Add Support for Local Whisper Models and Integrate llmR for Summariza…

…tion (#23)

* refactor: rely on the llmR package for LLM interaction

Removed the llm related functions since they will be provided by the llmR package

* chore: update R ver in renv snapshot

* feat(stt): add support for local Whisper models

- Added `use_whisper_local_stt` function to support local Whisper models via Python with reticulate.
- Added `use_mlx_whisper_local_stt` function for MLX Whisper models, optimized for Mac OS with Apple Silicon.
- Updated `perform_speech_to_text` to use `whisper_local` as the default model.
- Enhanced `speech_to_summary_workflow` to display the selected speech-to-text model.
- Updated documentation and NAMESPACE to export the new functions.
- Added `reticulate` to the Suggests field in DESCRIPTION for Python integration.

* fix: update to use llmR

* fix: use rlang to check and install suggested pkgs

* docs: update documentation

Update README to describe the use of llmR for summarisation and the addition of the new local models for stt.

* version bump

* chores

* docs: version bump

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: minutemaker
 Title: GenAI-based meeting and conferences minutes generator
-Version: 0.10.0
+Version: 0.12.0
 Authors@R: 
     person("Angelo", "D'Ambrosio", , "a.dambrosioMD@gmail.com", role = c("aut", "cre"),
            comment = c(ORCID = "0000-0002-2045-5155"))
@@ -11,6 +11,7 @@ Imports:
     dplyr (>= 1.1.4),
     httr (>= 1.4.7),
     jsonlite (>= 1.8.8),
+    llmR (>= 1.1.0),
     lubridate (>= 1.9.3),
     purrr (>= 1.0.2),
     readr (>= 2.1.4),
@@ -19,14 +20,17 @@ Imports:
     styler (>= 1.10.2),
     tools (>= 4.3.2),
     vctrs (>= 0.6.5)
+Remotes: 
+    github::bakaburg1/llmR
 Config/testthat/edition: 3
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.1
+RoxygenNote: 7.3.2
 Suggests: 
     av (>= 0.9.0),
     devtools (>= 2.4.5),
     parallel (>= 4.3.2),
+    reticulate (>= 1.38.0),
     testthat (>= 3.0.0),
     text2vec (>= 0.6.4),
     tictoc (>= 1.2),

NAMESPACE

@@ -13,15 +13,15 @@ export(infer_agenda_from_transcript)
 export(merge_transcripts)
 export(parse_transcript_json)
 export(perform_speech_to_text)
-export(prompt_llm)
 export(run_in_terminal)
 export(set_prompts)
 export(speech_to_summary_workflow)
 export(split_audio)
 export(summarise_full_meeting)
 export(summarise_transcript)
+export(use_mlx_whisper_local_stt)
+export(use_whisper_local_stt)
 export(validate_agenda)
 import(dplyr)
 importFrom(stats,setNames)
-importFrom(utils,hasName)
 importFrom(utils,tail)

NEWS.md

@@ -1,3 +1,19 @@
+# minutemaker 0.12.0
+
+#### Enhancements
+- **Support for Local Whisper Models**: Added functions `use_whisper_local_stt` and `use_mlx_whisper_local_stt` to support local Whisper models via Python with reticulate, with the second being optimized for Mac OS with Apple Silicon (Commit: [69e4f5e](https://github.com/bakaburg1/minutemaker/commit/69e4f5e59518da51d7f757a5076511d4224c6d65)).
+- **Integration with llmR**: Refactored the code to rely on the `llmR` package for LLM interactions, removing redundant LLM-related functions (Commit: [2331b46](https://github.com/bakaburg1/minutemaker/commit/2331b463e0606cd4ee49ecb353b89b163da06d9e)).
+- **Enhanced Speech-to-Text Workflow**: Updated `perform_speech_to_text` to use `whisper_local` as the default model and enhanced `speech_to_summary_workflow` to display the selected speech-to-text model (Commit: [69e4f5e](https://github.com/bakaburg1/minutemaker/commit/69e4f5e59518da51d7f757a5076511d4224c6d65)).
+
+#### Fixes
+- **Dependency Management**: Replaced custom dependency check function with `rlang::check_installed` for better package management (Commit: [3227b0d](https://github.com/bakaburg1/minutemaker/commit/3227b0d7dba8785949c1d66c83d232bb38438c08)).
+
+#### Documentation
+- **Updated README**: Revised README to describe the use of `llmR` for summarization and the addition of new local models for speech-to-text (Commit: [8bff883](https://github.com/bakaburg1/minutemaker/commit/8bff88380c5dc977a52c2207f1ef380904784bf4)).
+
+#### Summary
+This pull request introduces significant enhancements to the `minutemaker` package by adding support for local Whisper models, integrating the `llmR` package for LLM interactions, and improving the speech-to-text workflow. Additionally, it fixes dependency management issues and updates the documentation to reflect these changes.
+
 # minutemaker 0.10.0
 
 #### Enhancements