Skip to content
Merged

Dev #36

Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 17 additions & 0 deletions CONTRIBUTORS.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,22 @@
# EndpointR Development Guide

## Pre-PR Checklist

- [ ] export necessary funcs and artefacts
- [ ] document with examples/full roxygen2 skeleton
- [ ] check DESCRIPTION for version bump or dependencies update
- [ ] update news.md
- [ ] update todos.md
- [ ] update \_pkgdown.yml (function reference, news etc.)
- [ ] run `spelling::spell_check_package()`
- [ ] `devtools::document()`
- [ ] run `testthat::test()`
- [ ] run `devtools::check()`
- [ ] run `pkgdown::build_site()`
- [ ] inspect site incl. vignettes
- [ ] PR
- [ ] Check CI/CD

## Commands

- Run all tests: `testthat::test()`
Expand Down
5 changes: 3 additions & 2 deletions DESCRIPTION
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,8 @@ License: MIT + file LICENSE
Encoding: UTF-8
Roxygen: list(markdown = TRUE)
RoxygenNote: 7.3.2
Suggests:
Suggests:
spelling,
broom,
ggplot2,
here,
Expand All @@ -32,10 +33,10 @@ Imports:
tibble,
S7,
jsonvalidate,
readr,
arrow
VignetteBuilder: knitr
Depends:
R (>= 3.5)
LazyData: true
URL: https://jpcompartir.github.io/EndpointR/
Language: en-GB
3 changes: 3 additions & 0 deletions NAMESPACE
Original file line number Diff line number Diff line change
@@ -1,6 +1,9 @@
# Generated by roxygen2: do not edit by hand

export(ant_build_messages_request)
export(ant_complete_chunks)
export(ant_complete_df)
export(ant_complete_text)
export(create_json_schema)
export(get_api_key)
export(hf_build_request)
Expand Down
4 changes: 4 additions & 0 deletions NEWS.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,10 @@
- adds parquet writing to oai_complete_df and oai_embed_df
- adds chunks func to oai_embed, and re-writes all batch -\> chunk logic
- implements the Anthropic messages API with structured outputs (via BETA)
- adds `ant_complete_df()` and `ant_complete_chunks()` for batch/chunked processing with the Anthropic API, with parquet writing and metadata tracking
- metadata tracking now includes `schema` and `system_prompt` for both OpenAI and Anthropic chunked processing functions
- bug fix: S7 schema objects now correctly serialised to metadata.json (previously caused "No method asJSON S3 class: S7_object" error)
- adds spelling test, sets language to en-GB in DESCRIPTION

# EndpointR 0.1.2

Expand Down
Loading