{ "_id": "6a21b045cd65a98ecbd39317", "Package": "cat.web", "Title": "Web Content Classification with LLMs", "Version": "0.1.2", "Authors@R": "person(\"Chris\", \"Soria\", role = c(\"aut\", \"cre\"),\nemail = \"chrissoria@berkeley.edu\")", "Description": "R interface to the Python catweb package. Classifies,\nextracts, explores, and summarizes web content (URLs or text)\nusing LLMs. A thin domain wrapper around cat.stack that adds\nautomatic URL fetching and web-context prompt injection (source\ndomain, content type, metadata).", "License": "GPL (>= 3)", "URL": "https://christophersoria.com/cat-llm/cat.web/,\nhttps://github.com/chrissoria/cat-llm", "BugReports": "https://github.com/chrissoria/cat-llm/issues", "Encoding": "UTF-8", "Roxygen": "list(markdown = TRUE)", "RoxygenNote": "7.3.2", "SystemRequirements": "Python (>= 3.9), pip", "VignetteBuilder": "knitr", "Config/testthat/edition": "3", "Config/pak/sysreqs": "libpng-dev python3", "Repository": "https://chrissoria.r-universe.dev", "Date/Publication": "2026-06-04 16:16:50 UTC", "RemoteUrl": "https://github.com/chrissoria/cat-llm", "RemoteRef": "main", "RemoteSha": "f2d83209be8d621fceb422d434fb5b3b98fe301b", "RemoteSubdir": "r-package/cat.web", "NeedsCompilation": "no", "Packaged": { "Date": "2026-06-04 16:59:43 UTC", "User": "root" }, "Author": "Chris Soria [aut, cre]", "Maintainer": "Chris Soria ", "MD5sum": "2664ce8598e0065f37961871d4570d17", "_user": "chrissoria", "_type": "src", "_file": "cat.web_0.1.2.tar.gz", "_fileid": "1ac71c32b4579a4c106c5dd33075eb355128a95f32dd847169758288fcb0b348", "_filesize": 110035, "_sha256": "1ac71c32b4579a4c106c5dd33075eb355128a95f32dd847169758288fcb0b348", "_created": "2026-06-04T16:59:43.000Z", "_published": "2026-06-04T17:05:09.308Z", "_distro": "noble", "_jobs": [ { "job": 79571398712, "time": 148, "config": "linux-devel-x86_64", "r": "4.7.0", "check": "OK", "artifact": "7417862050" }, { "job": 79571398626, "time": 130, "config": "linux-release-x86_64", "r": "4.6.0", "check": "OK", "artifact": "7417855003" }, { "job": 79571398726, "time": 113, "config": "macos-oldrel-arm64", "r": "4.5.3", "check": "OK", "artifact": "7417919092" }, { "job": 79571398668, "time": 106, "config": "macos-release-arm64", "r": "4.6.0", "check": "OK", "artifact": "7417902359" }, { "job": 79570839695, "time": 183, "config": "source", "r": "4.6.0", "check": "OK", "artifact": "7417805703" }, { "job": 79571398689, "time": 194, "config": "wasm-release", "r": "4.6.0", "check": "OK", "artifact": "7417880182" }, { "job": 79571398683, "time": 86, "config": "windows-devel", "r": "4.7.0", "check": "OK", "artifact": "7417838279" }, { "job": 79571398876, "time": 71, "config": "windows-oldrel", "r": "4.5.3", "check": "OK", "artifact": "7417832387" }, { "job": 79571398655, "time": 100, "config": "windows-release", "r": "4.6.0", "check": "OK", "artifact": "7417843469" } ], "_buildurl": "https://github.com/r-universe/chrissoria/actions/runs/26966613610", "_status": "success", "_host": "GitHub-Actions", "_upstream": "https://github.com/chrissoria/cat-llm", "_commit": { "id": "f2d83209be8d621fceb422d434fb5b3b98fe301b", "author": "Christopher Soria ", "committer": "Christopher Soria ", "message": "docs: document cat-stack 1.6.5 Ollama timeout behavior\n\nAdds a 'HTTP timeouts on local Ollama runs' subsection under Testing,\nexplaining the new provider-conditional defaults (120s cloud / 600s\nOllama) and how to override per-client or process-wide. Docs-only;\nno code change in cat-llm.\n\nCo-Authored-By: Claude Opus 4.7 \n", "time": 1780589810 }, "_maintainer": { "name": "Chris Soria", "email": "chrissoria@berkeley.edu", "login": "chrissoria", "linkedin": "in/christopher-soria-9340931a", "description": "UC Berkeley Demography", "uuid": 15951118 }, "_registered": true, "_dependencies": [ { "package": "reticulate", "version": ">= 1.28", "role": "Imports" }, { "package": "cat.stack", "version": ">= 0.1.0", "role": "Imports" }, { "package": "testthat", "version": ">= 3.0.0", "role": "Suggests" }, { "package": "knitr", "role": "Suggests" }, { "package": "rmarkdown", "role": "Suggests" } ], "_owner": "chrissoria", "_selfowned": true, "_usedby": 1, "_updates": [ { "week": "2025-23", "n": 16 }, { "week": "2025-26", "n": 1 }, { "week": "2025-32", "n": 2 }, { "week": "2025-38", "n": 6 }, { "week": "2025-40", "n": 1 }, { "week": "2025-41", "n": 3 }, { "week": "2025-42", "n": 3 }, { "week": "2025-43", "n": 18 }, { "week": "2025-44", "n": 1 }, { "week": "2025-45", "n": 2 }, { "week": "2025-47", "n": 1 }, { "week": "2025-50", "n": 9 }, { "week": "2026-01", "n": 26 }, { "week": "2026-02", "n": 9 }, { "week": "2026-03", "n": 4 }, { "week": "2026-05", "n": 1 }, { "week": "2026-06", "n": 6 }, { "week": "2026-07", "n": 15 }, { "week": "2026-08", "n": 2 }, { "week": "2026-09", "n": 7 }, { "week": "2026-10", "n": 18 }, { "week": "2026-11", "n": 11 }, { "week": "2026-12", "n": 2 }, { "week": "2026-13", "n": 5 }, { "week": "2026-14", "n": 3 }, { "week": "2026-17", "n": 1 }, { "week": "2026-18", "n": 7 }, { "week": "2026-20", "n": 47 }, { "week": "2026-21", "n": 19 }, { "week": "2026-23", "n": 6 } ], "_tags": [ { "name": "v2.0.0", "date": "2026-01-17" }, { "name": "v2.7.0", "date": "2026-03-07" }, { "name": "v3.1.2", "date": "2026-06-03" } ], "_stars": 8, "_contributors": [ { "user": "chrissoria", "count": 261, "uuid": 15951118 }, { "user": "claude", "count": 9, "uuid": 81847 } ], "_userbio": { "uuid": 15951118, "type": "user", "name": "Chris Soria ", "description": "UC Berkeley Demography" }, "_downloads": { "count": 0, "source": "https://cranlogs.r-pkg.org/downloads/total/last-month/cat.web" }, "_devurl": "https://github.com/chrissoria/cat-llm", "_pkgdown": "https://christophersoria.com/cat-llm/cat.web/", "_searchresults": 4, "_rbuild": "4.6.0", "_assets": [ "extra/cat.web.html", "extra/citation.cff", "extra/citation.html", "extra/citation.json", "extra/citation.txt", "extra/contents.json", "extra/NEWS.html", "extra/NEWS.txt", "extra/readme.html", "extra/readme.md", "manual.pdf" ], "_cranurl": false, "_exports": [ "classify", "explore", "extract", "summarize" ], "_help": [ { "page": "classify", "title": "Classify web content using LLMs", "topics": [ "classify" ] }, { "page": "explore", "title": "Explore raw categories in web content", "topics": [ "explore" ] }, { "page": "extract", "title": "Discover categories from web content using LLMs", "topics": [ "extract" ] }, { "page": "summarize", "title": "Summarize web content using LLMs", "topics": [ "summarize" ] } ], "_readme": "https://github.com/chrissoria/cat-llm/raw/main/r-package/cat.web/README.md", "_rundeps": [ "cat.stack", "here", "jsonlite", "lattice", "Matrix", "png", "rappdirs", "Rcpp", "RcppTOML", "reticulate", "rlang", "rprojroot", "withr" ], "_vignettes": [ { "source": "web-content-classification.Rmd", "filename": "web-content-classification.html", "title": "Classifying Web Content", "engine": "knitr::rmarkdown", "headings": [ "What cat.web adds", "Install", "Classify a list of URLs", "Classify raw text instead", "Use web context to disambiguate", "Summarize before classifying", "Tips for web-data work", "Where to learn more" ], "created": "2026-05-17 04:03:24", "modified": "2026-05-17 04:03:24", "commits": 1 } ], "_score": 5.556302500767287, "_indexed": true, "_nocasepkg": "cat.web", "_universes": [ "chrissoria" ], "_binaries": [ { "r": "4.7.0", "os": "linux", "version": "0.1.2", "date": "2026-06-04T17:02:18.000Z", "distro": "noble", "commit": "f2d83209be8d621fceb422d434fb5b3b98fe301b", "fileid": "27b18b1610c839bb2736e6563be09ae1b980c196085b389ad0356216fd77a5c6", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/chrissoria/actions/runs/26966613610" }, { "r": "4.6.0", "os": "linux", "version": "0.1.2", "date": "2026-06-04T17:01:59.000Z", "distro": "noble", "commit": "f2d83209be8d621fceb422d434fb5b3b98fe301b", "fileid": "c7d341bc2a4ac2ec6b6d0fce9d00c0a48325fbf07c4b31dda9563e131f82aef0", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/chrissoria/actions/runs/26966613610" }, { "r": "4.5.3", "os": "mac", "version": "0.1.2", "date": "2026-06-04T17:04:41.000Z", "commit": "f2d83209be8d621fceb422d434fb5b3b98fe301b", "fileid": "d97c1571e1e219c564bdc271a261946f3ff8954a5048ce5e55e0aa960a95befa", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/chrissoria/actions/runs/26966613610" }, { "r": "4.6.0", "os": "mac", "version": "0.1.2", "date": "2026-06-04T17:04:02.000Z", "commit": "f2d83209be8d621fceb422d434fb5b3b98fe301b", "fileid": "4e7a9789570197e11f8dfc609ccb01e38ab2016eb8aa9a07b5e6ea5b7533f07a", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/chrissoria/actions/runs/26966613610" }, { "r": "4.6.0", "os": "wasm", "version": "0.1.2", "date": "2026-06-04T17:03:14.000Z", "commit": "f2d83209be8d621fceb422d434fb5b3b98fe301b", "fileid": "d750ca7b8321335893dd7b4d653f77badc7aa2575db9f0f1665c34dc3325b61f", "status": "success", "buildurl": "https://github.com/r-universe/chrissoria/actions/runs/26966613610" }, { "r": "4.7.0", "os": "win", "version": "0.1.2", "date": "2026-06-04T17:01:08.000Z", "commit": "f2d83209be8d621fceb422d434fb5b3b98fe301b", "fileid": "63c4f923176ff3dbcc7213fe69e8980981793b8491e67c8058bc18e3aca1c127", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/chrissoria/actions/runs/26966613610" }, { "r": "4.5.3", "os": "win", "version": "0.1.2", "date": "2026-06-04T17:00:53.000Z", "commit": "f2d83209be8d621fceb422d434fb5b3b98fe301b", "fileid": "4b90ca1a84eb60da8391e1feaf1ceadbdd8e9807e74da97fbd7b0047a8a259ce", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/chrissoria/actions/runs/26966613610" }, { "r": "4.6.0", "os": "win", "version": "0.1.2", "date": "2026-06-04T17:01:21.000Z", "commit": "f2d83209be8d621fceb422d434fb5b3b98fe301b", "fileid": "d2f9e4f3ee42ea841dec1fd112e728a80f75e9442b79f4f9d2adb6872c200f16", "status": "success", "check": "OK", "buildurl": "https://github.com/r-universe/chrissoria/actions/runs/26966613610" } ] }