postgres/typesense
1
0
Fork 0
mirror of https://github.com/typesense/typesense.git synced 2025-05-21 14:12:27 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Merge branch 'v0.25-join' into v0.26-facets

Browse Source
This commit is contained in:
Kishore Nallan 2023-08-02 18:00:49 +05:30
commit 4e3374a945
5 changed files with 90 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
bazel/onnx.patch
View File

@ -11,6 +11,19 @@ index 88b46890b7..d090499971 100644
__cmake_contentNameLower
__cmake_contentName
--- cmake/CMakeLists.txt
+++ cmake/CMakeLists.txt
@@ -1268,6 +1268,7 @@ if (onnxruntime_USE_CUDA)
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_53,code=sm_53") # TX1, Nano
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_62,code=sm_62") # TX2
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_72,code=sm_72") # AGX Xavier, NX Xavier
+ set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_75,code=sm_75") # T4
if (CMAKE_CUDA_COMPILER_VERSION VERSION_GREATER_EQUAL 11)
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} -gencode=arch=compute_87,code=sm_87") # AGX Orin, NX Orin
endif()
diff --git a/.gitmodules b/.gitmodules
index 8e4217162b..bb63b7d9c5 100644
--- .gitmodules

3
src/batched_indexer.cpp
View File

@ -200,7 +200,8 @@ void BatchedIndexer::run() {
config.get_disk_used_max_percentage(),
config.get_memory_used_max_percentage());
if (resource_check != cached_resource_stat_t::OK && orig_req->http_method != "DELETE") {
if (resource_check != cached_resource_stat_t::OK &&
orig_req->http_method != "DELETE" && found_rpath->handler != post_health) {
const std::string& err_msg = "Rejecting write: running out of resource type: " +
std::string(magic_enum::enum_name(resource_check));
LOG(ERROR) << err_msg;

1
src/index.cpp
View File

@ -1155,6 +1155,7 @@ void Index::tokenize_string_array(const std::vector<std::string>& strings,
token_to_offsets[last_token].push_back(0);
}
}
void Index::initialize_facet_indexes(const field& facet_field) {
facet_index_v4->initialize(facet_field.name);
}

74
test/collection_faceting_test.cpp
View File

@ -1055,6 +1055,78 @@ TEST_F(CollectionFacetingTest, FacetByNestedIntField) {
ASSERT_EQ("companyRank", wildcard_facets[1].field_name);
}
TEST_F(CollectionFacetingTest, FacetByNestedArrayField) {
nlohmann::json schema = R"({
"name": "coll1",
"enable_nested_fields": true,
"fields": [
{"name": "data", "type": "object", "optional": false, "facet": true }
]
})"_json;
auto op = collectionManager.create_collection(schema);
ASSERT_TRUE(op.ok());
Collection* coll1 = op.get();
auto doc1 = R"({
"data": {"details": [{"name": "Foo"}, {"name": "Foo"}]}
})"_json;
auto doc2 = R"({
"data": {"details": [{"name": "Foo"}, {"name": "Foo"}]}
})"_json;
ASSERT_TRUE(coll1->add(doc1.dump(), CREATE).ok());
ASSERT_TRUE(coll1->add(doc2.dump(), CREATE).ok());
auto results = coll1->search("*", {}, "", {"data.details.name"}, {}, {0}, 10, 1,
token_ordering::FREQUENCY, {true}, 10, spp::sparse_hash_set<std::string>(),
spp::sparse_hash_set<std::string>(), 10, "", 30, 4).get();
ASSERT_EQ(2, results["found"].get<size_t>());
ASSERT_EQ(1, results["facet_counts"].size());
ASSERT_EQ("data.details.name", results["facet_counts"][0]["field_name"]);
ASSERT_EQ(1, results["facet_counts"][0]["counts"].size());
ASSERT_EQ(2, results["facet_counts"][0]["counts"][0]["count"].get<size_t>());
ASSERT_EQ("Foo", results["facet_counts"][0]["counts"][0]["value"].get<std::string>());
}
TEST_F(CollectionFacetingTest, FacetByArrayField) {
nlohmann::json schema = R"({
"name": "coll1",
"enable_nested_fields": true,
"fields": [
{"name": "data", "type": "string[]", "optional": false, "facet": true }
]
})"_json;
auto op = collectionManager.create_collection(schema);
ASSERT_TRUE(op.ok());
Collection* coll1 = op.get();
auto doc1 = R"({
"data": ["Foo", "Foo"]
})"_json;
auto doc2 = R"({
"data": ["Foo", "Foo"]
})"_json;
ASSERT_TRUE(coll1->add(doc1.dump(), CREATE).ok());
ASSERT_TRUE(coll1->add(doc2.dump(), CREATE).ok());
auto results = coll1->search("*", {}, "", {"data"}, {}, {0}, 10, 1,
token_ordering::FREQUENCY, {true}, 10, spp::sparse_hash_set<std::string>(),
spp::sparse_hash_set<std::string>(), 10, "", 30, 4).get();
ASSERT_EQ(2, results["found"].get<size_t>());
ASSERT_EQ(1, results["facet_counts"].size());
ASSERT_EQ("data", results["facet_counts"][0]["field_name"]);
ASSERT_EQ(1, results["facet_counts"][0]["counts"].size());
ASSERT_EQ(2, results["facet_counts"][0]["counts"][0]["count"].get<size_t>());
ASSERT_EQ("Foo", results["facet_counts"][0]["counts"][0]["value"].get<std::string>());
}
TEST_F(CollectionFacetingTest, FacetParseTest){
std::vector<field> fields = {
field("score", field_types::INT32, true),
@ -1875,4 +1947,4 @@ TEST_F(CollectionFacetingTest, FacetingReturnParentObject) {
ASSERT_EQ(2, results["facet_counts"][0]["counts"].size());
ASSERT_EQ("{\"b\":0,\"color\":\"red\",\"g\":0,\"r\":255}", results["facet_counts"][0]["counts"][0]["value"]);
ASSERT_EQ("{\"b\":255,\"color\":\"blue\",\"g\":0,\"r\":0}", results["facet_counts"][0]["counts"][1]["value"]);
}
}

6
test/collection_vector_search_test.cpp
View File

@ -775,7 +775,7 @@ TEST_F(CollectionVectorTest, HybridSearchWithExplicitVector) {
ASSERT_EQ(2, search_res["found"].get<size_t>());
ASSERT_EQ(2, search_res["hits"].size());
ASSERT_FLOAT_EQ(0.0462081432, search_res["hits"][0]["vector_distance"].get<float>());
ASSERT_FLOAT_EQ(0.046207964, search_res["hits"][0]["vector_distance"].get<float>());
ASSERT_FLOAT_EQ(0.1213316321, search_res["hits"][1]["vector_distance"].get<float>());
// to pass k param
@ -825,10 +825,6 @@ TEST_F(CollectionVectorTest, HybridSearchWithExplicitVector) {
ASSERT_FLOAT_EQ(2.0f, search_res["hits"][0]["vector_distance"].get<float>());
ASSERT_FLOAT_EQ(2.0f, search_res["hits"][1]["vector_distance"].get<float>());
ASSERT_FLOAT_EQ(2.0f, search_res["hits"][2]["vector_distance"].get<float>());
ASSERT_FLOAT_EQ(2.0f, search_res["hits"][0]["hybrid_search_info"]["vector_distance"].get<float>());
ASSERT_FLOAT_EQ(2.0f, search_res["hits"][1]["hybrid_search_info"]["vector_distance"].get<float>());
ASSERT_FLOAT_EQ(2.0f, search_res["hits"][2]["hybrid_search_info"]["vector_distance"].get<float>());
}
TEST_F(CollectionVectorTest, HybridSearchOnlyVectorMatches) {