update hippo client

.editorconfig

@@ -0,0 +1,18 @@
+# EditorConfig is awesome: https://EditorConfig.org
+
+# top-most EditorConfig file
+root = true
+
+[*]
+end_of_line = lf
+charset = utf-8
+trim_trailing_whitespace = false
+insert_final_newline = false
+
+[Dockerfile*]
+indent_style = space
+indent_size = 4
+
+[*.json]
+indent_style = space
+indent_size = 4

.gitignore

@@ -9,3 +9,18 @@ __MACOSX
 build/
 venv/
 .idea/
+
+# vscode files
+.vscode/*
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/settings.json
+!.vscode/*.code-snippets
+!.vscode/c_cpp_properties.json
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix

.vscode/launch.json

@@ -0,0 +1,28 @@
+{
+    // Use IntelliSense to learn about possible attributes.
+    // Hover to view descriptions of existing attributes.
+    // For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
+    "version": "0.2.0",
+    "configurations": [
+        {
+            "name": "Python: Streamlit",
+            "type": "debugpy",
+            "request": "launch",
+            "module": "streamlit",
+            "args": [
+                "run",
+                "vectordb_bench/frontend/vdb_benchmark.py",
+                "--logger.level",
+                "info",
+                "--theme.base",
+                "light",
+                "--theme.primaryColor",
+                "#3670F2",
+                "--theme.secondaryBackgroundColor",
+                "#F0F2F6",
+            ],
+            "subProcess": true,
+            "justMyCode": false
+        }
+    ]
+}

.vscode/settings.json

@@ -0,0 +1,10 @@
+{
+    "[python]": {
+        "editor.formatOnSave": false,
+        // "editor.codeActionsOnSave": {
+        //     "source.fixAll": "always",
+        //     "source.organizeImports": "always"
+        // },
+        "editor.defaultFormatter": "charliermarsh.ruff"
+    }
+}

.vscode/tasks.json

@@ -0,0 +1,29 @@
+{
+    // See https://go.microsoft.com/fwlink/?LinkId=733558
+    // for the documentation about the tasks.json format
+    "version": "2.0.0",
+    "tasks": [
+        {
+            "label": "build vectordb bench",
+            "type": "shell",
+            "command": "python",
+            "args": [
+                "-m",
+                "pip",
+                "install",
+                "-e",
+                ".[test]"
+            ],
+            "group": {
+                "kind": "build",
+                "isDefault": true
+            }
+        },
+        {
+            "label": "run vectordb bench",
+            "type": "shell",
+            "command": "init_bench",
+            "problemMatcher": []
+        }
+    ]
+}

vectordb_bench/backend/clients/__init__.py

@@ -32,6 +32,7 @@ class DB(Enum):
     PgVectoRS = "PgVectoRS"
     Redis = "Redis"
     Chroma = "Chroma"
+    Hippo = "Hippo"
 
 
     @property
@@ -76,6 +77,10 @@ def init_cls(self) -> Type[VectorDB]:
         if self == DB.Chroma:
             from .chroma.chroma import ChromaClient
             return ChromaClient
+
+        if self == DB.Hippo:
+            from .hippo.hippo import Hippo
+            return Hippo
 
     @property
     def config_cls(self) -> Type[DBConfig]:
@@ -120,6 +125,10 @@ def config_cls(self) -> Type[DBConfig]:
             from .chroma.config import ChromaConfig
             return ChromaConfig
 
+        if self == DB.Hippo:
+            from .hippo.config import HippoConfig
+            return HippoConfig
+
     def case_config_cls(self, index_type: IndexType | None = None) -> Type[DBCaseConfig]:
         if self == DB.Milvus:
             from .milvus.config import _milvus_case_config
@@ -149,6 +158,10 @@ def case_config_cls(self, index_type: IndexType | None = None) -> Type[DBCaseCon
             from .pgvecto_rs.config import _pgvecto_rs_case_config
             return _pgvecto_rs_case_config.get(index_type)
 
+        if self == DB.Hippo:
+            from .hippo.config import HippoIndexConfig
+            return HippoIndexConfig
+
         # DB.Pinecone, DB.Chroma, DB.Redis
         return EmptyDBCaseConfig
 

vectordb_bench/backend/clients/hippo/config.py

@@ -0,0 +1,67 @@
+from pydantic import BaseModel, Field, SecretStr
+from transwarp_hippo_api.hippo_type import IndexType
+from transwarp_hippo_api.hippo_type import MetricType as HippoMetricType
+
+from ..api import DBCaseConfig, DBConfig, MetricType
+
+
+class HippoConfig(DBConfig):
+    ip: SecretStr = ""
+    port: SecretStr = "18902"
+    username: SecretStr = "shiva"
+    password: SecretStr = "shiva"
+    number_of_shards: int = Field(default=1, ge=1)
+    number_of_replicas: int = Field(default=1, ge=1)
+    insert_batch_size: int = Field(default=100, ge=1)
+
+    def to_dict(self) -> dict:
+        return {
+            "host_port": [
+                f"{self.ip.get_secret_value()}:{self.port.get_secret_value()}"
+            ],
+            "username": self.username.get_secret_value(),
+            "pwd": self.password.get_secret_value(),
+            "number_of_shards": self.number_of_shards,
+            "number_of_replicas": self.number_of_replicas,
+            "insert_batch_size": self.insert_batch_size,
+        }
+
+
+class HippoIndexConfig(BaseModel, DBCaseConfig):
+    index: IndexType = IndexType.HNSW  # HNSW, FLAT, IVF_FLAT, IVF_SQ, IVF_PQ, ANNOY
+    metric_type: MetricType | None = None
+    M: int = 30  # [4,96]
+    ef_construction: int = 360  # [8, 512]
+    ef_search: int = 100  # [topk, 32768]
+    nlist: int = 1024  # [1,65536]
+    nprobe: int = 64  # [1, nlist]
+    m: int = 16  # divisible by dim
+    nbits: int = 8  # [1, 16]
+    k_factor: int = 100  # [10, 1000]
+
+    def parse_metric(self) -> HippoMetricType:
+        if self.metric_type == MetricType.COSINE:
+            return HippoMetricType.COSINE
+        if self.metric_type == MetricType.IP:
+            return HippoMetricType.IP
+        if self.metric_type == MetricType.L2:
+            return HippoMetricType.L2
+        return ""
+
+    def index_param(self) -> dict:
+        return {
+            "M": self.M,
+            "ef_construction": self.ef_construction,
+            "ef_search": self.ef_search,
+            "nlist": self.nlist,
+            "nprobe": self.nprobe,
+            "m": self.m,
+            "nbits": self.nbits,
+        }
+
+    def search_param(self) -> dict:
+        return {
+            "ef_search": self.ef_search,
+            "nprobe": self.nprobe,
+            "k_factor": self.k_factor,
+        }