refactor: change rerank interface from map-based to vector-based (#458)
* refactor: change rerank interface from map-based to vector-based (#452) - Define QueryResult = list[Doc] type alias in doc.py - Change C++ Reranker::rerank() signature from map<string, DocPtrList> to vector<DocPtrList> - Extend bind_schema() to accept field_names for index-based field lookup - Update ScoreBasedReranker/WeightedReranker/CallbackReranker implementations - Adapt collection.cc MultiQuery path to use vector<DocPtrList> - Update Python binding to expose rerank() and use vector<double> weights - Refactor Python RerankFunction interface to list[QueryResult] -> QueryResult - Remove Python-layer rerank logic from RrfReRanker/WeightedReRanker (delegate to C++) - Update query_executor to return list[list[Doc]] instead of dict - Update all related unit tests (C++ and Python) * refactor: replace list[Doc] with QueryResult type alias in executor and rerank functions * refactor: replace list[list[Doc]] with list[QueryResult] in query_executor * fix: remove unused Doc import in rerank_function.py (ruff F401) * refactor(query_executor): merge duplicate rerank return paths * refactor: RrfReRanker/WeightedReRanker.rerank() directly call C++ reranker * refactor: simplify QueryExecutor into unified class, remove Factory/subclasses/validation/concurrency * refactor: rename _VectorQuery to _SearchQuery, from_vector_query to from_search_query * refactor(query_executor): split execute into single/multi paths, rename core_vector to search_query, drop unused core_vectors * style: apply ruff formatter to test_reranker.py and query_executor.py * refactor: make rescore() private in ScoreBasedReranker hierarchy * style: apply clang-format to reranker.h * style: apply clang-format to all modified C++ files * refactor: rename private methods in QueryExecutor for clearer semantics * refactor: rename mvq to multi_query for clarity * fix: make BasicRRF test order-independent for equal scores * fix: update collection_test to use vector-based reranker interface * fix: update reranker tests to expect TypeError instead of NotImplementedError * refactor: remove PendingQuery wrapper, use SearchQuery directly in MultiQuery path * refactor: simplify MultiQuery path - remove seen_fields, merge field_names into main loop * fix: address review comments - defensive checks and remove fields param from C API - ScoreBasedReranker::rerank(): early return empty list when topn <= 0 - WeightedReranker::rescore(): null-check schema_ before use - CallbackReranker::rerank(): check callback_ is not empty before invoke - C API zvec_reranker_create_weighted(): remove unused fields parameter * fix: remove duplicate field name test (check was intentionally removed) * fix: address egolearner review comments - Rename QueryResult to DocList for clarity (见名知义) - Change docstring to #: comment for type alias - Fix output_fields check: use 'is not None' instead of truthy check (None means unset, [] means explicit empty list - different semantics) - Raise ValueError when search-by-id finds no document * refactor: remove redundant output_fields assignment in _build_search_query * refactor: address egolearner review comments (C++ refactoring) - c_api.cc: simplify weighted reranker creation with inline vector ctor - python_reranker.cc: refactor unwrap_rerank_result - take by value, early error return, move semantics - Rename C API functions for consistent naming: zvec_reranker_create_rrf -> zvec_create_rrf_reranker zvec_reranker_create_weighted -> zvec_create_weighted_reranker zvec_reranker_destroy -> zvec_destroy_reranker zvec_reranker_get_rank_constant -> zvec_get_reranker_rank_constant - reranker.h/cc: bind_schema returns Result<void>, caches vector<const FieldSchema*> to avoid repeated schema lookups in rescore - python_param.cc: rename py::arg vector_query to search_query * revert: rollback bind_schema refactoring due to thread-safety concern The field_schemas_ caching approach introduces a data race when the same WeightedReranker instance is shared across concurrent queries: bind_schema() writes field_schemas_ while rerank() reads it concurrently. Revert to storing schema_ + field_names_ and looking up fields in rescore(). Add @note thread-safety warning to WeightedReranker class documentation. * fix: unify error message format in collection.cc Change 'Vector field not found: X' to 'Invalid query: field X not found' for consistent error formatting as suggested by zhourrr. * fix: sort __all__ and remove duplicates in __init__.pyi Fix RUF022 lint error: sort __all__ alphabetically and remove duplicate entries (DenseEmbeddingFunction, ReRanker). * style: format query_executor.py with ruff formatter * fix: resolve Python test failures after FTS rebase integration - test_query_executor.py: update method names to match refactored API (_do_build -> _build_queries, _do_merge_rerank_results -> _merge_and_rerank) - test_reranker.py: fix expected exception type (TypeError from pybind11) - test_collection_fts.py: update error message match patterns - test_collection_fts_vector_hybrid.py: remove obsolete 'metrics' param, update weights from dict to positional list, adapt validation tests for multi-vector queries (now supported with reranker) - test_collection_dql.py: remove 'metrics' param, update weights format - collection.cc: distinguish FTS vs vector fields in MultiQuery path using get_fts_clause() to route field lookup correctly - reranker.cc: use get_field() instead of get_vector_field() in rescore to support FTS+vector hybrid weighted reranking * refactor: pass topn as rerank() parameter, move rerank_field to model rerankers * fix: address review comments - rename test functions and restore duplicate field check * refactor: simplify MultiQuery field lookup, let validate_and_sanitize handle type check
This commit is contained in:
@@ -1538,19 +1538,19 @@ void ZVecPyParams::bind_vector_query(py::module_ &m) {
|
||||
.def(py::init<>())
|
||||
.def_readwrite("num_candidates", &SubQuery::num_candidates_)
|
||||
.def_static(
|
||||
"from_vector_query",
|
||||
"from_search_query",
|
||||
[](const SearchQuery &sq) {
|
||||
SubQuery sub;
|
||||
sub.num_candidates_ = sq.topk_;
|
||||
sub.target_ = sq.target_;
|
||||
return sub;
|
||||
},
|
||||
py::arg("vector_query"),
|
||||
py::arg("search_query"),
|
||||
"Create a SubQuery from a single-target search query.");
|
||||
|
||||
// _VectorQuery is the historical Python class name; it now wraps the
|
||||
// _SearchQuery is the Python class name; it wraps the
|
||||
// single-target SearchQuery so external Python code keeps working unchanged.
|
||||
py::class_<SearchQuery>(m, "_VectorQuery")
|
||||
py::class_<SearchQuery>(m, "_SearchQuery")
|
||||
.def(py::init<>())
|
||||
// properties
|
||||
.def_readwrite("topk", &SearchQuery::topk_)
|
||||
@@ -1805,7 +1805,7 @@ void ZVecPyParams::bind_vector_query(py::module_ &m) {
|
||||
},
|
||||
[](py::tuple t) {
|
||||
if (t.size() != 10)
|
||||
throw std::runtime_error("Invalid pickle data for _VectorQuery");
|
||||
throw std::runtime_error("Invalid pickle data for _SearchQuery");
|
||||
|
||||
SearchQuery obj{};
|
||||
obj.topk_ = t[0].cast<int>();
|
||||
|
||||
@@ -13,6 +13,7 @@
|
||||
// limitations under the License.
|
||||
|
||||
#include "python_reranker.h"
|
||||
#include <stdexcept>
|
||||
#include <pybind11/functional.h>
|
||||
#include <pybind11/stl.h>
|
||||
#include <zvec/db/collection.h>
|
||||
@@ -20,9 +21,40 @@
|
||||
|
||||
namespace zvec {
|
||||
|
||||
namespace {
|
||||
|
||||
inline void reranker_throw_if_error(const Status &status) {
|
||||
switch (status.code()) {
|
||||
case StatusCode::OK:
|
||||
return;
|
||||
case StatusCode::NOT_FOUND:
|
||||
throw py::key_error(status.message());
|
||||
case StatusCode::INVALID_ARGUMENT:
|
||||
throw py::value_error(status.message());
|
||||
default:
|
||||
throw std::runtime_error(status.message());
|
||||
}
|
||||
}
|
||||
|
||||
inline DocPtrList unwrap_rerank_result(Result<DocPtrList> result) {
|
||||
if (!result.has_value()) {
|
||||
reranker_throw_if_error(result.error());
|
||||
}
|
||||
return std::move(result).value();
|
||||
}
|
||||
|
||||
} // namespace
|
||||
|
||||
void ZVecPyReranker::Initialize(py::module_ &m) {
|
||||
// Bind Reranker base class (abstract, cannot be instantiated directly)
|
||||
py::class_<Reranker, Reranker::Ptr>(m, "_Reranker");
|
||||
py::class_<Reranker, Reranker::Ptr>(m, "_Reranker")
|
||||
.def(
|
||||
"rerank",
|
||||
[](const Reranker &self, const std::vector<DocPtrList> &query_results,
|
||||
int topn) {
|
||||
return unwrap_rerank_result(self.rerank(query_results, topn));
|
||||
},
|
||||
py::arg("query_results"), py::arg("topn") = 10);
|
||||
|
||||
// Bind ScoreBasedReranker intermediate class
|
||||
py::class_<ScoreBasedReranker, Reranker, std::shared_ptr<ScoreBasedReranker>>(
|
||||
@@ -37,7 +69,7 @@ void ZVecPyReranker::Initialize(py::module_ &m) {
|
||||
// Bind WeightedReranker
|
||||
py::class_<WeightedReranker, ScoreBasedReranker,
|
||||
std::shared_ptr<WeightedReranker>>(m, "_WeightedReranker")
|
||||
.def(py::init<std::map<std::string, double>>(), py::arg("weights"))
|
||||
.def(py::init<std::vector<double>>(), py::arg("weights"))
|
||||
.def_property_readonly("weights", &WeightedReranker::weights);
|
||||
|
||||
// Bind CallbackReranker
|
||||
|
||||
Reference in New Issue
Block a user