ai-ready-data](<https://devfeed.tech/tags/ai-ready-data.md>), [allowed](<https://devfeed.tech/tags/allowed.md>), [easy](<https://devfeed.tech/tags/easy.md>), [governance](<https://devfeed.tech/tags/governance.md>), [querying](<https://devfeed.tech/tags/querying.md>), [write](<https://devfeed.tech/tags/write.md>)

### AI overview

The article's central recommendation is to enforce AI governance at the data access layer, where each agent query can be checked against role, purpose, and permission and recorded for audit. It describes four practices: federated access to govern data across cloud and on-premises systems without first centralizing it; shared business context and definitions for agents and analysts; read-only defaults, RBAC/ABAC, and detailed audit trails; and designing around sovereignty, residency, privacy, and risk-based regulatory requirements from the start. Guardrails add a separate behavioral layer: they complement row- and column-level access controls by limiting prompts, topics, or agent and data-product behavior. The text reports that structured business context raised one foundation model's enterprise-question accuracy from roughly 50% to over 90%, while providing no details on how that result was measured.

### Source excerpt

AI governance is easy to write down and hard to enforce once agents start querying ...

## No pipeline, no second copy: Querying Amazon S3 from Elasticsearch with ES|QL

DevFeed: [No pipeline, no second copy: Querying Amazon S3 from Elasticsearch with ES|QL](<https://devfeed.tech/articles/no-pipeline-no-second-copy-querying-amazon-s3-from-elasticsearch-with-es-ql-130587.md>)

Original publisher: [Read original article](<https://www.elastic.co/search-labs/blog/query-amazon-s3-esql-data-federation>)

Author: Udayasimha Theepireddy,Srinivas Pendyala

Published: 2026-11-11T17:00:00Z

Content type: tutorial

Language: en

Sources: [Elasticsearch Labs](<https://devfeed.tech/sources/elasticsearch-labs.md>)

Topics: [elasticsearch](<https://devfeed.tech/topics/elasticsearch.md>), [Amazon S3](<https://devfeed.tech/topics/amazon-s3.md>), [kibana](<https://devfeed.tech/topics/kibana.md>), [Parquet files in Amazon S3](<https://devfeed.tech/topics/parquet-files-in-amazon-s3.md>), [etl](<https://devfeed.tech/topics/etl.md>), [Elastic Cloud](<https://devfeed.tech/topics/elastic-cloud.md>), [Data pipelines](<https://devfeed.tech/topics/data-pipelines.md>), [VPC Flow Logs](<https://devfeed.tech/topics/vpc-flow-logs.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-s3](<https://devfeed.tech/tags/amazon-s3.md>), [aws](<https://devfeed.tech/tags/aws.md>), [copy](<https://devfeed.tech/tags/copy.md>), [credentials](<https://devfeed.tech/tags/credentials.md>), [data](<https://devfeed.tech/tags/data.md>), [data-federation](<https://devfeed.tech/tags/data-federation.md>), [elasticsearch](<https://devfeed.tech/tags/elasticsearch.md>), [es-ql](<https://devfeed.tech/tags/es-ql.md>), [federated](<https://devfeed.tech/tags/federated.md>), [identity](<https://devfeed.tech/tags/identity.md>), [index](<https://devfeed.tech/tags/index.md>), [integrations](<https://devfeed.tech/tags/integrations.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [query](<https://devfeed.tech/tags/query.md>), [querying](<https://devfeed.tech/tags/querying.md>), [s3](<https://devfeed.tech/tags/s3.md>), [source](<https://devfeed.tech/tags/source.md>), [syntax](<https://devfeed.tech/tags/syntax.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

ES|QL Data Federation lets Elasticsearch query Parquet, CSV, TSV, and NDJSON files in Amazon S3 using the usual `FROM` syntax, without copying data into the cluster or defining mappings. It infers schemas from files and can push filters and column selection into the Parquet reader; datasets share a namespace with indices, allowing queries across hot indices and S3 data. Setup requires Elastic Cloud Hosted 9.5 or later with an Enterprise subscription; 9.5 requires enabling the feature and specifying the S3 region, while 9.6 enables it by default and detects the region. Federated identity uses temporary AWS credentials and is available only on Hosted; self-managed, ECE, and ECK deployments use static credentials. AWS access can be scoped to `s3:GetObject` and `s3:ListBucket`. Federation incurs S3 read and possible transfer costs, while indexing may be appropriate for workloads requiring kNN, joins, or time-series functions. The feature is described as experimental in 9.5 and 9.6, so the source recommends treating it as exploratory.

### Source excerpt

With ES|QL Data Federation, an S3 bucket is a data source you query with the same FROM syntax you use for an index, and federated identity keeps AWS credentials out of Elasticsearch.

## Continuous Horizon Forecasting

DevFeed: [Continuous Horizon Forecasting](<https://devfeed.tech/articles/continuous-horizon-forecasting-128677.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.13228>)

Author: Malcolm Wolff, Elliott Zackrone, Souhaib Ben Taieb, Michael W. Mahoney, Kin G. Olivares

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

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Time Series](<https://devfeed.tech/topics/time-series.md>)

Tags: [approximation](<https://devfeed.tech/tags/approximation.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [bias](<https://devfeed.tech/tags/bias.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [horizon](<https://devfeed.tech/tags/horizon.md>), [inference](<https://devfeed.tech/tags/inference.md>), [machine](<https://devfeed.tech/tags/machine.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [math-st](<https://devfeed.tech/tags/math-st.md>), [multi-horizon-forecasting](<https://devfeed.tech/tags/multi-horizon-forecasting.md>), [operator](<https://devfeed.tech/tags/operator.md>), [query](<https://devfeed.tech/tags/query.md>), [querying](<https://devfeed.tech/tags/querying.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>), [stat-th](<https://devfeed.tech/tags/stat-th.md>), [statistics](<https://devfeed.tech/tags/statistics.md>), [theoretical](<https://devfeed.tech/tags/theoretical.md>), [variance](<https://devfeed.tech/tags/variance.md>)

### AI overview

Continuous Horizon (CH) treats the forecast horizon as a query to a continuous forecasting operator, rather than producing a fixed vector or generating forecasts recurrently. The paper says this generalizes recursive, direct, and multi-step strategies, and presents a Universal Operator Approximation Theorem plus a bias-variance decomposition proving lower estimation variance than the discrete strategies. In simulations and tests on 16 M-series benchmark datasets, CH achieves competitive RMSE accuracy. It also enables parallel inference, targeted horizon queries, and interpolation or extrapolation at unseen horizons. The supplied text is an abstract and does not provide details of the experiments or methods.

### Source excerpt

arXiv:2611.13228v1 Announce Type: cross Abstract: Multi-horizon forecasting has been dominated by discrete forecast strategies that treat model outputs as fixed-vectors or recurrently create them. In this paper, we introduce the Continuous Horizon (CH) strategy that generalizes upon recursive, direct, and multi-step strategies by redefining forecasts as a continuous operator and the forecast horizon as a query variable rather than an index. We present the theoretical foundations for the CH strategy, a Universal Operator Approximation Theorem, and a continuous-horizon bias-variance decomposition that formally proves the estimation variance improvements of CH over the discrete strategies. We validate the CH strategy empirically through a simulation study, and on 16 large-scale datasets from the M-series benchmark, showing how CH achieves competitive RMSE accuracy, while uniquely enabling parallel inference, targeted horizon querying, and interpolation and extrapolation across unseen horizons.

## Natural Language Interfaces for Databases: What Changes for SQL-Literate Users?

DevFeed: [Natural Language Interfaces for Databases: What Changes for SQL-Literate Users?](<https://devfeed.tech/articles/natural-language-interfaces-for-databases-what-changes-for-sql-literate-users-125654.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2511.14718>)

Author: Panos Ipeirotis, Haotian Zheng

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

Content type: article

Language: en

Sources: [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>)

Topics: [text2sql](<https://devfeed.tech/topics/text2sql.md>), [AI for SQL query generation](<https://devfeed.tech/topics/ai-for-sql-query-generation.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [cs-hc](<https://devfeed.tech/tags/cs-hc.md>), [databases](<https://devfeed.tech/tags/databases.md>), [interfaces](<https://devfeed.tech/tags/interfaces.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [querying](<https://devfeed.tech/tags/querying.md>), [sql](<https://devfeed.tech/tags/sql.md>), [users](<https://devfeed.tech/tags/users.md>)

### AI overview

In a study of 20 SQL-literate participants completing 12 BIRD tasks each, the GPT-4o-backed NLIDB SQL-LLM reduced query completion time by 31% compared with manual SQL in Snowflake, but accuracy was 46% versus 64%. The sample could not establish that accuracy difference ($p = 0.08$); excluding one SQL-LLM timeout session narrowed it to 14 points. Think-aloud data from 11 participants suggest the work shifted: SQL-LLM users relied on the model for initial schema navigation, mainly on easier tasks, then checked its generated SQL, while Snowflake users explored the schema and wrote queries manually. Coded behavior rates did not differ detectably, and positive task remarks did not reliably indicate correct answers. The findings suggest faster querying with verification still required; they are limited to this small sample and tasks that included hints naming target columns and operators.

### Source excerpt

arXiv:2511.14718v4 Announce Type: replace Abstract: Natural Language Interfaces for Databases (NLIDBs) let users query data in everyday language instead of SQL, and modern systems translate most questions accurately. Does an NLIDB remove the work of querying, or move it? We compared SQL-LLM, a GPT-4o-backed NLIDB, with Snowflake, a manual-SQL platform. Twenty SQL-literate professionals and graduate students, ten per interface, each completed 12 BIRD benchmark tasks with hints naming target columns and operators. SQL-LLM cut completion time per query by 31%. It did not improve accuracy: SQL-LLM users answered 46% of queries correctly versus 64% for Snowflake, a gap this sample cannot confirm ($p = 0.08$) that narrows to 14 points without one session where the system timed out. Think-aloud audio from 11 participants (4 SQL-LLM, 7 Snowflake) showed how the work shifted: SQL-LLM users left initial schema navigation to the model, mainly on easier tasks, and focused on checking the generated SQL, while Snowflake users explored the schema and wrote queries by hand. Coded behavior rates did not differ detectably between arms, and positive remarks during a task did not reliably predict a correct answer. The evidence fits a reallocation of querying work, not its removal: users still had to check the generated SQL.

## Ducks in a Column

DevFeed: [Ducks in a Column](<https://devfeed.tech/articles/ducks-in-a-column-127523.md>)

Original publisher: [Read original article](<https://duckdb.org/2026/11/10/ducks-in-a-column.html>)

Author: The DuckDB team

Published: 2026-11-10T00:00:00Z

Content type: article

Language: en

Sources: [DuckDB](<https://devfeed.tech/sources/duckdb.md>)

Topics: [DuckDB](<https://devfeed.tech/topics/duckdb.md>), [parquet](<https://devfeed.tech/topics/parquet.md>), [database-optimization](<https://devfeed.tech/topics/database-optimization.md>), [table-partitioning](<https://devfeed.tech/topics/table-partitioning.md>), [CSV](<https://devfeed.tech/topics/csv.md>), [data lake](<https://devfeed.tech/topics/data-lake.md>)

Tags: [aggregation](<https://devfeed.tech/tags/aggregation.md>), [columnar](<https://devfeed.tech/tags/columnar.md>), [duckdb](<https://devfeed.tech/tags/duckdb.md>), [parquet](<https://devfeed.tech/tags/parquet.md>), [querying](<https://devfeed.tech/tags/querying.md>), [sql](<https://devfeed.tech/tags/sql.md>), [using-duckdb](<https://devfeed.tech/tags/using-duckdb.md>), [window-functions](<https://devfeed.tech/tags/window-functions.md>), [writing](<https://devfeed.tech/tags/writing.md>)

### AI overview

DuckDB's columnar storage lets analytical queries read only named columns, and Parquet adds row-group statistics that can skip data excluded by filters. The article demonstrates querying CSV, Parquet, remote files and DataFrames in place; using EXCLUDE, REPLACE and COLUMNS() for column-level SQL; and simplifying analysis with GROUP BY ALL, FILTER, arg_max, PIVOT/UNPIVOT, window functions, QUALIFY and ASOF JOIN. For faster later reads, it recommends partitioning on commonly filtered columns, sorting before writing Parquet, choosing narrow types, and checking EXPLAIN ANALYZE to see which files and columns were scanned. It also notes that approximate aggregates can use less memory than exact counterparts, while giving a small-table example where an approximate distinct count differs from the exact count.

### Source excerpt

DuckDB is fast among other reasons because it stores data by column, so a query reads only the columns it names. This post covers DuckDB features that take advantage of that design choice: querying files in place, column-level SQL, aggregation shortcuts, window functions, ASOF joins, and writing well-organized Parquet.

## Black-box model classification under the discriminative factorization

DevFeed: [Black-box model classification under the discriminative factorization](<https://devfeed.tech/articles/black-box-model-classification-under-the-discriminative-factorization-123135.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2605.07878>)

Author: Hayden Helm, Merrick Ohata, Carey Priebe

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

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [text-classification](<https://devfeed.tech/topics/text-classification.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [Language models](<https://devfeed.tech/topics/language-models.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [auditing](<https://devfeed.tech/tags/auditing.md>), [budget](<https://devfeed.tech/tags/budget.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [embedded](<https://devfeed.tech/tags/embedded.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generative](<https://devfeed.tech/tags/generative.md>), [inference](<https://devfeed.tech/tags/inference.md>), [models](<https://devfeed.tech/tags/models.md>), [oracle](<https://devfeed.tech/tags/oracle.md>), [performance](<https://devfeed.tech/tags/performance.md>), [probability](<https://devfeed.tech/tags/probability.md>), [properties](<https://devfeed.tech/tags/properties.md>), [quality](<https://devfeed.tech/tags/quality.md>), [queries](<https://devfeed.tech/tags/queries.md>), [query](<https://devfeed.tech/tags/query.md>), [querying](<https://devfeed.tech/tags/querying.md>), [responses](<https://devfeed.tech/tags/responses.md>), [set](<https://devfeed.tech/tags/set.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>)

### AI overview

The paper introduces discriminative factorization to assess query-set quality for black-box model classification, where model properties are inferred from embedded responses to API queries. It bounds the probability of chance-level classification by a term that decreases exponentially with the query budget. Across three auditing tasks, estimated factorization parameters predict the observed performance decay rate, and query sets selected using those estimates reproduce the empirical ranking of oracle-selected query sets. The supplied text is an abstract excerpt, so it does not provide details of the tasks or factorization procedure.

### Source excerpt

arXiv:2605.07878v2 Announce Type: replace Abstract: Access to modern generative systems is often restricted to querying an API (the ``black-box'' setting) and many properties of the system are unknown to the user at inference time. Recent work has shown that low-dimensional representations of models based on the relationship of their embedded responses to a set of queries are useful for inferring model-level properties. However, the quality of these representations is highly sensitive to the query set. We introduce the \emph{discriminative factorization} to distinguish between high- and low-quality query sets in the context of black-box model-level classification. Under this framework, the probability of chance-level classification is bounded by a term that decays exponentially in the query budget. On three auditing tasks, estimated factorization parameters predict the empirical performance decay rate. We conclude by showing that query sets selected using the estimated factorization reproduce the empirical ordering of oracle query sets.

## Speculative Ad-hoc Querying

DevFeed: [Speculative Ad-hoc Querying](<https://devfeed.tech/articles/speculative-ad-hoc-querying-113623.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2503.00714>)

Author: Haoyu Li, Srikanth Kandula, Maria Angels de Luis Balaguer, Aditya Akella, Venkat Arun

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>)

Topics: [Tool](<https://devfeed.tech/topics/tool.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>)

Tags: [agent-workflows](<https://devfeed.tech/tags/agent-workflows.md>), [agentic-systems](<https://devfeed.tech/tags/agentic-systems.md>), [api](<https://devfeed.tech/tags/api.md>), [compilation](<https://devfeed.tech/tags/compilation.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [cs-hc](<https://devfeed.tech/tags/cs-hc.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ma](<https://devfeed.tech/tags/cs-ma.md>), [database](<https://devfeed.tech/tags/database.md>), [i-o](<https://devfeed.tech/tags/i-o.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [latency](<https://devfeed.tech/tags/latency.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llms](<https://devfeed.tech/tags/llms.md>), [productivity](<https://devfeed.tech/tags/productivity.md>), [queries](<https://devfeed.tech/tags/queries.md>), [query](<https://devfeed.tech/tags/query.md>), [querying](<https://devfeed.tech/tags/querying.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>), [scheduler](<https://devfeed.tech/tags/scheduler.md>), [sql](<https://devfeed.tech/tags/sql.md>), [tables](<https://devfeed.tech/tags/tables.md>)

### AI overview

Wonder uses a small auxiliary LLM to prepare analytical SQL work while a primary agent reasons. Rather than predict an exact next query, it anticipates shared query shapes and data needs, materializes reusable superset results, then rewrites later queries to use them. Its scheduler gives foreground queries priority and uses reasoning intervals for speculation; people writing SQL can also guide preparation with incomplete queries and see intermediate results. In replayed agent workflows, Wonder reduced SQL execution time by up to 31.8% and combined reasoning and active SQL time by up to 22.6%, alongside about 6% higher recorded API cost and 10% more read I/O on the full dataset. A separate 24-person study reported lower latency on both analytical tasks, faster answers on one, and increased productivity for 87.5% of participants.

### Source excerpt

arXiv:2503.00714v2 Announce Type: replace Abstract: Large language models (LLMs) invite substantial effort and investment, yet agentic systems can spend much of their time waiting for tools. This paper explores how a small auxiliary LLM can reduce these waits by speculatively preparing a database while the primary LLM reasons. The challenge is that the auxiliary model must anticipate the primary model's actions before the primary model takes them. Our key insight is that database systems give the speculator a structural advantage: it need not predict the exact next query. Instead, it can prepare work shared by many plausible queries. Predicting query shapes enables advance compilation, predicting data access warms caches, and predicting broader data requirements enables precomputation of superset results that subsequent queries can refine. We present Wonder, a system that exploits this advantage for analytical SQL workloads. Wonder constructs reusable superset queries, materializes their components, and rewrites subsequent queries against the resulting temporary tables. Its scheduler prioritizes foreground queries while using reasoning intervals for speculative preparation. The same engine supports humans writing SQL, using incomplete queries to guide speculation and displaying intermediate results as they type. In a replay-based evaluation of agent workflows, Wonder reduces SQL execution time by up to 31.8% and combined primary-agent reasoning and active SQL time by up to 22.6%, with approximately 6% higher recorded main-agent and prediction API cost and 10% more read I/O on the full dataset. A separate 24-participant study finds significantly lower query latency on both analytical tasks and improved time-to-answer on one, with 87.5% of participants reporting increased productivity.

## Your Data Has 100 Attributes - How Many Indexes Do You Need To Search Within Millisecond?

DevFeed: [Your Data Has 100 Attributes - How Many Indexes Do You Need To Search Within Millisecond?](<https://devfeed.tech/articles/your-data-has-100-attributes-how-many-indexes-do-you-need-to-search-within-millisecond-113702.md>)

Original publisher: [Read original article](<https://hackernoon.com/your-data-has-100-attributes-how-many-indexes-do-you-need-to-search-within-millisecond?source=rss>)

Author: Anuj Kapoor

Published: 2026-11-03T02:38:11Z

Content type: tutorial

Language: en

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

Topics: [database-optimization](<https://devfeed.tech/topics/database-optimization.md>), [data-engineering](<https://devfeed.tech/topics/data-engineering.md>)

Tags: [algorithm](<https://devfeed.tech/tags/algorithm.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [binary-search](<https://devfeed.tech/tags/binary-search.md>), [browser](<https://devfeed.tech/tags/browser.md>), [completion](<https://devfeed.tech/tags/completion.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [data](<https://devfeed.tech/tags/data.md>), [data-attribution](<https://devfeed.tech/tags/data-attribution.md>), [data-storage](<https://devfeed.tech/tags/data-storage.md>), [data-system](<https://devfeed.tech/tags/data-system.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [engine](<https://devfeed.tech/tags/engine.md>), [fields](<https://devfeed.tech/tags/fields.md>), [filter](<https://devfeed.tech/tags/filter.md>), [github](<https://devfeed.tech/tags/github.md>), [indexes](<https://devfeed.tech/tags/indexes.md>), [indexing](<https://devfeed.tech/tags/indexing.md>), [kiaradb](<https://devfeed.tech/tags/kiaradb.md>), [query](<https://devfeed.tech/tags/query.md>), [query-gui](<https://devfeed.tech/tags/query-gui.md>), [querying](<https://devfeed.tech/tags/querying.md>), [reuse](<https://devfeed.tech/tags/reuse.md>), [search](<https://devfeed.tech/tags/search.md>)

### AI overview

KiaraDB targets in-memory searches over read-mostly records with many attributes and unpredictable filter combinations. It stores records as shared-value tree paths, assigns each node a depth-first entry/exit range, and builds one value-to-node index per attribute. Query conditions are combined by testing containment between sorted node ranges, avoiding prebuilt indexes for every field combination and large intermediate record-ID sets. The excerpt provides Java and TypeScript examples and reports that, on a synthetic 100,000-record dataset, kiara-ts 1.2.0's tree engine made selective queries well below a millisecond, reduced preparation from 1.31 to 0.87 seconds, and used about 14% less memory than an earlier engine in the same library; broad queries improved less. These results are limited to that comparison and dataset. The approach requires data to fit in RAM and suits snapshot replacement every few minutes or hours, rather than high-volume writes; it is not durable or transactional storage.

### Source excerpt

When data is read far more often than written, you can afford to organize it once and reuse that work on every query.

## Lakehouse Analytics: Querying & Ingesting Apache Iceberg Data with Tanzu Greenplum

DevFeed: [Lakehouse Analytics: Querying & Ingesting Apache Iceberg Data with Tanzu Greenplum](<https://devfeed.tech/articles/lakehouse-analytics-querying-ingesting-apache-iceberg-data-with-tanzu-greenplum-113401.md>)

Original publisher: [Read original article](<https://blogs.vmware.com/tanzu/lakehouse-analytics-querying-ingesting-apache-iceberg-data-with-tanzu-greenplum/>)

Author: venkatesh venky raghavan alexander denissov and yiming li

Published: 2026-11-03T00:02:19Z

Content type: article

Language: en

Sources: [VMware](<https://devfeed.tech/sources/vmware-blogs.md>)

Topics: [Apache Iceberg](<https://devfeed.tech/topics/apache-iceberg.md>), [data lake](<https://devfeed.tech/topics/data-lake.md>), [Apache Spark](<https://devfeed.tech/topics/spark.md>), [Apache Flink](<https://devfeed.tech/topics/apache-flink.md>), [parquet](<https://devfeed.tech/topics/parquet.md>)

Tags: [amazon-web-services-aws](<https://devfeed.tech/tags/amazon-web-services-aws.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [apache-flink](<https://devfeed.tech/tags/apache-flink.md>), [apache-iceberg](<https://devfeed.tech/tags/apache-iceberg.md>), [apache-iceberg-tables](<https://devfeed.tech/tags/apache-iceberg-tables.md>), [apache-spark](<https://devfeed.tech/tags/apache-spark.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [engine](<https://devfeed.tech/tags/engine.md>), [greenplum](<https://devfeed.tech/tags/greenplum.md>), [iceberg](<https://devfeed.tech/tags/iceberg.md>), [lakehouse](<https://devfeed.tech/tags/lakehouse.md>), [modern-apps](<https://devfeed.tech/tags/modern-apps.md>), [querying](<https://devfeed.tech/tags/querying.md>), [sql](<https://devfeed.tech/tags/sql.md>), [storage](<https://devfeed.tech/tags/storage.md>), [tables](<https://devfeed.tech/tags/tables.md>), [writing](<https://devfeed.tech/tags/writing.md>)

### AI overview

PXF 8 lets Tanzu Greenplum query and append to Apache Iceberg tables on S3 in place, using its MPP SQL engine without copying data into a separate warehouse. The post describes column projection, filter pushdown, and partition pruning to reduce unnecessary reads, plus transaction-level atomicity for staged writes managed by `pxf.iceberg_autocommit`. Setup requires a PXF Iceberg catalog configuration, an `iceberg_pxf_fdw` foreign server, a user mapping, and a foreign table whose columns match the known Iceberg schema. PXF supports JDBC and Hadoop catalogs; Hadoop colocates metadata with S3 data but is discouraged for production because filesystem updates are non-atomic. The article presents Iceberg as enabling interoperable data access, while performance, governance, and cost benefits are asserted rather than quantified.

### Source excerpt

Technial post shows users how PXF 8 allows Tanzu Greenplum to directly access Iceberg tables stored in cloud object stores to facilitate reading Apache Iceberg metadata and manifests, querying Iceberg tables in place, pushing down filters efficiently, and writing data into Apache Iceberg-managed storage. Tanzu Greenplum empowers organizations to run its massively parallel SQL engine ... Continued The post Lakehouse Analytics: Querying & Ingesting Apache Iceberg Data with Tanzu Greenplum appeared first on VMware Blogs.

## MS-GPT: Rethinking MS/MS De Novo Structure Elucidation as Spectrum-Induced Posterior Querying of a Molecule-Language Model

DevFeed: [MS-GPT: Rethinking MS/MS De Novo Structure Elucidation as Spectrum-Induced Posterior Querying of a Molecule-Language Model](<https://devfeed.tech/articles/ms-gpt-rethinking-ms-ms-de-novo-structure-elucidation-as-spectrum-induced-posterior-querying-of-a-molecule-language-model-111427.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2607.23607>)

Author: Xin Zhao, Yumin Liu, Zhuo Li, Weichu Zheng, Feng Zhu, Xiaokang Yang, Yaohui Jin, Yanyan Xu

Published: 2026-11-02T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>)

Tags: [adapter](<https://devfeed.tech/tags/adapter.md>), [art](<https://devfeed.tech/tags/art.md>), [candidate](<https://devfeed.tech/tags/candidate.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [decoder](<https://devfeed.tech/tags/decoder.md>), [domain](<https://devfeed.tech/tags/domain.md>), [fingerprint](<https://devfeed.tech/tags/fingerprint.md>), [generate](<https://devfeed.tech/tags/generate.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [inference](<https://devfeed.tech/tags/inference.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [libraries](<https://devfeed.tech/tags/libraries.md>), [lora](<https://devfeed.tech/tags/lora.md>), [pool](<https://devfeed.tech/tags/pool.md>), [pretraining](<https://devfeed.tech/tags/pretraining.md>), [querying](<https://devfeed.tech/tags/querying.md>), [scaling](<https://devfeed.tech/tags/scaling.md>), [similarity](<https://devfeed.tech/tags/similarity.md>), [spectrum](<https://devfeed.tech/tags/spectrum.md>), [structure](<https://devfeed.tech/tags/structure.md>), [top](<https://devfeed.tech/tags/top.md>)

### AI overview

MS-GPT addresses the mismatch between molecule-language models trained on exact molecular fingerprints and inference from uncertain MS/MS-derived fingerprints. It conditions a model on fingerprints and formulas, calibrates a band of fingerprint queries around the oracle-fingerprint manifold, then pools candidates and ranks them by generation frequency and posterior similarity. A lightweight LoRA adapter is used to reduce domain-specific posterior bias while retaining the pretrained molecular prior. On NPLIB1, Top-1/Top-10 exact-match accuracy is 17.1%/27.6%; on MassSpecGym it is 10.2%/13.2%. Larger candidate pools improve recovery, with inference cost rising nearly linearly. These findings are from the supplied abstract.

### Source excerpt

arXiv:2607.23607v2 Announce Type: replace Abstract: Molecular structure elucidation from tandem mass spectra (MS/MS) is a central inverse problem in analytical chemistry. Most existing approaches to MS/MS identification remain tied to reference libraries or predefined candidate sets, whereas de novo methods aim to generate structures directly from spectra. A common de novo route predicts a molecular fingerprint from the spectrum and then decodes structures from it, enabling decoder pretraining on large molecule-only corpora. However, this paradigm creates a training-inference mismatch: the decoder is trained on oracle fingerprints computed from molecules, but at inference it is queried with a noisy spectrum-induced fingerprint posterior that is typically collapsed to a single thresholded fingerprint. We introduce MS-GPT, which recasts fingerprint-mediated de novo elucidation as spectrum-induced posterior querying of a conditional molecule-language model. MS-GPT conditions a molecule-language model on fingerprints and formulas, then converts the spectrum-induced posterior into a band of fingerprint queries near the oracle-fingerprint manifold through active-bit density calibration. Candidates sampled across this band are pooled and ranked by generation frequency and posterior similarity. A lightweight LoRA adapter further mitigates domain-specific posterior bias while preserving the pretrained molecular prior. On NPLIB1 and MassSpecGym, MS-GPT sets a new state of the art, reaching Top-1/Top-10 exact-match accuracy of 17.1%/27.6% and 10.2%/13.2%, respectively, and candidate-pool scaling improves recovery with a near-linear increase in inference cost. The source code and model checkpoints are available at https://github.com/VIKI623/MS-GPT.

## GraphRAGProv: GraphRAG Meets How-Provenance

DevFeed: [GraphRAGProv: GraphRAG Meets How-Provenance](<https://devfeed.tech/articles/graphragprov-graphrag-meets-how-provenance-103248.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.37237>)

Author: Wadie El Amrani, Luis Gal\\'arraga

Published: 2026-10-28T04:00:00Z

Content type: article

Language: en

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

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [RDF (Resource Description Framework)](<https://devfeed.tech/topics/rdf.md>), [Ground truth / benchmark quality](<https://devfeed.tech/topics/ground-truth-benchmark-quality.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [announce](<https://devfeed.tech/tags/announce.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [demo](<https://devfeed.tech/tags/demo.md>), [experimental](<https://devfeed.tech/tags/experimental.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graphrag](<https://devfeed.tech/tags/graphrag.md>), [knowledge-graphs](<https://devfeed.tech/tags/knowledge-graphs.md>), [llm](<https://devfeed.tech/tags/llm.md>), [polynomials](<https://devfeed.tech/tags/polynomials.md>), [provenance](<https://devfeed.tech/tags/provenance.md>), [queries](<https://devfeed.tech/tags/queries.md>), [query](<https://devfeed.tech/tags/query.md>), [querying](<https://devfeed.tech/tags/querying.md>), [rdf](<https://devfeed.tech/tags/rdf.md>), [source](<https://devfeed.tech/tags/source.md>), [text](<https://devfeed.tech/tags/text.md>), [transformation](<https://devfeed.tech/tags/transformation.md>), [transparency](<https://devfeed.tech/tags/transparency.md>)

### AI overview

GraphRAGProv uses SPARQL over source-grounded RDF graphs to compute answers and how-provenance polynomials that show which statement occurrences were used and how they were combined. Links from each occurrence to its source text let users inspect the extracted statements and the query's reasoning, making queries a way to evaluate the text-to-graph transformation. An interactive demo across 400 cases from two multi-hop QA benchmarks found extraction and query errors even when final answers were correct.

### Source excerpt

arXiv:2610.37237v1 Announce Type: new Abstract: GraphRAG systems often use knowledge graphs to retrieve relevant context for an LLM that produces the final answer. That makes answers more inscrutable and therefore less appealing for domains where transparency is paramount. We present GraphRAGProv, an architecture that executes SPARQL queries over source-grounded RDF graphs to compute answers and their how-provenance polynomials. These polynomials record which statement occurrences were used and how they were combined. Because each occurrence is linked to its source text, users can follow these links to check whether the extracted statements reflect the text and whether the query combines them to answer the question. Querying thereby becomes a way to inspect and evaluate the text-to-graph transformation. Our interactive demo examines 400 cases from two multi-hop QA benchmarks, revealing extraction and query errors even when the final answer is correct.

## TT-SAX: A Two-Track Time Series Symbolization for Natural Language Shape Querying

DevFeed: [TT-SAX: A Two-Track Time Series Symbolization for Natural Language Shape Querying](<https://devfeed.tech/articles/tt-sax-a-two-track-time-series-symbolization-for-natural-language-shape-querying-96708.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.30593>)

Author: Zhao Tan, Xianglong Bao, Zhipeng Xi, Ming Jin

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

Content type: article

Language: en

Sources: [arXiv: Databases](<https://devfeed.tech/sources/arxiv-databases.md>)

Topics: [Time Series](<https://devfeed.tech/topics/time-series.md>), [Temporal data](<https://devfeed.tech/topics/temporal-data.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [challenge](<https://devfeed.tech/tags/challenge.md>), [classification](<https://devfeed.tech/tags/classification.md>), [compression](<https://devfeed.tech/tags/compression.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-db](<https://devfeed.tech/tags/cs-db.md>), [databases](<https://devfeed.tech/tags/databases.md>), [design](<https://devfeed.tech/tags/design.md>), [design-principles](<https://devfeed.tech/tags/design-principles.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [first](<https://devfeed.tech/tags/first.md>), [foundation](<https://devfeed.tech/tags/foundation.md>), [indexing](<https://devfeed.tech/tags/indexing.md>), [natural-language](<https://devfeed.tech/tags/natural-language.md>), [queries](<https://devfeed.tech/tags/queries.md>), [query](<https://devfeed.tech/tags/query.md>), [querying](<https://devfeed.tech/tags/querying.md>), [redesign](<https://devfeed.tech/tags/redesign.md>), [research](<https://devfeed.tech/tags/research.md>), [scale](<https://devfeed.tech/tags/scale.md>), [string](<https://devfeed.tech/tags/string.md>), [study](<https://devfeed.tech/tags/study.md>), [time-series](<https://devfeed.tech/tags/time-series.md>)

### AI overview

TT-SAX adapts SAX for natural-language time-series shape queries by retaining each segment's level letter and adding a trend letter measured across neighboring segments and graded to match query adjectives. The authors identify missing direction, overly local direction measurements, and arbitrary letters as limitations in six classical symbolizations. On NLQTSBench, TT-SAX outperforms those six methods on shape queries across six LLMs; ablations attribute gains to the identified limitations. The evidence is limited to the supplied abstract.

### Source excerpt

arXiv:2610.30593v1 Announce Type: new Abstract: Natural language querying for time series databases aims to let users find what they need in long histories of data by asking in plain language. Shape queries ask how a series moves. They are the main challenge of this task. Recent work makes them feasible by using symbolization as a bridge between the query and the long history. However, existing symbolizations were designed for compression, similarity indexing, or classification. What a symbolization should provide for natural language querying has not been systematically studied. We therefore examine the definitions of six classical symbolizations against this task and identify three limitations. (1) Direction is missing from the string, (2) direction is measured at too small a scale, and (3) the letters are arbitrary. Three design principles follow. We follow these principles and make a minimal redesign of SAX called TT-SAX (two-track SAX). The level letters stay. Each segment gains a trend letter. It is measured across neighboring segments rather than inside one, and graded to match the adjectives that queries use. We conduct extensive experiments on the public NLQTSBench benchmark, comparing TT-SAX with the six classical symbolizations across six LLMs. TT-SAX outperforms all six on shape queries, and ablations trace its gains back to the three limitations one by one. This paper is the first systematic study of time series symbolization with natural language querying as the design goal. It provides a foundation for future research on this task. Our code is available at https://github.com/Atlamtiz/tt-sax.

## Best AI Agent Gateways in 2026, Compared

DevFeed: [Best AI Agent Gateways in 2026, Compared](<https://devfeed.tech/articles/best-ai-agent-gateways-in-2026-compared-95872.md>)

Original publisher: [Read original article](<https://www.lyzr.ai/blog/best-ai-agent-gateways-compared/>)

Author: Lyzr Team

Published: 2026-10-22T14:14:04Z

Content type: comparison

Language: en

Sources: [Lyzr.ai](<https://devfeed.tech/sources/lyzr-ai.md>)

Topics: [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [litellm](<https://devfeed.tech/topics/litellm.md>), [observability](<https://devfeed.tech/topics/observability.md>), [ai observability](<https://devfeed.tech/topics/ai-observability.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [gateway](<https://devfeed.tech/topics/gateway.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2026](<https://devfeed.tech/tags/2026.md>), [3](<https://devfeed.tech/tags/3.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [best](<https://devfeed.tech/tags/best.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [external](<https://devfeed.tech/tags/external.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [gateways](<https://devfeed.tech/tags/gateways.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-servers](<https://devfeed.tech/tags/mcp-servers.md>), [model](<https://devfeed.tech/tags/model.md>), [model-access](<https://devfeed.tech/tags/model-access.md>), [querying](<https://devfeed.tech/tags/querying.md>), [servers](<https://devfeed.tech/tags/servers.md>), [systems](<https://devfeed.tech/tags/systems.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

There is no universal best AI agent gateway: fit depends on which traffic it manages, policy enforcement, deployment and existing infrastructure. Bifrost unifies model and supported MCP tool traffic in a self-hosted gateway; LiteLLM offers self-hosted provider routing and MCP access controls; Portkey combines model routing, guardrails, tool controls and observability, with features dependent on tier and deployment. Kong extends its API gateway with AI policies and MCP support, while Azure API Management adds AI and MCP capabilities that vary by tier, including a dedicated tier described as public preview. Envoy AI Gateway suits Envoy and Kubernetes platforms but requires more surrounding stack work; TrueFoundry integrates gateway functions into its broader AI platform, with MCP depth to confirm. The comparison relies on official documentation, not benchmarks, and performance figures are vendor-reported. Gateways can control supported requests passing through them, but may not govern an agent's full workflow or activity across systems; a separate control plane may be needed for cross-environment agent discovery and governance.

### Source excerpt

An enterprise standardises model access through a gateway. Then its agents start calling external tools, querying internal systems and talking to MCP servers. A gateway...

## How Ridgeline unified Iceberg and ClickHouse into one analytics layer for investment management

DevFeed: [How Ridgeline unified Iceberg and ClickHouse into one analytics layer for investment management](<https://devfeed.tech/articles/how-ridgeline-unified-iceberg-and-clickhouse-into-one-analytics-layer-for-investment-management-87284.md>)

Original publisher: [Read original article](<https://clickhouse.com/blog/ridgeline-iceberg-clickhouse-cloud>)

Author: ClickHouse

Published: 2026-10-14T17:36:29Z

Content type: article

Language: en

Sources: [ClickHouse Blog](<https://devfeed.tech/sources/clickhouse-blog.md>)

Topics: [clickhouse](<https://devfeed.tech/topics/clickhouse.md>), [Apache Kafka](<https://devfeed.tech/topics/apache-kafka.md>), [table-partitioning](<https://devfeed.tech/topics/table-partitioning.md>), [Apache Spark](<https://devfeed.tech/topics/spark.md>), [Amazon Redshift](<https://devfeed.tech/topics/amazon-redshift.md>)

Tags: [architecture](<https://devfeed.tech/tags/architecture.md>), [aws](<https://devfeed.tech/tags/aws.md>), [clickhouse](<https://devfeed.tech/tags/clickhouse.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-native](<https://devfeed.tech/tags/cloud-native.md>), [cost](<https://devfeed.tech/tags/cost.md>), [data](<https://devfeed.tech/tags/data.md>), [deployments](<https://devfeed.tech/tags/deployments.md>), [iceberg](<https://devfeed.tech/tags/iceberg.md>), [it](<https://devfeed.tech/tags/it.md>), [performance](<https://devfeed.tech/tags/performance.md>), [querying](<https://devfeed.tech/tags/querying.md>)

### AI overview

Ridgeline moved its investment performance analytics from Postgres to ClickHouse Cloud, using Iceberg for older history and ClickHouse for recent data. The architecture handles larger customer workloads, cut reporting batches from hours to minutes, and helped the company more than double the customers live on its platform.

### Source excerpt

Ridgeline rebuilt its performance analytics on ClickHouse Cloud, querying decades of Iceberg history alongside recent data so it can serve investment managers 10x larger than before and more than double the customers live on its platform.

## How to Query Data the Professional Way in SQL Server: A Performance-First Guide for Beginners

DevFeed: [How to Query Data the Professional Way in SQL Server: A Performance-First Guide for Beginners](<https://devfeed.tech/articles/how-to-query-data-the-professional-way-in-sql-server-a-performance-first-guide-for-beginners-64288.md>)

Original publisher: [Read original article](<https://hackernoon.com/how-to-query-data-the-professional-way-in-sql-server-a-performance-first-guide-for-beginners?source=rss>)

Author: Surendra Reddy

Published: 2026-10-02T18:19:28Z

Content type: tutorial

Language: en

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

Topics: [sql-server](<https://devfeed.tech/topics/sql-server.md>), [SQL](<https://devfeed.tech/topics/sql.md>), [database-optimization](<https://devfeed.tech/topics/database-optimization.md>), [database monitoring](<https://devfeed.tech/topics/database-monitoring.md>)

Tags: [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [database](<https://devfeed.tech/tags/database.md>), [guide](<https://devfeed.tech/tags/guide.md>), [performance](<https://devfeed.tech/tags/performance.md>), [querying](<https://devfeed.tech/tags/querying.md>), [sql](<https://devfeed.tech/tags/sql.md>), [sql-beginner-tips](<https://devfeed.tech/tags/sql-beginner-tips.md>), [sql-database](<https://devfeed.tech/tags/sql-database.md>), [sql-injection](<https://devfeed.tech/tags/sql-injection.md>), [sql-server](<https://devfeed.tech/tags/sql-server.md>)

### AI overview

This beginner-focused tutorial presents SQL Server query practices for improving performance, including selecting needed columns, indexing filters and joins, keeping predicates sargable, limiting result sets with pagination, and using execution plans and Query Store to diagnose slow queries. It also recommends parameterized queries to reduce SQL injection risk and enable plan reuse.

### Source excerpt

How to Query Data the Professional Way in SQL Server: A Performance-First Guide for Beginners

## DuckDB and Hugging Face: Querying Datasets Directly

DevFeed: [DuckDB and Hugging Face: Querying Datasets Directly](<https://devfeed.tech/articles/duckdb-and-hugging-face-querying-datasets-directly-59796.md>)

Original publisher: [Read original article](<https://duckdb.org/2026/09/25/hugging-face.html>)

Author: The DuckDB team

Published: 2026-09-25T00:00:00Z

Content type: article

Language: en

Sources: [DuckDB](<https://devfeed.tech/sources/duckdb.md>)

Topics: [DuckDB](<https://devfeed.tech/topics/duckdb.md>), [hugging face](<https://devfeed.tech/topics/hugging-face.md>), [big-data](<https://devfeed.tech/topics/big-data.md>)

Tags: [datasets](<https://devfeed.tech/tags/datasets.md>), [duckdb](<https://devfeed.tech/tags/duckdb.md>), [extensions](<https://devfeed.tech/tags/extensions.md>), [hugging-face](<https://devfeed.tech/tags/hugging-face.md>), [integration](<https://devfeed.tech/tags/integration.md>), [querying](<https://devfeed.tech/tags/querying.md>)

### AI overview

DuckDB v0.10.3 added the hf:// protocol for querying files in Hugging Face dataset repositories directly, without first downloading a local copy. Queries can read CSV, JSONL, or Parquet, combine files with glob patterns, filter and select columns, and pin a branch or commit revision for reproducibility. The text describes uses such as inspecting datasets, creating filtered local Parquet subsets, aggregating benchmark files, and joining Hub data with local tables. Public datasets need no setup; private or gated datasets require a Hugging Face token configured through DuckDB's Secrets Manager. For repeated queries, the text recommends materializing data locally to avoid repeatedly contacting the remote endpoint.

### Source excerpt

Hugging Face hosts hundreds of thousands of datasets, and DuckDB can read them directly, exactly where they are and without downloading anything, over the DuckDB `hf://` protocol. This post looks at how the integration works and the scenarios where it works best.

## Querying the entire internet (100 billion rows!) with MotherDuck

DevFeed: [Querying the entire internet (100 billion rows!) with MotherDuck](<https://devfeed.tech/articles/querying-the-entire-internet-100-billion-rows-with-motherduck-78943.md>)

Original publisher: [Read original article](<https://motherduck.com/blog/querying-the-entire-internet-100-billion-rows-with-motherduck>)

Author: Dumky de Wilde

Published: 2026-09-22T00:00:00Z

Content type: article

Language: en

Sources: [MotherDuck](<https://devfeed.tech/sources/motherduck.md>)

Topics: [DuckDB](<https://devfeed.tech/topics/duckdb.md>), [hosting](<https://devfeed.tech/topics/hosting.md>), [Internet](<https://devfeed.tech/topics/internet.md>), [Web](<https://devfeed.tech/topics/web.md>), [database-optimization](<https://devfeed.tech/topics/database-optimization.md>), [Query (disambiguation)](<https://devfeed.tech/topics/query.md>), [cosine similarity search](<https://devfeed.tech/topics/cosine-similarity-search.md>)

Tags: [2021](<https://devfeed.tech/tags/2021.md>), [2022](<https://devfeed.tech/tags/2022.md>), [2023](<https://devfeed.tech/tags/2023.md>), [2025](<https://devfeed.tech/tags/2025.md>), [2026](<https://devfeed.tech/tags/2026.md>), [3](<https://devfeed.tech/tags/3.md>), [can](<https://devfeed.tech/tags/can.md>), [cluster](<https://devfeed.tech/tags/cluster.md>), [data](<https://devfeed.tech/tags/data.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [download](<https://devfeed.tech/tags/download.md>), [duckdb](<https://devfeed.tech/tags/duckdb.md>), [fast](<https://devfeed.tech/tags/fast.md>), [internet](<https://devfeed.tech/tags/internet.md>), [motherduck](<https://devfeed.tech/tags/motherduck.md>), [query](<https://devfeed.tech/tags/query.md>), [querying](<https://devfeed.tech/tags/querying.md>), [s3](<https://devfeed.tech/tags/s3.md>), [web](<https://devfeed.tech/tags/web.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

DuckDB can analyze Common Crawl's S3-hosted Parquet data without downloading the full dataset or using a cluster: sort-key statistics let it skip most row groups, while selecting only needed columns reduces reads. The article contrasts Common Crawl's broad, link-following crawl (which does not run JavaScript) with the HTTP Archive's technology-focused sampling and the Wayback Machine's URL history. Using quarterly web-graph hostname lists plus the columnar URL index, the author compares platform hostnames against established hosting references and scans 109.4 billion index rows to study GitHub Pages. The results suggest relative growth in hosted platforms and a 75% rise in crawled GitHub Pages user sites per million pages over four years, while projects per user site are roughly flat. These are proxies: Common Crawl counts pages it crawls, misses bot-blocked or unlinked sites, and crawl coverage varies, so the measurements do not represent all sites built.

### Source excerpt

Common Crawl publishes petabytes of web crawl data on S3. With DuckDB and MotherDuck you can query the Common Crawl dataset directly, no cluster and no download, and measure how fast the vibe-coded web is growing.

## How and Why Netflix Built a Real-Time Distributed Graph: Part 3 -- Querying the graph with gRPC...

DevFeed: [How and Why Netflix Built a Real-Time Distributed Graph: Part 3 -- Querying the graph with gRPC...](<https://devfeed.tech/articles/how-and-why-netflix-built-a-real-time-distributed-graph-part-3-querying-the-graph-with-grpc-138.md>)

Original publisher: [Read original article](<https://netflixtechblog.com/how-and-why-netflix-built-a-real-time-distributed-graph-part-3-querying-the-graph-with-grpc-0f3468349607?source=rss----2615bd06b42e---4>)

Author: Netflix Technology Blog

Published: 2026-08-07T16:01:02Z

Content type: article

Language: en

Sources: [Netflix](<https://devfeed.tech/sources/netflix-techblog-medium.md>)

Topics: [gRPC](<https://devfeed.tech/topics/grpc.md>), [real-time](<https://devfeed.tech/topics/real-time.md>), [rate-limiting](<https://devfeed.tech/topics/rate-limiting.md>), [consistency](<https://devfeed.tech/topics/consistency.md>), [Apache Flink](<https://devfeed.tech/topics/apache-flink.md>)

Tags: [apache-flink](<https://devfeed.tech/tags/apache-flink.md>), [api](<https://devfeed.tech/tags/api.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [blog](<https://devfeed.tech/tags/blog.md>), [data-processing](<https://devfeed.tech/tags/data-processing.md>), [graph](<https://devfeed.tech/tags/graph.md>), [grpc](<https://devfeed.tech/tags/grpc.md>), [latency](<https://devfeed.tech/tags/latency.md>), [netflix](<https://devfeed.tech/tags/netflix.md>), [next](<https://devfeed.tech/tags/next.md>), [patterns](<https://devfeed.tech/tags/patterns.md>), [personalization](<https://devfeed.tech/tags/personalization.md>), [querying](<https://devfeed.tech/tags/querying.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [serving](<https://devfeed.tech/tags/serving.md>), [storage](<https://devfeed.tech/tags/storage.md>), [streaming](<https://devfeed.tech/tags/streaming.md>)

### AI overview

Netflix describes a gRPC serving layer for its Real-Time Distributed Graph, designed to query billions of nodes and edges across both high-fan-out and multi-hop workloads. It uses breadth-first traversal to batch each graph level, asynchronous I/O and bounded parallelism to reduce wait time without overwhelming storage, and streamed adjacency lists with early filters and configurable edge limits to control data volume. Selective EVCache caching favors stable, frequently used nodes; enrichment is opt-in and fail-open, while reads use eventual consistency. Netflix reports 15-30 ms P50 and under-100 ms P99 for single-hop queries, 100-150 ms P99 for three hops, and 70-80% node-cache hit rates. The tradeoffs include memory use proportional to frontier width and harder debugging for asynchronous flows.

### Source excerpt

How and Why Netflix Built a Real-Time Distributed Graph: Part 3 -- Querying the graph with gRPC execution API Authors: Nilesh Mishra and Ajit Koti This is the third entry of a multi-part blog series describing how we built a Real-Time Distributed Graph (RDG). In Part 1, we discussed the motivation for creating the RDG and the architecture of the data processing pipeline that populates it. In Part 2, we discussed how we designed the storage layer to handle billions of nodes and edges while maintaining single-digit-millisecond latency. In Part 3, we will explore how we designed a fast, flexible serving layer to efficiently query the graph. Introduction In Part 1 of this series, we described why Netflix needed a Real-Time Distributed Graph (RDG) and how we used Apache Flink to build an ingestion and processing pipeline that turns streaming events into graph primitives. In Part 2, we explored how we designed a storage layer capable of handling billions of nodes and edges while still delivering single-digit-millisecond latency. In this post, we focus on the next challenge: querying the graph efficiently to power real-time insights for our internal partners. All of the work on ingestion and storage only matters if we can actually ask complex questions and get answers back quickly. As we optimized for lower latency, we found that the serving layer posed its own set of challenges, distinct from those of ingestion and storage. How do we turn a constantly evolving, billion-edge graph into sub-100ms responses across a wide variety of workloads? This is the problem we tackle in this post. The Real World Needs As we integrated the RDG into Netflix's ecosystem, we realized that "querying the graph" is not a one-size-fits-all operation. We needed to handle a wide range of access patterns: from high-volume security lookups to deep, exploratory personalization traces. Let's revisit our example from Part 1 and expand on it slightly. In the earlier posts, we focused on accounts, device

## Using Dot Notation to Query Nested Fields in MongoDB

DevFeed: [Using Dot Notation to Query Nested Fields in MongoDB](<https://devfeed.tech/articles/using-dot-notation-to-query-nested-fields-in-mongodb-21840.md>)

Original publisher: [Read original article](<https://www.thepolyglotdeveloper.com/blog/2026/04/using-dot-notation-to-query-nested-fields-in-mongodb/>)

Author: Nic Raboy

Published: 2026-04-28T20:29:24Z

Content type: tutorial

Language: en

Sources: [Nic Raboy](<https://devfeed.tech/sources/nic-raboy.md>)

Topics: [MongoDB](<https://devfeed.tech/topics/mongodb.md>), [Query (disambiguation)](<https://devfeed.tech/topics/query.md>)

Tags: [arrays](<https://devfeed.tech/tags/arrays.md>), [collection](<https://devfeed.tech/tags/collection.md>), [collections](<https://devfeed.tech/tags/collections.md>), [complex](<https://devfeed.tech/tags/complex.md>), [complexity](<https://devfeed.tech/tags/complexity.md>), [data](<https://devfeed.tech/tags/data.md>), [database](<https://devfeed.tech/tags/database.md>), [field](<https://devfeed.tech/tags/field.md>), [fields](<https://devfeed.tech/tags/fields.md>), [filter](<https://devfeed.tech/tags/filter.md>), [flat](<https://devfeed.tech/tags/flat.md>), [mongodb](<https://devfeed.tech/tags/mongodb.md>), [nested](<https://devfeed.tech/tags/nested.md>), [nested-objects](<https://devfeed.tech/tags/nested-objects.md>), [nesting](<https://devfeed.tech/tags/nesting.md>), [object](<https://devfeed.tech/tags/object.md>), [period](<https://devfeed.tech/tags/period.md>), [query](<https://devfeed.tech/tags/query.md>), [querying](<https://devfeed.tech/tags/querying.md>), [tutorial](<https://devfeed.tech/tags/tutorial.md>)

### AI overview

MongoDB dot notation lets you filter documents by nested fields by joining each level of the field path with periods. The excerpt demonstrates querying fields several levels deep, including examples about a person's employer and location. Following along requires a configured MongoDB instance, basic familiarity with collection queries, and the sample documents; the supplied text cuts off before further examples.

### Source excerpt

If you're just starting to dabble with MongoDB, you've probably come to a point where your documents are looking a little complex. These documents might have gone from flat, relational-looking pieces ... The post Using Dot Notation to Query Nested Fields in MongoDB appeared first on DataCamp.

## From REST to GraphQL in minutes with prebuilt Connectors

DevFeed: [From REST to GraphQL in minutes with prebuilt Connectors](<https://devfeed.tech/articles/from-rest-to-graphql-in-minutes-with-prebuilt-connectors-23307.md>)

Original publisher: [Read original article](<https://www.apollographql.com/blog/from-rest-to-graphql-in-minutes-with-prebuilt-connectors>)

Author: Amanda Martin

Published: 2025-06-13T07:15:23Z

Content type: tutorial

Language: en

Sources: [Apollo Blog](<https://devfeed.tech/sources/apollo-blog.md>)

Topics: [Apollo Connectors](<https://devfeed.tech/topics/apollo-connectors.md>), [GraphQL](<https://devfeed.tech/topics/graphql.md>), [REST API](<https://devfeed.tech/topics/rest-api.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [apis](<https://devfeed.tech/tags/apis.md>), [apollo](<https://devfeed.tech/tags/apollo.md>), [apollo-connectors](<https://devfeed.tech/tags/apollo-connectors.md>), [browser](<https://devfeed.tech/tags/browser.md>), [cli](<https://devfeed.tech/tags/cli.md>), [command](<https://devfeed.tech/tags/command.md>), [comment](<https://devfeed.tech/tags/comment.md>), [community](<https://devfeed.tech/tags/community.md>), [connectors](<https://devfeed.tech/tags/connectors.md>), [data](<https://devfeed.tech/tags/data.md>), [docs](<https://devfeed.tech/tags/docs.md>), [download](<https://devfeed.tech/tags/download.md>), [files](<https://devfeed.tech/tags/files.md>), [graph](<https://devfeed.tech/tags/graph.md>), [graphql](<https://devfeed.tech/tags/graphql.md>), [live-data](<https://devfeed.tech/tags/live-data.md>), [openapi](<https://devfeed.tech/tags/openapi.md>), [querying](<https://devfeed.tech/tags/querying.md>), [rest](<https://devfeed.tech/tags/rest.md>), [schema](<https://devfeed.tech/tags/schema.md>)

### AI overview

The guide shows how to run a prebuilt REST Connector locally as a GraphQL API, using Space Devs Launch Library 2. It requires an Apollo Studio account and an installed, authenticated Rover CLI. Initialize a new graph with Rover, then download the connector's GraphQL files and supergraph.yaml from the Connectors Community repo into the project; remove duplicate or unneeded generated files and start the router using Rover's provided command. Explore the live graph in Apollo Sandbox. The connector can also be tailored: the example adds a comment above the upcoming launches query in launches.graphql so the query builder shows guidance about valid search strings. The supplied text ends mid-sentence, so it does not establish further steps.

### Source excerpt

We've all been there: vague API docs, an outdated OpenAPI spec, and a half-buried list of endpoints that leave you guessing. With prebuilt REST Connectors, you skip the guesswork. Just download the schema files, run your graph locally, and start querying live data with GraphQL.

[Next page](<https://devfeed.tech/tags/querying.md?cursor=WyIyMDI1LTA2LTEzVDA3OjE1OjIzKzAwOjAwIiwgIjU4MjFlODU2LTRhYmQtNGI1ZS05OWQ2LTEzMTNmZmI3N2I3YSJd>)