eric/audita
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity

Commit Graph

  • 87e560dd3d Added architecture reference documentation for the upcoming Go rewrite Eric Rakestraw 2026-05-10 23:04:29 +00:00
  • 09fc6fd364 Updated .gitignore in preparation for the Go rewrite Eric Rakestraw 2026-05-10 22:40:27 +00:00
  • 2e47c8a1b6 Move python implementation under python/ in preparation for the upcoming Go rewrite Eric Rakestraw 2026-05-10 22:37:38 +00:00
  • e797e3d9ff Update the CLI to use a safe, best-effort console emitter so logging issues cannot fail the run python-final Eric Rakestraw 2026-05-04 13:04:36 -05:00
  • a70f481a93 Implemented invocation-level failure diagnostics Eric Rakestraw 2026-05-04 12:10:27 -05:00
  • 434f812b98 Bugfix for local LLMs with no API key supplied Eric Rakestraw 2026-05-04 11:22:49 -05:00
  • fac1629417 An API key is no longer required if base_url is pointed to a non-default endpoint Eric Rakestraw 2026-05-04 11:11:06 -05:00
  • 410c57f8d5 Adjusted the protected-glossary capitalization logic so capitalization checks only apply when the same protected glossary identity was already present in the original text. Eric Rakestraw 2026-05-01 07:08:11 -05:00
  • 9ab5a60123 Implemented a shared, more permissive editorial validatior for the grammar and spoken_word modules Eric Rakestraw 2026-05-01 07:01:51 -05:00
  • 0d5bdd1c84 Added a configuration flag to set the maximum number of tokens in validation prompts Eric Rakestraw 2026-04-29 22:33:45 -05:00
  • 54ce3d08c9 Added validation-specific LLM configuration options Eric Rakestraw 2026-04-29 20:45:51 -05:00
  • 4c899122d9 Added a configuration flag to set the target number of sections, and updated default min and max section token limits Eric Rakestraw 2026-04-29 20:10:00 -05:00
  • f841f7eb71 Added a configurable LLM timeout Eric Rakestraw 2026-04-29 18:08:39 -05:00
  • d8bc84934e Enhancements to LLM concurrency to improve overall throughput Eric Rakestraw 2026-04-29 16:04:36 -05:00
  • db6004fadc Implement support for segments with an optional categories key Eric Rakestraw 2026-04-28 22:41:16 -05:00
  • 177e45f1fd Removed historical prototype code Eric Rakestraw 2026-04-28 22:35:32 -05:00
  • e71e5b8faf Replaced the deterministic GrammarOnlyValidator with an LLM-backed grammar_only_guard Eric Rakestraw 2026-04-28 22:29:28 -05:00
  • bbbef37d9a Implemented optional concurrency for the LLM backend Eric Rakestraw 2026-04-28 22:14:25 -05:00
  • f834ffad97 Implemented provider-neutral OpenAI-compatible LLM endpoint support Eric Rakestraw 2026-04-28 21:45:38 -05:00
  • 8cab965abf Implemented support for the seriatim JSON schema for input transcripts Eric Rakestraw 2026-04-27 22:11:19 -05:00
  • b9eef0043b Updated the spoken-word module prompts to preserve intentional emphatic repetition Eric Rakestraw 2026-04-25 14:46:19 -05:00
  • a255ff28b7 Added new deterministic validators to catch early failures Eric Rakestraw 2026-04-25 14:14:43 -05:00
  • 619c615d21 Implemented a custom validator for the glossary module that allows changes from one protected glossary term to another Eric Rakestraw 2026-04-25 13:58:20 -05:00
  • bf05d79fc6 Added a validator to prevent changes that result in an empty or whitespace-only string Eric Rakestraw 2026-04-25 13:42:18 -05:00
  • 5944f13404 Narrowed the grammar module LLM prompt and added support for a <-> an replacements Eric Rakestraw 2026-04-25 13:25:19 -05:00
  • 4724cd16c8 Implemented the grammar LLM review module Eric Rakestraw 2026-04-25 09:06:06 -05:00
  • 52d29f7228 Implemented the spoken_word LLM review module Eric Rakestraw 2026-04-25 08:12:36 -05:00
  • 92c8c371a6 Implemented a --modules CLI flag to allow runtime selection of the modules to be run Eric Rakestraw 2026-04-25 07:48:21 -05:00
  • 2d1d21d314 Completed the MVP for the new Audita refactor Eric Rakestraw 2026-04-24 13:17:36 -05:00
  • 34b3c09e43 Replaced the stub LLM-based validator class with two real LLM-based validator implementations Eric Rakestraw 2026-04-24 11:52:22 -05:00
  • bca2152971 Added an interface for validators, and implemented an initial deterministic validator to protect terms in the provided glossary Eric Rakestraw 2026-04-24 11:08:32 -05:00
  • f39de37974 Moved the current implementation to src/audita_prototype, moved current test suite to tests/audita_prototype, and started a new, more modular application skeleton in src/audita Eric Rakestraw 2026-04-24 10:17:38 -05:00
  • 889b620f2e Update default max segment gap to 4.0 and adjust related tests Eric Rakestraw 2026-04-23 20:50:12 -05:00
  • 3277587e3a Improvements around reporting and work directory retention options Eric Rakestraw 2026-04-23 12:08:44 -05:00
  • c4e2db75f1 Implemented a second-stage validator for grammar corrections that allows homophone-related changes Eric Rakestraw 2026-04-23 11:25:35 -05:00
  • dee6ae4067 More bugfixes in the glossary protection guard Eric Rakestraw 2026-04-23 10:51:47 -05:00
  • 671188aaba Update README with new configuration options and defaults Eric Rakestraw 2026-04-23 07:08:58 -05:00
  • 10bec989ce Raise default LLM confidence thresholds and automatically retry segments with low-confidence corrections Eric Rakestraw 2026-04-22 17:50:18 -05:00
  • d7788da1f4 Implemented a validation step to confirm that grammatical changes do not change substantive meaning Eric Rakestraw 2026-04-22 15:58:05 -05:00
  • 87c47517a0 More bugfixes in the glossary protection guard module Eric Rakestraw 2026-04-22 12:17:52 -05:00
  • 15cdf01f58 Bugfixes in the LLM retry loop Eric Rakestraw 2026-04-22 11:36:24 -05:00
  • 13b81aab2a Extend glossary term protection to the initial glossary LLM stage Eric Rakestraw 2026-04-22 11:15:36 -05:00
  • 183f8ba31d Bugfixes in the glossary protection guard: allow changes toward protected glossary terms, but deny changes away from protected terms Eric Rakestraw 2026-04-22 11:04:35 -05:00
  • 9afb5c5a4e Grammar corrections now run through a deterministic guard that blocks protected glossary names/aliases from being changed Eric Rakestraw 2026-04-22 09:04:00 -05:00
  • e50124fa0d Updated default config values to improve reliability and readability Eric Rakestraw 2026-04-22 08:47:22 -05:00
  • c1672af9b4 Implemented deterministic transcript normalization before the LLM stages Eric Rakestraw 2026-04-22 07:22:40 -05:00
  • 445329de81 Implemented a second LLM stage for grammatical review Eric Rakestraw 2026-04-21 15:42:09 -05:00
  • ca01e46d77 Updated configuration to utilize segment ids provided in the input transcript Eric Rakestraw 2026-04-21 15:01:31 -05:00
  • 7e1a3f721a Added support for multiple LLM passes to correct the transcript based upon the provided glossary Eric Rakestraw 2026-04-21 13:12:08 -05:00
  • 4296e3576e Refactor to request matching/replacement substrings from LLMs, rather than requesting a complete replacement for the full original text Eric Rakestraw 2026-04-21 12:33:15 -05:00
  • 23532cade1 Simplified the json schema passed to the LLM, and implemented more forgiving error handling for LLM proposed corrections Eric Rakestraw 2026-04-21 11:14:56 -05:00
  • 8c80c942dd Updated the LLM prompt to enforce acoustic/phoenetic similarity requirements for proposed corrections Eric Rakestraw 2026-04-21 10:46:00 -05:00
  • 8f6c721f06 Added executable root launcher for audita Eric Rakestraw 2026-04-21 10:19:39 -05:00
  • e10349302f Initial version of application Eric Rakestraw 2026-04-21 10:00:01 -05:00
  • fd0f57274d Initial commit Eric Rakestraw 2026-04-21 14:01:41 +00:00