⬆️(dependencies) update python dependencies

CHANGELOG.md

@@ -31,7 +31,6 @@ and this project adheres to
 - ✨(backend) add deletion endpoint
 - ✨(backend) add path filter
 - ✨(backend) add search_type param
-- ✨(backend) implement reranker #47
 
 ## Changed
 

src/backend/core/schemas.py

@@ -120,7 +120,6 @@ class SearchQueryParametersSchema(BaseModel):
     order_direction: Optional[Literal["asc", "desc"]] = Field(default="desc")
     nb_results: Optional[conint(ge=1, le=300)] = Field(default=50)
     search_type: Optional[SearchTypeEnum] = Field(default=None)
-    rerank: Optional[bool] = Field(default=None)
 
 
 class DeleteDocumentsSchema(BaseModel):

src/backend/core/services/reranking.py

@@ -1,128 +0,0 @@
-"""Reranking utilities using rerankers library."""
-
-import logging
-from functools import cache
-
-from django.conf import settings
-
-from rerankers import Reranker  # pylint: disable=import-error
-from rerankers.models.ranker import BaseRanker  # pylint: disable=import-error
-
-from core.services.indexing import format_document
-from core.utils import get_language_value
-
-logger = logging.getLogger(__name__)
-
-
-def rerank(query: str, hits: list[dict]) -> list[dict]:
-    """
-    Rerank search results using the configured reranker model.
-
-    Args:
-        query: The search query string
-        hits: List of OpenSearch hit objects with _source containing title and content
-
-    Returns:
-        List of reranked results in the same format as input with a _reranked_score
-    """
-
-    reranker = get_reranker()
-    if reranker is None:
-        logger.warning("Could not import reranker, returning original results")
-        return hits
-
-    try:
-        return _rerank(reranker, query, hits)
-
-    except Exception as e:  # noqa: BLE001# pylint: disable=broad-exception-caught
-        logger.error("Reranking failed: %s, returning original results", str(e))
-        return hits
-
-
-@cache
-def get_reranker() -> BaseRanker | None:
-    """
-    Get the reranker instance.
-    Returns None if the reranker library is not available or if initialization fails but
-    does not raise an exception to avoid crashing the application.
-    """
-    try:
-        logger.info("Initializing reranker model: %s", settings.RERANKER_MODEL_NAME)
-        return Reranker(
-            settings.RERANKER_MODEL_NAME,
-            model_type=settings.RERANKER_MODEL_TYPE,
-            api_key=settings.RERANKER_API_KEY,
-        )
-    except Exception as e:  # noqa: BLE001# pylint: disable=broad-exception-caught
-        logger.error("Failed to initialize reranker: %s", str(e))
-        return None
-
-
-def _rerank(reranker: BaseRanker, query: str, original_hits: list[dict]) -> list[dict]:
-    """Rerank the original results using the provided reranker."""
-    docs, doc_ids = prepare_rerank_data(original_hits)
-
-    logger.info("Reranking %d results for query: %s", len(original_hits), query)
-    reranked = reranker.rank(query=query, docs=docs, doc_ids=doc_ids)
-
-    reranked_results: list[dict] = []
-    for reranked_result in reranked.results:
-        matching_hits = [
-            hit for hit in original_hits if hit["_id"] == reranked_result.doc_id
-        ]
-
-        if not matching_hits:
-            logger.warning(
-                "Reranked document ID %s not found in original hits, skipping",
-                reranked_result.doc_id,
-            )
-            continue
-
-        if len(matching_hits) > 1:
-            logger.warning(
-                "Multiple hits found for document ID %s, using first match",
-                reranked_result.doc_id,
-            )
-
-        hit = matching_hits[0]
-        hit["_reranked_score"] = reranked_result.score
-        reranked_results.append(hit)
-
-    logger.info("Reranking completed, returned %d results", len(reranked_results))
-
-    return reranked_results
-
-
-def prepare_rerank_data(original_hits: list[dict]) -> tuple[list[str], list[str]]:
-    """
-    Prepare the documents for reranking by extracting the title and content from the original hits.
-    """
-    docs = []
-    doc_ids = []
-    for hit in original_hits:
-        title = get_language_value(hit["_source"], "title")
-        content = get_language_value(hit["_source"], "content")
-
-        docs.append(format_document(title, content))
-        doc_ids.append(hit["_id"])
-
-    return docs, doc_ids
-
-
-def should_rerank(is_rerank_requested: bool | None) -> bool:
-    """
-    Determine whether to perform reranking based on the input parameter and settings.
-    logs warning if reranking was explicitly requested but the reranker is disabled in settings.
-    falls back to settings.RERANKER_ENABLED if is_rerank_requested is None.
-    """
-    if is_rerank_requested and not settings.RERANKER_ENABLED:
-        logger.warning(
-            "Reranking was explicitly requested but the reranker "
-            "is disabled in settings. Reranking skipped."
-        )
-        return False
-
-    if is_rerank_requested is None:
-        return settings.RERANKER_ENABLED
-
-    return is_rerank_requested and settings.RERANKER_ENABLED

src/backend/core/services/search.py

@@ -9,7 +9,6 @@ from core.enums import SearchTypeEnum
 
 from .embedding import embed_text
 from .opensearch import check_hybrid_search_enabled, opensearch_client
-from .reranking import rerank, should_rerank
 
 logger = logging.getLogger(__name__)
 
@@ -28,7 +27,6 @@ def search(  # noqa : PLR0913
     tags,
     search_type,
     path=None,
-    rerank_requested=None,
 ):
     """Perform an OpenSearch search"""
     query = get_query(
@@ -42,7 +40,7 @@ def search(  # noqa : PLR0913
         path=path,
         search_type=search_type,
     )
-    response = opensearch_client().search(  # pylint: disable=unexpected-keyword-arg
+    return opensearch_client().search(  # pylint: disable=unexpected-keyword-arg
         index=",".join(search_indices),
         body={
             "_source": enums.SOURCE_FIELDS,  # limit the fields to return
@@ -64,14 +62,6 @@ def search(  # noqa : PLR0913
         ignore_unavailable=True,
     )
 
-    if should_rerank(rerank_requested) and q != "*":
-        response["hits"]["hits"] = rerank(
-            query=q,
-            hits=response["hits"]["hits"],
-        )
-
-    return response
-
 
 # pylint: disable=too-many-arguments, too-many-positional-arguments
 def get_query(  # noqa : PLR0913

src/backend/core/tests/test_api_documents_search.py

@@ -8,7 +8,6 @@ of documents is slow and better done only once.
 import logging
 import operator
 import random
-from unittest import mock
 
 import pytest
 import responses
@@ -994,36 +993,3 @@ def test_api_documents_search_filtering_by_path(settings):
     assert len(response.json()) == 2
     for hit in response.json():
         assert hit["_source"]["path"].startswith(path_filter)
-
-
-@responses.activate
-@mock.patch("core.services.reranking.rerank")
-def test_api_documents_rerank_blocked(
-    mock_rerank,
-    settings,
-    caplog,
-):
-    """Test can disable rerank at run time even when enabled in settings"""
-    settings.RERANKER_ENABLED = True
-
-    setup_oicd_resource_server(responses, settings, sub="user_sub")
-    service = factories.ServiceFactory()
-
-    documents = bulk_create_documents([{"title": "Fox"}, {"title": "Wolf"}])
-    prepare_index(service.index_name, documents)
-    mock_rerank.return_value = documents
-
-    with caplog.at_level(logging.INFO):
-        response = APIClient().post(
-            "/api/v1.0/documents/search/",
-            {
-                "q": "programming",
-                "rerank": False,
-                "visited": [doc["id"] for doc in documents],
-            },
-            format="json",
-            HTTP_AUTHORIZATION=f"Bearer {build_authorization_bearer()}",
-        )
-
-    assert response.status_code == 200
-    assert not mock_rerank.called

src/backend/core/tests/test_reranking.py

@@ -1,140 +0,0 @@
-"""
-Test suite for reranking service
-"""
-
-import logging
-from unittest.mock import MagicMock, patch
-
-import pytest
-
-from core.services.reranking import rerank
-
-pytestmark = pytest.mark.django_db
-
-logger = logging.getLogger(__name__)
-
-
-ORIGINAL_HITS = [
-    {
-        "_id": "doc-1",
-        "_score": 1.5,
-        "_source": {
-            "title.en": "Dogs and wolves",
-            "content.en": "Dogs are domesticated wolves",
-        },
-    },
-    {
-        "_id": "doc-2",
-        "_score": 1.2,
-        "_source": {
-            "title.en": "Cats as pets",
-            "content.en": "Cats are popular pets",
-        },
-    },
-    {
-        "_id": "doc-3",
-        "_score": 1.0,
-        "_source": {
-            "title.en": "Birds in nature",
-            "content.en": "Birds fly in the sky",
-        },
-    },
-]
-
-RERANKER_RESULTS = [
-    {"doc_id": "doc-2", "score": 0.95},
-    {"doc_id": "doc-1", "score": 0.87},
-    {"doc_id": "doc-3", "score": 0.45},
-]
-
-
-@pytest.fixture(name="get_reranker")
-def mock_get_reranker():
-    """Mock reranker result with reranked scores"""
-    with patch("core.services.reranking.get_reranker") as mocked_get_reranker:
-        reranker_result = MagicMock()
-
-        reranker_result.results = [
-            MagicMock(**reranker_result) for reranker_result in RERANKER_RESULTS
-        ]
-
-        mock_reranker = MagicMock()
-        mock_reranker.rank.return_value = reranker_result
-        mocked_get_reranker.return_value = mock_reranker
-
-        # Yield both the patched function and the mock reranker instance
-        yield mock_reranker
-
-
-@patch("core.services.reranking.get_reranker")
-def test_return_original_results_if_reranker_import_fails(mocked_get_reranker, caplog):
-    """Test that original results are returned if reranker import fails"""
-    mocked_get_reranker.return_value = None
-
-    with caplog.at_level(logging.WARNING):
-        result = rerank("test query", ORIGINAL_HITS)
-
-    assert result == ORIGINAL_HITS
-    assert any(
-        "Could not import reranker, returning original results" in message
-        for message in caplog.messages
-    )
-
-
-@patch("core.services.reranking.get_reranker")
-def test_return_original_results_if_reranking_fails(mocked_get_reranker, caplog):
-    """Test that original results are returned if reranking fails"""
-    mock_reranker = MagicMock()
-    mock_reranker.rank.side_effect = Exception("Reranking service error")
-    mocked_get_reranker.return_value = mock_reranker
-
-    q = "test query"
-    with caplog.at_level(logging.ERROR):
-        result = rerank(q, ORIGINAL_HITS)
-
-    assert result == ORIGINAL_HITS
-    assert any(
-        "Reranking failed: Reranking service error, returning original results"
-        in message
-        for message in caplog.messages
-    )
-
-
-def test_reranking_success(get_reranker, caplog):
-    """Test successful reranking of search results"""
-    mock_reranker = get_reranker
-
-    q = "test query"
-    with caplog.at_level(logging.INFO):
-        reranked_hits = rerank(q, ORIGINAL_HITS.copy())
-
-    assert any(
-        f"Reranking 3 results for query: {q}" in message for message in caplog.messages
-    )
-    assert any(
-        "Reranking completed, returned 3 results" in message
-        for message in caplog.messages
-    )
-
-    mock_reranker.rank.assert_called_once()
-    call_args = mock_reranker.rank.call_args
-    assert call_args.kwargs["query"] == q
-    assert len(call_args.kwargs["docs"]) == len(RERANKER_RESULTS)
-
-    for ranked_hit_index, ranked_hit in enumerate(reranked_hits):
-        reranker_result = RERANKER_RESULTS[ranked_hit_index]
-        expected_doc_id = reranker_result["doc_id"]
-        expected_score = reranker_result["score"]
-        expected_reranked_hit = ORIGINAL_HITS[
-            next(
-                _hit_index
-                for _hit_index, hit in enumerate(ORIGINAL_HITS)
-                if hit["_id"] == expected_doc_id
-            )
-        ]
-
-        assert expected_doc_id == ranked_hit["_id"]
-        assert expected_reranked_hit["_id"] == ranked_hit["_id"]
-        assert expected_reranked_hit["_source"] == ranked_hit["_source"]
-        assert expected_reranked_hit["_score"] == ranked_hit["_score"]
-        assert expected_score == expected_reranked_hit["_reranked_score"]

src/backend/core/tests/test_search.py

@@ -5,7 +5,6 @@ Test suite for opensearch search service
 import logging
 import operator
 from json import dumps as json_dumps
-from unittest.mock import patch
 
 import pytest
 import responses
@@ -713,58 +712,3 @@ def test_search_filtering_by_query_path_and_tag():
 
     assert result["hits"]["total"]["value"] == len(documents_to_search)
     assert returned_ids == expected_ids
-
-
-# pylint: disable=too-many-arguments, too-many-positional-arguments
-@responses.activate
-@patch("core.services.search.rerank")
-@pytest.mark.parametrize(
-    "rerank_requested, reranker_enabled, rerank_called, caplog_messages",
-    [
-        (True, True, True, []),
-        (
-            True,
-            False,
-            False,
-            [
-                "Reranking was explicitly requested but the reranker is "
-                "disabled in settings. Reranking skipped."
-            ],
-        ),
-        (False, True, False, []),
-        (False, False, False, []),
-        (None, False, False, []),
-        (None, True, True, []),
-    ],
-)
-def test_search_rerank(  # noqa : PLR0913
-    mock_rerank,
-    rerank_requested,
-    reranker_enabled,
-    rerank_called,
-    caplog_messages,
-    settings,
-    caplog,
-):
-    """Test that rerank activation according to args and settings"""
-    settings.RERANKER_ENABLED = reranker_enabled
-
-    documents = bulk_create_documents(
-        [
-            {"title": "wolf", "content": "wolves live in packs and hunt together"},
-            {"title": "dog", "content": "dogs are loyal domestic animals"},
-            {"title": "cat", "content": "cats are curious and independent pets"},
-        ]
-    )
-    mock_rerank.return_value = documents
-    service = factories.ServiceFactory(name=SERVICE_NAME)
-    prepare_index(service.index_name, documents)
-
-    with caplog.at_level(logging.INFO):
-        search(
-            q="canine pet", rerank_requested=rerank_requested, **search_params(service)
-        )
-
-    assert mock_rerank.called == rerank_called
-    for message in caplog_messages:
-        assert message in caplog.text

src/backend/core/views.py

@@ -354,9 +354,6 @@ class SearchDocumentView(ResourceServerMixin, views.APIView):
             - 'full_text': Uses only full-text search, even if hybrid search is enabled
                 on the server.
             if the not specified, the server will use hybrid search when enabled
-        rerank : bool, optional
-            Enable or disable reranking of results. If not specified, falls back to
-            the RERANKER_ENABLED setting.
 
         Returns:
         --------
@@ -367,6 +364,7 @@ class SearchDocumentView(ResourceServerMixin, views.APIView):
         # Get list of groups related to the user from SCIM provider (consider caching result)
         audience = self._get_service_provider_audience()
         user_sub = self.request.user.sub
+        groups = []
         params = schemas.SearchQueryParametersSchema(**request.data)
 
         # Get index list for search query
@@ -389,7 +387,7 @@ class SearchDocumentView(ResourceServerMixin, views.APIView):
             reach=params.reach,
             visited=params.visited,
             user_sub=user_sub,
-            groups=[],
+            groups=groups,
             tags=params.tags,
             path=params.path,
             search_type=params.search_type
@@ -397,7 +395,6 @@ class SearchDocumentView(ResourceServerMixin, views.APIView):
             else SearchTypeEnum.HYBRID
             if check_hybrid_search_enabled()
             else SearchTypeEnum.FULL_TEXT,
-            rerank_requested=params.rerank,
         )["hits"]["hits"]
         logger.info("found %d results", len(result))
         logger.debug("results %s", result)

src/backend/find/settings.py

@@ -319,24 +319,6 @@ class Base(Configuration):
         default=1024, environ_name="EMBEDDING_DIMENSION", environ_prefix=None
     )
 
-    # Reranking
-    RERANKER_ENABLED = values.BooleanValue(
-        default=False, environ_name="RERANKER_ENABLED", environ_prefix=None
-    )
-    RERANKER_MODEL_NAME = values.Value(
-        default=None,
-        environ_name="RERANKER_MODEL_NAME",
-        environ_prefix=None,
-    )
-    RERANKER_MODEL_TYPE = values.Value(
-        default=None,
-        environ_name="RERANKER_MODEL_TYPE",
-        environ_prefix=None,
-    )
-    RERANKER_API_KEY = values.Value(
-        default=None, environ_name="RERANKER_API_KEY", environ_prefix=None
-    )
-
     # CORS
     CORS_ALLOW_CREDENTIALS = True
     CORS_ALLOW_ALL_ORIGINS = values.BooleanValue(True)

src/backend/pyproject.toml

@@ -23,32 +23,31 @@ description = "An application to print markdown to pdf from a set of managed tem
 keywords = ["Django", "Contacts", "Templates", "RBAC"]
 license = { file = "LICENSE" }
 readme = "README.md"
-requires-python = "~=3.12.0"
+requires-python = "~=3.14.3"
 dependencies = [
     "celery[redis]==5.6.2",
     "django-configurations==2.5.1",
     "django-cors-headers==4.9.0",
-    "redis==5.3.1",
+    "redis==7.3.0",
     "django-redis==6.0.0",
-    "django==5.2.12",
-    "django-lasuite[all]==0.0.22",
+    "django==6.0.3",
+    "django-lasuite[all]==0.0.25",
     "djangorestframework==3.16.1",
     "drf_spectacular==0.29.0",
-    "dockerflow==2024.4.2",
+    "dockerflow==2026.3.4",
     "factory_boy==3.3.3",
-    "gunicorn==23.0.0",
+    "gunicorn==25.1.0",
     "py3langid==0.3.0",
-    "langchain-text-splitters==1.1.0",
+    "langchain-text-splitters==1.1.1",
     "mozilla-django-oidc==5.0.2",
-    "psycopg[binary]==3.3.2",
+    "psycopg[binary]==3.3.3",
     "pydantic==2.12.5",
     "pyjwt==2.10.1",
     "requests==2.32.5",
-    "rerankers[api]==0.10.0",
-    "sentry-sdk==2.48.0",
+    "sentry-sdk==2.54.0",
     "url-normalize==2.2.1",
     "opensearch-py==3.1.0",
-    "whitenoise==6.11.0",
+    "whitenoise==6.12.0",
 ]
 
 [project.urls]
@@ -60,21 +59,21 @@ dependencies = [
 [project.optional-dependencies]
 dev = [
     "django-extensions==4.1",
-    "drf-spectacular-sidecar==2026.1.1",
-    "faker==40.1.0",
+    "drf-spectacular-sidecar==2026.3.1",
+    "faker==40.11.0",
     "ipdb==0.13.13",
-    "ipython==9.8.0",
-    "pyfakefs==6.0.0",
+    "ipython==9.11.0",
+    "pyfakefs==6.1.5",
     "pylint-django==2.7.0",
-    "pylint==4.0.4",
+    "pylint==4.0.5",
     "pytest-cov==7.0.0",
-    "pytest-django==4.11.1",
+    "pytest-django==4.12.0",
     "pytest==9.0.2",
     "pytest-icdiff==0.9",
     "pytest-xdist==3.8.0",
-    "responses==0.25.8",
-    "ruff==0.14.10",
-    "types-requests==2.32.4.20250913",
+    "responses==0.26.0",
+    "ruff==0.15.6",
+    "types-requests==2.32.4.20260107",
 ]
 
 [tool.setuptools]

src/backend/uv.lock

@@ -514,7 +514,6 @@ dependencies = [
     { name = "pyjwt" },
     { name = "redis" },
     { name = "requests" },
-    { name = "rerankers", extra = ["api"] },
     { name = "sentry-sdk" },
     { name = "url-normalize" },
     { name = "whitenoise" },
@@ -575,7 +574,6 @@ requires-dist = [
     { name = "pytest-xdist", marker = "extra == 'dev'", specifier = "==3.8.0" },
     { name = "redis", specifier = "==5.3.1" },
     { name = "requests", specifier = "==2.32.5" },
-    { name = "rerankers", extras = ["api"], specifier = "==0.10.0" },
     { name = "responses", marker = "extra == 'dev'", specifier = "==0.25.8" },
     { name = "ruff", marker = "extra == 'dev'", specifier = "==0.14.10" },
     { name = "sentry-sdk", specifier = "==2.48.0" },
@@ -1419,20 +1417,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/3f/51/d4db610ef29373b879047326cbf6fa98b6c1969d6f6dc423279de2b1be2c/requests_toolbelt-1.0.0-py2.py3-none-any.whl", hash = "sha256:cccfdd665f0a24fcf4726e690f65639d272bb0637b9b92dfd91a5568ccf6bd06", size = 54481, upload-time = "2023-05-01T04:11:28.427Z" },
 ]
 
-[[package]]
-name = "rerankers"
-version = "0.10.0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/a2/1e/3ed2026be7c135939905eac4f50d1bf8339180821c6757b2e91b83de2fa5/rerankers-0.10.0.tar.gz", hash = "sha256:b8e8b363abc4e9757151956949c27b197993c0a774437287a932f855afc17a73", size = 49679, upload-time = "2025-05-22T08:22:53.396Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/df/ed/f3b81ca8743d69b95d679b95e6e1d22cb7cc678ae77c6a57827303a7e48c/rerankers-0.10.0-py3-none-any.whl", hash = "sha256:634a6befa130a245ed46022ade217ee482869448f01aae2051ed54d7d5bd2791", size = 53084, upload-time = "2025-05-22T08:22:52.022Z" },
-]
-
-[package.optional-dependencies]
-api = [
-    { name = "requests" },
-]
-
 [[package]]
 name = "responses"
 version = "0.25.8"