Enhanced Agenda Management and Utilization #20
Conversation
Allow the user to proceed with the transcription after the agenda is generated without re-running the workflow function
test.R file has been added to the list of files to be ignored by the build and CMD CHECK processes
The function `interrogate_llm` now retrieves the language model provider setting from global options using `getOption("minutemaker_llm_provider")`. This change allows for more flexible configuration and avoids hardcoding the provider. Additionally, an error handling mechanism has been introduced to stop the execution with a descriptive message if the provider is not set, guiding the user to set the provider option globally.
A new function `validate_agenda` has been implemented to check the validity of an entire agenda. This function ensures that the agenda is a non-empty list and that each element of the list is a valid agenda item. It also supports loading the agenda from a file path if provided. The function will be useful for users to validate their agenda data structures before proceeding with further processing.
A new function, format_agenda, has been introduced to convert a machine-readable agenda into a human-readable format.
- Implemented a new `multipart_summary` argument in the `speech_to_summary_workflow` function to allow users to specify whether the summarization should be done in parts for each agenda element or as a single summary. - Updated the `speech_to_summary_workflow` function to validate the `overwrite_transcript` argument more robustly and handle the existence of a formatted output file with clearer messaging and logic. - Enhanced the documentation for several parameters in the `speech_to_summary_workflow` function to improve clarity and consistency. - Made minor code refactoring for better readability and maintainability.
Tranform the agenda into text before using to drive the non multipart summarisation
WalkthroughThe Changes
Poem
Recent Review DetailsConfiguration used: CodeRabbit UI Files selected for processing (14)
Files skipped from review due to trivial changes (3)
Additional comments not posted (16)
Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media? TipsChatThere are 3 ways to chat with CodeRabbit:
Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (invoked as PR comments)
Additionally, you can add CodeRabbit Configration File (
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
Actionable comments outside the diff hunks (1)
README.md (1)
Line range hint
4-4: Capitalize the first letter of the sentence in the comment.- <!-- README.md is generated from README.Rmd. Please edit that file --> + <!-- README.md is generated from README.Rmd. Please edit that file. -->The comment at the beginning of the file should start with a capital letter for consistency and professionalism in documentation.
| # summarisation section with: | ||
| summary_structure <- paste0( | ||
| get_prompts("summary_structure"), | ||
| "\n- My Extra section" | ||
| "\n- My extra summarisation instruction" | ||
| ) | ||
|
|
||
| # The use can also use the summarisation instruction to add and agenda to drive | ||
| # the summarisation focus: | ||
| agenda <- format_agenda(agenda) | ||
| summary_structure <- get_prompts("summary_structure") | ||
|
|
||
| summary_structure <- stringr::str_glue(" | ||
| {summary_structure} | ||
| Here is an agenda of the event to keep into account while summarizing: | ||
| {agenda} | ||
| Stricly follow the agenda to understand which information is worth summarizing. | ||
| ") | ||
|
|
||
| # Finally, the user can add extra output instructions to the default ones (check | ||
| # them using get_prompts("output_summarisation") for the summarisation and | ||
| # get_prompts("output_rolling_aggregation") for the rolling aggregation). For |
There was a problem hiding this comment.
📝 NOTE
This review was outside the diff hunks and was mapped to the diff hunk with the greatest overlap. Original lines [344-428]
Ensure consistency in summarization terminology.
There is inconsistent use of the terms "summarise" and "summarize" throughout the document. It's important to stick to one form to maintain consistency and professionalism in the documentation. Consider using "summarize" consistently as it is more common in American English.
- summarise_transcript
+ summarize_transcript
- summarise_full_meeting
+ summarize_full_meeting
Enhancements:
multipart_summaryargument inspeech_to_summary_workflow()to allow users to choose between summarizing each agenda item separately (the previous approach, now the default) or as a single summary just using the agenda to focus the model, offering greater flexibility in the summarization process (Commit: 99168d4).format_agenda()function to convert machine-readable agendas into human-readable text, improving the usability of agenda-driven summarization (Commit: 0d27980).validate_agenda()function to ensure the validity of agenda structures before summarization, enhancing the reliability of the summarization process (Commit: 5e943af).overwrite_formatted_outputisFALSE(Commit: 99168d4).getOption("minutemaker_llm_provider"), allowing for more flexible and centralized LLM provider management (Commit: 159335d).interrogate_llm()to retrieve the LLM provider setting from global options, providing a more dynamic and user-friendly approach to specifying the LLM provider (Commit: 15723d6).Fixes:
validate_agenda()function (Commit: 6bdabad).