revert to default 'n_chunks = 1' for #212

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: pkgmatch
 Title: Find R Packages Matching Either Descriptions or Other R Packages
-Version: 0.5.0.091
+Version: 0.5.0.093
 Authors@R: c(
     person("Mark", "Padgham", , "[email protected]", role = c("aut", "cre"),
            comment = c(ORCID = "0000-0003-2172-5265")),

R/embeddings.R

@@ -43,11 +43,11 @@ convert_paths_to_pkgs <- function (packages) {
 #' @param packages A vector of either names of installed packages, or local
 #' paths to directories containing R packages.
 #' @param n_chunks Number of randomly permuted chunks of input text to use to
-#' generate average embeddings. Values should generally be > 1, because the
-#' text of many packages exceeds the context window for the language models,
-#' and so permutations ensure that all text is captured in resultant
-#' embeddings. Note, however, that computation times scale linearly with this
-#' value.
+#' generate average embeddings. Issue #212 demonstrates that > 95% of all CRAN packages
+#' have <= 8192 tokens, and so fit within the context windows of the embeddings
+#' models used here. Chunking is therefore generally not necessary, and so this
+#' parameter defaults to a value of 1. Also note that computation
+#' times scale linearly with this value.
 #' @param functions_only If `TRUE`, calculate embeddings for function
 #' descriptions only. This is intended to generate a separate set of embeddings
 #' which can then be used to match plain-text queries of functions, rather than
@@ -69,7 +69,7 @@ convert_paths_to_pkgs <- function (packages) {
 #' names (emb_pkg)
 #' colnames (emb_pkg$text_with_fns) # "curl"
 pkgmatch_embeddings_from_pkgs <- function (packages = NULL,
-                                           n_chunks = 5L,
+                                           n_chunks = 1L,
                                            functions_only = FALSE) {
 
     checkmate::assert_integer (n_chunks, len = 1L)

codemeta.json

@@ -8,7 +8,7 @@
   "codeRepository": "https://github.com/ropensci-review-tools/pkgmatch",
   "issueTracker": "https://github.com/ropensci-review-tools/pkgmatch/issues",
   "license": "https://spdx.org/licenses/MIT",
-  "version": "0.5.0.091",
+  "version": "0.5.0.093",
   "programmingLanguage": {
     "@type": "ComputerLanguage",
     "name": "R",

tests/testthat/emb_fns/127.0.0.1-11434/api/embed-bbf259-POST.json → tests/testthat/emb_fns/127.0.0.1-11434/api/embed-087b47-POST.json

@@ -772,7 +772,7 @@
             -0.026968248
         ]
     ],
-    "total_duration": 79280349,
-    "load_duration": 4627018,
+    "total_duration": 70626051,
+    "load_duration": 2804237,
     "prompt_eval_count": 59
 }

tests/testthat/emb_fns/127.0.0.1-11434/api/embed-01c87f-POST.json → tests/testthat/emb_fns/127.0.0.1-11434/api/embed-4cd790-POST.json

@@ -772,7 +772,7 @@
             0.013035012
         ]
     ],
-    "total_duration": 246722930,
-    "load_duration": 2980597,
+    "total_duration": 215597663,
+    "load_duration": 3358566,
     "prompt_eval_count": 179
 }

tests/testthat/emb_fns/127.0.0.1-11434/api/embed-e77513-POST.json → tests/testthat/emb_fns/127.0.0.1-11434/api/embed-7262ab-POST.json

@@ -772,7 +772,7 @@
             -0.028184487
         ]
     ],
-    "total_duration": 596613308,
-    "load_duration": 3612651,
+    "total_duration": 531537702,
+    "load_duration": 2863633,
     "prompt_eval_count": 398
 }

tests/testthat/emb_fns/127.0.0.1-11434/api/embed-7b40e3-POST.json → tests/testthat/emb_fns/127.0.0.1-11434/api/embed-7ff10e-POST.json

@@ -772,7 +772,7 @@
             -0.00089879567
         ]
     ],
-    "total_duration": 165977790,
-    "load_duration": 3171402,
+    "total_duration": 154286877,
+    "load_duration": 3780620,
     "prompt_eval_count": 136
 }

tests/testthat/emb_fns/127.0.0.1-11434/api/embed-900891-POST.json → tests/testthat/emb_fns/127.0.0.1-11434/api/embed-d47a3d-POST.json

@@ -772,7 +772,7 @@
             -0.027917823
         ]
     ],
-    "total_duration": 101383275,
-    "load_duration": 3401316,
+    "total_duration": 89842063,
+    "load_duration": 2867599,
     "prompt_eval_count": 78
 }

tests/testthat/emb_fns/127.0.0.1-11434/api/embed-aed6d5-POST.json → tests/testthat/emb_fns/127.0.0.1-11434/api/embed-e7dd13-POST.json

@@ -772,7 +772,7 @@
             0.030365974
         ]
     ],
-    "total_duration": 22076367,
-    "load_duration": 3098162,
+    "total_duration": 20790669,
+    "load_duration": 2997282,
     "prompt_eval_count": 7
 }

tests/testthat/emb_raw/127.0.0.1-11434/api/embed-a89f4f-POST.json → tests/testthat/emb_raw/127.0.0.1-11434/api/embed-938ed4-POST.json

@@ -772,7 +772,7 @@
             0.019178685
         ]
     ],
-    "total_duration": 3675698007,
-    "load_duration": 8009516,
+    "total_duration": 3342807364,
+    "load_duration": 7954258,
     "prompt_eval_count": 2340
 }

tests/testthat/emb_raw/127.0.0.1-11434/api/embed-16a4d0-POST.json → tests/testthat/emb_raw/127.0.0.1-11434/api/embed-9850cd-POST.json

@@ -772,7 +772,7 @@
             -0.025955537
         ]
     ],
-    "total_duration": 1841401918,
-    "load_duration": 3642221,
+    "total_duration": 1712754778,
+    "load_duration": 3436951,
     "prompt_eval_count": 1245
 }

tests/testthat/emb_raw/127.0.0.1-11434/api/embed-ab65e4-POST.json → tests/testthat/emb_raw/127.0.0.1-11434/api/embed-da127c-POST.json

@@ -772,7 +772,7 @@
             -0.033488743
         ]
     ],
-    "total_duration": 99158692,
-    "load_duration": 3039868,
+    "total_duration": 91215769,
+    "load_duration": 2897947,
     "prompt_eval_count": 78
 }

tests/testthat/emb_test_text/127.0.0.1-11434/api/embed-998b4f-POST.json → tests/testthat/emb_test_text/127.0.0.1-11434/api/embed-eddb51-POST.json

@@ -772,7 +772,7 @@
             -0.050223053
         ]
     ],
-    "total_duration": 16871019,
-    "load_duration": 3581706,
+    "total_duration": 17789547,
+    "load_duration": 3063146,
     "prompt_eval_count": 2
 }

tests/testthat/sim_fns/127.0.0.1-11434/api/embed-cec9f9-POST.json → tests/testthat/sim_fns/127.0.0.1-11434/api/embed-a41331-POST.json

@@ -772,7 +772,7 @@
             -0.062179822
         ]
     ],
-    "total_duration": 20789325,
-    "load_duration": 3424775,
+    "total_duration": 20631645,
+    "load_duration": 3081596,
     "prompt_eval_count": 3
 }

tests/testthat/update/127.0.0.1-11434/api/embed-8383b1-POST.json → tests/testthat/sim_pkgs_pkg/127.0.0.1-11434/api/embed-28c968-POST.json

@@ -772,7 +772,7 @@
             -0.044476017
         ]
     ],
-    "total_duration": 417098616,
-    "load_duration": 292983345,
+    "total_duration": 412787173,
+    "load_duration": 292817504,
     "prompt_eval_count": 98
 }

tests/testthat/sim_pkgs_pkg/127.0.0.1-11434/api/embed-21b458-POST.json → tests/testthat/sim_pkgs_pkg/127.0.0.1-11434/api/embed-771081-POST.json

@@ -772,7 +772,7 @@
             0.004767239
         ]
     ],
-    "total_duration": 48521639,
-    "load_duration": 8504563,
+    "total_duration": 409662080,
+    "load_duration": 369778651,
     "prompt_eval_count": 22
 }

tests/testthat/update/127.0.0.1-11434/api/embed-e954c2-POST.json → tests/testthat/sim_pkgs_pkg/127.0.0.1-11434/api/embed-cd0aa1-POST.json

@@ -772,7 +772,7 @@
             -0.047969084
         ]
     ],
-    "total_duration": 161241449,
-    "load_duration": 3558935,
+    "total_duration": 130933287,
+    "load_duration": 3235448,
     "prompt_eval_count": 114
 }