Multifile processing, prompts config #79
Open
+706
−239
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Outdated suggestions cannot be applied.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.
Currently WIP!
Prompts moved to toml config files, so later prompts can be easily tuned for concrete task. Source code prompt config added to prompts/code.tom
There're some doubts regarding entities capitalization, currently I switched it of, cos for code it harmful I think, mb it's nice to control by parameter, cos it looks like it beneficial for natural language.
Every chunk embeded with metadata now, inserted text has !none in that fields
insert accepts either text or Path object, or list of one of them:
File name, path and chunk number added in entity and relationship extraction.