vectordb-bench 0.0.11__py3-none-any.whl → 0.0.12__py3-none-any.whl

vectordb_bench/frontend/{const → config}/dbCaseConfigs.py

@@ -1,43 +1,147 @@
-from enum import IntEnum
+from enum import IntEnum, Enum
 import typing
 from pydantic import BaseModel
 from vectordb_bench.backend.cases import CaseLabel, CaseType
 from vectordb_bench.backend.clients import DB
 from vectordb_bench.backend.clients.api import IndexType
+from vectordb_bench.frontend.components.custom.getCustomConfig import get_custom_configs
 
-from vectordb_bench.models import CaseConfigParamType
+from vectordb_bench.models import CaseConfig, CaseConfigParamType
 
 MAX_STREAMLIT_INT = (1 << 53) - 1
 
 DB_LIST = [d for d in DB if d != DB.Test]
 
-DIVIDER = "DIVIDER"
-CASE_LIST_WITH_DIVIDER = [
+
+class Delimiter(Enum):
+    Line = "line"
+
+
+class BatchCaseConfig(BaseModel):
+    label: str = ""
+    description: str = ""
+    cases: list[CaseConfig] = []
+
+
+class UICaseItem(BaseModel):
+    isLine: bool = False
+    label: str = ""
+    description: str = ""
+    cases: list[CaseConfig] = []
+    caseLabel: CaseLabel = CaseLabel.Performance
+
+    def __init__(
+        self,
+        isLine: bool = False,
+        case_id: CaseType = None,
+        custom_case: dict = {},
+        cases: list[CaseConfig] = [],
+        label: str = "",
+        description: str = "",
+        caseLabel: CaseLabel = CaseLabel.Performance,
+    ):
+        if isLine is True:
+            super().__init__(isLine=True)
+        elif case_id is not None and isinstance(case_id, CaseType):
+            c = case_id.case_cls(custom_case)
+            super().__init__(
+                label=c.name,
+                description=c.description,
+                cases=[CaseConfig(case_id=case_id, custom_case=custom_case)],
+                caseLabel=c.label,
+            )
+        else:
+            super().__init__(
+                label=label,
+                description=description,
+                cases=cases,
+                caseLabel=caseLabel,
+            )
+
+    def __hash__(self) -> int:
+        return hash(self.json())
+
+
+class UICaseItemCluster(BaseModel):
+    label: str = ""
+    uiCaseItems: list[UICaseItem] = []
+
+
+def get_custom_case_items() -> list[UICaseItem]:
+    custom_configs = get_custom_configs()
+    return [
+        UICaseItem(
+            case_id=CaseType.PerformanceCustomDataset, custom_case=custom_config.dict()
+        )
+        for custom_config in custom_configs
+    ]
+
+
+def get_custom_case_cluter() -> UICaseItemCluster:
+    return UICaseItemCluster(
+        label="Custom Search Performance Test", uiCaseItems=get_custom_case_items()
+    )
+
+
+UI_CASE_CLUSTERS: list[UICaseItemCluster] = [
+    UICaseItemCluster(
+        label="Search Performance Test",
+        uiCaseItems=[
+            UICaseItem(case_id=CaseType.Performance768D100M),
+            UICaseItem(case_id=CaseType.Performance768D10M),
+            UICaseItem(case_id=CaseType.Performance768D1M),
+            UICaseItem(isLine=True),
+            UICaseItem(case_id=CaseType.Performance1536D5M),
+            UICaseItem(case_id=CaseType.Performance1536D500K),
+            UICaseItem(case_id=CaseType.Performance1536D50K),
+        ],
+    ),
+    UICaseItemCluster(
+        label="Filter Search Performance Test",
+        uiCaseItems=[
+            UICaseItem(case_id=CaseType.Performance768D10M1P),
+            UICaseItem(case_id=CaseType.Performance768D10M99P),
+            UICaseItem(case_id=CaseType.Performance768D1M1P),
+            UICaseItem(case_id=CaseType.Performance768D1M99P),
+            UICaseItem(isLine=True),
+            UICaseItem(case_id=CaseType.Performance1536D5M1P),
+            UICaseItem(case_id=CaseType.Performance1536D5M99P),
+            UICaseItem(case_id=CaseType.Performance1536D500K1P),
+            UICaseItem(case_id=CaseType.Performance1536D500K99P),
+        ],
+    ),
+    UICaseItemCluster(
+        label="Capacity Test",
+        uiCaseItems=[
+            UICaseItem(case_id=CaseType.CapacityDim960),
+            UICaseItem(case_id=CaseType.CapacityDim128),
+        ],
+    ),
+]
+
+# DIVIDER = "DIVIDER"
+DISPLAY_CASE_ORDER: list[CaseType] = [
     CaseType.Performance768D100M,
     CaseType.Performance768D10M,
     CaseType.Performance768D1M,
-    DIVIDER,
     CaseType.Performance1536D5M,
     CaseType.Performance1536D500K,
     CaseType.Performance1536D50K,
-    DIVIDER,
     CaseType.Performance768D10M1P,
     CaseType.Performance768D1M1P,
-    DIVIDER,
     CaseType.Performance1536D5M1P,
     CaseType.Performance1536D500K1P,
-    DIVIDER,
     CaseType.Performance768D10M99P,
     CaseType.Performance768D1M99P,
-    DIVIDER,
     CaseType.Performance1536D5M99P,
     CaseType.Performance1536D500K99P,
-    DIVIDER,
     CaseType.CapacityDim960,
     CaseType.CapacityDim128,
 ]
+CASE_NAME_ORDER = [case.case_cls().name for case in DISPLAY_CASE_ORDER]
 
-CASE_LIST = [item for item in CASE_LIST_WITH_DIVIDER if isinstance(item, CaseType)]
+# CASE_LIST = [
+#     item for item in CASE_LIST_WITH_DIVIDER if isinstance(item, CaseType)]
 
 
 class InputType(IntEnum):
@@ -53,7 +157,7 @@ class CaseConfigInput(BaseModel):
     inputHelp: str = ""
     displayLabel: str = ""
     # todo type should be a function
-    isDisplayed: typing.Any = lambda x: True
+    isDisplayed: typing.Any = lambda config: True
 
 
 CaseConfigParamInput_IndexType = CaseConfigInput(
@@ -146,7 +250,7 @@ CaseConfigParamInput_EFConstruction_ES = CaseConfigInput(
 CaseConfigParamInput_maintenance_work_mem_PgVector = CaseConfigInput(
     label=CaseConfigParamType.maintenance_work_mem,
     inputHelp="Recommended value: 1.33x the index size, not to exceed the available free memory."
-              "Specify in gigabytes. e.g. 8GB",
+    "Specify in gigabytes. e.g. 8GB",
     inputType=InputType.Text,
     inputConfig={
         "value": "8GB",
@@ -157,7 +261,7 @@ CaseConfigParamInput_max_parallel_workers_PgVector = CaseConfigInput(
     label=CaseConfigParamType.max_parallel_workers,
     displayLabel="Max parallel workers",
     inputHelp="Recommended value: (cpu cores - 1). This will set the parameters: max_parallel_maintenance_workers,"
-              " max_parallel_workers & table(parallel_workers)",
+    " max_parallel_workers & table(parallel_workers)",
     inputType=InputType.Number,
     inputConfig={
         "min": 0,
@@ -514,7 +618,8 @@ CaseConfigParamInput_QuantizationRatio_PgVectoRS = CaseConfigInput(
         "options": ["x4", "x8", "x16", "x32", "x64"],
     },
     isDisplayed=lambda config: config.get(CaseConfigParamType.quantizationType, None)
-    == "product" and config.get(CaseConfigParamType.IndexType, None)
+    == "product"
+    and config.get(CaseConfigParamType.IndexType, None)
     in [
         IndexType.HNSW.value,
         IndexType.IVFFlat.value,
@@ -582,22 +687,24 @@ ESPerformanceConfig = [
     CaseConfigParamInput_NumCandidates_ES,
 ]
 
-PgVectorLoadingConfig = [CaseConfigParamInput_IndexType_PgVector,
-                         CaseConfigParamInput_Lists_PgVector,
-                         CaseConfigParamInput_m,
-                         CaseConfigParamInput_EFConstruction_PgVector,
-                         CaseConfigParamInput_maintenance_work_mem_PgVector,
-                         CaseConfigParamInput_max_parallel_workers_PgVector,
-                         ]
-PgVectorPerformanceConfig = [CaseConfigParamInput_IndexType_PgVector,
-                             CaseConfigParamInput_m,
-                             CaseConfigParamInput_EFConstruction_PgVector,
-                             CaseConfigParamInput_EFSearch_PgVector,
-                             CaseConfigParamInput_Lists_PgVector,
-                             CaseConfigParamInput_Probes_PgVector,
-                             CaseConfigParamInput_maintenance_work_mem_PgVector,
-                             CaseConfigParamInput_max_parallel_workers_PgVector,
-                             ]
+PgVectorLoadingConfig = [
+    CaseConfigParamInput_IndexType_PgVector,
+    CaseConfigParamInput_Lists_PgVector,
+    CaseConfigParamInput_m,
+    CaseConfigParamInput_EFConstruction_PgVector,
+    CaseConfigParamInput_maintenance_work_mem_PgVector,
+    CaseConfigParamInput_max_parallel_workers_PgVector,
+]
+PgVectorPerformanceConfig = [
+    CaseConfigParamInput_IndexType_PgVector,
+    CaseConfigParamInput_m,
+    CaseConfigParamInput_EFConstruction_PgVector,
+    CaseConfigParamInput_EFSearch_PgVector,
+    CaseConfigParamInput_Lists_PgVector,
+    CaseConfigParamInput_Probes_PgVector,
+    CaseConfigParamInput_maintenance_work_mem_PgVector,
+    CaseConfigParamInput_max_parallel_workers_PgVector,
+]
 
 PgVectoRSLoadingConfig = [
     CaseConfigParamInput_IndexType,

vectordb_bench/frontend/{const → config}/styles.py

@@ -46,6 +46,7 @@ DB_TO_ICON = {
     DB.PgVectoRS: "https://assets.zilliz.com/PG_Vector_d464f2ef5f.png",
     DB.Redis: "https://assets.zilliz.com/Redis_Cloud_74b8bfef39.png",
     DB.Chroma: "https://assets.zilliz.com/chroma_ceb3f06ed7.png",
+    DB.AWSOpenSearch: "https://assets.zilliz.com/opensearch_1eee37584e.jpeg",
 }
 
 # RedisCloud color: #0D6EFD
@@ -59,4 +60,5 @@ COLOR_MAP = {
     DB.WeaviateCloud.value: "#20C997",
     DB.PgVector.value: "#4C779A",
     DB.Redis.value: "#0D6EFD",
+    DB.AWSOpenSearch.value: "#0DCAF0",
 }

vectordb_bench/frontend/pages/concurrent.py

@@ -1,18 +1,14 @@
-
-
-
 import streamlit as st
-from vectordb_bench.backend.cases import CaseType
 from vectordb_bench.frontend.components.check_results.footer import footer
-from vectordb_bench.frontend.components.check_results.expanderStyle import initMainExpanderStyle
-from vectordb_bench.frontend.components.check_results.priceTable import priceTable
 from vectordb_bench.frontend.components.check_results.headerIcon import drawHeaderIcon
-from vectordb_bench.frontend.components.check_results.nav import NavToResults, NavToRunTest
-from vectordb_bench.frontend.components.check_results.charts import drawMetricChart
+from vectordb_bench.frontend.components.check_results.nav import (
+    NavToResults,
+    NavToRunTest,
+)
 from vectordb_bench.frontend.components.check_results.filters import getshownData
 from vectordb_bench.frontend.components.concurrent.charts import drawChartsByCase
 from vectordb_bench.frontend.components.get_results.saveAsImage import getResults
-from vectordb_bench.frontend.const.styles import *
+from vectordb_bench.frontend.config.styles import FAVICON
 from vectordb_bench.interface import benchMarkRunner
 from vectordb_bench.models import TestResult
 
@@ -30,26 +26,23 @@ def main():
     drawHeaderIcon(st)
 
     allResults = benchMarkRunner.get_results()
-    
+
     def check_conc_data(res: TestResult):
         case_results = res.results
         count = 0
         for case_result in case_results:
             if len(case_result.metrics.conc_num_list) > 0:
                 count += 1
-        
+
         return count > 0
-    
+
     checkedResults = [res for res in allResults if check_conc_data(res)]
-        
 
     st.title("VectorDB Benchmark (Concurrent Performance)")
 
     # results selector
     resultSelectorContainer = st.sidebar.container()
-    shownData, _, showCases = getshownData(
-        checkedResults, resultSelectorContainer)
-    
+    shownData, _, showCaseNames = getshownData(checkedResults, resultSelectorContainer)
 
     resultSelectorContainer.divider()
 
@@ -61,8 +54,8 @@ def main():
     # save or share
     resultesContainer = st.sidebar.container()
     getResults(resultesContainer, "vectordb_bench_concurrent")
-    
-    drawChartsByCase(shownData, showCases, st.container())
+
+    drawChartsByCase(shownData, showCaseNames, st.container())
 
     # footer
     footer(st.container())

vectordb_bench/frontend/pages/custom.py

@@ -0,0 +1,64 @@
+import streamlit as st
+from vectordb_bench.frontend.components.check_results.headerIcon import drawHeaderIcon
+from vectordb_bench.frontend.components.custom.displayCustomCase import displayCustomCase
+from vectordb_bench.frontend.components.custom.displaypPrams import displayParams
+from vectordb_bench.frontend.components.custom.getCustomConfig import CustomCaseConfig, generate_custom_case, get_custom_configs, save_custom_configs
+from vectordb_bench.frontend.components.custom.initStyle import initStyle
+from vectordb_bench.frontend.config.styles import FAVICON, PAGE_TITLE
+
+
+class CustomCaseManager():
+    customCaseItems: list[CustomCaseConfig]
+
+    def __init__(self):
+        self.customCaseItems = get_custom_configs()
+
+    def addCase(self):
+        new_custom_case = generate_custom_case()
+        new_custom_case.dataset_config.name = f"{new_custom_case.dataset_config.name} {len(self.customCaseItems)}"
+        self.customCaseItems += [new_custom_case]
+        self.save()
+
+    def deleteCase(self, idx: int):
+        self.customCaseItems.pop(idx)
+        self.save()
+
+    def save(self):
+        save_custom_configs(self.customCaseItems)
+
+
+def main():
+    st.set_page_config(
+        page_title=PAGE_TITLE,
+        page_icon=FAVICON,
+        # layout="wide",
+        # initial_sidebar_state="collapsed",
+    )
+
+    # header
+    drawHeaderIcon(st)
+
+    # init style
+    initStyle(st)
+
+    st.title("Custom Dataset")
+    displayParams(st)
+    customCaseManager = CustomCaseManager()
+
+    for idx, customCase in enumerate(customCaseManager.customCaseItems):
+        expander = st.expander(customCase.dataset_config.name, expanded=True)
+        key = f"custom_case_{idx}"
+        displayCustomCase(customCase, expander, key=key)
+
+        columns = expander.columns(8)
+        columns[0].button(
+            "Save", key=f"{key}_", type="secondary", on_click=lambda: customCaseManager.save())
+        columns[1].button(":red[Delete]", key=f"{key}_delete", type="secondary",
+                          on_click=lambda: customCaseManager.deleteCase(idx))
+
+    st.button("\+ New Dataset", key=f"add_custom_configs",
+              type="primary", on_click=lambda: customCaseManager.addCase())
+
+
+if __name__ == "__main__":
+    main()

vectordb_bench/frontend/pages/quries_per_dollar.py

@@ -8,7 +8,7 @@ from vectordb_bench.frontend.components.check_results.nav import NavToResults, N
 from vectordb_bench.frontend.components.check_results.charts import drawMetricChart
 from vectordb_bench.frontend.components.check_results.filters import getshownData
 from vectordb_bench.frontend.components.get_results.saveAsImage import getResults
-from vectordb_bench.frontend.const.styles import *
+from vectordb_bench.frontend.config.styles import *
 from vectordb_bench.interface import benchMarkRunner
 from vectordb_bench.metric import QURIES_PER_DOLLAR_METRIC
 
@@ -26,7 +26,7 @@ def main():
 
     # results selector
     resultSelectorContainer = st.sidebar.container()
-    shownData, _, showCases = getshownData(allResults, resultSelectorContainer)
+    shownData, _, showCaseNames = getshownData(allResults, resultSelectorContainer)
 
     resultSelectorContainer.divider()
 
@@ -45,8 +45,8 @@ def main():
     priceMap = priceTable(priceTableContainer, shownData)
 
     # charts
-    for case in showCases:
-        data = [data for data in shownData if data["case_name"] == case.name]
+    for caseName in showCaseNames:
+        data = [data for data in shownData if data["case_name"] == caseName]
         dataWithMetric = []
         metric = QURIES_PER_DOLLAR_METRIC
         for d in data:
@@ -56,7 +56,7 @@ def main():
                 d[metric] = d["qps"] / price * 3.6
                 dataWithMetric.append(d)
         if len(dataWithMetric) > 0:
-            chartContainer = st.expander(case.name, True)
+            chartContainer = st.expander(caseName, True)
             drawMetricChart(data, metric, chartContainer)
 
     # footer

vectordb_bench/frontend/pages/run_test.py

@@ -5,6 +5,7 @@ from vectordb_bench.frontend.components.run_test.dbConfigSetting import dbConfig
 from vectordb_bench.frontend.components.run_test.dbSelector import dbSelector
 from vectordb_bench.frontend.components.run_test.generateTasks import generate_tasks
 from vectordb_bench.frontend.components.run_test.hideSidebar import hideSidebar
+from vectordb_bench.frontend.components.run_test.initStyle import initStyle
 from vectordb_bench.frontend.components.run_test.submitTask import submitTask
 from vectordb_bench.frontend.components.check_results.nav import NavToResults
 from vectordb_bench.frontend.components.check_results.headerIcon import drawHeaderIcon
@@ -15,6 +16,9 @@ def main():
     # set page config
     initRunTestPageConfig(st)
     
+    # init style
+    initStyle(st)
+    
     # header
     drawHeaderIcon(st)
 

vectordb_bench/frontend/pages/tables.py

@@ -1,7 +1,7 @@
 import streamlit as st
 from vectordb_bench.frontend.components.check_results.headerIcon import drawHeaderIcon
 from vectordb_bench.frontend.components.tables.data import getNewResults
-from vectordb_bench.frontend.const.styles import FAVICON
+from vectordb_bench.frontend.config.styles import FAVICON
 
 
 def main():
@@ -21,4 +21,4 @@ def main():
 
 
 if __name__ == "__main__":
-    main()
+    main()

vectordb_bench/frontend/utils.py

@@ -1,6 +1,22 @@
-from vectordb_bench.models import CaseType
+import random
+import string
+
 
 passwordKeys = ["password", "api_key"]
+
+
 def inputIsPassword(key: str) -> bool:
     return key.lower() in passwordKeys
 
+
+def addHorizontalLine(st):
+    st.markdown(
+        "<div style='border: 1px solid #cccccc60; margin-bottom: 24px;'></div>",
+        unsafe_allow_html=True,
+    )
+
+
+def generate_random_string(length):
+    letters = string.ascii_letters + string.digits
+    result = ''.join(random.choice(letters) for _ in range(length))
+    return result

vectordb_bench/frontend/vdb_benchmark.py

@@ -6,7 +6,7 @@ from vectordb_bench.frontend.components.check_results.nav import NavToQuriesPerD
 from vectordb_bench.frontend.components.check_results.charts import drawCharts
 from vectordb_bench.frontend.components.check_results.filters import getshownData
 from vectordb_bench.frontend.components.get_results.saveAsImage import getResults
-from vectordb_bench.frontend.const.styles import *
+from vectordb_bench.frontend.config.styles import *
 from vectordb_bench.interface import benchMarkRunner
 
 
@@ -24,7 +24,7 @@ def main():
 
     # results selector and filter
     resultSelectorContainer = st.sidebar.container()
-    shownData, failedTasks, showCases = getshownData(
+    shownData, failedTasks, showCaseNames = getshownData(
         allResults, resultSelectorContainer
     )
 
@@ -40,7 +40,7 @@ def main():
     getResults(resultesContainer, "vectordb_bench")
 
     # charts
-    drawCharts(st, shownData, failedTasks, showCases)
+    drawCharts(st, shownData, failedTasks, showCaseNames)
 
     # footer
     footer(st.container())

vectordb_bench/models.py

@@ -94,6 +94,10 @@ class CaseConfig(BaseModel):
         self._k = value
     '''
 
+    def __hash__(self) -> int:
+        return hash(self.json())
+
+
 class TaskStage(StrEnum):
     """Enumerations of various stages of the task"""
 
@@ -250,18 +254,18 @@ class TestResult(BaseModel):
 
         max_db = max(map(len, [f.task_config.db.name for f in filtered_results]))
         max_db_labels = (
-                max(map(len, [f.task_config.db_config.db_label for f in filtered_results]))
-                + 3
+            max(map(len, [f.task_config.db_config.db_label for f in filtered_results]))
+            + 3
         )
         max_case = max(
             map(len, [f.task_config.case_config.case_id.name for f in filtered_results])
         )
         max_load_dur = (
-                max(map(len, [str(f.metrics.load_duration) for f in filtered_results])) + 3
+            max(map(len, [str(f.metrics.load_duration) for f in filtered_results])) + 3
         )
         max_qps = max(map(len, [str(f.metrics.qps) for f in filtered_results])) + 3
         max_recall = (
-                max(map(len, [str(f.metrics.recall) for f in filtered_results])) + 3
+            max(map(len, [str(f.metrics.recall) for f in filtered_results])) + 3
         )
 
         max_db_labels = 8 if max_db_labels < 8 else max_db_labels

vectordb_bench/results/getLeaderboardData.py

@@ -2,7 +2,7 @@ from vectordb_bench import config
 import ujson
 import pathlib
 from vectordb_bench.backend.cases import CaseType
-from vectordb_bench.frontend.const.dbPrices import DB_DBLABEL_TO_PRICE
+from vectordb_bench.frontend.config.dbPrices import DB_DBLABEL_TO_PRICE
 from vectordb_bench.interface import benchMarkRunner
 from vectordb_bench.models import CaseResult, ResultLabel, TestResult
 

{vectordb_bench-0.0.11.dist-info → vectordb_bench-0.0.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vectordb-bench
-Version: 0.0.11
+Version: 0.0.12
 Summary: VectorDBBench is not just an offering of benchmark results for mainstream vector databases and cloud services, it's your go-to tool for the ultimate performance and cost-effectiveness comparison. Designed with ease-of-use in mind, VectorDBBench is devised to help users, even non-professionals, reproduce results or test new systems, making the hunt for the optimal choice amongst a plethora of cloud services and open-source vector databases a breeze.
 Author-email: XuanYang-cn <xuan.yang@zilliz.com>
 Project-URL: repository, https://github.com/zilliztech/VectorDBBench
@@ -39,6 +39,10 @@ Requires-Dist: chromadb ; extra == 'all'
 Requires-Dist: psycopg2 ; extra == 'all'
 Requires-Dist: psycopg ; extra == 'all'
 Requires-Dist: psycopg-binary ; extra == 'all'
+Requires-Dist: opensearch-dsl ==2.1.0 ; extra == 'all'
+Requires-Dist: opensearch-py ==2.6.0 ; extra == 'all'
+Provides-Extra: awsopensearch
+Requires-Dist: awsopensearch ; extra == 'awsopensearch'
 Provides-Extra: chromadb
 Requires-Dist: chromadb ; extra == 'chromadb'
 Provides-Extra: elastic
@@ -91,18 +95,19 @@ pip install vectordb-bench[pinecone]
 ```
 All the database client supported
 
-|Optional database client|install command|
-|---------------|---------------|
-|pymilvus(*default*)|`pip install vectordb-bench`|
-|all|`pip install vectordb-bench[all]`|
-|qdrant|`pip install vectordb-bench[qdrant]`|
-|pinecone|`pip install vectordb-bench[pinecone]`|
-|weaviate|`pip install vectordb-bench[weaviate]`|
-|elastic|`pip install vectordb-bench[elastic]`|
-|pgvector|`pip install vectordb-bench[pgvector]`|
-|pgvecto.rs|`pip install vectordb-bench[pgvecto_rs]`|
-|redis|`pip install vectordb-bench[redis]`|
-|chromadb|`pip install vectordb-bench[chromadb]`|
+| Optional database client | install command                             |
+|--------------------------|---------------------------------------------|
+| pymilvus(*default*)      | `pip install vectordb-bench`                |
+| all                      | `pip install vectordb-bench[all]`           |
+| qdrant                   | `pip install vectordb-bench[qdrant]`        |
+| pinecone                 | `pip install vectordb-bench[pinecone]`      |
+| weaviate                 | `pip install vectordb-bench[weaviate]`      |
+| elastic                  | `pip install vectordb-bench[elastic]`       |
+| pgvector                 | `pip install vectordb-bench[pgvector]`      |
+| pgvecto.rs               | `pip install vectordb-bench[pgvecto_rs]`    |
+| redis                    | `pip install vectordb-bench[redis]`         |
+| chromadb                 | `pip install vectordb-bench[chromadb]`      |
+| awsopensearch            | `pip install vectordb-bench[awsopensearch]` |
 
 ### Run
 
@@ -345,6 +350,24 @@ Case No. | Case Type | Dataset Size  | Filtering Rate | Results |
 
 Each case provides an in-depth examination of a vector database's abilities, providing you a comprehensive view of the database's performance.
 
+#### Custom Dataset for Performance case
+
+Through the `/custom` page, users can customize their own performance case using local datasets. After saving, the corresponding case can be selected from the `/run_test` page to perform the test.
+
+![image](fig/custom_dataset.png)
+![image](fig/custom_case_run_test.png)
+
+We have strict requirements for the data set format, please follow them.
+- `Folder Path` - The path to the folder containing all the files. Please ensure that all files in the folder are in the `Parquet` format.
+  - Vectors data files: The file must be named `train.parquet` and should have two columns: `id` as an incrementing `int` and `emb` as an array of `float32`.
+  - Query test vectors: The file must be named `test.parquet` and should have two columns: `id` as an incrementing `int` and `emb` as an array of `float32`.
+  - Ground truth file: The file must be named `neighbors.parquet` and should have two columns: `id` corresponding to query vectors and `neighbors_id` as an array of `int`.
+
+- `Train File Count` - If the vector file is too large, you can consider splitting it into multiple files. The naming format for the split files should be `train-[index]-of-[file_count].parquet`. For example, `train-01-of-10.parquet` represents the second file (0-indexed) among 10 split files.
+
+- `Use Shuffled Data` - If you check this option, the vector data files need to be modified. VectorDBBench will load the data labeled with `shuffle`. For example, use `shuffle_train.parquet` instead of `train.parquet` and `shuffle_train-04-of-10.parquet` instead of `train-04-of-10.parquet`. The `id` column in the shuffled data can be in any order.
+
+
 ## Goals
 Our goals of this benchmark are:
 ### Reproducibility & Usability