feat: Add high-level API for Python (#123)

* feat: init high level api Signed-off-by: 盐粒 Yanli <mail@yanli.one> * feat: pretify things Signed-off-by: 盐粒 Yanli <mail@yanli.one> * feat: add test && filter subpackage Signed-off-by: 盐粒 Yanli <mail@yanli.one> * fix: dependency Signed-off-by: 盐粒 Yanli <mail@yanli.one> * test: fix Action Signed-off-by: 盐粒 Yanli <mail@yanli.one> * feat: add isort for format Signed-off-by: 盐粒 Yanli <mail@yanli.one> * fix: create extension with init client Signed-off-by: 盐粒 Yanli <mail@yanli.one> * docs: add readme Signed-off-by: 盐粒 Yanli <mail@yanli.one> * chore: bump version Signed-off-by: 盐粒 Yanli <mail@yanli.one> * feat: rename things Signed-off-by: 盐粒 Yanli <mail@yanli.one> * feat: delete embedder Signed-off-by: 盐粒 Yanli <mail@yanli.one> * feat: simplify filter Signed-off-by: 盐粒 Yanli <mail@yanli.one> * feat: config ruff Signed-off-by: 盐粒 Yanli <mail@yanli.one> * feat: clean up client.py Signed-off-by: 盐粒 Yanli <mail@yanli.one> * feat: modify PGVectoRs interfaces Signed-off-by: 盐粒 Yanli <mail@yanli.one> * chore: add docs Signed-off-by: 盐粒 Yanli <mail@yanli.one> * feat: delete text column Signed-off-by: 盐粒 Yanli <mail@yanli.one> * rename things Signed-off-by: 盐粒 Yanli <mail@yanli.one> * Revert "feat: delete text column" This reverts commit df5452b9ad. Signed-off-by: 盐粒 Yanli <mail@yanli.one> * feat: rename insert Signed-off-by: 盐粒 Yanli <mail@yanli.one> * chore: delete __all__ for filters.py Signed-off-by: 盐粒 Yanli <mail@yanli.one> * chore: update things Signed-off-by: 盐粒 Yanli <mail@yanli.one> * chore: update lint config Signed-off-by: 盐粒 Yanli <mail@yanli.one> * pretify things Signed-off-by: 盐粒 Yanli <mail@yanli.one> * pdm lock -G :all -S direct_minimal_versions Signed-off-by: 盐粒 Yanli <mail@yanli.one> * replace relative import Signed-off-by: 盐粒 Yanli <mail@yanli.one> * change Record.from_text Signed-off-by: 盐粒 Yanli <mail@yanli.one> * make lint happ Signed-off-by: 盐粒 Yanli <mail@yanli.one> * fix Record.from_text Signed-off-by: 盐粒 Yanli <mail@yanli.one> --------- Signed-off-by: 盐粒 Yanli <mail@yanli.one>
2025-07-30 19:23:05 +03:00 · 2023-11-16 20:52:15 +08:00
parent 9ce6c3b4cb
commit f8344dd039
12 changed files with 844 additions and 174 deletions
--- a/.github/workflows/python_check.yml
+++ b/.github/workflows/python_check.yml
@ -61,7 +61,7 @@ jobs:
    - name: Install Dependencies
      working-directory: bindings/python
      run: |
-        pdm sync -d
+        pdm sync -G :all
    
    # - name: Install Docker for macOS
    #   if: matrix.os == 'macos-latest'
--- a/bindings/python/README.md
+++ b/bindings/python/README.md
@ -1,9 +1,7 @@
-# Python bindings for pgvector.rs
+# Python bindings for pgvecto.rs

 [![pdm-managed](https://img.shields.io/badge/pdm-managed-blueviolet)](https://pdm.fming.dev)

-Currently supports [SQLAlchemy](https://github.com/sqlalchemy/sqlalchemy).
-
 ## Usage

 Install from PyPI:
@ -11,15 +9,68 @@ Install from PyPI:
 pip install pgvecto_rs
 ```

-See the usage examples:
- [SQLAlchemy](#SQLAlchemy)
+See the [usage of SDK](#sdk)
+
+Or use it as an extension of postgres clients:
+- [SQLAlchemy](#sqlalchemy)
 - [psycopg3](#psycopg3)

+### SDK
+
+Our SDK is designed to use the pgvecto.rs out-of-box. You can exploit the power of pgvecto.rs to do similarity search or retrieve with filters, without writing any SQL code.
+
+Install dependencies:
+```bash
+pip install "pgvecto_rs[sdk]"
+```
+
+A minimal example:
+
+```Python
+from pgvecto_rs.sdk import PGVectoRs, Record
+
+# Create a client
+client = PGVectoRs(
+    db_url="postgresql+psycopg://postgres:mysecretpassword@localhost:5432/postgres",
+    table_name="example",
+    dimension=3,
+)
+
+try:
+    # Add some records
+    client.add_records(
+        [
+            Record.from_text("hello 1", [1, 2, 3]),
+            Record.from_text("hello 2", [1, 2, 4]),
+        ]
+    )
+
+    # Search with default operator (sqrt_euclid).
+    # The results is sorted by distance
+    for rec, dis in client.search([1, 2, 5]):
+        print(rec.text)
+        print(dis)
+finally:
+    # Clean up (i.e. drop the table)
+    client.drop()
+```
+
+Output:
+```
+hello 2
+1.0
+hello 1
+4.0
+```
+
+See [examples/sdk_example.py](examples/sdk_example.py) and [tests/test_sdk.py](tests/test_sdk.py) for more examples.
+
+
 ### SQLAlchemy

-Install [SQLAlchemy](https://github.com/sqlalchemy/sqlalchemy) and [psycopg3](https://www.psycopg.org/psycopg3/docs/basic/install.html)
+Install dependencies:
 ```bash
-pip install "psycopg[binary]" sqlalchemy
+pip install "pgvecto_rs[sqlalchemy]"
 ```

 Then write your code. See [examples/sqlalchemy_example.py](examples/sqlalchemy_example.py) and [tests/test_sqlalchemy.py](tests/test_sqlalchemy.py) for example.
@ -31,9 +82,9 @@ All the operators include:

 ### psycopg3

-Install [psycopg3](https://www.psycopg.org/psycopg3/docs/basic/install.html)
+Install dependencies:
 ```bash
-pip install "psycopg[binary]"
+pip install "pgvecto_rs[psycopg3]"
 ```

 Then write your code. See [examples/psycopg_example.py](examples/psycopg_example.py) and [tests/test_psycopg.py](tests/test_psycopg.py) for example.
--- a/bindings/python/examples/sdk_example.py
+++ b/bindings/python/examples/sdk_example.py
@ -0,0 +1,74 @@
+import os
+
+from openai import OpenAI
+
+from pgvecto_rs.sdk import PGVectoRs, Record, filters
+
+URL = "postgresql+psycopg://{username}:{password}@{host}:{port}/{db_name}".format(
+    port=os.getenv("DB_PORT", 5432),
+    host=os.getenv("DB_HOST", "localhost"),
+    username=os.getenv("DB_USER", "postgres"),
+    password=os.getenv("DB_PASS", "mysecretpassword"),
+    db_name=os.getenv("DB_NAME", "postgres"),
+)
+embedding = OpenAI().embeddings
+
+
+def embed(text: str):
+    return (
+        embedding.create(input=text, model="text-embedding-ada-002").data[0].embedding
+    )
+
+
+texts = [
+    "Hello world",
+    "Hello PostgreSQL",
+    "Hello pgvecto.rs!",
+]
+records1 = [Record.from_text(text, embed(text), {"src": "one"}) for text in texts]
+records2 = [Record.from_text(text, embed(text), {"src": "two"}) for text in texts]
+target = embed("Hello vector database!")
+
+# Create an empty client
+client = PGVectoRs(
+    db_url=URL,
+    collection_name="example",
+    dimension=1536,
+)
+try:
+    # Add some records
+    client.insert(records1)
+    client.insert(records2)
+
+    # Query (With a filter from the filters module)
+    print("#################### First Query ####################")
+    for record, dis in client.search(
+        target, filter=filters.meta_contains({"src": "one"})
+    ):
+        print(f"DISTANCE SCORE: {dis}")
+        print(record)
+
+    # Another Query (Equivalent to the first one, but with a lambda filter written by hand)
+    print("#################### Second Query ####################")
+    for record, dis in client.search(
+        target, filter=lambda r: r.meta.contains({"src": "one"})
+    ):
+        print(f"DISTANCE SCORE: {dis}")
+        print(record)
+
+    # Yet Another Query (With a more complex filter)
+    print("#################### Third Query ####################")
+
+    def complex_filter(r: filters.FilterInput) -> filters.FilterOutput:
+        t1 = r.text.endswith("!") == False  # noqa: E712
+        t2 = r.meta.contains({"src": "two"})
+        t = t1 & t2
+        return t
+
+    for record, dis in client.search(target, filter=complex_filter):
+        print(f"DISTANCE SCORE: {dis}")
+        print(record)
+
+finally:
+    # Clean up
+    client.drop()
--- a/bindings/python/pdm.lock
+++ b/bindings/python/pdm.lock
@ -2,11 +2,38 @@
 # It is not intended for manual editing.

 [metadata]
-groups = ["default", "dev", "lint"]
-cross_platform = true
-static_urls = false
-lock_version = "4.3"
-content_hash = "sha256:32c5bb376292d321bc5237e9df415259c527346f042aa4c6dde68bd0adc10525"
+groups = ["default", "lint", "psycopg3", "sdk", "sqlalchemy", "test"]
+strategy = ["cross_platform", "direct_minimal_versions"]
+lock_version = "4.4"
+content_hash = "sha256:f65e8d98636d7592453753c6ba60e73a6912f0e21205dff0e0f92bb148befce3"
+
+[[package]]
+name = "annotated-types"
+version = "0.6.0"
+requires_python = ">=3.8"
+summary = "Reusable constraint types to use with typing.Annotated"
+dependencies = [
+    "typing-extensions>=4.0.0; python_version < \"3.9\"",
+]
+files = [
+    {file = "annotated_types-0.6.0-py3-none-any.whl", hash = "sha256:0641064de18ba7a25dee8f96403ebc39113d0cb953a01429249d5c7564666a43"},
+    {file = "annotated_types-0.6.0.tar.gz", hash = "sha256:563339e807e53ffd9c267e99fc6d9ea23eb8443c08f112651963e24e22f84a5d"},
+]
+
+[[package]]
+name = "anyio"
+version = "3.7.1"
+requires_python = ">=3.7"
+summary = "High level compatibility layer for multiple asynchronous event loop implementations"
+dependencies = [
+    "exceptiongroup; python_version < \"3.11\"",
+    "idna>=2.8",
+    "sniffio>=1.1",
+]
+files = [
+    {file = "anyio-3.7.1-py3-none-any.whl", hash = "sha256:91dee416e570e92c64041bd18b900d1d6fa78dff7048769ce5ac5ddad004fbb5"},
+    {file = "anyio-3.7.1.tar.gz", hash = "sha256:44a3c9aba0f5defa43261a8b3efb97891f2bd7d804e0e1f56419befa1adfc780"},
+]

 [[package]]
 name = "backports-zoneinfo"
@ -23,39 +50,13 @@ files = [
 ]

 [[package]]
-name = "black"
-version = "23.10.0"
-requires_python = ">=3.8"
-summary = "The uncompromising code formatter."
-dependencies = [
-    "click>=8.0.0",
-    "mypy-extensions>=0.4.3",
-    "packaging>=22.0",
-    "pathspec>=0.9.0",
-    "platformdirs>=2",
-    "tomli>=1.1.0; python_version < \"3.11\"",
-    "typing-extensions>=4.0.1; python_version < \"3.11\"",
-]
+name = "certifi"
+version = "2023.7.22"
+requires_python = ">=3.6"
+summary = "Python package for providing Mozilla's CA Bundle."
 files = [
-    {file = "black-23.10.0-cp311-cp311-macosx_10_16_arm64.whl", hash = "sha256:30b78ac9b54cf87bcb9910ee3d499d2bc893afd52495066c49d9ee6b21eee06e"},
-    {file = "black-23.10.0-cp311-cp311-macosx_10_16_x86_64.whl", hash = "sha256:0e232f24a337fed7a82c1185ae46c56c4a6167fb0fe37411b43e876892c76699"},
-    {file = "black-23.10.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:31946ec6f9c54ed7ba431c38bc81d758970dd734b96b8e8c2b17a367d7908171"},
-    {file = "black-23.10.0-cp311-cp311-win_amd64.whl", hash = "sha256:c870bee76ad5f7a5ea7bd01dc646028d05568d33b0b09b7ecfc8ec0da3f3f39c"},
-    {file = "black-23.10.0-py3-none-any.whl", hash = "sha256:e223b731a0e025f8ef427dd79d8cd69c167da807f5710add30cdf131f13dd62e"},
-    {file = "black-23.10.0.tar.gz", hash = "sha256:31b9f87b277a68d0e99d2905edae08807c007973eaa609da5f0c62def6b7c0bd"},
-]
-
-[[package]]
-name = "click"
-version = "8.1.7"
-requires_python = ">=3.7"
-summary = "Composable command line interface toolkit"
-dependencies = [
-    "colorama; platform_system == \"Windows\"",
-]
-files = [
-    {file = "click-8.1.7-py3-none-any.whl", hash = "sha256:ae74fb96c20a0277a1d615f1e4d73c8414f5a98db8b799a7931d1582f3390c28"},
-    {file = "click-8.1.7.tar.gz", hash = "sha256:ca9853ad459e787e2192211578cc907e7594e294c7ccc834310722b41b9ca6de"},
+    {file = "certifi-2023.7.22-py3-none-any.whl", hash = "sha256:92d6037539857d8206b8f6ae472e8b77db8058fec5937a1ef3f54304089edbb9"},
+    {file = "certifi-2023.7.22.tar.gz", hash = "sha256:539cc1d13202e33ca466e88b2807e29f4c13049d6d87031a3c110744495cb082"},
 ]

 [[package]]
@ -68,6 +69,16 @@ files = [
    {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
 ]

+[[package]]
+name = "distro"
+version = "1.8.0"
+requires_python = ">=3.6"
+summary = "Distro - an OS platform information API"
+files = [
+    {file = "distro-1.8.0-py3-none-any.whl", hash = "sha256:99522ca3e365cac527b44bde033f64c6945d90eb9f769703caaec52b09bbd3ff"},
+    {file = "distro-1.8.0.tar.gz", hash = "sha256:02e111d1dc6a50abb8eed6bf31c3e48ed8b0830d1ea2a1b78c61765c2513fdd8"},
+]
+
 [[package]]
 name = "exceptiongroup"
 version = "1.1.3"
@ -80,30 +91,109 @@ files = [

 [[package]]
 name = "greenlet"
-version = "3.0.0"
+version = "3.0.1"
 requires_python = ">=3.7"
 summary = "Lightweight in-process concurrent programming"
 files = [
-    {file = "greenlet-3.0.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:211ef8d174601b80e01436f4e6905aca341b15a566f35a10dd8d1e93f5dbb3b7"},
-    {file = "greenlet-3.0.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6512592cc49b2c6d9b19fbaa0312124cd4c4c8a90d28473f86f92685cc5fef8e"},
-    {file = "greenlet-3.0.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:871b0a8835f9e9d461b7fdaa1b57e3492dd45398e87324c047469ce2fc9f516c"},
-    {file = "greenlet-3.0.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b505fcfc26f4148551826a96f7317e02c400665fa0883fe505d4fcaab1dabfdd"},
-    {file = "greenlet-3.0.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:123910c58234a8d40eaab595bc56a5ae49bdd90122dde5bdc012c20595a94c14"},
-    {file = "greenlet-3.0.0-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:96d9ea57292f636ec851a9bb961a5cc0f9976900e16e5d5647f19aa36ba6366b"},
-    {file = "greenlet-3.0.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:0b72b802496cccbd9b31acea72b6f87e7771ccfd7f7927437d592e5c92ed703c"},
-    {file = "greenlet-3.0.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:527cd90ba3d8d7ae7dceb06fda619895768a46a1b4e423bdb24c1969823b8362"},
-    {file = "greenlet-3.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:37f60b3a42d8b5499be910d1267b24355c495064f271cfe74bf28b17b099133c"},
-    {file = "greenlet-3.0.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:1482fba7fbed96ea7842b5a7fc11d61727e8be75a077e603e8ab49d24e234383"},
-    {file = "greenlet-3.0.0-cp312-cp312-macosx_13_0_arm64.whl", hash = "sha256:be557119bf467d37a8099d91fbf11b2de5eb1fd5fc5b91598407574848dc910f"},
-    {file = "greenlet-3.0.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:73b2f1922a39d5d59cc0e597987300df3396b148a9bd10b76a058a2f2772fc04"},
-    {file = "greenlet-3.0.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d1e22c22f7826096ad503e9bb681b05b8c1f5a8138469b255eb91f26a76634f2"},
-    {file = "greenlet-3.0.0-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1d363666acc21d2c204dd8705c0e0457d7b2ee7a76cb16ffc099d6799744ac99"},
-    {file = "greenlet-3.0.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:334ef6ed8337bd0b58bb0ae4f7f2dcc84c9f116e474bb4ec250a8bb9bd797a66"},
-    {file = "greenlet-3.0.0-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:6672fdde0fd1a60b44fb1751a7779c6db487e42b0cc65e7caa6aa686874e79fb"},
-    {file = "greenlet-3.0.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:952256c2bc5b4ee8df8dfc54fc4de330970bf5d79253c863fb5e6761f00dda35"},
-    {file = "greenlet-3.0.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:269d06fa0f9624455ce08ae0179430eea61085e3cf6457f05982b37fd2cefe17"},
-    {file = "greenlet-3.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:9adbd8ecf097e34ada8efde9b6fec4dd2a903b1e98037adf72d12993a1c80b51"},
-    {file = "greenlet-3.0.0.tar.gz", hash = "sha256:19834e3f91f485442adc1ee440171ec5d9a4840a1f7bd5ed97833544719ce10b"},
+    {file = "greenlet-3.0.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:f89e21afe925fcfa655965ca8ea10f24773a1791400989ff32f467badfe4a064"},
+    {file = "greenlet-3.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:28e89e232c7593d33cac35425b58950789962011cc274aa43ef8865f2e11f46d"},
+    {file = "greenlet-3.0.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b8ba29306c5de7717b5761b9ea74f9c72b9e2b834e24aa984da99cbfc70157fd"},
+    {file = "greenlet-3.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:19bbdf1cce0346ef7341705d71e2ecf6f41a35c311137f29b8a2dc2341374565"},
+    {file = "greenlet-3.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:599daf06ea59bfedbec564b1692b0166a0045f32b6f0933b0dd4df59a854caf2"},
+    {file = "greenlet-3.0.1-cp310-cp310-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b641161c302efbb860ae6b081f406839a8b7d5573f20a455539823802c655f63"},
+    {file = "greenlet-3.0.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:d57e20ba591727da0c230ab2c3f200ac9d6d333860d85348816e1dca4cc4792e"},
+    {file = "greenlet-3.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:5805e71e5b570d490938d55552f5a9e10f477c19400c38bf1d5190d760691846"},
+    {file = "greenlet-3.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:52e93b28db27ae7d208748f45d2db8a7b6a380e0d703f099c949d0f0d80b70e9"},
+    {file = "greenlet-3.0.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:f7bfb769f7efa0eefcd039dd19d843a4fbfbac52f1878b1da2ed5793ec9b1a65"},
+    {file = "greenlet-3.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:91e6c7db42638dc45cf2e13c73be16bf83179f7859b07cfc139518941320be96"},
+    {file = "greenlet-3.0.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1757936efea16e3f03db20efd0cd50a1c86b06734f9f7338a90c4ba85ec2ad5a"},
+    {file = "greenlet-3.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:19075157a10055759066854a973b3d1325d964d498a805bb68a1f9af4aaef8ec"},
+    {file = "greenlet-3.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e9d21aaa84557d64209af04ff48e0ad5e28c5cca67ce43444e939579d085da72"},
+    {file = "greenlet-3.0.1-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2847e5d7beedb8d614186962c3d774d40d3374d580d2cbdab7f184580a39d234"},
+    {file = "greenlet-3.0.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:97e7ac860d64e2dcba5c5944cfc8fa9ea185cd84061c623536154d5a89237884"},
+    {file = "greenlet-3.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:b2c02d2ad98116e914d4f3155ffc905fd0c025d901ead3f6ed07385e19122c94"},
+    {file = "greenlet-3.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:22f79120a24aeeae2b4471c711dcf4f8c736a2bb2fabad2a67ac9a55ea72523c"},
+    {file = "greenlet-3.0.1-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:100f78a29707ca1525ea47388cec8a049405147719f47ebf3895e7509c6446aa"},
+    {file = "greenlet-3.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:60d5772e8195f4e9ebf74046a9121bbb90090f6550f81d8956a05387ba139353"},
+    {file = "greenlet-3.0.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:daa7197b43c707462f06d2c693ffdbb5991cbb8b80b5b984007de431493a319c"},
+    {file = "greenlet-3.0.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ea6b8aa9e08eea388c5f7a276fabb1d4b6b9d6e4ceb12cc477c3d352001768a9"},
+    {file = "greenlet-3.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8d11ebbd679e927593978aa44c10fc2092bc454b7d13fdc958d3e9d508aba7d0"},
+    {file = "greenlet-3.0.1-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:dbd4c177afb8a8d9ba348d925b0b67246147af806f0b104af4d24f144d461cd5"},
+    {file = "greenlet-3.0.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:20107edf7c2c3644c67c12205dc60b1bb11d26b2610b276f97d666110d1b511d"},
+    {file = "greenlet-3.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8bef097455dea90ffe855286926ae02d8faa335ed8e4067326257cb571fc1445"},
+    {file = "greenlet-3.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:b2d3337dcfaa99698aa2377c81c9ca72fcd89c07e7eb62ece3f23a3fe89b2ce4"},
+    {file = "greenlet-3.0.1-cp38-cp38-macosx_11_0_universal2.whl", hash = "sha256:d2905ce1df400360463c772b55d8e2518d0e488a87cdea13dd2c71dcb2a1fa16"},
+    {file = "greenlet-3.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0a02d259510b3630f330c86557331a3b0e0c79dac3d166e449a39363beaae174"},
+    {file = "greenlet-3.0.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:55d62807f1c5a1682075c62436702aaba941daa316e9161e4b6ccebbbf38bda3"},
+    {file = "greenlet-3.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3fcc780ae8edbb1d050d920ab44790201f027d59fdbd21362340a85c79066a74"},
+    {file = "greenlet-3.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4eddd98afc726f8aee1948858aed9e6feeb1758889dfd869072d4465973f6bfd"},
+    {file = "greenlet-3.0.1-cp38-cp38-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:eabe7090db68c981fca689299c2d116400b553f4b713266b130cfc9e2aa9c5a9"},
+    {file = "greenlet-3.0.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:f2f6d303f3dee132b322a14cd8765287b8f86cdc10d2cb6a6fae234ea488888e"},
+    {file = "greenlet-3.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:d923ff276f1c1f9680d32832f8d6c040fe9306cbfb5d161b0911e9634be9ef0a"},
+    {file = "greenlet-3.0.1-cp38-cp38-win32.whl", hash = "sha256:0b6f9f8ca7093fd4433472fd99b5650f8a26dcd8ba410e14094c1e44cd3ceddd"},
+    {file = "greenlet-3.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:990066bff27c4fcf3b69382b86f4c99b3652bab2a7e685d968cd4d0cfc6f67c6"},
+    {file = "greenlet-3.0.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:ce85c43ae54845272f6f9cd8320d034d7a946e9773c693b27d620edec825e376"},
+    {file = "greenlet-3.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:89ee2e967bd7ff85d84a2de09df10e021c9b38c7d91dead95b406ed6350c6997"},
+    {file = "greenlet-3.0.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:87c8ceb0cf8a5a51b8008b643844b7f4a8264a2c13fcbcd8a8316161725383fe"},
+    {file = "greenlet-3.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d6a8c9d4f8692917a3dc7eb25a6fb337bff86909febe2f793ec1928cd97bedfc"},
+    {file = "greenlet-3.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9fbc5b8f3dfe24784cee8ce0be3da2d8a79e46a276593db6868382d9c50d97b1"},
+    {file = "greenlet-3.0.1-cp39-cp39-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:85d2b77e7c9382f004b41d9c72c85537fac834fb141b0296942d52bf03fe4a3d"},
+    {file = "greenlet-3.0.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:696d8e7d82398e810f2b3622b24e87906763b6ebfd90e361e88eb85b0e554dc8"},
+    {file = "greenlet-3.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:329c5a2e5a0ee942f2992c5e3ff40be03e75f745f48847f118a3cfece7a28546"},
+    {file = "greenlet-3.0.1-cp39-cp39-win32.whl", hash = "sha256:cf868e08690cb89360eebc73ba4be7fb461cfbc6168dd88e2fbbe6f31812cd57"},
+    {file = "greenlet-3.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:ac4a39d1abae48184d420aa8e5e63efd1b75c8444dd95daa3e03f6c6310e9619"},
+    {file = "greenlet-3.0.1.tar.gz", hash = "sha256:816bd9488a94cba78d93e1abb58000e8266fa9cc2aa9ccdd6eb0696acb24005b"},
+]
+
+[[package]]
+name = "h11"
+version = "0.14.0"
+requires_python = ">=3.7"
+summary = "A pure-Python, bring-your-own-I/O implementation of HTTP/1.1"
+files = [
+    {file = "h11-0.14.0-py3-none-any.whl", hash = "sha256:e3fe4ac4b851c468cc8363d500db52c2ead036020723024a109d37346efaa761"},
+    {file = "h11-0.14.0.tar.gz", hash = "sha256:8f19fbbe99e72420ff35c00b27a34cb9937e902a8b810e2c88300c6f0a3b699d"},
+]
+
+[[package]]
+name = "httpcore"
+version = "1.0.2"
+requires_python = ">=3.8"
+summary = "A minimal low-level HTTP client."
+dependencies = [
+    "certifi",
+    "h11<0.15,>=0.13",
+]
+files = [
+    {file = "httpcore-1.0.2-py3-none-any.whl", hash = "sha256:096cc05bca73b8e459a1fc3dcf585148f63e534eae4339559c9b8a8d6399acc7"},
+    {file = "httpcore-1.0.2.tar.gz", hash = "sha256:9fc092e4799b26174648e54b74ed5f683132a464e95643b226e00c2ed2fa6535"},
+]
+
+[[package]]
+name = "httpx"
+version = "0.25.1"
+requires_python = ">=3.8"
+summary = "The next generation HTTP client."
+dependencies = [
+    "anyio",
+    "certifi",
+    "httpcore",
+    "idna",
+    "sniffio",
+]
+files = [
+    {file = "httpx-0.25.1-py3-none-any.whl", hash = "sha256:fec7d6cc5c27c578a391f7e87b9aa7d3d8fbcd034f6399f9f79b45bcc12a866a"},
+    {file = "httpx-0.25.1.tar.gz", hash = "sha256:ffd96d5cf901e63863d9f1b4b6807861dbea4d301613415d9e6e57ead15fc5d0"},
+]
+
+[[package]]
+name = "idna"
+version = "3.4"
+requires_python = ">=3.5"
+summary = "Internationalized Domain Names in Applications (IDNA)"
+files = [
+    {file = "idna-3.4-py3-none-any.whl", hash = "sha256:90b77e79eaa3eba6de819a0c442c0b4ceefc341a7a2ab77d7562bf49f425c5c2"},
+    {file = "idna-3.4.tar.gz", hash = "sha256:814f528e8dead7d329833b91c5faa87d60bf71824cd12a7530b5526063d02cb4"},
 ]

 [[package]]
@ -117,49 +207,51 @@ files = [
 ]

 [[package]]
-name = "mypy-extensions"
-version = "1.0.0"
-requires_python = ">=3.5"
-summary = "Type system extensions for programs checked with the mypy type checker."
+name = "numpy"
+version = "1.23.0"
+requires_python = ">=3.8"
+summary = "NumPy is the fundamental package for array computing with Python."
 files = [
-    {file = "mypy_extensions-1.0.0-py3-none-any.whl", hash = "sha256:4392f6c0eb8a5668a69e23d168ffa70f0be9ccfd32b5cc2d26a34ae5b844552d"},
-    {file = "mypy_extensions-1.0.0.tar.gz", hash = "sha256:75dbf8955dc00442a438fc4d0666508a9a97b6bd41aa2f0ffe9d2f2725af0782"},
+    {file = "numpy-1.23.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:58bfd40eb478f54ff7a5710dd61c8097e169bc36cc68333d00a9bcd8def53b38"},
+    {file = "numpy-1.23.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:196cd074c3f97c4121601790955f915187736f9cf458d3ee1f1b46aff2b1ade0"},
+    {file = "numpy-1.23.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f1d88ef79e0a7fa631bb2c3dda1ea46b32b1fe614e10fedd611d3d5398447f2f"},
+    {file = "numpy-1.23.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d54b3b828d618a19779a84c3ad952e96e2c2311b16384e973e671aa5be1f6187"},
+    {file = "numpy-1.23.0-cp310-cp310-win32.whl", hash = "sha256:2b2da66582f3a69c8ce25ed7921dcd8010d05e59ac8d89d126a299be60421171"},
+    {file = "numpy-1.23.0-cp310-cp310-win_amd64.whl", hash = "sha256:97a76604d9b0e79f59baeca16593c711fddb44936e40310f78bfef79ee9a835f"},
+    {file = "numpy-1.23.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:d8cc87bed09de55477dba9da370c1679bd534df9baa171dd01accbb09687dac3"},
+    {file = "numpy-1.23.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:f0f18804df7370571fb65db9b98bf1378172bd4e962482b857e612d1fec0f53e"},
+    {file = "numpy-1.23.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ac86f407873b952679f5f9e6c0612687e51547af0e14ddea1eedfcb22466babd"},
+    {file = "numpy-1.23.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ae8adff4172692ce56233db04b7ce5792186f179c415c37d539c25de7298d25d"},
+    {file = "numpy-1.23.0-cp38-cp38-win32.whl", hash = "sha256:fe8b9683eb26d2c4d5db32cd29b38fdcf8381324ab48313b5b69088e0e355379"},
+    {file = "numpy-1.23.0-cp38-cp38-win_amd64.whl", hash = "sha256:5043bcd71fcc458dfb8a0fc5509bbc979da0131b9d08e3d5f50fb0bbb36f169a"},
+    {file = "numpy-1.23.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:1c29b44905af288b3919803aceb6ec7fec77406d8b08aaa2e8b9e63d0fe2f160"},
+    {file = "numpy-1.23.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:98e8e0d8d69ff4d3fa63e6c61e8cfe2d03c29b16b58dbef1f9baa175bbed7860"},
+    {file = "numpy-1.23.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:79a506cacf2be3a74ead5467aee97b81fca00c9c4c8b3ba16dbab488cd99ba10"},
+    {file = "numpy-1.23.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:092f5e6025813e64ad6d1b52b519165d08c730d099c114a9247c9bb635a2a450"},
+    {file = "numpy-1.23.0-cp39-cp39-win32.whl", hash = "sha256:d6ca8dabe696c2785d0c8c9b0d8a9b6e5fdbe4f922bde70d57fa1a2848134f95"},
+    {file = "numpy-1.23.0-cp39-cp39-win_amd64.whl", hash = "sha256:fc431493df245f3c627c0c05c2bd134535e7929dbe2e602b80e42bf52ff760bc"},
+    {file = "numpy-1.23.0-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:f9c3fc2adf67762c9fe1849c859942d23f8d3e0bee7b5ed3d4a9c3eeb50a2f07"},
+    {file = "numpy-1.23.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d0d2094e8f4d760500394d77b383a1b06d3663e8892cdf5df3c592f55f3bff66"},
+    {file = "numpy-1.23.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:94b170b4fa0168cd6be4becf37cb5b127bd12a795123984385b8cd4aca9857e5"},
+    {file = "numpy-1.23.0.tar.gz", hash = "sha256:bd3fa4fe2e38533d5336e1272fc4e765cabbbde144309ccee8675509d5cd7b05"},
 ]

 [[package]]
-name = "numpy"
-version = "1.24.4"
-requires_python = ">=3.8"
-summary = "Fundamental package for array computing in Python"
+name = "openai"
+version = "1.2.2"
+requires_python = ">=3.7.1"
+summary = "Client library for the openai API"
+dependencies = [
+    "anyio<4,>=3.5.0",
+    "distro<2,>=1.7.0",
+    "httpx<1,>=0.23.0",
+    "pydantic<3,>=1.9.0",
+    "tqdm>4",
+    "typing-extensions<5,>=4.5",
+]
 files = [
-    {file = "numpy-1.24.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c0bfb52d2169d58c1cdb8cc1f16989101639b34c7d3ce60ed70b19c63eba0b64"},
-    {file = "numpy-1.24.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:ed094d4f0c177b1b8e7aa9cba7d6ceed51c0e569a5318ac0ca9a090680a6a1b1"},
-    {file = "numpy-1.24.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:79fc682a374c4a8ed08b331bef9c5f582585d1048fa6d80bc6c35bc384eee9b4"},
-    {file = "numpy-1.24.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7ffe43c74893dbf38c2b0a1f5428760a1a9c98285553c89e12d70a96a7f3a4d6"},
-    {file = "numpy-1.24.4-cp310-cp310-win32.whl", hash = "sha256:4c21decb6ea94057331e111a5bed9a79d335658c27ce2adb580fb4d54f2ad9bc"},
-    {file = "numpy-1.24.4-cp310-cp310-win_amd64.whl", hash = "sha256:b4bea75e47d9586d31e892a7401f76e909712a0fd510f58f5337bea9572c571e"},
-    {file = "numpy-1.24.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:f136bab9c2cfd8da131132c2cf6cc27331dd6fae65f95f69dcd4ae3c3639c810"},
-    {file = "numpy-1.24.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:e2926dac25b313635e4d6cf4dc4e51c8c0ebfed60b801c799ffc4c32bf3d1254"},
-    {file = "numpy-1.24.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:222e40d0e2548690405b0b3c7b21d1169117391c2e82c378467ef9ab4c8f0da7"},
-    {file = "numpy-1.24.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7215847ce88a85ce39baf9e89070cb860c98fdddacbaa6c0da3ffb31b3350bd5"},
-    {file = "numpy-1.24.4-cp311-cp311-win32.whl", hash = "sha256:4979217d7de511a8d57f4b4b5b2b965f707768440c17cb70fbf254c4b225238d"},
-    {file = "numpy-1.24.4-cp311-cp311-win_amd64.whl", hash = "sha256:b7b1fc9864d7d39e28f41d089bfd6353cb5f27ecd9905348c24187a768c79694"},
-    {file = "numpy-1.24.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1452241c290f3e2a312c137a9999cdbf63f78864d63c79039bda65ee86943f61"},
-    {file = "numpy-1.24.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:04640dab83f7c6c85abf9cd729c5b65f1ebd0ccf9de90b270cd61935eef0197f"},
-    {file = "numpy-1.24.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a5425b114831d1e77e4b5d812b69d11d962e104095a5b9c3b641a218abcc050e"},
-    {file = "numpy-1.24.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dd80e219fd4c71fc3699fc1dadac5dcf4fd882bfc6f7ec53d30fa197b8ee22dc"},
-    {file = "numpy-1.24.4-cp38-cp38-win32.whl", hash = "sha256:4602244f345453db537be5314d3983dbf5834a9701b7723ec28923e2889e0bb2"},
-    {file = "numpy-1.24.4-cp38-cp38-win_amd64.whl", hash = "sha256:692f2e0f55794943c5bfff12b3f56f99af76f902fc47487bdfe97856de51a706"},
-    {file = "numpy-1.24.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:2541312fbf09977f3b3ad449c4e5f4bb55d0dbf79226d7724211acc905049400"},
-    {file = "numpy-1.24.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:9667575fb6d13c95f1b36aca12c5ee3356bf001b714fc354eb5465ce1609e62f"},
-    {file = "numpy-1.24.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f3a86ed21e4f87050382c7bc96571755193c4c1392490744ac73d660e8f564a9"},
-    {file = "numpy-1.24.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d11efb4dbecbdf22508d55e48d9c8384db795e1b7b51ea735289ff96613ff74d"},
-    {file = "numpy-1.24.4-cp39-cp39-win32.whl", hash = "sha256:6620c0acd41dbcb368610bb2f4d83145674040025e5536954782467100aa8835"},
-    {file = "numpy-1.24.4-cp39-cp39-win_amd64.whl", hash = "sha256:befe2bf740fd8373cf56149a5c23a0f601e82869598d41f8e188a0e9869926f8"},
-    {file = "numpy-1.24.4-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:31f13e25b4e304632a4619d0e0777662c2ffea99fcae2029556b17d8ff958aef"},
-    {file = "numpy-1.24.4-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:95f7ac6540e95bc440ad77f56e520da5bf877f87dca58bd095288dce8940532a"},
-    {file = "numpy-1.24.4-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:e98f220aa76ca2a977fe435f5b04d7b3470c0a2e6312907b37ba6068f26787f2"},
-    {file = "numpy-1.24.4.tar.gz", hash = "sha256:80f5e3a4e498641401868df4208b74581206afbee7cf7b8329daae82676d9463"},
+    {file = "openai-1.2.2-py3-none-any.whl", hash = "sha256:e9238e506b8ee8fc00af5b656de7907986317d7cfcf581964ff6e54a449be727"},
+    {file = "openai-1.2.2.tar.gz", hash = "sha256:cbeff4eaf6cdcdccb24c9190d9880a827c034b221ed996201c10d578850b3db8"},
 ]

 [[package]]
@ -172,26 +264,6 @@ files = [
    {file = "packaging-23.2.tar.gz", hash = "sha256:048fb0e9405036518eaaf48a55953c750c11e1a1b68e0dd1a9d62ed0c092cfc5"},
 ]

-[[package]]
-name = "pathspec"
-version = "0.11.2"
-requires_python = ">=3.7"
-summary = "Utility library for gitignore style pattern matching of file paths."
-files = [
-    {file = "pathspec-0.11.2-py3-none-any.whl", hash = "sha256:1d6ed233af05e679efb96b1851550ea95bbb64b7c490b0f5aa52996c11e92a20"},
-    {file = "pathspec-0.11.2.tar.gz", hash = "sha256:e0d8d0ac2f12da61956eb2306b69f9469b42f4deb0f3cb6ed47b9cce9996ced3"},
-]
-
-[[package]]
-name = "platformdirs"
-version = "3.11.0"
-requires_python = ">=3.7"
-summary = "A small Python package for determining appropriate platform-specific dirs, e.g. a \"user data dir\"."
-files = [
-    {file = "platformdirs-3.11.0-py3-none-any.whl", hash = "sha256:e9d171d00af68be50e9202731309c4e658fd8bc76f55c11c7dd760d023bda68e"},
-    {file = "platformdirs-3.11.0.tar.gz", hash = "sha256:cf8ee52a3afdb965072dcc652433e0c7e3e40cf5ea1477cd4b3b1d2eb75495b3"},
-]
-
 [[package]]
 name = "pluggy"
 version = "1.3.0"
@ -295,9 +367,128 @@ files = [
    {file = "psycopg-3.1.12.tar.gz", hash = "sha256:cec7ad2bc6a8510e56c45746c631cf9394148bdc8a9a11fd8cf8554ce129ae78"},
 ]

+[[package]]
+name = "pydantic"
+version = "2.5.1"
+requires_python = ">=3.7"
+summary = "Data validation using Python type hints"
+dependencies = [
+    "annotated-types>=0.4.0",
+    "pydantic-core==2.14.3",
+    "typing-extensions>=4.6.1",
+]
+files = [
+    {file = "pydantic-2.5.1-py3-none-any.whl", hash = "sha256:dc5244a8939e0d9a68f1f1b5f550b2e1c879912033b1becbedb315accc75441b"},
+    {file = "pydantic-2.5.1.tar.gz", hash = "sha256:0b8be5413c06aadfbe56f6dc1d45c9ed25fd43264414c571135c97dd77c2bedb"},
+]
+
+[[package]]
+name = "pydantic-core"
+version = "2.14.3"
+requires_python = ">=3.7"
+summary = ""
+dependencies = [
+    "typing-extensions!=4.7.0,>=4.6.0",
+]
+files = [
+    {file = "pydantic_core-2.14.3-cp310-cp310-macosx_10_7_x86_64.whl", hash = "sha256:ba44fad1d114539d6a1509966b20b74d2dec9a5b0ee12dd7fd0a1bb7b8785e5f"},
+    {file = "pydantic_core-2.14.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:4a70d23eedd88a6484aa79a732a90e36701048a1509078d1b59578ef0ea2cdf5"},
+    {file = "pydantic_core-2.14.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7cc24728a1a9cef497697e53b3d085fb4d3bc0ef1ef4d9b424d9cf808f52c146"},
+    {file = "pydantic_core-2.14.3-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:ab4a2381005769a4af2ffddae74d769e8a4aae42e970596208ec6d615c6fb080"},
+    {file = "pydantic_core-2.14.3-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:905a12bf088d6fa20e094f9a477bf84bd823651d8b8384f59bcd50eaa92e6a52"},
+    {file = "pydantic_core-2.14.3-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:38aed5a1bbc3025859f56d6a32f6e53ca173283cb95348e03480f333b1091e7d"},
+    {file = "pydantic_core-2.14.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1767bd3f6370458e60c1d3d7b1d9c2751cc1ad743434e8ec84625a610c8b9195"},
+    {file = "pydantic_core-2.14.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:7cb0c397f29688a5bd2c0dbd44451bc44ebb9b22babc90f97db5ec3e5bb69977"},
+    {file = "pydantic_core-2.14.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:9ff737f24b34ed26de62d481ef522f233d3c5927279f6b7229de9b0deb3f76b5"},
+    {file = "pydantic_core-2.14.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a1a39fecb5f0b19faee9a8a8176c805ed78ce45d760259a4ff3d21a7daa4dfc1"},
+    {file = "pydantic_core-2.14.3-cp310-none-win32.whl", hash = "sha256:ccbf355b7276593c68fa824030e68cb29f630c50e20cb11ebb0ee450ae6b3d08"},
+    {file = "pydantic_core-2.14.3-cp310-none-win_amd64.whl", hash = "sha256:536e1f58419e1ec35f6d1310c88496f0d60e4f182cacb773d38076f66a60b149"},
+    {file = "pydantic_core-2.14.3-cp311-cp311-macosx_10_7_x86_64.whl", hash = "sha256:f1f46700402312bdc31912f6fc17f5ecaaaa3bafe5487c48f07c800052736289"},
+    {file = "pydantic_core-2.14.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:88ec906eb2d92420f5b074f59cf9e50b3bb44f3cb70e6512099fdd4d88c2f87c"},
+    {file = "pydantic_core-2.14.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:056ea7cc3c92a7d2a14b5bc9c9fa14efa794d9f05b9794206d089d06d3433dc7"},
+    {file = "pydantic_core-2.14.3-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:076edc972b68a66870cec41a4efdd72a6b655c4098a232314b02d2bfa3bfa157"},
+    {file = "pydantic_core-2.14.3-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e71f666c3bf019f2490a47dddb44c3ccea2e69ac882f7495c68dc14d4065eac2"},
+    {file = "pydantic_core-2.14.3-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f518eac285c9632be337323eef9824a856f2680f943a9b68ac41d5f5bad7df7c"},
+    {file = "pydantic_core-2.14.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9dbab442a8d9ca918b4ed99db8d89d11b1f067a7dadb642476ad0889560dac79"},
+    {file = "pydantic_core-2.14.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:0653fb9fc2fa6787f2fa08631314ab7fc8070307bd344bf9471d1b7207c24623"},
+    {file = "pydantic_core-2.14.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:c54af5069da58ea643ad34ff32fd6bc4eebb8ae0fef9821cd8919063e0aeeaab"},
+    {file = "pydantic_core-2.14.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:cc956f78651778ec1ab105196e90e0e5f5275884793ab67c60938c75bcca3989"},
+    {file = "pydantic_core-2.14.3-cp311-none-win32.whl", hash = "sha256:5b73441a1159f1fb37353aaefb9e801ab35a07dd93cb8177504b25a317f4215a"},
+    {file = "pydantic_core-2.14.3-cp311-none-win_amd64.whl", hash = "sha256:7349f99f1ef8b940b309179733f2cad2e6037a29560f1b03fdc6aa6be0a8d03c"},
+    {file = "pydantic_core-2.14.3-cp311-none-win_arm64.whl", hash = "sha256:ec79dbe23702795944d2ae4c6925e35a075b88acd0d20acde7c77a817ebbce94"},
+    {file = "pydantic_core-2.14.3-cp312-cp312-macosx_10_7_x86_64.whl", hash = "sha256:8f5624f0f67f2b9ecaa812e1dfd2e35b256487566585160c6c19268bf2ffeccc"},
+    {file = "pydantic_core-2.14.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:6c2d118d1b6c9e2d577e215567eedbe11804c3aafa76d39ec1f8bc74e918fd07"},
+    {file = "pydantic_core-2.14.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fe863491664c6720d65ae438d4efaa5eca766565a53adb53bf14bc3246c72fe0"},
+    {file = "pydantic_core-2.14.3-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:136bc7247e97a921a020abbd6ef3169af97569869cd6eff41b6a15a73c44ea9b"},
+    {file = "pydantic_core-2.14.3-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:aeafc7f5bbddc46213707266cadc94439bfa87ecf699444de8be044d6d6eb26f"},
+    {file = "pydantic_core-2.14.3-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e16aaf788f1de5a85c8f8fcc9c1ca1dd7dd52b8ad30a7889ca31c7c7606615b8"},
+    {file = "pydantic_core-2.14.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f8fc652c354d3362e2932a79d5ac4bbd7170757a41a62c4fe0f057d29f10bebb"},
+    {file = "pydantic_core-2.14.3-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:f1b92e72babfd56585c75caf44f0b15258c58e6be23bc33f90885cebffde3400"},
+    {file = "pydantic_core-2.14.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:75f3f534f33651b73f4d3a16d0254de096f43737d51e981478d580f4b006b427"},
+    {file = "pydantic_core-2.14.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:c9ffd823c46e05ef3eb28b821aa7bc501efa95ba8880b4a1380068e32c5bed47"},
+    {file = "pydantic_core-2.14.3-cp312-none-win32.whl", hash = "sha256:12e05a76b223577a4696c76d7a6b36a0ccc491ffb3c6a8cf92d8001d93ddfd63"},
+    {file = "pydantic_core-2.14.3-cp312-none-win_amd64.whl", hash = "sha256:1582f01eaf0537a696c846bea92082082b6bfc1103a88e777e983ea9fbdc2a0f"},
+    {file = "pydantic_core-2.14.3-cp312-none-win_arm64.whl", hash = "sha256:96fb679c7ca12a512d36d01c174a4fbfd912b5535cc722eb2c010c7b44eceb8e"},
+    {file = "pydantic_core-2.14.3-cp38-cp38-macosx_10_7_x86_64.whl", hash = "sha256:10904368261e4509c091cbcc067e5a88b070ed9a10f7ad78f3029c175487490f"},
+    {file = "pydantic_core-2.14.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:260692420028319e201b8649b13ac0988974eeafaaef95d0dfbf7120c38dc000"},
+    {file = "pydantic_core-2.14.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3c1bf1a7b05a65d3b37a9adea98e195e0081be6b17ca03a86f92aeb8b110f468"},
+    {file = "pydantic_core-2.14.3-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:d7abd17a838a52140e3aeca271054e321226f52df7e0a9f0da8f91ea123afe98"},
+    {file = "pydantic_core-2.14.3-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a5c51460ede609fbb4fa883a8fe16e749964ddb459966d0518991ec02eb8dfb9"},
+    {file = "pydantic_core-2.14.3-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d06c78074646111fb01836585f1198367b17d57c9f427e07aaa9ff499003e58d"},
+    {file = "pydantic_core-2.14.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:af452e69446fadf247f18ac5d153b1f7e61ef708f23ce85d8c52833748c58075"},
+    {file = "pydantic_core-2.14.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:e3ad4968711fb379a67c8c755beb4dae8b721a83737737b7bcee27c05400b047"},
+    {file = "pydantic_core-2.14.3-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:c5ea0153482e5b4d601c25465771c7267c99fddf5d3f3bdc238ef930e6d051cf"},
+    {file = "pydantic_core-2.14.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:96eb10ef8920990e703da348bb25fedb8b8653b5966e4e078e5be382b430f9e0"},
+    {file = "pydantic_core-2.14.3-cp38-none-win32.whl", hash = "sha256:ea1498ce4491236d1cffa0eee9ad0968b6ecb0c1cd711699c5677fc689905f00"},
+    {file = "pydantic_core-2.14.3-cp38-none-win_amd64.whl", hash = "sha256:2bc736725f9bd18a60eec0ed6ef9b06b9785454c8d0105f2be16e4d6274e63d0"},
+    {file = "pydantic_core-2.14.3-cp39-cp39-macosx_10_7_x86_64.whl", hash = "sha256:1ea992659c03c3ea811d55fc0a997bec9dde863a617cc7b25cfde69ef32e55af"},
+    {file = "pydantic_core-2.14.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:d2b53e1f851a2b406bbb5ac58e16c4a5496038eddd856cc900278fa0da97f3fc"},
+    {file = "pydantic_core-2.14.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0c7f8e8a7cf8e81ca7d44bea4f181783630959d41b4b51d2f74bc50f348a090f"},
+    {file = "pydantic_core-2.14.3-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8d3b9c91eeb372a64ec6686c1402afd40cc20f61a0866850f7d989b6bf39a41a"},
+    {file = "pydantic_core-2.14.3-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9ef3e2e407e4cad2df3c89488a761ed1f1c33f3b826a2ea9a411b0a7d1cccf1b"},
+    {file = "pydantic_core-2.14.3-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f86f20a9d5bee1a6ede0f2757b917bac6908cde0f5ad9fcb3606db1e2968bcf5"},
+    {file = "pydantic_core-2.14.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:61beaa79d392d44dc19d6f11ccd824d3cccb865c4372157c40b92533f8d76dd0"},
+    {file = "pydantic_core-2.14.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:d41df8e10b094640a6b234851b624b76a41552f637b9fb34dc720b9fe4ef3be4"},
+    {file = "pydantic_core-2.14.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:2c08ac60c3caa31f825b5dbac47e4875bd4954d8f559650ad9e0b225eaf8ed0c"},
+    {file = "pydantic_core-2.14.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:98d8b3932f1a369364606417ded5412c4ffb15bedbcf797c31317e55bd5d920e"},
+    {file = "pydantic_core-2.14.3-cp39-none-win32.whl", hash = "sha256:caa94726791e316f0f63049ee00dff3b34a629b0d099f3b594770f7d0d8f1f56"},
+    {file = "pydantic_core-2.14.3-cp39-none-win_amd64.whl", hash = "sha256:2494d20e4c22beac30150b4be3b8339bf2a02ab5580fa6553ca274bc08681a65"},
+    {file = "pydantic_core-2.14.3-pp310-pypy310_pp73-macosx_10_7_x86_64.whl", hash = "sha256:fe272a72c7ed29f84c42fedd2d06c2f9858dc0c00dae3b34ba15d6d8ae0fbaaf"},
+    {file = "pydantic_core-2.14.3-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:7e63a56eb7fdee1587d62f753ccd6d5fa24fbeea57a40d9d8beaef679a24bdd6"},
+    {file = "pydantic_core-2.14.3-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b7692f539a26265cece1e27e366df5b976a6db6b1f825a9e0466395b314ee48b"},
+    {file = "pydantic_core-2.14.3-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:af46f0b7a1342b49f208fed31f5a83b8495bb14b652f621e0a6787d2f10f24ee"},
+    {file = "pydantic_core-2.14.3-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:6e2f9d76c00e805d47f19c7a96a14e4135238a7551a18bfd89bb757993fd0933"},
+    {file = "pydantic_core-2.14.3-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:de52ddfa6e10e892d00f747bf7135d7007302ad82e243cf16d89dd77b03b649d"},
+    {file = "pydantic_core-2.14.3-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:38113856c7fad8c19be7ddd57df0c3e77b1b2336459cb03ee3903ce9d5e236ce"},
+    {file = "pydantic_core-2.14.3-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:354db020b1f8f11207b35360b92d95725621eb92656725c849a61e4b550f4acc"},
+    {file = "pydantic_core-2.14.3-pp37-pypy37_pp73-macosx_10_7_x86_64.whl", hash = "sha256:76fc18653a5c95e5301a52d1b5afb27c9adc77175bf00f73e94f501caf0e05ad"},
+    {file = "pydantic_core-2.14.3-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2646f8270f932d79ba61102a15ea19a50ae0d43b314e22b3f8f4b5fabbfa6e38"},
+    {file = "pydantic_core-2.14.3-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:37dad73a2f82975ed563d6a277fd9b50e5d9c79910c4aec787e2d63547202315"},
+    {file = "pydantic_core-2.14.3-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:113752a55a8eaece2e4ac96bc8817f134c2c23477e477d085ba89e3aa0f4dc44"},
+    {file = "pydantic_core-2.14.3-pp37-pypy37_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:8488e973547e8fb1b4193fd9faf5236cf1b7cd5e9e6dc7ff6b4d9afdc4c720cb"},
+    {file = "pydantic_core-2.14.3-pp37-pypy37_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:3d1dde10bd9962b1434053239b1d5490fc31a2b02d8950a5f731bc584c7a5a0f"},
+    {file = "pydantic_core-2.14.3-pp38-pypy38_pp73-macosx_10_7_x86_64.whl", hash = "sha256:2c83892c7bf92b91d30faca53bb8ea21f9d7e39f0ae4008ef2c2f91116d0464a"},
+    {file = "pydantic_core-2.14.3-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:849cff945284c577c5f621d2df76ca7b60f803cc8663ff01b778ad0af0e39bb9"},
+    {file = "pydantic_core-2.14.3-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4aa89919fbd8a553cd7d03bf23d5bc5deee622e1b5db572121287f0e64979476"},
+    {file = "pydantic_core-2.14.3-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bf15145b1f8056d12c67255cd3ce5d317cd4450d5ee747760d8d088d85d12a2d"},
+    {file = "pydantic_core-2.14.3-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:4cc6bb11f4e8e5ed91d78b9880774fbc0856cb226151b0a93b549c2b26a00c19"},
+    {file = "pydantic_core-2.14.3-pp38-pypy38_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:832d16f248ca0cc96929139734ec32d21c67669dcf8a9f3f733c85054429c012"},
+    {file = "pydantic_core-2.14.3-pp38-pypy38_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:b02b5e1f54c3396c48b665050464803c23c685716eb5d82a1d81bf81b5230da4"},
+    {file = "pydantic_core-2.14.3-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:1f2d4516c32255782153e858f9a900ca6deadfb217fd3fb21bb2b60b4e04d04d"},
+    {file = "pydantic_core-2.14.3-pp39-pypy39_pp73-macosx_10_7_x86_64.whl", hash = "sha256:0a3e51c2be472b7867eb0c5d025b91400c2b73a0823b89d4303a9097e2ec6655"},
+    {file = "pydantic_core-2.14.3-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:df33902464410a1f1a0411a235f0a34e7e129f12cb6340daca0f9d1390f5fe10"},
+    {file = "pydantic_core-2.14.3-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:27828f0227b54804aac6fb077b6bb48e640b5435fdd7fbf0c274093a7b78b69c"},
+    {file = "pydantic_core-2.14.3-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1e2979dc80246e18e348de51246d4c9b410186ffa3c50e77924bec436b1e36cb"},
+    {file = "pydantic_core-2.14.3-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:b28996872b48baf829ee75fa06998b607c66a4847ac838e6fd7473a6b2ab68e7"},
+    {file = "pydantic_core-2.14.3-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:ca55c9671bb637ce13d18ef352fd32ae7aba21b4402f300a63f1fb1fd18e0364"},
+    {file = "pydantic_core-2.14.3-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:aecd5ed096b0e5d93fb0367fd8f417cef38ea30b786f2501f6c34eabd9062c38"},
+    {file = "pydantic_core-2.14.3-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:44aaf1a07ad0824e407dafc637a852e9a44d94664293bbe7d8ee549c356c8882"},
+    {file = "pydantic_core-2.14.3.tar.gz", hash = "sha256:3ad083df8fe342d4d8d00cc1d3c1a23f0dc84fce416eb301e69f1ddbbe124d3f"},
+]
+
 [[package]]
 name = "pytest"
-version = "7.4.2"
+version = "7.4.3"
 requires_python = ">=3.7"
 summary = "pytest: simple powerful testing with Python"
 dependencies = [
@ -309,8 +500,8 @@ dependencies = [
    "tomli>=1.0.0; python_version < \"3.11\"",
 ]
 files = [
-    {file = "pytest-7.4.2-py3-none-any.whl", hash = "sha256:1d881c6124e08ff0a1bb75ba3ec0bfd8b5354a01c194ddd5a0a870a48d99b002"},
-    {file = "pytest-7.4.2.tar.gz", hash = "sha256:a766259cfab564a2ad52cb1aae1b881a75c3eb7e34ca3779697c23ed47c47069"},
+    {file = "pytest-7.4.3-py3-none-any.whl", hash = "sha256:0d009c083ea859a71b76adf7c1d502e4bc170b80a8ef002da5806527b9591fac"},
+    {file = "pytest-7.4.3.tar.gz", hash = "sha256:d989d136982de4e3b29dabcc838ad581c64e8ed52c11fbe86ddebd9da0818cd5"},
 ]

 [[package]]
@ -338,9 +529,19 @@ files = [
    {file = "ruff-0.1.1.tar.gz", hash = "sha256:c90461ae4abec261609e5ea436de4a4b5f2822921cf04c16d2cc9327182dbbcc"},
 ]

+[[package]]
+name = "sniffio"
+version = "1.3.0"
+requires_python = ">=3.7"
+summary = "Sniff out which async library your code is running under"
+files = [
+    {file = "sniffio-1.3.0-py3-none-any.whl", hash = "sha256:eecefdce1e5bbfb7ad2eeaabf7c1eeb404d7757c379bd1f7e5cce9d8bf425384"},
+    {file = "sniffio-1.3.0.tar.gz", hash = "sha256:e60305c5e5d314f5389259b7f22aaa33d8f7dee49763119234af3755c55b9101"},
+]
+
 [[package]]
 name = "sqlalchemy"
-version = "2.0.22"
+version = "2.0.23"
 requires_python = ">=3.7"
 summary = "Database Abstraction Library"
 dependencies = [
@ -348,34 +549,57 @@ dependencies = [
    "typing-extensions>=4.2.0",
 ]
 files = [
-    {file = "SQLAlchemy-2.0.22-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:4f6ff392b27a743c1ad346d215655503cec64405d3b694228b3454878bf21590"},
-    {file = "SQLAlchemy-2.0.22-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f776c2c30f0e5f4db45c3ee11a5f2a8d9de68e81eb73ec4237de1e32e04ae81c"},
-    {file = "SQLAlchemy-2.0.22-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c8f1792d20d2f4e875ce7a113f43c3561ad12b34ff796b84002a256f37ce9437"},
-    {file = "SQLAlchemy-2.0.22-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d80eeb5189d7d4b1af519fc3f148fe7521b9dfce8f4d6a0820e8f5769b005051"},
-    {file = "SQLAlchemy-2.0.22-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:69fd9e41cf9368afa034e1c81f3570afb96f30fcd2eb1ef29cb4d9371c6eece2"},
-    {file = "SQLAlchemy-2.0.22-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:54bcceaf4eebef07dadfde424f5c26b491e4a64e61761dea9459103ecd6ccc95"},
-    {file = "SQLAlchemy-2.0.22-cp311-cp311-win32.whl", hash = "sha256:7ee7ccf47aa503033b6afd57efbac6b9e05180f492aeed9fcf70752556f95624"},
-    {file = "SQLAlchemy-2.0.22-cp311-cp311-win_amd64.whl", hash = "sha256:b560f075c151900587ade06706b0c51d04b3277c111151997ea0813455378ae0"},
-    {file = "SQLAlchemy-2.0.22-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:2c9bac865ee06d27a1533471405ad240a6f5d83195eca481f9fc4a71d8b87df8"},
-    {file = "SQLAlchemy-2.0.22-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:625b72d77ac8ac23da3b1622e2da88c4aedaee14df47c8432bf8f6495e655de2"},
-    {file = "SQLAlchemy-2.0.22-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b39a6e21110204a8c08d40ff56a73ba542ec60bab701c36ce721e7990df49fb9"},
-    {file = "SQLAlchemy-2.0.22-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:53a766cb0b468223cafdf63e2d37f14a4757476157927b09300c8c5832d88560"},
-    {file = "SQLAlchemy-2.0.22-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:0e1ce8ebd2e040357dde01a3fb7d30d9b5736b3e54a94002641dfd0aa12ae6ce"},
-    {file = "SQLAlchemy-2.0.22-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:505f503763a767556fa4deae5194b2be056b64ecca72ac65224381a0acab7ebe"},
-    {file = "SQLAlchemy-2.0.22-cp312-cp312-win32.whl", hash = "sha256:154a32f3c7b00de3d090bc60ec8006a78149e221f1182e3edcf0376016be9396"},
-    {file = "SQLAlchemy-2.0.22-cp312-cp312-win_amd64.whl", hash = "sha256:129415f89744b05741c6f0b04a84525f37fbabe5dc3774f7edf100e7458c48cd"},
-    {file = "SQLAlchemy-2.0.22-py3-none-any.whl", hash = "sha256:3076740335e4aaadd7deb3fe6dcb96b3015f1613bd190a4e1634e1b99b02ec86"},
-    {file = "SQLAlchemy-2.0.22.tar.gz", hash = "sha256:5434cc601aa17570d79e5377f5fd45ff92f9379e2abed0be5e8c2fba8d353d2b"},
+    {file = "SQLAlchemy-2.0.23-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:638c2c0b6b4661a4fd264f6fb804eccd392745c5887f9317feb64bb7cb03b3ea"},
+    {file = "SQLAlchemy-2.0.23-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:e3b5036aa326dc2df50cba3c958e29b291a80f604b1afa4c8ce73e78e1c9f01d"},
+    {file = "SQLAlchemy-2.0.23-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:787af80107fb691934a01889ca8f82a44adedbf5ef3d6ad7d0f0b9ac557e0c34"},
+    {file = "SQLAlchemy-2.0.23-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c14eba45983d2f48f7546bb32b47937ee2cafae353646295f0e99f35b14286ab"},
+    {file = "SQLAlchemy-2.0.23-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:0666031df46b9badba9bed00092a1ffa3aa063a5e68fa244acd9f08070e936d3"},
+    {file = "SQLAlchemy-2.0.23-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:89a01238fcb9a8af118eaad3ffcc5dedaacbd429dc6fdc43fe430d3a941ff965"},
+    {file = "SQLAlchemy-2.0.23-cp310-cp310-win32.whl", hash = "sha256:cabafc7837b6cec61c0e1e5c6d14ef250b675fa9c3060ed8a7e38653bd732ff8"},
+    {file = "SQLAlchemy-2.0.23-cp310-cp310-win_amd64.whl", hash = "sha256:87a3d6b53c39cd173990de2f5f4b83431d534a74f0e2f88bd16eabb5667e65c6"},
+    {file = "SQLAlchemy-2.0.23-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:d5578e6863eeb998980c212a39106ea139bdc0b3f73291b96e27c929c90cd8e1"},
+    {file = "SQLAlchemy-2.0.23-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:62d9e964870ea5ade4bc870ac4004c456efe75fb50404c03c5fd61f8bc669a72"},
+    {file = "SQLAlchemy-2.0.23-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c80c38bd2ea35b97cbf7c21aeb129dcbebbf344ee01a7141016ab7b851464f8e"},
+    {file = "SQLAlchemy-2.0.23-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75eefe09e98043cff2fb8af9796e20747ae870c903dc61d41b0c2e55128f958d"},
+    {file = "SQLAlchemy-2.0.23-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:bd45a5b6c68357578263d74daab6ff9439517f87da63442d244f9f23df56138d"},
+    {file = "SQLAlchemy-2.0.23-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:a86cb7063e2c9fb8e774f77fbf8475516d270a3e989da55fa05d08089d77f8c4"},
+    {file = "SQLAlchemy-2.0.23-cp311-cp311-win32.whl", hash = "sha256:b41f5d65b54cdf4934ecede2f41b9c60c9f785620416e8e6c48349ab18643855"},
+    {file = "SQLAlchemy-2.0.23-cp311-cp311-win_amd64.whl", hash = "sha256:9ca922f305d67605668e93991aaf2c12239c78207bca3b891cd51a4515c72e22"},
+    {file = "SQLAlchemy-2.0.23-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:d0f7fb0c7527c41fa6fcae2be537ac137f636a41b4c5a4c58914541e2f436b45"},
+    {file = "SQLAlchemy-2.0.23-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:7c424983ab447dab126c39d3ce3be5bee95700783204a72549c3dceffe0fc8f4"},
+    {file = "SQLAlchemy-2.0.23-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f508ba8f89e0a5ecdfd3761f82dda2a3d7b678a626967608f4273e0dba8f07ac"},
+    {file = "SQLAlchemy-2.0.23-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6463aa765cf02b9247e38b35853923edbf2f6fd1963df88706bc1d02410a5577"},
+    {file = "SQLAlchemy-2.0.23-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:e599a51acf3cc4d31d1a0cf248d8f8d863b6386d2b6782c5074427ebb7803bda"},
+    {file = "SQLAlchemy-2.0.23-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:fd54601ef9cc455a0c61e5245f690c8a3ad67ddb03d3b91c361d076def0b4c60"},
+    {file = "SQLAlchemy-2.0.23-cp312-cp312-win32.whl", hash = "sha256:42d0b0290a8fb0165ea2c2781ae66e95cca6e27a2fbe1016ff8db3112ac1e846"},
+    {file = "SQLAlchemy-2.0.23-cp312-cp312-win_amd64.whl", hash = "sha256:227135ef1e48165f37590b8bfc44ed7ff4c074bf04dc8d6f8e7f1c14a94aa6ca"},
+    {file = "SQLAlchemy-2.0.23-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:64ac935a90bc479fee77f9463f298943b0e60005fe5de2aa654d9cdef46c54df"},
+    {file = "SQLAlchemy-2.0.23-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:c4722f3bc3c1c2fcc3702dbe0016ba31148dd6efcd2a2fd33c1b4897c6a19693"},
+    {file = "SQLAlchemy-2.0.23-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4af79c06825e2836de21439cb2a6ce22b2ca129bad74f359bddd173f39582bf5"},
+    {file = "SQLAlchemy-2.0.23-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:683ef58ca8eea4747737a1c35c11372ffeb84578d3aab8f3e10b1d13d66f2bc4"},
+    {file = "SQLAlchemy-2.0.23-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:d4041ad05b35f1f4da481f6b811b4af2f29e83af253bf37c3c4582b2c68934ab"},
+    {file = "SQLAlchemy-2.0.23-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:aeb397de65a0a62f14c257f36a726945a7f7bb60253462e8602d9b97b5cbe204"},
+    {file = "SQLAlchemy-2.0.23-cp38-cp38-win32.whl", hash = "sha256:42ede90148b73fe4ab4a089f3126b2cfae8cfefc955c8174d697bb46210c8306"},
+    {file = "SQLAlchemy-2.0.23-cp38-cp38-win_amd64.whl", hash = "sha256:964971b52daab357d2c0875825e36584d58f536e920f2968df8d581054eada4b"},
+    {file = "SQLAlchemy-2.0.23-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:616fe7bcff0a05098f64b4478b78ec2dfa03225c23734d83d6c169eb41a93e55"},
+    {file = "SQLAlchemy-2.0.23-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:0e680527245895aba86afbd5bef6c316831c02aa988d1aad83c47ffe92655e74"},
+    {file = "SQLAlchemy-2.0.23-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9585b646ffb048c0250acc7dad92536591ffe35dba624bb8fd9b471e25212a35"},
+    {file = "SQLAlchemy-2.0.23-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4895a63e2c271ffc7a81ea424b94060f7b3b03b4ea0cd58ab5bb676ed02f4221"},
+    {file = "SQLAlchemy-2.0.23-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:cc1d21576f958c42d9aec68eba5c1a7d715e5fc07825a629015fe8e3b0657fb0"},
+    {file = "SQLAlchemy-2.0.23-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:967c0b71156f793e6662dd839da54f884631755275ed71f1539c95bbada9aaab"},
+    {file = "SQLAlchemy-2.0.23-cp39-cp39-win32.whl", hash = "sha256:0a8c6aa506893e25a04233bc721c6b6cf844bafd7250535abb56cb6cc1368884"},
+    {file = "SQLAlchemy-2.0.23-cp39-cp39-win_amd64.whl", hash = "sha256:f3420d00d2cb42432c1d0e44540ae83185ccbbc67a6054dcc8ab5387add6620b"},
+    {file = "SQLAlchemy-2.0.23-py3-none-any.whl", hash = "sha256:31952bbc527d633b9479f5f81e8b9dfada00b91d6baba021a869095f1a97006d"},
+    {file = "SQLAlchemy-2.0.23.tar.gz", hash = "sha256:c1bda93cbbe4aa2aa0aa8655c5aeda505cd219ff3e8da91d1d329e143e4aff69"},
 ]

 [[package]]
 name = "toml"
-version = "0.10.2"
-requires_python = ">=2.6, !=3.0.*, !=3.1.*, !=3.2.*"
+version = "0.10.0"
 summary = "Python Library for Tom's Obvious, Minimal Language"
 files = [
-    {file = "toml-0.10.2-py2.py3-none-any.whl", hash = "sha256:806143ae5bfb6a3c6e736a764057db0e6a0e05e338b5630894a5f779cabb4f9b"},
-    {file = "toml-0.10.2.tar.gz", hash = "sha256:b3bda1d108d5dd99f4a20d24d9c348e91c4db7ab1b749200bded2f839ccbe68f"},
+    {file = "toml-0.10.0-py2.py3-none-any.whl", hash = "sha256:235682dd292d5899d361a811df37e04a8828a5b1da3115886b73cf81ebc9100e"},
+    {file = "toml-0.10.0.tar.gz", hash = "sha256:229f81c57791a41d65e399fc06bf0848bab550a9dfd5ed66df18ce5f05e73d5c"},
 ]

 [[package]]
@ -388,6 +612,19 @@ files = [
    {file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"},
 ]

+[[package]]
+name = "tqdm"
+version = "4.66.1"
+requires_python = ">=3.7"
+summary = "Fast, Extensible Progress Meter"
+dependencies = [
+    "colorama; platform_system == \"Windows\"",
+]
+files = [
+    {file = "tqdm-4.66.1-py3-none-any.whl", hash = "sha256:d302b3c5b53d47bce91fea46679d9c3c6508cf6332229aa1e7d8653723793386"},
+    {file = "tqdm-4.66.1.tar.gz", hash = "sha256:d88e651f9db8d8551a62556d3cff9e3034274ca5d66e93197cf2490e2dcb69c7"},
+]
+
 [[package]]
 name = "typing-extensions"
 version = "4.8.0"
--- a/bindings/python/pyproject.toml
+++ b/bindings/python/pyproject.toml
@ -1,40 +1,58 @@
 [project]
-name = "pgvecto_rs"
-version = "0.1.2"
+name = "pgvecto-rs"
+version = "0.1.3"
 description = "Python binding for pgvecto.rs"
 authors = [
-    {name = "TensorChord", email = "envd-maintainers@tensorchord.ai"},
-    {name = "盐粒 Yanli", email = "mail@yanli.one"},
+    { name = "TensorChord", email = "envd-maintainers@tensorchord.ai" },
+    { name = "盐粒 Yanli", email = "mail@yanli.one" },
 ]
 dependencies = [
-    "numpy>=1.23",
-    "toml>=0.10",
+  "numpy>=1.23",
+  "toml>=0.10",
 ]
 requires-python = ">=3.8"
 readme = "README.md"
-license = {text = "Apache-2.0"}
+license = { text = "Apache-2.0" }
+classifiers = [
+  "Programming Language :: Python :: 3 :: Only",
+  "Programming Language :: Python :: 3.8",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+]

 [build-system]
-requires = ["pdm-backend"]
 build-backend = "pdm.backend"
+requires      = [
+  "pdm-backend",
+]

 [project.optional-dependencies]
-lint = [
-    "black>=23.10.0",
-    "ruff>=0.1.1",
+psycopg3   = [
+  "psycopg[binary]>=3.1.12",
+]
+sdk        = [
+  "openai>=1.2.2",
+  "pgvecto_rs[sqlalchemy]",
+]
+sqlalchemy = [
+  "pgvecto_rs[psycopg3]",
+  "SQLAlchemy>=2.0.23",
 ]
-
 [tool.pdm.dev-dependencies]
-dev = [
-    "SQLAlchemy>=2",
-    "pytest>=7.4",
-    "psycopg[binary]>=3.1.12",
-]
+lint = ["ruff>=0.1.1"]
+test = ["pytest>=7.4.3"]

 [tool.pdm.scripts]
-test = "pytest tests/"
-format = {composite = ["black .", "ruff check --fix ."]}
-check = {composite = ["black --check .", "ruff check ."]}
+test   = "pytest tests/"
+format = "ruff format ."
+fix    = "ruff --fix ."
+check  = { composite = ["ruff format . --check", "ruff ."] }
+
+[tool.ruff]
+select = ["E", "F", "I", "TID"]
+ignore = ["E731", "E501"]
+src    = ["src"]

 [tool.pytest.ini_options]
 addopts = "-r aR"
--- a/bindings/python/src/pgvecto_rs/psycopg/init.py
+++ b/bindings/python/src/pgvecto_rs/psycopg/init.py
@ -4,7 +4,7 @@ from psycopg.adapt import Dumper, Loader
 from psycopg.pq import Format
 from psycopg.types import TypeInfo

-from ..utils.serializer import from_db_str, to_db_str
+from pgvecto_rs.utils.serializer import from_db_str, to_db_str

 __all__ = ["register_vector"]

--- a/bindings/python/src/pgvecto_rs/sdk/init.py
+++ b/bindings/python/src/pgvecto_rs/sdk/init.py
@ -0,0 +1,5 @@
+from pgvecto_rs.sdk.client import PGVectoRs
+from pgvecto_rs.sdk.filters import Filter
+from pgvecto_rs.sdk.record import Record
+
+__all__ = ["PGVectoRs", "Record", "Filter"]
--- a/bindings/python/src/pgvecto_rs/sdk/client.py
+++ b/bindings/python/src/pgvecto_rs/sdk/client.py
@ -0,0 +1,124 @@
+from typing import List, Literal, Optional, Tuple, Type, Union
+from uuid import UUID
+
+from numpy import ndarray
+from sqlalchemy import ColumnElement, Float, create_engine, delete, insert, select, text
+from sqlalchemy.dialects import postgresql
+from sqlalchemy.engine import Engine
+from sqlalchemy.orm import Mapped, mapped_column
+from sqlalchemy.orm.session import Session
+from sqlalchemy.types import String
+
+from pgvecto_rs.sdk.filters import Filter
+from pgvecto_rs.sdk.record import Record, RecordORM, RecordORMType
+from pgvecto_rs.sqlalchemy import Vector
+
+
+class PGVectoRs:
+    _engine: Engine
+    _table: Type[RecordORM]
+    dimension: int
+
+    def __init__(
+        self,
+        db_url: str,
+        collection_name: str,
+        dimension: int,
+    ) -> None:
+        """Connect to an existing table or create a new empty one.
+
+        Args:
+            db_url (str): url to the database.
+            table_name (str): name of the table.
+            dimension (int): dimension of the embeddings.
+        """
+
+        class _Table(RecordORM):
+            __tablename__ = f"collection_{collection_name}"
+            id: Mapped[UUID] = mapped_column(
+                postgresql.UUID(as_uuid=True), primary_key=True
+            )
+            text: Mapped[str] = mapped_column(String)
+            meta: Mapped[dict] = mapped_column(postgresql.JSONB)
+            embedding: Mapped[ndarray] = mapped_column(Vector(dimension))
+
+        self._engine = create_engine(db_url)
+        with Session(self._engine) as session:
+            session.execute(text("CREATE EXTENSION IF NOT EXISTS vectors"))
+            session.commit()
+        self._table = _Table
+        self._table.__table__.create(self._engine)
+        self.dimension = dimension
+
+    def insert(self, records: List[Record]) -> None:
+        with Session(self._engine) as session:
+            for record in records:
+                session.execute(
+                    insert(self._table).values(
+                        id=record.id,
+                        text=record.text,
+                        meta=record.meta,
+                        embedding=record.embedding,
+                    )
+                )
+            session.commit()
+
+    def search(
+        self,
+        embedding: Union[ndarray, List[float]],
+        distance_op: Literal["<->", "<=>", "<#>"] = "<->",
+        top_k: int = 4,
+        filter: Optional[Filter] = None,
+    ) -> List[Tuple[Record, float]]:
+        """Search for the nearest records.
+
+        Args:
+            embedding : Target embedding.
+            distance_op : Distance op.
+            top_k : Max records to return. Defaults to 4.
+            filter : Read our document. Defaults to None.
+            order_by_dis : Order by distance. Defaults to True.
+
+        Returns:
+            List of records and coresponding distances.
+
+        """
+        with Session(self._engine) as session:
+            stmt = (
+                select(
+                    self._table,
+                    self._table.embedding.op(distance_op, return_type=Float)(
+                        embedding
+                    ).label("distance"),
+                )
+                .limit(top_k)
+                .order_by("distance")
+            )
+            if filter is not None:
+                stmt = stmt.where(filter(self._table))
+            res = session.execute(stmt)
+            return [(Record.from_orm(row[0]), row[1]) for row in res]
+
+    # ================ Delete ================
+    def delete(self, filter: Filter) -> None:
+        with Session(self._engine) as session:
+            session.execute(delete(self._table).where(filter(self._table)))
+            session.commit()
+
+    def delete_all(self) -> None:
+        with Session(self._engine) as session:
+            session.execute(delete(self._table))
+            session.commit()
+
+    def delete_by_ids(self, ids: List[UUID]) -> None:
+        def filter(record: RecordORMType) -> ColumnElement[bool]:
+            return record.id.in_(ids)
+
+        with Session(self._engine) as session:
+            session.execute(delete(self._table).where(filter(self._table)))
+            session.commit()
+
+    # ================ Drop ================
+    def drop(self) -> None:
+        """Drop the table which the client is connected to."""
+        self._table.__table__.drop(self._engine)
--- a/bindings/python/src/pgvecto_rs/sdk/filters.py
+++ b/bindings/python/src/pgvecto_rs/sdk/filters.py
@ -0,0 +1,13 @@
+from typing import Callable, Type
+
+from sqlalchemy import ColumnElement
+
+from pgvecto_rs.sdk.record import RecordORMType
+
+Filter = Type[Callable[[RecordORMType], ColumnElement[bool]]]
+FilterInput = RecordORMType
+FilterOutput = ColumnElement[bool]
+
+
+def meta_contains(meta_contains: dict) -> Filter:
+    return lambda r: r.meta.contains(meta_contains)
--- a/bindings/python/src/pgvecto_rs/sdk/record.py
+++ b/bindings/python/src/pgvecto_rs/sdk/record.py
@ -0,0 +1,52 @@
+from typing import List, Optional, Type, Union
+from uuid import UUID, uuid4
+
+from numpy import array, float32, ndarray
+from sqlalchemy.orm import DeclarativeBase, Mapped
+
+
+class RecordORM(DeclarativeBase):
+    __tablename__: str
+    id: Mapped[UUID]
+    text: Mapped[str]
+    meta: Mapped[dict]
+    embedding: Mapped[ndarray]
+
+
+RecordORMType = Type[RecordORM]
+
+
+class Record:
+    id: UUID
+    text: str
+    meta: dict
+    embedding: ndarray
+
+    def __init__(self, id: UUID, text: str, meta: dict, embedding: ndarray):
+        self.id = id
+        self.text = text
+        self.meta = meta
+        self.embedding = embedding
+
+    def __repr__(self) -> str:
+        return f"""============= Record =============
+[id]       : {self.id}
+[text]     : {self.text}
+[meta]     : {self.meta}
+[embedding]: {self.embedding}
+========== End of Record ========="""
+
+    @classmethod
+    def from_orm(cls, orm: RecordORM):
+        return cls(orm.id, orm.text, orm.meta, orm.embedding)
+
+    @classmethod
+    def from_text(
+        cls,
+        text: str,
+        embedding: Union[ndarray, List[float]],
+        meta: Optional[dict] = None,
+    ):
+        if isinstance(embedding, list):
+            embedding = array(embedding, dtype=float32)
+        return cls(uuid4(), text, meta or {}, embedding)
--- a/bindings/python/src/pgvecto_rs/sqlalchemy/init.py
+++ b/bindings/python/src/pgvecto_rs/sqlalchemy/init.py
@ -1,6 +1,6 @@
 import sqlalchemy.types as types

-from ..utils import serializer
+from pgvecto_rs.utils import serializer


 class Vector(types.UserDefinedType):
--- a/bindings/python/tests/test_sdk.py
+++ b/bindings/python/tests/test_sdk.py
@ -0,0 +1,96 @@
+from typing import List
+
+import numpy as np
+import pytest
+
+from pgvecto_rs.sdk import Filter, PGVectoRs, Record, filters
+from tests import (
+    EXPECTED_NEG_COS_DIS,
+    EXPECTED_NEG_DOT_PROD_DIS,
+    EXPECTED_SQRT_EUCLID_DIS,
+    OP_NEG_COS_DIS,
+    OP_NEG_DOT_PROD_DIS,
+    OP_SQRT_EUCLID_DIS,
+    URL,
+    VECTORS,
+)
+
+URL = URL.replace("postgresql", "postgresql+psycopg")
+mockTexts = {
+    "text0": VECTORS[0],
+    "text1": VECTORS[1],
+    "text2": VECTORS[2],
+}
+
+
+class MockEmbedder:
+    def embed(self, text: str) -> np.ndarray:
+        if isinstance(mockTexts[text], list):
+            return np.array(mockTexts[text], dtype=np.float32)
+        return mockTexts[text]
+
+
+@pytest.fixture(scope="module")
+def client():
+    client = PGVectoRs(db_url=URL, collection_name="empty", dimension=3)
+    try:
+        records1 = [
+            Record.from_text(t, v, {"src": "src1"}) for t, v in mockTexts.items()
+        ]
+        records2 = [
+            Record.from_text(t, v, {"src": "src2"}) for t, v in mockTexts.items()
+        ]
+        client.insert(records1)
+        client.insert(records2)
+        yield client
+    finally:
+        client.drop()
+
+
+filter_src1 = filters.meta_contains({"src": "src1"})
+filter_src2: Filter = lambda r: r.meta.contains({"src": "src2"})
+
+
+@pytest.mark.parametrize("filter", [filter_src1, filter_src2])
+@pytest.mark.parametrize(
+    "dis_op, dis_oprand, dis_expected",
+    zip(
+        ["<->", "<#>", "<=>"],
+        [OP_SQRT_EUCLID_DIS, OP_NEG_DOT_PROD_DIS, OP_NEG_COS_DIS],
+        [EXPECTED_SQRT_EUCLID_DIS, EXPECTED_NEG_DOT_PROD_DIS, EXPECTED_NEG_COS_DIS],
+    ),
+)
+def test_search_filter_and_op(
+    client: PGVectoRs,
+    filter: Filter,
+    dis_op: str,
+    dis_oprand: List[float],
+    dis_expected: List[float],
+):
+    for rec, dis in client.search(dis_oprand, dis_op, top_k=99, filter=filter):
+        cnt = None
+        for i in range(len(VECTORS)):
+            if np.allclose(rec.embedding, VECTORS[i]):
+                cnt = i
+                break
+        assert np.allclose(dis, dis_expected[cnt])
+
+
+@pytest.mark.parametrize(
+    "dis_op, dis_oprand, dis_expected",
+    zip(
+        ["<->", "<#>", "<=>"],
+        [OP_SQRT_EUCLID_DIS, OP_NEG_DOT_PROD_DIS, OP_NEG_COS_DIS],
+        [EXPECTED_SQRT_EUCLID_DIS, EXPECTED_NEG_DOT_PROD_DIS, EXPECTED_NEG_COS_DIS],
+    ),
+)
+def test_search_order_and_limit(
+    client: PGVectoRs,
+    dis_op: str,
+    dis_oprand: List[float],
+    dis_expected: List[float],
+):
+    dis_expected = dis_expected.copy()
+    dis_expected.sort()
+    for i, (rec, dis) in enumerate(client.search(dis_oprand, dis_op, top_k=4)):
+        assert np.allclose(dis, dis_expected[i // 2])