<!-- .github/pull_request_template.md -->
## Description
<!-- Provide a clear description of the changes in this PR -->
- Created get_default_tasks_by_indices to filter default tasks by
specific indices
- Added get_no_summary_tasks function to skip summarization tasks
- Added get_just_chunks_tasks function for chunk extraction and data
points only
- Added NO_SUMMARIES and JUST_CHUNKS to the TaskGetters enum
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
- **New Features**
- The evaluation configuration now includes expanded task retrieval
options. Users can choose customized modes that bypass summarization or
focus solely on extracting data chunks, offering a more tailored
evaluation experience.
- Enhanced asynchronous task processing brings increased flexibility and
smoother performance during task selection.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
<!-- .github/pull_request_template.md -->
## Description
<!-- Provide a clear description of the changes in this PR -->
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
- **New Features**
- Introduced a class-based retrieval mechanism to enhance answer
generation with improved context extraction and completion.
- Added a new evaluation metric for contextual relevancy and an option
to enable context evaluation during the evaluation process.
- **Refactor**
- Transitioned from a function-based answer resolver to a more modular
retriever approach to improve extensibility.
- **Tests**
- Updated tests to align with the new answer generation and evaluation
process.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Co-authored-by: lxobr <122801072+lxobr@users.noreply.github.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: Daniel Molnar <soobrosa@gmail.com>
Co-authored-by: Boris <boris@topoteretes.com>
<!-- .github/pull_request_template.md -->
## Description
This PR contains eval framework changes due to the autooptimizer
integration
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
- **New Features**
- Enhanced answer generation now returns structured answer details.
- Search functionality accepts configurable prompt inputs.
- Option to generate a metrics dashboard from evaluations.
- Corpus building tasks now support adjustable chunk settings for
greater flexibility.
- New task retrieval functionality allows for flexible task
configuration.
- Introduced new methods for creating and managing metrics dashboards.
- **Refactor/Chore**
- Streamlined API signatures and reorganized module interfaces for
better consistency.
- Updated import paths to reflect new module structure.
- **Tests**
- Updated test scenarios to align with new configurations and parameter
adjustments.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
2025-03-03 19:55:47 +01:00
Renamed from evals/eval_framework/eval_config.py (Browse further)
