Added partially extracted slots support for the GroupSlots #394
Conversation
There was a problem hiding this comment.
It appears this PR is a release PR (change its base from master if that is not the case).
Here's a release checklist:
- Update package version
- Update
poetry.lock - Change PR merge option
- Update template repo
- Search for objects to be deprecated
- Test parts not covered with pytest:
- web_api tutorials
- Test integrations with external services (telegram; stats)
|
llm_response must inherit from BaseResponse |
- Simplify slot regexps - More extensive tests for slot storage changes
|
I don't like name regex in this tutorial. For example, here I use email and bitcoin address which both have fairly unique regex (i.e. unlikely false positives -> more options with requests): (regex for these can be found here; although email regex is pretty long, this might be better) Also, I don't think that |
|
Consider adding way of defining minimal slots required for the group extraction to succeed |
# Description Added flag `allow_partial_extraction` to the `GroupSlot` class constructor. If `True`, group slot only saves successfully extracted sub-slots. --------- Co-authored-by: Roman Zlobin <RLKRo@proton.me>
# Changelog ## Breaking Changes - Dropped support for python 3.8; added support for python 3.12 (#400); - Reworked DB architecture to support partials turn reads/writes (#93). Old Context storages are incompatible with the new ones. See tutorial Context Storages: 8 for more info; - `Context.labels`, `Context.requests`, `Context.responses` are now only lazily loaded (#93). Items from older turns can be loaded on demand. Their `__getitem__` and `get` methods are now async. ## Features - Added `LLMResponse` and `LLMCondition` classes that allow using LLMs (#376). See the new LLM Integration tutorials and LLM user guide for more info; - Added option to extract group slots partially (#394). See tutorial Slots: 2 for more information; - `Message.original_message` is replaced with `Message.origin` which stores both the original message and the interface from which the message originated (#398); - Added `Context.current_turn_id` field which stores the number of the current turn (#93); - Added `Context.created_at`, `Context.updated_at` timestamp fields (#93); - Added `Context.turns` property which allows iterating over requests/labels/responses by their turn ids (#93); - `Context.labels`, `Context.requests`, `Context.responses` now support slicing (#93). `__getitem__`, `__setitem__` and `__delitem__` methods can now accept slices of turn ids in addition to single turn id. `get` method can now accepts iterable of turn ids in addition to single turn id. ## Documentation - Documentation is now versioned (#346, #409). You can select preferred version via the drop-down menu in the top-right corner. ## Developer changes - Context now has field `origin_interface` to store name of the interface that created it (#398); - Added script `docs_no_docker` for building documentation without docker (ef11ff9); - Added in-RAM context storage to be the default one instead of a plain dict (#93); - Removed methods `Context.add_request`, `Context.add_label` and `Context.add_response` (#93). Use setters with `Context.current_turn_id` instead.
Description
Added flag
allow_partially_extractedto theGroupSlotclass constructor. IfTruenon extracted slots from Group Slot would not be overwritten with default values.Checklist