Feat: add support for scoring function #1594

Samoed · 2024-12-14T19:05:11Z

Checklist

Run tests locally to make sure nothing is broken using make test.
Run the formatter to format the code using make lint.

Currently, there is no way to specify the scoring function except by passing it as kwargs, but ColBERT models require it.

Ref #1592 (comment)
Closes #1589

@sam-hey

KennethEnevoldsen

I really appreciate this PR, but I believe this should be done using the model implemented similarity metric:

mteb/mteb/encoder_interface.py

Line 71 in b466051

def similarity(

Samoed · 2024-12-15T10:46:46Z

I've aligned RetrievalEvaluator with the other evaluators. It now uses model.similarity.

KennethEnevoldsen

I like this a lot better. Should we move it to v2.0.0?

mteb/evaluation/evaluators/RetrievalEvaluator.py

KennethEnevoldsen · 2024-12-15T19:36:21Z

mteb/evaluation/evaluators/RetrievalEvaluator.py

            if is_nan.sum() > 0:
                logger.warning(
                    f"Found {is_nan.sum()} NaN values in the similarity scores. Replacing NaN values with -1."
                )
-            cos_scores[is_nan] = -1
+            similarity_scores[is_nan] = -1


I might have actually removed this over in v2.0.0 (it is not needed)

KennethEnevoldsen · 2024-12-15T19:36:35Z

mteb/evaluation/evaluators/RetrievalEvaluator.py

@@ -112,21 +100,12 @@ def search(
        corpus: dict[str, dict[str, str]],
        queries: dict[str, str | list[str]],
        top_k: int,
-        score_function: str,


breaking? should we move to v2.0.0?

I don't think this is very breaking because, in the implementation from the main branch, score_function can only be passed with evaluator.run, and I doubt many users have specified this.

Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsen@gmail.com>

Samoed · 2024-12-15T19:53:14Z

This PR can be moved to 2.0, but this change mainly benefits ColBert and I don't think it will break anything. However, if you believe it's breaking, I can move it to 2.0.

KennethEnevoldsen · 2024-12-15T19:55:31Z

So technically breaking, in practice not breaking. I agree with that. Let's keep it as it is and merge this in.

Samoed · 2024-12-15T20:13:14Z

Also found that BitextMiningEvaluator uses cosine as score function. I think this also should be changed

mteb/mteb/evaluation/evaluators/BitextMiningEvaluator.py

Line 112 in 992b20b

score_function=cos_sim,

Because PairClassification , STSEvaluator and SummarizatonEvaluator already can use model.similarity

KennethEnevoldsen · 2024-12-15T22:15:44Z

Would love to add that as well. Feel free to add it in a separate PR and merge this one though

* feat: add new arctic v2.0 models (#1574) * feat: add new arctic v2.0 models * chore: make lint * 1.24.0 Automatically generated by python-semantic-release * fix: Add namaa MrTydi reranking dataset (#1573) * Add dataset class and file requirements * pass tests * make lint changes * adjust meta data and remove load_data --------- Co-authored-by: Omar Elshehy <omarelshehy@Omars-MacBook-Pro.local> * Update tasks table * 1.24.1 Automatically generated by python-semantic-release * fix: Eval langs not correctly passed to monolingual tasks (#1587) * fix SouthAfricanLangClassification.py * add check for langs * lint * 1.24.2 Automatically generated by python-semantic-release * feat: Add ColBert (#1563) * feat: add max_sim operator for IR tasks to support multi-vector models * docs: add doc for Model2VecWrapper.__init__(...) * feat: add ColBERTWrapper to models & add ColBERTv2 * fix: resolve issues * fix: resolve issues * Update README.md Co-authored-by: Roman Solomatin <samoed.roman@gmail.com> * Update README.md Co-authored-by: Isaac Chung <chungisaac1217@gmail.com> * Update README.md Co-authored-by: Isaac Chung <chungisaac1217@gmail.com> * Update mteb/evaluation/evaluators/RetrievalEvaluator.py Co-authored-by: Isaac Chung <chungisaac1217@gmail.com> * Update README.md Co-authored-by: Isaac Chung <chungisaac1217@gmail.com> * README.md: rm subset * doc: update example for Late Interaction * get colbert running without errors * fix: pass is_query to pylate * fix: max_sim add pad_sequence * feat: integrate Jinja templates for ColBERTv2 and add model prompt handling * feat: add revision & prompt_name * doc: pad_sequence * rm TODO jina colbert v2 * doc: warning: higher resource usage for MaxSim --------- Co-authored-by: sam021313 <40773225+sam021313@users.noreply.github.com> Co-authored-by: Roman Solomatin <samoed.roman@gmail.com> Co-authored-by: Isaac Chung <chungisaac1217@gmail.com> * 1.25.0 Automatically generated by python-semantic-release * doc: colbert add score_function & doc section (#1592) * doc: colbert add score_function & doc section * doc: Update README.md Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsen@gmail.com> * doc: Update README.md Co-authored-by: Isaac Chung <chungisaac1217@gmail.com> --------- Co-authored-by: sam021313 <40773225+sam021313@users.noreply.github.com> Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsen@gmail.com> Co-authored-by: Isaac Chung <chungisaac1217@gmail.com> * Feat: add support for scoring function (#1594) * add support for scoring function * lint * move similarity to wrapper * remove score function * lint * remove from InstructionRetrievalEvaluator * Update mteb/evaluation/evaluators/RetrievalEvaluator.py Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsen@gmail.com> * remove score function from README.md --------- Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsen@gmail.com> * Add new models nvidia, gte, linq (#1436) * Add new models nvidia, gte, linq * add warning for gte-Qwen and nvidia models re: instruction used in docs as well --------- Co-authored-by: isaac-chung <chungisaac1217@gmail.com> * Leaderboard: Refined plots (#1601) * Added embedding size guide to performance-size plot, removed shading on radar chart * Changed plot names to something more descriptive * Made plots failsafe * fix: Leaderboard refinements (#1603) * Added explanation of aggregate measures * Added download button to result tables * Task info gets sorted by task name * Added custom, shareable links for each benchmark * Moved explanation of aggregate metrics to the summary tab * 1.25.1 Automatically generated by python-semantic-release * Feat: Use similarity scores if available (#1602) * Use similarity scores if available * lint * Add NanoBEIR Datasets (#1588) * add NanoClimateFeverRetrieval task, still requires some debugging * move task to correct place in init file * add all Nano datasets and results * format code * Update mteb/tasks/Retrieval/eng/tempCodeRunnerFile.py Co-authored-by: Roman Solomatin <samoed.roman@gmail.com> * pin revision to commit and add datasets to benchmark.py * create new benchmark for NanoBEIR * add revision when loading datasets * lint --------- Co-authored-by: Roman Solomatin <samoed.roman@gmail.com> Co-authored-by: isaac-chung <chungisaac1217@gmail.com> * Update tasks table * Feat: Evaluate missing languages (#1584) * init * fix tests * update mock retrieval * update tests * use subsets instead of langs * Apply suggestions from code review Co-authored-by: Isaac Chung <chungisaac1217@gmail.com> * fix tests * add to readme * rename subset in readme --------- Co-authored-by: Isaac Chung <chungisaac1217@gmail.com> * Add IBM Granite Embedding Models (#1613) * add IBM granite embedding models * lint formatting * add adapted_from and superseded_by to ModelMeta * fix: disable co2_tracker for API models (#1614) * 1.25.2 Automatically generated by python-semantic-release * fix: set `use_instructions` to True in models using prompts (#1616) feat: set `use_instructions` to True in models using prompts * 1.25.3 Automatically generated by python-semantic-release * update RetrievalEvaluator.py * update imports * update imports and metadata * fix tests * fix tests * fix output path for retrieval * fix similarity function --------- Co-authored-by: Daniel Buades Marcos <daniel.buades@clinia.com> Co-authored-by: github-actions <github-actions@github.com> Co-authored-by: Omar Elshehy <41394057+omarelshehy@users.noreply.github.com> Co-authored-by: Omar Elshehy <omarelshehy@Omars-MacBook-Pro.local> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: Sam <40773225+sam-hey@users.noreply.github.com> Co-authored-by: sam021313 <40773225+sam021313@users.noreply.github.com> Co-authored-by: Isaac Chung <chungisaac1217@gmail.com> Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsen@gmail.com> Co-authored-by: Alexey Vatolin <vatolinalex@gmail.com> Co-authored-by: Márton Kardos <power.up1163@gmail.com> Co-authored-by: KGupta10 <92774828+KGupta10@users.noreply.github.com> Co-authored-by: Aashka Trivedi <aashka.trivedi@gmail.com>

Samoed added 2 commits December 14, 2024 22:01

add support for scoring function

2498b9f

lint

a842dc6

Samoed requested a review from KennethEnevoldsen December 14, 2024 19:05

KennethEnevoldsen reviewed Dec 14, 2024

View reviewed changes

Samoed added 2 commits December 15, 2024 13:43

move similarity to wrapper

b440df7

remove score function

ebdddb7

Samoed added 2 commits December 15, 2024 13:47

lint

017b184

remove from InstructionRetrievalEvaluator

3a75c39

KennethEnevoldsen approved these changes Dec 15, 2024

View reviewed changes

Update mteb/evaluation/evaluators/RetrievalEvaluator.py

9ad1668

Co-authored-by: Kenneth Enevoldsen <kennethcenevoldsen@gmail.com>

Samoed added 2 commits December 15, 2024 23:04

Merge branch 'refs/heads/main' into add_support_for_score_funstion

115dc0e

remove score function from README.md

53c7567

Samoed merged commit 8e6ee46 into main Dec 15, 2024
10 checks passed

Samoed deleted the add_support_for_score_funstion branch December 15, 2024 23:32

Samoed mentioned this pull request Dec 16, 2024

Feat: Use similarity scores if available #1602

Merged

2 tasks

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Feat: add support for scoring function #1594

Feat: add support for scoring function #1594

Samoed commented Dec 14, 2024 •

edited

Loading

KennethEnevoldsen left a comment •

edited

Loading

Samoed commented Dec 15, 2024

KennethEnevoldsen left a comment

KennethEnevoldsen Dec 15, 2024

KennethEnevoldsen Dec 15, 2024

Samoed Dec 15, 2024

Samoed commented Dec 15, 2024

KennethEnevoldsen commented Dec 15, 2024

Samoed commented Dec 15, 2024

KennethEnevoldsen commented Dec 15, 2024

Feat: add support for scoring function #1594

Feat: add support for scoring function #1594

Conversation

Samoed commented Dec 14, 2024 • edited Loading

Checklist

KennethEnevoldsen left a comment • edited Loading

Choose a reason for hiding this comment

Samoed commented Dec 15, 2024

KennethEnevoldsen left a comment

Choose a reason for hiding this comment

KennethEnevoldsen Dec 15, 2024

Choose a reason for hiding this comment

KennethEnevoldsen Dec 15, 2024

Choose a reason for hiding this comment

Samoed Dec 15, 2024

Choose a reason for hiding this comment

Samoed commented Dec 15, 2024

KennethEnevoldsen commented Dec 15, 2024

Samoed commented Dec 15, 2024

KennethEnevoldsen commented Dec 15, 2024

Samoed commented Dec 14, 2024 •

edited

Loading

KennethEnevoldsen left a comment •

edited

Loading