Add configurable field extraction with rules-first and optional LLM f… - #50
Open
pjargo wants to merge 1 commit into
Open
Add configurable field extraction with rules-first and optional LLM f…#50pjargo wants to merge 1 commit into
pjargo wants to merge 1 commit into
Conversation
…allback New docex/extraction module: fields are declared as label phrases plus a type (money, date, text) in a dict or YAML config; a rules engine finds and type-validates values (same line, then next line), flags conflicting values instead of guessing, and an optional caller-provided llm_fn resolves only the fields the rules miss. Every stored value carries its source and the exact label text that identified it, and documents with missing or conflicting fields are flagged needs_review for metadata search. Includes a default CRE invoice field set, unit and integration tests, and an example. Co-authored-by: Cursor <cursoragent@cursor.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
…allback
New docex/extraction module: fields are declared as label phrases plus a type (money, date, text) in a dict or YAML config; a rules engine finds and type-validates values (same line, then next line), flags conflicting values instead of guessing, and an optional caller-provided llm_fn resolves only the fields the rules miss. Every stored value carries its source and the exact label text that identified it, and documents with missing or conflicting fields are flagged needs_review for metadata search. Includes a default CRE invoice field set, unit and integration tests, and an example.