Package: kagiPro 0.4.1

Rainer M. Krug

kagiPro: Kagi API Client for R

User-friendly R client for the Kagi APIs (Search, Enrich, Summarizer, and FastGPT). Build endpoint-specific query objects, run single or batch requests with one reusable connection, and write reproducible JSON outputs for analysis pipelines. Includes optional graceful error handling with dummy outputs and JSON-to-parquet conversion for downstream workflows.

Authors:Rainer M. Krug [aut, cre]

kagiPro_0.4.1.tar.gz
kagiPro_0.4.1.zip(r-4.7-any)kagiPro_0.4.1.zip(r-4.6-any)kagiPro_0.4.1.zip(r-4.5-any)
kagiPro_0.4.1.tgz(r-4.6-any)kagiPro_0.4.1.tgz(r-4.5-any)
kagiPro_0.4.1.tar.gz(r-4.7-any)kagiPro_0.4.1.tar.gz(r-4.6-any)
kagiPro_0.4.1.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION
card.svg |card.png
kagiPro/json (API)

# Install 'kagiPro' in R:
install.packages('kagiPro', repos = c('https://rkrug.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/rkrug/kagipro/issues

Pkgdown/docs site:https://rkrug.github.io

On CRAN:

Conda:

quarto

3.60 score 9 scripts 18 exports 60 dependencies

Last updated from:e4efb6151a (on main). Checks:9 OK. Indexed: yes.

TargetResultTimeFilesSyslog
linux-develOK159
source / vignettesOK207
linux-releaseOK161
macos-releaseOK179
macos-oldrelOK259
windows-develOK134
windows-releaseOK132
windows-oldrelOK141
wasm-releaseOK113

Exports:clean_requestcontent_markdowndownload_contentkagi_connectionkagi_fetchkagi_requestkagi_request_parquetkagi_update_querymarkdown_abstractopen_search_queryquery_enrich_newsquery_enrich_webquery_fastgptquery_searchquery_summarizeread_corpussummarize_with_kagisummarize_with_openai

Dependencies:arrowaskpassassertthatbitbit64blobclicodetoolscommonmarkcpp11curlDBIdbplyrdigestdplyrduckdbfuturefuture.applygenericsglobalsglueherehttrhttr2jsonlitelatticelifecyclelistenvmagrittrMatrixmimemirainanonextopensslparallellypillarpkgconfigpngpurrrR6ragnarrappdirsRcppRcppTOMLreticulaterlangrprojrootrvestS7selectrstringistringrsystibbletidyrtidyselectutf8vctrswithrxml2

Agent Quick Index
Connection and Authentication | Query Construction | Request Execution | Storage and Refresh | Content and Abstract Pipeline | Utility
Rendered fromagent-quick-index.qmdusingquarto::html

Last update: 2026-04-10
Started: 2026-04-10

API Contracts
Folder Contracts | Request/Parquet Workflow | Content/Abstract Workflow | Data Contracts | Base Parquet Corpus | Abstract Parquet | read_corpus(..., abstracts = TRUE) | Execution Contracts | Error-Handling Contracts | Stability Notes
Rendered fromapi-contracts.qmdusingquarto::html

Last update: 2026-04-10
Started: 2026-04-10

kagiPro Corpus Workflow: Search to Abstract-Linked Corpus
End-to-End Corpus Workflow (Multiple Queries) | 1) Create connection and multi-query search input | 2) Fetch search results into endpoint-structured project folders | 3) (Optional) Explicit parquet conversion step | 4) Download linked source content | 5) Convert downloaded content to markdown | 6) Build query-level abstract parquet files | 7) Read corpus and link abstracts | Practical Notes
Rendered fromcorpus-workflow.qmdusingquarto::html

Last update: 2026-04-10
Started: 2026-04-10

kagiPro Enrich Endpoint Guide
Enrich Endpoint: Context Discovery for Web and News | Create the connection once | Build web and news enrich queries | Execute a focused run for each enrich type | Move to a thematic batch workload | Handle request failures without losing the whole run | Convert enrich output to parquet | Operational recommendations
Rendered fromenrich-endpoint.qmdusingquarto::html

Last update: 2026-04-10
Started: 2026-04-08

kagiPro FastGPT Endpoint Guide
FastGPT Endpoint: Practical Prompt Workflows | Create one connection for all runs | Build a single prompt query | Execute and store the first response | Scale prompts to a batch job | Keep long runs resilient with graceful error handling | Convert FastGPT output to parquet | Operational recommendations
Rendered fromfastgpt-endpoint.qmdusingquarto::html

Last update: 2026-04-10
Started: 2026-04-08

kagiPro Quickstart Guide
kagiPro: First End-to-End Workflow | Project-folder first workflow | Install and load the package | Create a secure API connection | Build your first search query | Execute and persist search results | Run one example from each endpoint | Enrich web | Enrich news | Summarize (text input) | FastGPT | Convert JSON results to parquet | Bridge to OpenAlex-style vector input | Where to go next | Session info
Rendered fromquickstart.qmdusingquarto::html

Last update: 2026-04-10
Started: 2025-08-27

kagiPro Search Endpoint Guide
Search Endpoint: From Question to Reusable Search Pipeline | Start with a reusable connection | Build one precise search query | Execute the request and persist results | Scale from single query to query grid | Choose your failure policy explicitly | Convert search JSON to parquet for analysis | Operational recommendations
Rendered fromsearch-endpoint.qmdusingquarto::html

Last update: 2026-04-10
Started: 2026-04-08

kagiPro Summarize Endpoint Guide
Summarize Endpoint: Robust Summaries in Real Pipelines | Establish a reusable connection | Build summarize queries for URL and text sources | Execute a normal summarize request | Handle known short-input failures safely | Run mixed batches with one success and one failure | Convert summarize JSON to parquet | Operational recommendations
Rendered fromsummarize-endpoint.qmdusingquarto::html

Last update: 2026-04-10
Started: 2026-04-08