From 63e34e5227641405a0c1577da93ff4e43a18a209 Mon Sep 17 00:00:00 2001 From: Zhuo Qiu Date: Thu, 11 Jul 2024 15:21:59 +0800 Subject: [PATCH] feat: support MyScale vector database (#6092) --- .github/workflows/api-tests.yml | 3 +- api/.env.example | 10 +- api/configs/middleware/__init__.py | 2 + api/configs/middleware/vdb/myscale_config.py | 39 ++++ api/controllers/console/datasets/datasets.py | 4 +- .../rag/datasource/vdb/myscale/__init__.py | 0 .../datasource/vdb/myscale/myscale_vector.py | 170 +++++++++++++++ api/core/rag/datasource/vdb/vector_factory.py | 3 + api/core/rag/datasource/vdb/vector_type.py | 1 + api/poetry.lock | 203 +++++++++++++++++- api/pyproject.toml | 1 + .../integration_tests/vdb/myscale/__init__.py | 0 .../vdb/myscale/test_myscale.py | 29 +++ dev/pytest/pytest_vdb.sh | 1 + docker/.env.example | 12 +- docker/docker-compose.yaml | 21 ++ .../config/users.d/custom_users_config.xml | 17 ++ 17 files changed, 510 insertions(+), 6 deletions(-) create mode 100644 api/configs/middleware/vdb/myscale_config.py create mode 100644 api/core/rag/datasource/vdb/myscale/__init__.py create mode 100644 api/core/rag/datasource/vdb/myscale/myscale_vector.py create mode 100644 api/tests/integration_tests/vdb/myscale/__init__.py create mode 100644 api/tests/integration_tests/vdb/myscale/test_myscale.py create mode 100644 docker/volumes/myscale/config/users.d/custom_users_config.xml diff --git a/.github/workflows/api-tests.yml b/.github/workflows/api-tests.yml index e424171019..aa7e68dbac 100644 --- a/.github/workflows/api-tests.yml +++ b/.github/workflows/api-tests.yml @@ -75,7 +75,7 @@ jobs: - name: Run Workflow run: poetry run -C api bash dev/pytest/pytest_workflow.sh - - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma) + - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale) uses: hoverkraft-tech/compose-action@v2.0.0 with: compose-file: | @@ -89,5 +89,6 @@ jobs: pgvecto-rs pgvector chroma + myscale - name: Test Vector Stores run: poetry run -C api bash dev/pytest/pytest_vdb.sh diff --git a/api/.env.example b/api/.env.example index 1f6e6f69b7..228218be0d 100644 --- a/api/.env.example +++ b/api/.env.example @@ -83,7 +83,7 @@ OCI_REGION=your-region WEB_API_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,* CONSOLE_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,* -# Vector database configuration, support: weaviate, qdrant, milvus, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector +# Vector database configuration, support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector VECTOR_STORE=weaviate # Weaviate configuration @@ -106,6 +106,14 @@ MILVUS_USER=root MILVUS_PASSWORD=Milvus MILVUS_SECURE=false +# MyScale configuration +MYSCALE_HOST=127.0.0.1 +MYSCALE_PORT=8123 +MYSCALE_USER=default +MYSCALE_PASSWORD= +MYSCALE_DATABASE=default +MYSCALE_FTS_PARAMS= + # Relyt configuration RELYT_HOST=127.0.0.1 RELYT_PORT=5432 diff --git a/api/configs/middleware/__init__.py b/api/configs/middleware/__init__.py index 067bcd7af4..a32b70bdc7 100644 --- a/api/configs/middleware/__init__.py +++ b/api/configs/middleware/__init__.py @@ -13,6 +13,7 @@ from configs.middleware.storage.tencent_cos_storage_config import TencentCloudCO from configs.middleware.vdb.analyticdb_config import AnalyticdbConfig from configs.middleware.vdb.chroma_config import ChromaConfig from configs.middleware.vdb.milvus_config import MilvusConfig +from configs.middleware.vdb.myscale_config import MyScaleConfig from configs.middleware.vdb.opensearch_config import OpenSearchConfig from configs.middleware.vdb.oracle_config import OracleConfig from configs.middleware.vdb.pgvector_config import PGVectorConfig @@ -187,6 +188,7 @@ class MiddlewareConfig( AnalyticdbConfig, ChromaConfig, MilvusConfig, + MyScaleConfig, OpenSearchConfig, OracleConfig, PGVectorConfig, diff --git a/api/configs/middleware/vdb/myscale_config.py b/api/configs/middleware/vdb/myscale_config.py new file mode 100644 index 0000000000..e513cad0e8 --- /dev/null +++ b/api/configs/middleware/vdb/myscale_config.py @@ -0,0 +1,39 @@ +from typing import Optional + +from pydantic import BaseModel, Field, PositiveInt + + +class MyScaleConfig(BaseModel): + """ + MyScale configs + """ + + MYSCALE_HOST: Optional[str] = Field( + description='MyScale host', + default=None, + ) + + MYSCALE_PORT: Optional[PositiveInt] = Field( + description='MyScale port', + default=8123, + ) + + MYSCALE_USER: Optional[str] = Field( + description='MyScale user', + default=None, + ) + + MYSCALE_PASSWORD: Optional[str] = Field( + description='MyScale password', + default=None, + ) + + MYSCALE_DATABASE: Optional[str] = Field( + description='MyScale database name', + default=None, + ) + + MYSCALE_FTS_PARAMS: Optional[str] = Field( + description='MyScale fts index parameters', + default=None, + ) diff --git a/api/controllers/console/datasets/datasets.py b/api/controllers/console/datasets/datasets.py index 50edec33c3..70c506bb0e 100644 --- a/api/controllers/console/datasets/datasets.py +++ b/api/controllers/console/datasets/datasets.py @@ -548,7 +548,7 @@ class DatasetRetrievalSettingApi(Resource): RetrievalMethod.SEMANTIC_SEARCH ] } - case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH | VectorType.ANALYTICDB: + case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH | VectorType.ANALYTICDB | VectorType.MYSCALE: return { 'retrieval_method': [ RetrievalMethod.SEMANTIC_SEARCH, @@ -572,7 +572,7 @@ class DatasetRetrievalSettingMockApi(Resource): RetrievalMethod.SEMANTIC_SEARCH ] } - case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH| VectorType.ANALYTICDB: + case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH| VectorType.ANALYTICDB | VectorType.MYSCALE: return { 'retrieval_method': [ RetrievalMethod.SEMANTIC_SEARCH, diff --git a/api/core/rag/datasource/vdb/myscale/__init__.py b/api/core/rag/datasource/vdb/myscale/__init__.py new file mode 100644 index 0000000000..e69de29bb2 diff --git a/api/core/rag/datasource/vdb/myscale/myscale_vector.py b/api/core/rag/datasource/vdb/myscale/myscale_vector.py new file mode 100644 index 0000000000..811b08818c --- /dev/null +++ b/api/core/rag/datasource/vdb/myscale/myscale_vector.py @@ -0,0 +1,170 @@ +import json +import logging +import uuid +from enum import Enum +from typing import Any + +from clickhouse_connect import get_client +from flask import current_app +from pydantic import BaseModel + +from core.rag.datasource.entity.embedding import Embeddings +from core.rag.datasource.vdb.vector_base import BaseVector +from core.rag.datasource.vdb.vector_factory import AbstractVectorFactory +from core.rag.datasource.vdb.vector_type import VectorType +from core.rag.models.document import Document +from models.dataset import Dataset + + +class MyScaleConfig(BaseModel): + host: str + port: int + user: str + password: str + database: str + fts_params: str + + +class SortOrder(Enum): + ASC = "ASC" + DESC = "DESC" + + +class MyScaleVector(BaseVector): + + def __init__(self, collection_name: str, config: MyScaleConfig, metric: str = "Cosine"): + super().__init__(collection_name) + self._config = config + self._metric = metric + self._vec_order = SortOrder.ASC if metric.upper() in ["COSINE", "L2"] else SortOrder.DESC + self._client = get_client( + host=config.host, + port=config.port, + username=config.user, + password=config.password, + ) + self._client.command("SET allow_experimental_object_type=1") + + def get_type(self) -> str: + return VectorType.MYSCALE + + def create(self, texts: list[Document], embeddings: list[list[float]], **kwargs): + dimension = len(embeddings[0]) + self._create_collection(dimension) + return self.add_texts(documents=texts, embeddings=embeddings, **kwargs) + + def _create_collection(self, dimension: int): + logging.info(f"create MyScale collection {self._collection_name} with dimension {dimension}") + self._client.command(f"CREATE DATABASE IF NOT EXISTS {self._config.database}") + fts_params = f"('{self._config.fts_params}')" if self._config.fts_params else "" + sql = f""" + CREATE TABLE IF NOT EXISTS {self._config.database}.{self._collection_name}( + id String, + text String, + vector Array(Float32), + metadata JSON, + CONSTRAINT cons_vec_len CHECK length(vector) = {dimension}, + VECTOR INDEX vidx vector TYPE DEFAULT('metric_type = {self._metric}'), + INDEX text_idx text TYPE fts{fts_params} + ) ENGINE = MergeTree ORDER BY id + """ + self._client.command(sql) + + def add_texts(self, documents: list[Document], embeddings: list[list[float]], **kwargs): + ids = [] + columns = ["id", "text", "vector", "metadata"] + values = [] + for i, doc in enumerate(documents): + doc_id = doc.metadata.get("doc_id", str(uuid.uuid4())) + row = ( + doc_id, + self.escape_str(doc.page_content), + embeddings[i], + json.dumps(doc.metadata) if doc.metadata else {} + ) + values.append(str(row)) + ids.append(doc_id) + sql = f""" + INSERT INTO {self._config.database}.{self._collection_name} + ({",".join(columns)}) VALUES {",".join(values)} + """ + self._client.command(sql) + return ids + + @staticmethod + def escape_str(value: Any) -> str: + return "".join(f"\\{c}" if c in ("\\", "'") else c for c in str(value)) + + def text_exists(self, id: str) -> bool: + results = self._client.query(f"SELECT id FROM {self._config.database}.{self._collection_name} WHERE id='{id}'") + return results.row_count > 0 + + def delete_by_ids(self, ids: list[str]) -> None: + self._client.command( + f"DELETE FROM {self._config.database}.{self._collection_name} WHERE id IN {str(tuple(ids))}") + + def get_ids_by_metadata_field(self, key: str, value: str): + rows = self._client.query( + f"SELECT DISTINCT id FROM {self._config.database}.{self._collection_name} WHERE metadata.{key}='{value}'" + ).result_rows + return [row[0] for row in rows] + + def delete_by_metadata_field(self, key: str, value: str) -> None: + self._client.command( + f"DELETE FROM {self._config.database}.{self._collection_name} WHERE metadata.{key}='{value}'" + ) + + def search_by_vector(self, query_vector: list[float], **kwargs: Any) -> list[Document]: + return self._search(f"distance(vector, {str(query_vector)})", self._vec_order, **kwargs) + + def search_by_full_text(self, query: str, **kwargs: Any) -> list[Document]: + return self._search(f"TextSearch(text, '{query}')", SortOrder.DESC, **kwargs) + + def _search(self, dist: str, order: SortOrder, **kwargs: Any) -> list[Document]: + top_k = kwargs.get("top_k", 5) + score_threshold = kwargs.get("score_threshold", 0.0) + where_str = f"WHERE dist < {1 - score_threshold}" if \ + self._metric.upper() == "COSINE" and order == SortOrder.ASC and score_threshold > 0.0 else "" + sql = f""" + SELECT text, metadata, {dist} as dist FROM {self._config.database}.{self._collection_name} + {where_str} ORDER BY dist {order.value} LIMIT {top_k} + """ + try: + return [ + Document( + page_content=r["text"], + metadata=r["metadata"], + ) + for r in self._client.query(sql).named_results() + ] + except Exception as e: + logging.error(f"\033[91m\033[1m{type(e)}\033[0m \033[95m{str(e)}\033[0m") + return [] + + def delete(self) -> None: + self._client.command(f"DROP TABLE IF EXISTS {self._config.database}.{self._collection_name}") + + +class MyScaleVectorFactory(AbstractVectorFactory): + def init_vector(self, dataset: Dataset, attributes: list, embeddings: Embeddings) -> MyScaleVector: + if dataset.index_struct_dict: + class_prefix: str = dataset.index_struct_dict['vector_store']['class_prefix'] + collection_name = class_prefix.lower() + else: + dataset_id = dataset.id + collection_name = Dataset.gen_collection_name_by_id(dataset_id).lower() + dataset.index_struct = json.dumps( + self.gen_index_struct_dict(VectorType.MYSCALE, collection_name)) + + config = current_app.config + return MyScaleVector( + collection_name=collection_name, + config=MyScaleConfig( + host=config.get("MYSCALE_HOST", "localhost"), + port=int(config.get("MYSCALE_PORT", 8123)), + user=config.get("MYSCALE_USER", "default"), + password=config.get("MYSCALE_PASSWORD", ""), + database=config.get("MYSCALE_DATABASE", "default"), + fts_params=config.get("MYSCALE_FTS_PARAMS", ""), + ), + ) diff --git a/api/core/rag/datasource/vdb/vector_factory.py b/api/core/rag/datasource/vdb/vector_factory.py index b7733029f7..f8b58e1b9a 100644 --- a/api/core/rag/datasource/vdb/vector_factory.py +++ b/api/core/rag/datasource/vdb/vector_factory.py @@ -57,6 +57,9 @@ class Vector: case VectorType.MILVUS: from core.rag.datasource.vdb.milvus.milvus_vector import MilvusVectorFactory return MilvusVectorFactory + case VectorType.MYSCALE: + from core.rag.datasource.vdb.myscale.myscale_vector import MyScaleVectorFactory + return MyScaleVectorFactory case VectorType.PGVECTOR: from core.rag.datasource.vdb.pgvector.pgvector import PGVectorFactory return PGVectorFactory diff --git a/api/core/rag/datasource/vdb/vector_type.py b/api/core/rag/datasource/vdb/vector_type.py index 32c8713fda..77495044df 100644 --- a/api/core/rag/datasource/vdb/vector_type.py +++ b/api/core/rag/datasource/vdb/vector_type.py @@ -5,6 +5,7 @@ class VectorType(str, Enum): ANALYTICDB = 'analyticdb' CHROMA = 'chroma' MILVUS = 'milvus' + MYSCALE = 'myscale' PGVECTOR = 'pgvector' PGVECTO_RS = 'pgvecto-rs' QDRANT = 'qdrant' diff --git a/api/poetry.lock b/api/poetry.lock index 6acc65b58d..ae7cdbb32d 100644 --- a/api/poetry.lock +++ b/api/poetry.lock @@ -1398,6 +1398,96 @@ prompt-toolkit = ">=3.0.36" [package.extras] testing = ["pytest (>=7.2.1)", "pytest-cov (>=4.0.0)", "tox (>=4.4.3)"] +[[package]] +name = "clickhouse-connect" +version = "0.7.16" +description = "ClickHouse Database Core Driver for Python, Pandas, and Superset" +optional = false +python-versions = "~=3.8" +files = [ + {file = "clickhouse-connect-0.7.16.tar.gz", hash = "sha256:253a2089efad5729903d00382f73fa8da2cbbfdb118db498cf708ee9f4a2134f"}, + {file = "clickhouse_connect-0.7.16-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:00413deb9e086aabf661d18ac3a3539f25eb773c3675f49353e0d7e6ef1205fc"}, + {file = "clickhouse_connect-0.7.16-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:faadaf206ea7753782db017daedbf592e4edc7c71cb985aad787eb9dc516bf21"}, + {file = "clickhouse_connect-0.7.16-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1db8f1168f33fda78adddb733913b211ddf648984d8fef8d934e30df876e5f23"}, + {file = "clickhouse_connect-0.7.16-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8fa630bf50fb064cc53b7ea5d862066476d3c6074003f6d39d2594fb1a7abf67"}, + {file = "clickhouse_connect-0.7.16-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2cba9547dad41b2d333458615208a3c7db6f56a63473ffea2c05c44225ffa020"}, + {file = "clickhouse_connect-0.7.16-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:480f7856fcf42a21f17886e0b42d70499067c865fc2a0ea7c0eb5c0bdca281a8"}, + {file = "clickhouse_connect-0.7.16-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:b65f3eb570cbcf9fa383b4e0925d1ceb3efd3deba42a435625cad75b3a9ff7f3"}, + {file = "clickhouse_connect-0.7.16-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b78d3cc0fe42374bb9d5a05ba71578dc69f7e4b4c771e86dcf292ae0412265cc"}, + {file = "clickhouse_connect-0.7.16-cp310-cp310-win32.whl", hash = "sha256:1cb76b26fcde1ba6a8ae68e1db1f9e42d458879a0d4d2c9843cc998f42f445ac"}, + {file = "clickhouse_connect-0.7.16-cp310-cp310-win_amd64.whl", hash = "sha256:9298b344168271e952ea41021963ca1b81b9b3c38be8b036cb64a2556edbb4b7"}, + {file = "clickhouse_connect-0.7.16-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:8ae39a765735cc6e786e5f9a0dba799e7f8ee0bbd5dfc5d5ff755dfa9dd13855"}, + {file = "clickhouse_connect-0.7.16-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:3f32546f65dd234a49310cda454713a5f7fbc8ba978744e070355c7ea8819a5a"}, + {file = "clickhouse_connect-0.7.16-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:20865c81a5b378625a528ac8960e08cdca316147f87fad6deb9f16c0d5e5f62f"}, + {file = "clickhouse_connect-0.7.16-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:609c076261d779703bf29e7a27dafc8283153403ceab1ec23d50eb2acabc4b9d"}, + {file = "clickhouse_connect-0.7.16-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e07862e75ac7419c5671384055f11ca5e76dc2c0be4a6f3aed7bf419997184bc"}, + {file = "clickhouse_connect-0.7.16-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:d5db7da6f20b9a49b288063de9b3224a56634f8cb94d19d435af518ed81872c3"}, + {file = "clickhouse_connect-0.7.16-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:955c567ede68a10325045bb2adf1314ff569dfb7e52f6074c18182f3803279f6"}, + {file = "clickhouse_connect-0.7.16-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:df517bfe23d85f5aeeb17b262c06d0a5c24e0baea09688a96d02dc8589ef8b07"}, + {file = "clickhouse_connect-0.7.16-cp311-cp311-win32.whl", hash = "sha256:7f2c6132fc90df6a8318abb9f257c2b777404908b7d168ac08235d516f65a663"}, + {file = "clickhouse_connect-0.7.16-cp311-cp311-win_amd64.whl", hash = "sha256:ca1dba53da86691a11671d846988dc4f6ad02a66f5a0df9a87a46dc4ec9bb0a1"}, + {file = "clickhouse_connect-0.7.16-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:f8f7260073b6ee63e19d442ebb6954bc7741a5ce4ed563eb8074c8c6a0158eca"}, + {file = "clickhouse_connect-0.7.16-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:9b3dd93ada1099cb6df244d79973c811e90a4590685e78e60e8846914b3c261e"}, + {file = "clickhouse_connect-0.7.16-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3d3c3458bce25fe9c10e1dbf82dbeeeb2f04e382130f9811cc3bedf44c2028ca"}, + {file = "clickhouse_connect-0.7.16-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dcc302390b4ea975efd8d2ca53d295d40dc766179dd5e9fc158e808f01d9280d"}, + {file = "clickhouse_connect-0.7.16-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a94f6d095d7174c55825e0b5c04b77897a1b2a8a8bbb38f3f773fd3113a7be27"}, + {file = "clickhouse_connect-0.7.16-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:6b7e2572993ef2e1dee5012875a7a2d08cede319e32ccdd2db90ed26a0d0c037"}, + {file = "clickhouse_connect-0.7.16-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:e9c35ee425309ed8ef63bae31e1d3c5f35706fa27ae2836e61e7cb9bbe7f00cb"}, + {file = "clickhouse_connect-0.7.16-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:eb0471d5a32d07eaa37772871ee9e6b5eb37ab907c3c154833824ed68ee4795b"}, + {file = "clickhouse_connect-0.7.16-cp312-cp312-win32.whl", hash = "sha256:b531ee18b4ce16f1d2b8f6249859cbd600f7e0f312f80dda8deb969791a90f17"}, + {file = "clickhouse_connect-0.7.16-cp312-cp312-win_amd64.whl", hash = "sha256:38392308344770864843f7f8b914799684c13ce4b272d5a3a55e5512ff8a3ae0"}, + {file = "clickhouse_connect-0.7.16-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:052ca80d66e49c94d103c9842d2a5b0ebf4610981b79164660ef6b1bdc4b5e85"}, + {file = "clickhouse_connect-0.7.16-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:b496059d145c68e956aa10cd04e5c7cb4e97312eb3f7829cec8f4f7024f8ced6"}, + {file = "clickhouse_connect-0.7.16-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:de1e423fc9c415b9fdcbb6f23eccae981e3f0f0cf142e518efec709bda7c1394"}, + {file = "clickhouse_connect-0.7.16-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:555c64719cbc72675d58ea6dfc144fa8064ea1d673a54afd2d54e34c58f17c6b"}, + {file = "clickhouse_connect-0.7.16-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a0c3c063ab23df8f71a36505880bf5de6c18aee246938d787447e52b4d9d5531"}, + {file = "clickhouse_connect-0.7.16-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:5ed62e08cfe445d0430b91c26fb276e2a5175e456e9786594fb6e67c9ebd8c6c"}, + {file = "clickhouse_connect-0.7.16-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:d9eb056bd14ca3c1d7e3edd7ca79ea970d45e5e536930dbb6179aeb965d5bc3d"}, + {file = "clickhouse_connect-0.7.16-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:54e0a03b685ee6c138954846dafb6ec0e0baf8257f2587c61e34c017f3dc9d63"}, + {file = "clickhouse_connect-0.7.16-cp38-cp38-win32.whl", hash = "sha256:d8402c3145387726bd19f916ca2890576be70c4493f030c068f6f03a75addff7"}, + {file = "clickhouse_connect-0.7.16-cp38-cp38-win_amd64.whl", hash = "sha256:70e376d2ebc0f092fae35f7b50ff7296ee8ffd2dda3536238f6c39a5c949d115"}, + {file = "clickhouse_connect-0.7.16-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:cee4f91ad22401c3b96f5df3f3149ef2894e7c2d00b5abd9da80119e7b6592f7"}, + {file = "clickhouse_connect-0.7.16-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:a3009145f35e9ac2535dbd8fdbdc218abfe0971c9bc9b730eb5c3f6c40faeb5f"}, + {file = "clickhouse_connect-0.7.16-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7d0ef9f877ffbcb0f526ce9c35c657fc54930d043e45c077d9d886c0f1add727"}, + {file = "clickhouse_connect-0.7.16-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:acc437b3ff2f7991b209b861a89c003ac1971c890775190178438780e967a9d3"}, + {file = "clickhouse_connect-0.7.16-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7ed836dcee4ac097bd83714abe0af987b1ef767675a555e7643d793164c3f1cc"}, + {file = "clickhouse_connect-0.7.16-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:4c4e0d173239c0b4594c8703fae5c8ba3241c4e0763a8cf436b94564692671f9"}, + {file = "clickhouse_connect-0.7.16-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:a17a348dd8c00df343a01128497e8c3a6ae431f13c7a88e363ac12c035316ce0"}, + {file = "clickhouse_connect-0.7.16-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:805ae7ad39c043af13e2b5af45abb70330f0907749dc87ad4a2481a4ac209cc6"}, + {file = "clickhouse_connect-0.7.16-cp39-cp39-win32.whl", hash = "sha256:38fc6ca1bd73cf4dcebd22fbb8dceda267908ff674fc57fbc23c3b5df9c21ac1"}, + {file = "clickhouse_connect-0.7.16-cp39-cp39-win_amd64.whl", hash = "sha256:3dc67e99e40b5a8bc493a21016830b0f3800006a6038c1fd881f7cae6246cc44"}, + {file = "clickhouse_connect-0.7.16-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:b7f526fef71bd5265f47915340a6369a5b5685278b72b5aff281cc521a8ec376"}, + {file = "clickhouse_connect-0.7.16-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e00f87ba68bbc63dd32d7a304fd629b759f24b09f88fbc2bac0a9ed1fe7b2938"}, + {file = "clickhouse_connect-0.7.16-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:09c84f3b64d6bebedcfbbd19e8369b3df2cb7d313afb2a0d64a3e151d344c1c1"}, + {file = "clickhouse_connect-0.7.16-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:18d104ab78edee26e8cef056e2db83f03e1da918df0946e1ef1ad9a27a024dd0"}, + {file = "clickhouse_connect-0.7.16-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:cc1ad53e282ff5b4288fdfcf6df72cda542d9d997de5889d66a1f8e2b9f477f0"}, + {file = "clickhouse_connect-0.7.16-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:fddc99322054f5d3df8715ab3724bd36ac636f8ceaed4f5f3f60d377abd22d22"}, + {file = "clickhouse_connect-0.7.16-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:765a2de98197d1b4f6424611ceaca2ae896a1d7093b943403973888cb7c144e6"}, + {file = "clickhouse_connect-0.7.16-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1540e0a93e5f2147400f644606a399c91705066f05d5a91429616ee9812f4521"}, + {file = "clickhouse_connect-0.7.16-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ba928c4178b0d4a513e1b0ad32a464ab56cb1bc27736a7f41b32e4eb70eb08d6"}, + {file = "clickhouse_connect-0.7.16-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:a17ffc22e905081f002173b30959089de6987fd40c87e7794da9d978d723e610"}, + {file = "clickhouse_connect-0.7.16-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:26df09787232b495285d8358db145b9770f472e2e30147912634c5b56392e73f"}, + {file = "clickhouse_connect-0.7.16-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a2a3ce33241441dc7c718c19e31645323e6c5da793d46bbb670fd4e8557b8605"}, + {file = "clickhouse_connect-0.7.16-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:29f9dc9cc1f4ec4a333bf119abb5cee13563e89bc990d4d77b8f43cf630e9fb1"}, + {file = "clickhouse_connect-0.7.16-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a16a7ada11996a6fa0959c83e2e46ff32773e57eca40eff86176fd62a30054ca"}, + {file = "clickhouse_connect-0.7.16-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:ead20e1d4f3c5493dd075b7dc81b5d21be4b876aca6952e1c155824876c621f3"}, +] + +[package.dependencies] +certifi = "*" +lz4 = "*" +pytz = "*" +urllib3 = ">=1.26" +zstandard = "*" + +[package.extras] +arrow = ["pyarrow"] +numpy = ["numpy"] +orjson = ["orjson"] +pandas = ["pandas"] +sqlalchemy = ["sqlalchemy (>1.3.21,<2.0)"] +tzlocal = ["tzlocal (>=4.0)"] + [[package]] name = "clickhouse-driver" version = "0.2.8" @@ -4259,6 +4349,56 @@ html5 = ["html5lib"] htmlsoup = ["BeautifulSoup4"] source = ["Cython (>=3.0.7)"] +[[package]] +name = "lz4" +version = "4.3.3" +description = "LZ4 Bindings for Python" +optional = false +python-versions = ">=3.8" +files = [ + {file = "lz4-4.3.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:b891880c187e96339474af2a3b2bfb11a8e4732ff5034be919aa9029484cd201"}, + {file = "lz4-4.3.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:222a7e35137d7539c9c33bb53fcbb26510c5748779364014235afc62b0ec797f"}, + {file = "lz4-4.3.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f76176492ff082657ada0d0f10c794b6da5800249ef1692b35cf49b1e93e8ef7"}, + {file = "lz4-4.3.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f1d18718f9d78182c6b60f568c9a9cec8a7204d7cb6fad4e511a2ef279e4cb05"}, + {file = "lz4-4.3.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6cdc60e21ec70266947a48839b437d46025076eb4b12c76bd47f8e5eb8a75dcc"}, + {file = "lz4-4.3.3-cp310-cp310-win32.whl", hash = "sha256:c81703b12475da73a5d66618856d04b1307e43428a7e59d98cfe5a5d608a74c6"}, + {file = "lz4-4.3.3-cp310-cp310-win_amd64.whl", hash = "sha256:43cf03059c0f941b772c8aeb42a0813d68d7081c009542301637e5782f8a33e2"}, + {file = "lz4-4.3.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:30e8c20b8857adef7be045c65f47ab1e2c4fabba86a9fa9a997d7674a31ea6b6"}, + {file = "lz4-4.3.3-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:2f7b1839f795315e480fb87d9bc60b186a98e3e5d17203c6e757611ef7dcef61"}, + {file = "lz4-4.3.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:edfd858985c23523f4e5a7526ca6ee65ff930207a7ec8a8f57a01eae506aaee7"}, + {file = "lz4-4.3.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0e9c410b11a31dbdc94c05ac3c480cb4b222460faf9231f12538d0074e56c563"}, + {file = "lz4-4.3.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d2507ee9c99dbddd191c86f0e0c8b724c76d26b0602db9ea23232304382e1f21"}, + {file = "lz4-4.3.3-cp311-cp311-win32.whl", hash = "sha256:f180904f33bdd1e92967923a43c22899e303906d19b2cf8bb547db6653ea6e7d"}, + {file = "lz4-4.3.3-cp311-cp311-win_amd64.whl", hash = "sha256:b14d948e6dce389f9a7afc666d60dd1e35fa2138a8ec5306d30cd2e30d36b40c"}, + {file = "lz4-4.3.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:e36cd7b9d4d920d3bfc2369840da506fa68258f7bb176b8743189793c055e43d"}, + {file = "lz4-4.3.3-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:31ea4be9d0059c00b2572d700bf2c1bc82f241f2c3282034a759c9a4d6ca4dc2"}, + {file = "lz4-4.3.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:33c9a6fd20767ccaf70649982f8f3eeb0884035c150c0b818ea660152cf3c809"}, + {file = "lz4-4.3.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bca8fccc15e3add173da91be8f34121578dc777711ffd98d399be35487c934bf"}, + {file = "lz4-4.3.3-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e7d84b479ddf39fe3ea05387f10b779155fc0990125f4fb35d636114e1c63a2e"}, + {file = "lz4-4.3.3-cp312-cp312-win32.whl", hash = "sha256:337cb94488a1b060ef1685187d6ad4ba8bc61d26d631d7ba909ee984ea736be1"}, + {file = "lz4-4.3.3-cp312-cp312-win_amd64.whl", hash = "sha256:5d35533bf2cee56f38ced91f766cd0038b6abf46f438a80d50c52750088be93f"}, + {file = "lz4-4.3.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:363ab65bf31338eb364062a15f302fc0fab0a49426051429866d71c793c23394"}, + {file = "lz4-4.3.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:0a136e44a16fc98b1abc404fbabf7f1fada2bdab6a7e970974fb81cf55b636d0"}, + {file = "lz4-4.3.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:abc197e4aca8b63f5ae200af03eb95fb4b5055a8f990079b5bdf042f568469dd"}, + {file = "lz4-4.3.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:56f4fe9c6327adb97406f27a66420b22ce02d71a5c365c48d6b656b4aaeb7775"}, + {file = "lz4-4.3.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f0e822cd7644995d9ba248cb4b67859701748a93e2ab7fc9bc18c599a52e4604"}, + {file = "lz4-4.3.3-cp38-cp38-win32.whl", hash = "sha256:24b3206de56b7a537eda3a8123c644a2b7bf111f0af53bc14bed90ce5562d1aa"}, + {file = "lz4-4.3.3-cp38-cp38-win_amd64.whl", hash = "sha256:b47839b53956e2737229d70714f1d75f33e8ac26e52c267f0197b3189ca6de24"}, + {file = "lz4-4.3.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:6756212507405f270b66b3ff7f564618de0606395c0fe10a7ae2ffcbbe0b1fba"}, + {file = "lz4-4.3.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:ee9ff50557a942d187ec85462bb0960207e7ec5b19b3b48949263993771c6205"}, + {file = "lz4-4.3.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2b901c7784caac9a1ded4555258207d9e9697e746cc8532129f150ffe1f6ba0d"}, + {file = "lz4-4.3.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b6d9ec061b9eca86e4dcc003d93334b95d53909afd5a32c6e4f222157b50c071"}, + {file = "lz4-4.3.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f4c7bf687303ca47d69f9f0133274958fd672efaa33fb5bcde467862d6c621f0"}, + {file = "lz4-4.3.3-cp39-cp39-win32.whl", hash = "sha256:054b4631a355606e99a42396f5db4d22046a3397ffc3269a348ec41eaebd69d2"}, + {file = "lz4-4.3.3-cp39-cp39-win_amd64.whl", hash = "sha256:eac9af361e0d98335a02ff12fb56caeb7ea1196cf1a49dbf6f17828a131da807"}, + {file = "lz4-4.3.3.tar.gz", hash = "sha256:01fe674ef2889dbb9899d8a67361e0c4a2c833af5aeb37dd505727cf5d2a131e"}, +] + +[package.extras] +docs = ["sphinx (>=1.6.0)", "sphinx-bootstrap-theme"] +flake8 = ["flake8"] +tests = ["psutil", "pytest (!=3.3.0)", "pytest-cov"] + [[package]] name = "mailchimp-transactional" version = "1.0.56" @@ -9190,7 +9330,68 @@ docs = ["Sphinx", "repoze.sphinx.autointerface", "sphinx-rtd-theme"] test = ["coverage (>=5.0.3)", "zope.event", "zope.testing"] testing = ["coverage (>=5.0.3)", "zope.event", "zope.testing"] +[[package]] +name = "zstandard" +version = "0.22.0" +description = "Zstandard bindings for Python" +optional = false +python-versions = ">=3.8" +files = [ + {file = "zstandard-0.22.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:275df437ab03f8c033b8a2c181e51716c32d831082d93ce48002a5227ec93019"}, + {file = "zstandard-0.22.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:2ac9957bc6d2403c4772c890916bf181b2653640da98f32e04b96e4d6fb3252a"}, + {file = "zstandard-0.22.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fe3390c538f12437b859d815040763abc728955a52ca6ff9c5d4ac707c4ad98e"}, + {file = "zstandard-0.22.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1958100b8a1cc3f27fa21071a55cb2ed32e9e5df4c3c6e661c193437f171cba2"}, + {file = "zstandard-0.22.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:93e1856c8313bc688d5df069e106a4bc962eef3d13372020cc6e3ebf5e045202"}, + {file = "zstandard-0.22.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:1a90ba9a4c9c884bb876a14be2b1d216609385efb180393df40e5172e7ecf356"}, + {file = "zstandard-0.22.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:3db41c5e49ef73641d5111554e1d1d3af106410a6c1fb52cf68912ba7a343a0d"}, + {file = "zstandard-0.22.0-cp310-cp310-win32.whl", hash = "sha256:d8593f8464fb64d58e8cb0b905b272d40184eac9a18d83cf8c10749c3eafcd7e"}, + {file = "zstandard-0.22.0-cp310-cp310-win_amd64.whl", hash = "sha256:f1a4b358947a65b94e2501ce3e078bbc929b039ede4679ddb0460829b12f7375"}, + {file = "zstandard-0.22.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:589402548251056878d2e7c8859286eb91bd841af117dbe4ab000e6450987e08"}, + {file = "zstandard-0.22.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:a97079b955b00b732c6f280d5023e0eefe359045e8b83b08cf0333af9ec78f26"}, + {file = "zstandard-0.22.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:445b47bc32de69d990ad0f34da0e20f535914623d1e506e74d6bc5c9dc40bb09"}, + {file = "zstandard-0.22.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:33591d59f4956c9812f8063eff2e2c0065bc02050837f152574069f5f9f17775"}, + {file = "zstandard-0.22.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:888196c9c8893a1e8ff5e89b8f894e7f4f0e64a5af4d8f3c410f0319128bb2f8"}, + {file = "zstandard-0.22.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:53866a9d8ab363271c9e80c7c2e9441814961d47f88c9bc3b248142c32141d94"}, + {file = "zstandard-0.22.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:4ac59d5d6910b220141c1737b79d4a5aa9e57466e7469a012ed42ce2d3995e88"}, + {file = "zstandard-0.22.0-cp311-cp311-win32.whl", hash = "sha256:2b11ea433db22e720758cba584c9d661077121fcf60ab43351950ded20283440"}, + {file = "zstandard-0.22.0-cp311-cp311-win_amd64.whl", hash = "sha256:11f0d1aab9516a497137b41e3d3ed4bbf7b2ee2abc79e5c8b010ad286d7464bd"}, + {file = "zstandard-0.22.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:6c25b8eb733d4e741246151d895dd0308137532737f337411160ff69ca24f93a"}, + {file = "zstandard-0.22.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:f9b2cde1cd1b2a10246dbc143ba49d942d14fb3d2b4bccf4618d475c65464912"}, + {file = "zstandard-0.22.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a88b7df61a292603e7cd662d92565d915796b094ffb3d206579aaebac6b85d5f"}, + {file = "zstandard-0.22.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:466e6ad8caefb589ed281c076deb6f0cd330e8bc13c5035854ffb9c2014b118c"}, + {file = "zstandard-0.22.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a1d67d0d53d2a138f9e29d8acdabe11310c185e36f0a848efa104d4e40b808e4"}, + {file = "zstandard-0.22.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:39b2853efc9403927f9065cc48c9980649462acbdf81cd4f0cb773af2fd734bc"}, + {file = "zstandard-0.22.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8a1b2effa96a5f019e72874969394edd393e2fbd6414a8208fea363a22803b45"}, + {file = "zstandard-0.22.0-cp312-cp312-win32.whl", hash = "sha256:88c5b4b47a8a138338a07fc94e2ba3b1535f69247670abfe422de4e0b344aae2"}, + {file = "zstandard-0.22.0-cp312-cp312-win_amd64.whl", hash = "sha256:de20a212ef3d00d609d0b22eb7cc798d5a69035e81839f549b538eff4105d01c"}, + {file = "zstandard-0.22.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:d75f693bb4e92c335e0645e8845e553cd09dc91616412d1d4650da835b5449df"}, + {file = "zstandard-0.22.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:36a47636c3de227cd765e25a21dc5dace00539b82ddd99ee36abae38178eff9e"}, + {file = "zstandard-0.22.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:68953dc84b244b053c0d5f137a21ae8287ecf51b20872eccf8eaac0302d3e3b0"}, + {file = "zstandard-0.22.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2612e9bb4977381184bb2463150336d0f7e014d6bb5d4a370f9a372d21916f69"}, + {file = "zstandard-0.22.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:23d2b3c2b8e7e5a6cb7922f7c27d73a9a615f0a5ab5d0e03dd533c477de23004"}, + {file = "zstandard-0.22.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:1d43501f5f31e22baf822720d82b5547f8a08f5386a883b32584a185675c8fbf"}, + {file = "zstandard-0.22.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:a493d470183ee620a3df1e6e55b3e4de8143c0ba1b16f3ded83208ea8ddfd91d"}, + {file = "zstandard-0.22.0-cp38-cp38-win32.whl", hash = "sha256:7034d381789f45576ec3f1fa0e15d741828146439228dc3f7c59856c5bcd3292"}, + {file = "zstandard-0.22.0-cp38-cp38-win_amd64.whl", hash = "sha256:d8fff0f0c1d8bc5d866762ae95bd99d53282337af1be9dc0d88506b340e74b73"}, + {file = "zstandard-0.22.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:2fdd53b806786bd6112d97c1f1e7841e5e4daa06810ab4b284026a1a0e484c0b"}, + {file = "zstandard-0.22.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:73a1d6bd01961e9fd447162e137ed949c01bdb830dfca487c4a14e9742dccc93"}, + {file = "zstandard-0.22.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9501f36fac6b875c124243a379267d879262480bf85b1dbda61f5ad4d01b75a3"}, + {file = "zstandard-0.22.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:48f260e4c7294ef275744210a4010f116048e0c95857befb7462e033f09442fe"}, + {file = "zstandard-0.22.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:959665072bd60f45c5b6b5d711f15bdefc9849dd5da9fb6c873e35f5d34d8cfb"}, + {file = "zstandard-0.22.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:d22fdef58976457c65e2796e6730a3ea4a254f3ba83777ecfc8592ff8d77d303"}, + {file = "zstandard-0.22.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:a7ccf5825fd71d4542c8ab28d4d482aace885f5ebe4b40faaa290eed8e095a4c"}, + {file = "zstandard-0.22.0-cp39-cp39-win32.whl", hash = "sha256:f058a77ef0ece4e210bb0450e68408d4223f728b109764676e1a13537d056bb0"}, + {file = "zstandard-0.22.0-cp39-cp39-win_amd64.whl", hash = "sha256:e9e9d4e2e336c529d4c435baad846a181e39a982f823f7e4495ec0b0ec8538d2"}, + {file = "zstandard-0.22.0.tar.gz", hash = "sha256:8226a33c542bcb54cd6bd0a366067b610b41713b64c9abec1bc4533d69f51e70"}, +] + +[package.dependencies] +cffi = {version = ">=1.11", markers = "platform_python_implementation == \"PyPy\""} + +[package.extras] +cffi = ["cffi (>=1.11)"] + [metadata] lock-version = "2.0" python-versions = "^3.10" -content-hash = "7dc35227a8e2545597f7a9660850e9adb2569d38f97d72dbfdcdff88f3a38bdb" +content-hash = "76374a3483905c3219821ec31cefd75c64e0ccb3f0c5424acf1b8a1322587411" diff --git a/api/pyproject.toml b/api/pyproject.toml index 74fad2054a..88721b5a35 100644 --- a/api/pyproject.toml +++ b/api/pyproject.toml @@ -211,6 +211,7 @@ qdrant-client = "1.7.3" weaviate-client = "~3.21.0" alibabacloud_gpdb20160503 = "~3.8.0" alibabacloud_tea_openapi = "~0.3.9" +clickhouse-connect = "~0.7.16" ############################################################ # Transparent dependencies required by main dependencies diff --git a/api/tests/integration_tests/vdb/myscale/__init__.py b/api/tests/integration_tests/vdb/myscale/__init__.py new file mode 100644 index 0000000000..e69de29bb2 diff --git a/api/tests/integration_tests/vdb/myscale/test_myscale.py b/api/tests/integration_tests/vdb/myscale/test_myscale.py new file mode 100644 index 0000000000..b6260d549a --- /dev/null +++ b/api/tests/integration_tests/vdb/myscale/test_myscale.py @@ -0,0 +1,29 @@ +from core.rag.datasource.vdb.myscale.myscale_vector import MyScaleConfig, MyScaleVector +from tests.integration_tests.vdb.test_vector_store import ( + AbstractVectorTest, + setup_mock_redis, +) + + +class MyScaleVectorTest(AbstractVectorTest): + def __init__(self): + super().__init__() + self.vector = MyScaleVector( + collection_name=self.collection_name, + config=MyScaleConfig( + host="localhost", + port=8123, + user="default", + password="", + database="dify", + fts_params="", + ), + ) + + def get_ids_by_metadata_field(self): + ids = self.vector.get_ids_by_metadata_field(key='document_id', value=self.example_doc_id) + assert len(ids) == 1 + + +def test_myscale_vector(setup_mock_redis): + MyScaleVectorTest().run_all_tests() diff --git a/dev/pytest/pytest_vdb.sh b/dev/pytest/pytest_vdb.sh index c954c528fb..cb8aae6740 100755 --- a/dev/pytest/pytest_vdb.sh +++ b/dev/pytest/pytest_vdb.sh @@ -3,6 +3,7 @@ set -x pytest api/tests/integration_tests/vdb/chroma \ api/tests/integration_tests/vdb/milvus \ + api/tests/integration_tests/vdb/myscale \ api/tests/integration_tests/vdb/pgvecto_rs \ api/tests/integration_tests/vdb/pgvector \ api/tests/integration_tests/vdb/qdrant \ diff --git a/docker/.env.example b/docker/.env.example index 3e132c1b5d..4f7e13e823 100644 --- a/docker/.env.example +++ b/docker/.env.example @@ -243,7 +243,7 @@ TENCENT_COS_SCHEME=your-scheme # ------------------------------ # The type of vector store to use. -# Supported values are `weaviate`, `qdrant`, `milvus`, `relyt`, `pgvector`, `chroma`, `opensearch`, `tidb_vector`, `oracle`, `tencent`. +# Supported values are `weaviate`, `qdrant`, `milvus`, `myscale`, `relyt`, `pgvector`, `chroma`, `opensearch`, `tidb_vector`, `oracle`, `tencent`. VECTOR_STORE=weaviate # The Weaviate endpoint URL. Only available when VECTOR_STORE is `weaviate`. @@ -274,6 +274,16 @@ MILVUS_PASSWORD=Milvus # The milvus tls switch. MILVUS_SECURE=false +# MyScale configuration, only available when VECTOR_STORE is `myscale` +# For multi-language support, please set MYSCALE_FTS_PARAMS with referring to: +# https://myscale.com/docs/en/text-search/#understanding-fts-index-parameters +MYSCALE_HOST=myscale +MYSCALE_PORT=8123 +MYSCALE_USER=default +MYSCALE_PASSWORD= +MYSCALE_DATABASE=dify +MYSCALE_FTS_PARAMS= + # pgvector configurations, only available when VECTOR_STORE is `pgvecto-rs or pgvector` PGVECTOR_HOST=pgvector PGVECTOR_PORT=5432 diff --git a/docker/docker-compose.yaml b/docker/docker-compose.yaml index c34b50505f..7a3bb58748 100644 --- a/docker/docker-compose.yaml +++ b/docker/docker-compose.yaml @@ -83,6 +83,12 @@ x-shared-env: &shared-api-worker-env MILVUS_USER: ${MILVUS_USER:-root} MILVUS_PASSWORD: ${MILVUS_PASSWORD:-Milvus} MILVUS_SECURE: ${MILVUS_SECURE:-false} + MYSCALE_HOST: ${MYSCALE_HOST:-myscale} + MYSCALE_PORT: ${MYSCALE_PORT:-8123} + MYSCALE_USER: ${MYSCALE_USER:-default} + MYSCALE_PASSWORD: ${MYSCALE_PASSWORD:-} + MYSCALE_DATABASE: ${MYSCALE_DATABASE:-dify} + MYSCALE_FTS_PARAMS: ${MYSCALE_FTS_PARAMS:-} RELYT_HOST: ${RELYT_HOST:-db} RELYT_PORT: ${RELYT_PORT:-5432} RELYT_USER: ${RELYT_USER:-postgres} @@ -532,6 +538,21 @@ services: depends_on: - opensearch + # MyScale vector database + myscale: + container_name: myscale + image: myscale/myscaledb:1.6 + profiles: + - myscale + restart: always + tty: true + volumes: + - ./volumes/myscale/data:/var/lib/clickhouse + - ./volumes/myscale/log:/var/log/clickhouse-server + - ./volumes/myscale/config/users.d/custom_users_config.xml:/etc/clickhouse-server/users.d/custom_users_config.xml + ports: + - "${MYSCALE_PORT:-8123}:${MYSCALE_PORT:-8123}" + networks: # create a network between sandbox, api and ssrf_proxy, and can not access outside. ssrf_proxy_network: diff --git a/docker/volumes/myscale/config/users.d/custom_users_config.xml b/docker/volumes/myscale/config/users.d/custom_users_config.xml new file mode 100644 index 0000000000..67f24b69ee --- /dev/null +++ b/docker/volumes/myscale/config/users.d/custom_users_config.xml @@ -0,0 +1,17 @@ + + + + + + ::1 + 127.0.0.1 + 10.0.0.0/8 + 172.16.0.0/12 + 192.168.0.0/16 + + default + default + 1 + + + \ No newline at end of file