From a743d5dc71bbae5370db60ab2942da9f8ed7b2f3 Mon Sep 17 00:00:00 2001 From: wlleiiwang <1025164922@qq.com> Date: Thu, 27 Mar 2025 12:20:16 +0800 Subject: [PATCH] feat: tencent vectordb: use grpc client and set upsert batch size (#16016) Co-authored-by: wlleiiwang --- .../datasource/vdb/tencent/tencent_vector.py | 124 ++++++---- api/poetry.lock | 225 +++++++++++------- api/pyproject.toml | 2 +- .../vdb/__mock/tcvectordb.py | 106 +++++---- 4 files changed, 286 insertions(+), 171 deletions(-) diff --git a/api/core/rag/datasource/vdb/tencent/tencent_vector.py b/api/core/rag/datasource/vdb/tencent/tencent_vector.py index 304d9538a7..739e9e10ac 100644 --- a/api/core/rag/datasource/vdb/tencent/tencent_vector.py +++ b/api/core/rag/datasource/vdb/tencent/tencent_vector.py @@ -1,8 +1,9 @@ import json +import math from typing import Any, Optional from pydantic import BaseModel -from tcvectordb import VectorDBClient # type: ignore +from tcvectordb import RPCVectorDBClient, VectorDBException # type: ignore from tcvectordb.model import document, enum # type: ignore from tcvectordb.model import index as vdb_index # type: ignore from tcvectordb.model.document import Filter # type: ignore @@ -27,6 +28,7 @@ class TencentConfig(BaseModel): metric_type: str = "L2" shard: int = 1 replicas: int = 2 + max_upsert_batch_size: int = 128 def to_tencent_params(self): return {"url": self.url, "username": self.username, "key": self.api_key, "timeout": self.timeout} @@ -41,19 +43,10 @@ class TencentVector(BaseVector): def __init__(self, collection_name: str, config: TencentConfig): super().__init__(collection_name) self._client_config = config - self._client = VectorDBClient(**self._client_config.to_tencent_params()) - self._db = self._init_database() + self._client = RPCVectorDBClient(**self._client_config.to_tencent_params()) def _init_database(self): - exists = False - for db in self._client.list_databases(): - if db.database_name == self._client_config.database: - exists = True - break - if exists: - return self._client.database(self._client_config.database) - else: - return self._client.create_database(database_name=self._client_config.database) + return self._client.create_database_if_not_exists(database_name=self._client_config.database) def get_type(self) -> str: return VectorType.TENCENT @@ -62,8 +55,11 @@ class TencentVector(BaseVector): return {"type": self.get_type(), "vector_store": {"class_prefix": self._collection_name}} def _has_collection(self) -> bool: - collections = self._db.list_collections() - return any(collection.collection_name == self._collection_name for collection in collections) + return bool( + self._client.exists_collection( + database_name=self._client_config.database, collection_name=self.collection_name + ) + ) def _create_collection(self, dimension: int) -> None: lock_name = "vector_indexing_lock_{}".format(self._collection_name) @@ -75,7 +71,6 @@ class TencentVector(BaseVector): if self._has_collection(): return - self.delete() index_type = None for k, v in enum.IndexType.__members__.items(): if k == self._client_config.index_type: @@ -99,16 +94,41 @@ class TencentVector(BaseVector): params, ), vdb_index.FilterIndex(self.field_text, enum.FieldType.String, enum.IndexType.FILTER), - vdb_index.FilterIndex(self.field_metadata, enum.FieldType.String, enum.IndexType.FILTER), - ) - - self._db.create_collection( - name=self._collection_name, - shard=self._client_config.shard, - replicas=self._client_config.replicas, - description="Collection for Dify", - index=index, + vdb_index.FilterIndex(self.field_metadata, enum.FieldType.Json, enum.IndexType.FILTER), ) + try: + self._client.create_collection( + database_name=self._client_config.database, + collection_name=self._collection_name, + shard=self._client_config.shard, + replicas=self._client_config.replicas, + description="Collection for Dify", + index=index, + ) + except VectorDBException as e: + if "fieldType:json" not in e.message: + raise e + # vdb version not support json, use string + index = vdb_index.Index( + vdb_index.FilterIndex(self.field_id, enum.FieldType.String, enum.IndexType.PRIMARY_KEY), + vdb_index.VectorIndex( + self.field_vector, + dimension, + index_type, + metric_type, + params, + ), + vdb_index.FilterIndex(self.field_text, enum.FieldType.String, enum.IndexType.FILTER), + vdb_index.FilterIndex(self.field_metadata, enum.FieldType.String, enum.IndexType.FILTER), + ) + self._client.create_collection( + database_name=self._client_config.database, + collection_name=self._collection_name, + shard=self._client_config.shard, + replicas=self._client_config.replicas, + description="Collection for Dify", + index=index, + ) redis_client.set(collection_exist_cache_key, 1, ex=3600) def create(self, texts: list[Document], embeddings: list[list[float]], **kwargs): @@ -119,22 +139,34 @@ class TencentVector(BaseVector): texts = [doc.page_content for doc in documents] metadatas = [doc.metadata for doc in documents] total_count = len(embeddings) - docs = [] - for i in range(0, total_count): - if metadatas is None: - continue - metadata = metadatas[i] or {} - doc = document.Document( - id=metadata.get("doc_id"), - vector=embeddings[i], - text=texts[i], - metadata=json.dumps(metadata), + batch_size = self._client_config.max_upsert_batch_size + batch = math.ceil(total_count / batch_size) + for j in range(batch): + docs = [] + start_idx = j * batch_size + end_idx = min(total_count, (j + 1) * batch_size) + for i in range(start_idx, end_idx): + if metadatas is None: + continue + metadata = metadatas[i] or {} + doc = document.Document( + id=metadata.get("doc_id"), + vector=embeddings[i], + text=texts[i], + metadata=metadata, + ) + docs.append(doc) + self._client.upsert( + database_name=self._client_config.database, + collection_name=self.collection_name, + documents=docs, + timeout=self._client_config.timeout, ) - docs.append(doc) - self._db.collection(self._collection_name).upsert(docs, self._client_config.timeout) def text_exists(self, id: str) -> bool: - docs = self._db.collection(self._collection_name).query(document_ids=[id]) + docs = self._client.query( + database_name=self._client_config.database, collection_name=self.collection_name, document_ids=[id] + ) if docs and len(docs) > 0: return True return False @@ -142,17 +174,25 @@ class TencentVector(BaseVector): def delete_by_ids(self, ids: list[str]) -> None: if not ids: return - self._db.collection(self._collection_name).delete(document_ids=ids) + self._client.delete( + database_name=self._client_config.database, collection_name=self.collection_name, document_ids=ids + ) def delete_by_metadata_field(self, key: str, value: str) -> None: - self._db.collection(self._collection_name).delete(filter=Filter(Filter.In(f"metadata.{key}", [value]))) + self._client.delete( + database_name=self._client_config.database, + collection_name=self.collection_name, + filter=Filter(Filter.In(f"metadata.{key}", [value])), + ) def search_by_vector(self, query_vector: list[float], **kwargs: Any) -> list[Document]: document_ids_filter = kwargs.get("document_ids_filter") filter = None if document_ids_filter: filter = Filter(Filter.In("metadata.document_id", document_ids_filter)) - res = self._db.collection(self._collection_name).search( + res = self._client.search( + database_name=self._client_config.database, + collection_name=self.collection_name, vectors=[query_vector], filter=filter, params=document.HNSWSearchParams(ef=kwargs.get("ef", 10)), @@ -173,8 +213,6 @@ class TencentVector(BaseVector): for result in res[0]: meta = result.get(self.field_metadata) - if meta is not None: - meta = json.loads(meta) score = 1 - result.get("score", 0.0) if score > score_threshold: meta["score"] = score @@ -184,7 +222,7 @@ class TencentVector(BaseVector): return docs def delete(self) -> None: - self._db.drop_collection(name=self._collection_name) + self._client.drop_collection(database_name=self._client_config.database, collection_name=self.collection_name) class TencentVectorFactory(AbstractVectorFactory): diff --git a/api/poetry.lock b/api/poetry.lock index 94e1d81eb5..aed61ddded 100644 --- a/api/poetry.lock +++ b/api/poetry.lock @@ -845,6 +845,10 @@ files = [ {file = "Brotli-1.1.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:a37b8f0391212d29b3a91a799c8e4a2855e0576911cdfb2515487e30e322253d"}, {file = "Brotli-1.1.0-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:e84799f09591700a4154154cab9787452925578841a94321d5ee8fb9a9a328f0"}, {file = "Brotli-1.1.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:f66b5337fa213f1da0d9000bc8dc0cb5b896b726eefd9c6046f699b169c41b9e"}, + {file = "Brotli-1.1.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:5dab0844f2cf82be357a0eb11a9087f70c5430b2c241493fc122bb6f2bb0917c"}, + {file = "Brotli-1.1.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:e4fe605b917c70283db7dfe5ada75e04561479075761a0b3866c081d035b01c1"}, + {file = "Brotli-1.1.0-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:1e9a65b5736232e7a7f91ff3d02277f11d339bf34099a56cdab6a8b3410a02b2"}, + {file = "Brotli-1.1.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:58d4b711689366d4a03ac7957ab8c28890415e267f9b6589969e74b6e42225ec"}, {file = "Brotli-1.1.0-cp310-cp310-win32.whl", hash = "sha256:be36e3d172dc816333f33520154d708a2657ea63762ec16b62ece02ab5e4daf2"}, {file = "Brotli-1.1.0-cp310-cp310-win_amd64.whl", hash = "sha256:0c6244521dda65ea562d5a69b9a26120769b7a9fb3db2fe9545935ed6735b128"}, {file = "Brotli-1.1.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:a3daabb76a78f829cafc365531c972016e4aa8d5b4bf60660ad8ecee19df7ccc"}, @@ -857,8 +861,14 @@ files = [ {file = "Brotli-1.1.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:19c116e796420b0cee3da1ccec3b764ed2952ccfcc298b55a10e5610ad7885f9"}, {file = "Brotli-1.1.0-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:510b5b1bfbe20e1a7b3baf5fed9e9451873559a976c1a78eebaa3b86c57b4265"}, {file = "Brotli-1.1.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:a1fd8a29719ccce974d523580987b7f8229aeace506952fa9ce1d53a033873c8"}, + {file = "Brotli-1.1.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:c247dd99d39e0338a604f8c2b3bc7061d5c2e9e2ac7ba9cc1be5a69cb6cd832f"}, + {file = "Brotli-1.1.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:1b2c248cd517c222d89e74669a4adfa5577e06ab68771a529060cf5a156e9757"}, + {file = "Brotli-1.1.0-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:2a24c50840d89ded6c9a8fdc7b6ed3692ed4e86f1c4a4a938e1e92def92933e0"}, + {file = "Brotli-1.1.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:f31859074d57b4639318523d6ffdca586ace54271a73ad23ad021acd807eb14b"}, {file = "Brotli-1.1.0-cp311-cp311-win32.whl", hash = "sha256:39da8adedf6942d76dc3e46653e52df937a3c4d6d18fdc94a7c29d263b1f5b50"}, {file = "Brotli-1.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:aac0411d20e345dc0920bdec5548e438e999ff68d77564d5e9463a7ca9d3e7b1"}, + {file = "Brotli-1.1.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:32d95b80260d79926f5fab3c41701dbb818fde1c9da590e77e571eefd14abe28"}, + {file = "Brotli-1.1.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:b760c65308ff1e462f65d69c12e4ae085cff3b332d894637f6273a12a482d09f"}, {file = "Brotli-1.1.0-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:316cc9b17edf613ac76b1f1f305d2a748f1b976b033b049a6ecdfd5612c70409"}, {file = "Brotli-1.1.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:caf9ee9a5775f3111642d33b86237b05808dafcd6268faa492250e9b78046eb2"}, {file = "Brotli-1.1.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:70051525001750221daa10907c77830bc889cb6d865cc0b813d9db7fefc21451"}, @@ -869,8 +879,24 @@ files = [ {file = "Brotli-1.1.0-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:4093c631e96fdd49e0377a9c167bfd75b6d0bad2ace734c6eb20b348bc3ea180"}, {file = "Brotli-1.1.0-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:7e4c4629ddad63006efa0ef968c8e4751c5868ff0b1c5c40f76524e894c50248"}, {file = "Brotli-1.1.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:861bf317735688269936f755fa136a99d1ed526883859f86e41a5d43c61d8966"}, + {file = "Brotli-1.1.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:87a3044c3a35055527ac75e419dfa9f4f3667a1e887ee80360589eb8c90aabb9"}, + {file = "Brotli-1.1.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:c5529b34c1c9d937168297f2c1fde7ebe9ebdd5e121297ff9c043bdb2ae3d6fb"}, + {file = "Brotli-1.1.0-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:ca63e1890ede90b2e4454f9a65135a4d387a4585ff8282bb72964fab893f2111"}, + {file = "Brotli-1.1.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:e79e6520141d792237c70bcd7a3b122d00f2613769ae0cb61c52e89fd3443839"}, {file = "Brotli-1.1.0-cp312-cp312-win32.whl", hash = "sha256:5f4d5ea15c9382135076d2fb28dde923352fe02951e66935a9efaac8f10e81b0"}, {file = "Brotli-1.1.0-cp312-cp312-win_amd64.whl", hash = "sha256:906bc3a79de8c4ae5b86d3d75a8b77e44404b0f4261714306e3ad248d8ab0951"}, + {file = "Brotli-1.1.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:8bf32b98b75c13ec7cf774164172683d6e7891088f6316e54425fde1efc276d5"}, + {file = "Brotli-1.1.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:7bc37c4d6b87fb1017ea28c9508b36bbcb0c3d18b4260fcdf08b200c74a6aee8"}, + {file = "Brotli-1.1.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3c0ef38c7a7014ffac184db9e04debe495d317cc9c6fb10071f7fefd93100a4f"}, + {file = "Brotli-1.1.0-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:91d7cc2a76b5567591d12c01f019dd7afce6ba8cba6571187e21e2fc418ae648"}, + {file = "Brotli-1.1.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a93dde851926f4f2678e704fadeb39e16c35d8baebd5252c9fd94ce8ce68c4a0"}, + {file = "Brotli-1.1.0-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f0db75f47be8b8abc8d9e31bc7aad0547ca26f24a54e6fd10231d623f183d089"}, + {file = "Brotli-1.1.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:6967ced6730aed543b8673008b5a391c3b1076d834ca438bbd70635c73775368"}, + {file = "Brotli-1.1.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:7eedaa5d036d9336c95915035fb57422054014ebdeb6f3b42eac809928e40d0c"}, + {file = "Brotli-1.1.0-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:d487f5432bf35b60ed625d7e1b448e2dc855422e87469e3f450aa5552b0eb284"}, + {file = "Brotli-1.1.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:832436e59afb93e1836081a20f324cb185836c617659b07b129141a8426973c7"}, + {file = "Brotli-1.1.0-cp313-cp313-win32.whl", hash = "sha256:43395e90523f9c23a3d5bdf004733246fba087f2948f87ab28015f12359ca6a0"}, + {file = "Brotli-1.1.0-cp313-cp313-win_amd64.whl", hash = "sha256:9011560a466d2eb3f5a6e4929cf4a09be405c64154e12df0dd72713f6500e32b"}, {file = "Brotli-1.1.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:a090ca607cbb6a34b0391776f0cb48062081f5f60ddcce5d11838e67a01928d1"}, {file = "Brotli-1.1.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2de9d02f5bda03d27ede52e8cfe7b865b066fa49258cbab568720aa5be80a47d"}, {file = "Brotli-1.1.0-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2333e30a5e00fe0fe55903c8832e08ee9c3b1382aacf4db26664a16528d51b4b"}, @@ -880,6 +906,10 @@ files = [ {file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:fd5f17ff8f14003595ab414e45fce13d073e0762394f957182e69035c9f3d7c2"}, {file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_1_ppc64le.whl", hash = "sha256:069a121ac97412d1fe506da790b3e69f52254b9df4eb665cd42460c837193354"}, {file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:e93dfc1a1165e385cc8239fab7c036fb2cd8093728cbd85097b284d7b99249a2"}, + {file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_2_aarch64.whl", hash = "sha256:aea440a510e14e818e67bfc4027880e2fb500c2ccb20ab21c7a7c8b5b4703d75"}, + {file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_2_i686.whl", hash = "sha256:6974f52a02321b36847cd19d1b8e381bf39939c21efd6ee2fc13a28b0d99348c"}, + {file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_2_ppc64le.whl", hash = "sha256:a7e53012d2853a07a4a79c00643832161a910674a893d296c9f1259859a289d2"}, + {file = "Brotli-1.1.0-cp36-cp36m-musllinux_1_2_x86_64.whl", hash = "sha256:d7702622a8b40c49bffb46e1e3ba2e81268d5c04a34f460978c6b5517a34dd52"}, {file = "Brotli-1.1.0-cp36-cp36m-win32.whl", hash = "sha256:a599669fd7c47233438a56936988a2478685e74854088ef5293802123b5b2460"}, {file = "Brotli-1.1.0-cp36-cp36m-win_amd64.whl", hash = "sha256:d143fd47fad1db3d7c27a1b1d66162e855b5d50a89666af46e1679c496e8e579"}, {file = "Brotli-1.1.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:11d00ed0a83fa22d29bc6b64ef636c4552ebafcef57154b4ddd132f5638fbd1c"}, @@ -891,6 +921,10 @@ files = [ {file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:919e32f147ae93a09fe064d77d5ebf4e35502a8df75c29fb05788528e330fe74"}, {file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:23032ae55523cc7bccb4f6a0bf368cd25ad9bcdcc1990b64a647e7bbcce9cb5b"}, {file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:224e57f6eac61cc449f498cc5f0e1725ba2071a3d4f48d5d9dffba42db196438"}, + {file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_2_aarch64.whl", hash = "sha256:cb1dac1770878ade83f2ccdf7d25e494f05c9165f5246b46a621cc849341dc01"}, + {file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_2_i686.whl", hash = "sha256:3ee8a80d67a4334482d9712b8e83ca6b1d9bc7e351931252ebef5d8f7335a547"}, + {file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_2_ppc64le.whl", hash = "sha256:5e55da2c8724191e5b557f8e18943b1b4839b8efc3ef60d65985bcf6f587dd38"}, + {file = "Brotli-1.1.0-cp37-cp37m-musllinux_1_2_x86_64.whl", hash = "sha256:d342778ef319e1026af243ed0a07c97acf3bad33b9f29e7ae6a1f68fd083e90c"}, {file = "Brotli-1.1.0-cp37-cp37m-win32.whl", hash = "sha256:587ca6d3cef6e4e868102672d3bd9dc9698c309ba56d41c2b9c85bbb903cdb95"}, {file = "Brotli-1.1.0-cp37-cp37m-win_amd64.whl", hash = "sha256:2954c1c23f81c2eaf0b0717d9380bd348578a94161a65b3a2afc62c86467dd68"}, {file = "Brotli-1.1.0-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:efa8b278894b14d6da122a72fefcebc28445f2d3f880ac59d46c90f4c13be9a3"}, @@ -903,6 +937,10 @@ files = [ {file = "Brotli-1.1.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:1ab4fbee0b2d9098c74f3057b2bc055a8bd92ccf02f65944a241b4349229185a"}, {file = "Brotli-1.1.0-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:141bd4d93984070e097521ed07e2575b46f817d08f9fa42b16b9b5f27b5ac088"}, {file = "Brotli-1.1.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:fce1473f3ccc4187f75b4690cfc922628aed4d3dd013d047f95a9b3919a86596"}, + {file = "Brotli-1.1.0-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:d2b35ca2c7f81d173d2fadc2f4f31e88cc5f7a39ae5b6db5513cf3383b0e0ec7"}, + {file = "Brotli-1.1.0-cp38-cp38-musllinux_1_2_i686.whl", hash = "sha256:af6fa6817889314555aede9a919612b23739395ce767fe7fcbea9a80bf140fe5"}, + {file = "Brotli-1.1.0-cp38-cp38-musllinux_1_2_ppc64le.whl", hash = "sha256:2feb1d960f760a575dbc5ab3b1c00504b24caaf6986e2dc2b01c09c87866a943"}, + {file = "Brotli-1.1.0-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:4410f84b33374409552ac9b6903507cdb31cd30d2501fc5ca13d18f73548444a"}, {file = "Brotli-1.1.0-cp38-cp38-win32.whl", hash = "sha256:db85ecf4e609a48f4b29055f1e144231b90edc90af7481aa731ba2d059226b1b"}, {file = "Brotli-1.1.0-cp38-cp38-win_amd64.whl", hash = "sha256:3d7954194c36e304e1523f55d7042c59dc53ec20dd4e9ea9d151f1b62b4415c0"}, {file = "Brotli-1.1.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:5fb2ce4b8045c78ebbc7b8f3c15062e435d47e7393cc57c25115cfd49883747a"}, @@ -915,6 +953,10 @@ files = [ {file = "Brotli-1.1.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:949f3b7c29912693cee0afcf09acd6ebc04c57af949d9bf77d6101ebb61e388c"}, {file = "Brotli-1.1.0-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:89f4988c7203739d48c6f806f1e87a1d96e0806d44f0fba61dba81392c9e474d"}, {file = "Brotli-1.1.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:de6551e370ef19f8de1807d0a9aa2cdfdce2e85ce88b122fe9f6b2b076837e59"}, + {file = "Brotli-1.1.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:0737ddb3068957cf1b054899b0883830bb1fec522ec76b1098f9b6e0f02d9419"}, + {file = "Brotli-1.1.0-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:4f3607b129417e111e30637af1b56f24f7a49e64763253bbc275c75fa887d4b2"}, + {file = "Brotli-1.1.0-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:6c6e0c425f22c1c719c42670d561ad682f7bfeeef918edea971a79ac5252437f"}, + {file = "Brotli-1.1.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:494994f807ba0b92092a163a0a283961369a65f6cbe01e8891132b7a320e61eb"}, {file = "Brotli-1.1.0-cp39-cp39-win32.whl", hash = "sha256:f0d8a7a6b5983c2496e364b969f0e526647a06b075d034f3297dc66f3b360c64"}, {file = "Brotli-1.1.0-cp39-cp39-win_amd64.whl", hash = "sha256:cdad5b9014d83ca68c25d2e9444e28e967ef16e80f6b436918c700c117a85467"}, {file = "Brotli-1.1.0.tar.gz", hash = "sha256:81de08ac11bcb85841e440c13611c00b67d3bf82698314928d0b676362546724"}, @@ -3583,7 +3625,7 @@ version = "0.42.1" description = "Chinese Words Segmentation Utilities" optional = false python-versions = "*" -groups = ["main"] +groups = ["main", "vdb"] files = [ {file = "jieba-0.42.1.tar.gz", hash = "sha256:055ca12f62674fafed09427f176506079bc135638a14e23e25be909131928db2"}, ] @@ -6195,6 +6237,7 @@ files = [ {file = "psycopg2_binary-2.9.10-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:bb89f0a835bcfc1d42ccd5f41f04870c1b936d8507c6df12b7737febc40f0909"}, {file = "psycopg2_binary-2.9.10-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:f0c2d907a1e102526dd2986df638343388b94c33860ff3bbe1384130828714b1"}, {file = "psycopg2_binary-2.9.10-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:f8157bed2f51db683f31306aa497311b560f2265998122abe1dce6428bd86567"}, + {file = "psycopg2_binary-2.9.10-cp313-cp313-win_amd64.whl", hash = "sha256:27422aa5f11fbcd9b18da48373eb67081243662f9b46e6fd07c3eb46e4535142"}, {file = "psycopg2_binary-2.9.10-cp38-cp38-macosx_12_0_x86_64.whl", hash = "sha256:eb09aa7f9cecb45027683bb55aebaaf45a0df8bf6de68801a6afdc7947bb09d4"}, {file = "psycopg2_binary-2.9.10-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b73d6d7f0ccdad7bc43e6d34273f70d587ef62f824d7261c4ae9b8b1b6af90e8"}, {file = "psycopg2_binary-2.9.10-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ce5ab4bf46a211a8e924d307c1b1fcda82368586a19d0a24f8ae166f5c784864"}, @@ -8274,21 +8317,46 @@ files = [ [package.extras] widechars = ["wcwidth"] +[[package]] +name = "tcvdb-text" +version = "1.1.1" +description = "Tencent VectorDB Sparse Vector SDK" +optional = false +python-versions = ">=3" +groups = ["vdb"] +files = [ + {file = "tcvdb_text-1.1.1-py3-none-any.whl", hash = "sha256:981eb2323c0668129942c066de05e8f0d2165be36f567877906646dea07d17a9"}, + {file = "tcvdb_text-1.1.1.tar.gz", hash = "sha256:db36b5d7b640b194ae72c0c429718c9613b8ef9de5fffb9d510aba5be75ff1cb"}, +] + +[package.dependencies] +jieba = ">=0.42.1" +mmh3 = "*" +numpy = "*" +tqdm = "*" + [[package]] name = "tcvectordb" -version = "1.3.2" +version = "1.6.4" description = "Tencent VectorDB Python SDK" optional = false python-versions = ">=3" groups = ["vdb"] files = [ - {file = "tcvectordb-1.3.2-py3-none-any.whl", hash = "sha256:c4b6922d5df4cf14fcd3e61220d9374d1d53ec7270c254216ae35f8a752908f3"}, - {file = "tcvectordb-1.3.2.tar.gz", hash = "sha256:2772f5871a69744ffc7c970b321312d626078533a721de3c744059a81aab419e"}, + {file = "tcvectordb-1.6.4-py3-none-any.whl", hash = "sha256:06ef13e7edb4575b04615065fc90e1a28374e318ada305f3786629aec5c9318a"}, + {file = "tcvectordb-1.6.4.tar.gz", hash = "sha256:6fb18e15ccc6744d5147e9bbd781f84df3d66112de7d9cc615878b3f72d3a29a"}, ] [package.dependencies] -cos-python-sdk-v5 = ">=1.9.26" +cachetools = "*" +cos-python-sdk-v5 = "*" +grpcio = "*" +grpcio-tools = "*" +numpy = "*" requests = "*" +tcvdb-text = "*" +ujson = "5.9.0" +urllib3 = "*" [[package]] name = "tenacity" @@ -8889,90 +8957,77 @@ files = [ [[package]] name = "ujson" -version = "5.10.0" +version = "5.9.0" description = "Ultra fast JSON encoder and decoder for Python" optional = false python-versions = ">=3.8" groups = ["vdb"] files = [ - {file = "ujson-5.10.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:2601aa9ecdbee1118a1c2065323bda35e2c5a2cf0797ef4522d485f9d3ef65bd"}, - {file = "ujson-5.10.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:348898dd702fc1c4f1051bc3aacbf894caa0927fe2c53e68679c073375f732cf"}, - {file = "ujson-5.10.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:22cffecf73391e8abd65ef5f4e4dd523162a3399d5e84faa6aebbf9583df86d6"}, - {file = "ujson-5.10.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:26b0e2d2366543c1bb4fbd457446f00b0187a2bddf93148ac2da07a53fe51569"}, - {file = "ujson-5.10.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:caf270c6dba1be7a41125cd1e4fc7ba384bf564650beef0df2dd21a00b7f5770"}, - {file = "ujson-5.10.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:a245d59f2ffe750446292b0094244df163c3dc96b3ce152a2c837a44e7cda9d1"}, - {file = "ujson-5.10.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:94a87f6e151c5f483d7d54ceef83b45d3a9cca7a9cb453dbdbb3f5a6f64033f5"}, - {file = "ujson-5.10.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:29b443c4c0a113bcbb792c88bea67b675c7ca3ca80c3474784e08bba01c18d51"}, - {file = "ujson-5.10.0-cp310-cp310-win32.whl", hash = "sha256:c18610b9ccd2874950faf474692deee4223a994251bc0a083c114671b64e6518"}, - {file = "ujson-5.10.0-cp310-cp310-win_amd64.whl", hash = "sha256:924f7318c31874d6bb44d9ee1900167ca32aa9b69389b98ecbde34c1698a250f"}, - {file = "ujson-5.10.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:a5b366812c90e69d0f379a53648be10a5db38f9d4ad212b60af00bd4048d0f00"}, - {file = "ujson-5.10.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:502bf475781e8167f0f9d0e41cd32879d120a524b22358e7f205294224c71126"}, - {file = "ujson-5.10.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5b91b5d0d9d283e085e821651184a647699430705b15bf274c7896f23fe9c9d8"}, - {file = "ujson-5.10.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:129e39af3a6d85b9c26d5577169c21d53821d8cf68e079060602e861c6e5da1b"}, - {file = "ujson-5.10.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f77b74475c462cb8b88680471193064d3e715c7c6074b1c8c412cb526466efe9"}, - {file = "ujson-5.10.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:7ec0ca8c415e81aa4123501fee7f761abf4b7f386aad348501a26940beb1860f"}, - {file = "ujson-5.10.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:ab13a2a9e0b2865a6c6db9271f4b46af1c7476bfd51af1f64585e919b7c07fd4"}, - {file = "ujson-5.10.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:57aaf98b92d72fc70886b5a0e1a1ca52c2320377360341715dd3933a18e827b1"}, - {file = "ujson-5.10.0-cp311-cp311-win32.whl", hash = "sha256:2987713a490ceb27edff77fb184ed09acdc565db700ee852823c3dc3cffe455f"}, - {file = "ujson-5.10.0-cp311-cp311-win_amd64.whl", hash = "sha256:f00ea7e00447918ee0eff2422c4add4c5752b1b60e88fcb3c067d4a21049a720"}, - {file = "ujson-5.10.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:98ba15d8cbc481ce55695beee9f063189dce91a4b08bc1d03e7f0152cd4bbdd5"}, - {file = "ujson-5.10.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a9d2edbf1556e4f56e50fab7d8ff993dbad7f54bac68eacdd27a8f55f433578e"}, - {file = "ujson-5.10.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6627029ae4f52d0e1a2451768c2c37c0c814ffc04f796eb36244cf16b8e57043"}, - {file = "ujson-5.10.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f8ccb77b3e40b151e20519c6ae6d89bfe3f4c14e8e210d910287f778368bb3d1"}, - {file = "ujson-5.10.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f3caf9cd64abfeb11a3b661329085c5e167abbe15256b3b68cb5d914ba7396f3"}, - {file = "ujson-5.10.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:6e32abdce572e3a8c3d02c886c704a38a1b015a1fb858004e03d20ca7cecbb21"}, - {file = "ujson-5.10.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:a65b6af4d903103ee7b6f4f5b85f1bfd0c90ba4eeac6421aae436c9988aa64a2"}, - {file = "ujson-5.10.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:604a046d966457b6cdcacc5aa2ec5314f0e8c42bae52842c1e6fa02ea4bda42e"}, - {file = "ujson-5.10.0-cp312-cp312-win32.whl", hash = "sha256:6dea1c8b4fc921bf78a8ff00bbd2bfe166345f5536c510671bccececb187c80e"}, - {file = "ujson-5.10.0-cp312-cp312-win_amd64.whl", hash = "sha256:38665e7d8290188b1e0d57d584eb8110951a9591363316dd41cf8686ab1d0abc"}, - {file = "ujson-5.10.0-cp313-cp313-macosx_10_9_x86_64.whl", hash = "sha256:618efd84dc1acbd6bff8eaa736bb6c074bfa8b8a98f55b61c38d4ca2c1f7f287"}, - {file = "ujson-5.10.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:38d5d36b4aedfe81dfe251f76c0467399d575d1395a1755de391e58985ab1c2e"}, - {file = "ujson-5.10.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:67079b1f9fb29ed9a2914acf4ef6c02844b3153913eb735d4bf287ee1db6e557"}, - {file = "ujson-5.10.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d7d0e0ceeb8fe2468c70ec0c37b439dd554e2aa539a8a56365fd761edb418988"}, - {file = "ujson-5.10.0-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:59e02cd37bc7c44d587a0ba45347cc815fb7a5fe48de16bf05caa5f7d0d2e816"}, - {file = "ujson-5.10.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:2a890b706b64e0065f02577bf6d8ca3b66c11a5e81fb75d757233a38c07a1f20"}, - {file = "ujson-5.10.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:621e34b4632c740ecb491efc7f1fcb4f74b48ddb55e65221995e74e2d00bbff0"}, - {file = "ujson-5.10.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:b9500e61fce0cfc86168b248104e954fead61f9be213087153d272e817ec7b4f"}, - {file = "ujson-5.10.0-cp313-cp313-win32.whl", hash = "sha256:4c4fc16f11ac1612f05b6f5781b384716719547e142cfd67b65d035bd85af165"}, - {file = "ujson-5.10.0-cp313-cp313-win_amd64.whl", hash = "sha256:4573fd1695932d4f619928fd09d5d03d917274381649ade4328091ceca175539"}, - {file = "ujson-5.10.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:a984a3131da7f07563057db1c3020b1350a3e27a8ec46ccbfbf21e5928a43050"}, - {file = "ujson-5.10.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:73814cd1b9db6fc3270e9d8fe3b19f9f89e78ee9d71e8bd6c9a626aeaeaf16bd"}, - {file = "ujson-5.10.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:61e1591ed9376e5eddda202ec229eddc56c612b61ac6ad07f96b91460bb6c2fb"}, - {file = "ujson-5.10.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2c75269f8205b2690db4572a4a36fe47cd1338e4368bc73a7a0e48789e2e35a"}, - {file = "ujson-5.10.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7223f41e5bf1f919cd8d073e35b229295aa8e0f7b5de07ed1c8fddac63a6bc5d"}, - {file = "ujson-5.10.0-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:d4dc2fd6b3067c0782e7002ac3b38cf48608ee6366ff176bbd02cf969c9c20fe"}, - {file = "ujson-5.10.0-cp38-cp38-musllinux_1_2_i686.whl", hash = "sha256:232cc85f8ee3c454c115455195a205074a56ff42608fd6b942aa4c378ac14dd7"}, - {file = "ujson-5.10.0-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:cc6139531f13148055d691e442e4bc6601f6dba1e6d521b1585d4788ab0bfad4"}, - {file = "ujson-5.10.0-cp38-cp38-win32.whl", hash = "sha256:e7ce306a42b6b93ca47ac4a3b96683ca554f6d35dd8adc5acfcd55096c8dfcb8"}, - {file = "ujson-5.10.0-cp38-cp38-win_amd64.whl", hash = "sha256:e82d4bb2138ab05e18f089a83b6564fee28048771eb63cdecf4b9b549de8a2cc"}, - {file = "ujson-5.10.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:dfef2814c6b3291c3c5f10065f745a1307d86019dbd7ea50e83504950136ed5b"}, - {file = "ujson-5.10.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:4734ee0745d5928d0ba3a213647f1c4a74a2a28edc6d27b2d6d5bd9fa4319e27"}, - {file = "ujson-5.10.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d47ebb01bd865fdea43da56254a3930a413f0c5590372a1241514abae8aa7c76"}, - {file = "ujson-5.10.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dee5e97c2496874acbf1d3e37b521dd1f307349ed955e62d1d2f05382bc36dd5"}, - {file = "ujson-5.10.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7490655a2272a2d0b072ef16b0b58ee462f4973a8f6bbe64917ce5e0a256f9c0"}, - {file = "ujson-5.10.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:ba17799fcddaddf5c1f75a4ba3fd6441f6a4f1e9173f8a786b42450851bd74f1"}, - {file = "ujson-5.10.0-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:2aff2985cef314f21d0fecc56027505804bc78802c0121343874741650a4d3d1"}, - {file = "ujson-5.10.0-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:ad88ac75c432674d05b61184178635d44901eb749786c8eb08c102330e6e8996"}, - {file = "ujson-5.10.0-cp39-cp39-win32.whl", hash = "sha256:2544912a71da4ff8c4f7ab5606f947d7299971bdd25a45e008e467ca638d13c9"}, - {file = "ujson-5.10.0-cp39-cp39-win_amd64.whl", hash = "sha256:3ff201d62b1b177a46f113bb43ad300b424b7847f9c5d38b1b4ad8f75d4a282a"}, - {file = "ujson-5.10.0-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:5b6fee72fa77dc172a28f21693f64d93166534c263adb3f96c413ccc85ef6e64"}, - {file = "ujson-5.10.0-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:61d0af13a9af01d9f26d2331ce49bb5ac1fb9c814964018ac8df605b5422dcb3"}, - {file = "ujson-5.10.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ecb24f0bdd899d368b715c9e6664166cf694d1e57be73f17759573a6986dd95a"}, - {file = "ujson-5.10.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fbd8fd427f57a03cff3ad6574b5e299131585d9727c8c366da4624a9069ed746"}, - {file = "ujson-5.10.0-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:beeaf1c48e32f07d8820c705ff8e645f8afa690cca1544adba4ebfa067efdc88"}, - {file = "ujson-5.10.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:baed37ea46d756aca2955e99525cc02d9181de67f25515c468856c38d52b5f3b"}, - {file = "ujson-5.10.0-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:7663960f08cd5a2bb152f5ee3992e1af7690a64c0e26d31ba7b3ff5b2ee66337"}, - {file = "ujson-5.10.0-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:d8640fb4072d36b08e95a3a380ba65779d356b2fee8696afeb7794cf0902d0a1"}, - {file = "ujson-5.10.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:78778a3aa7aafb11e7ddca4e29f46bc5139131037ad628cc10936764282d6753"}, - {file = "ujson-5.10.0-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b0111b27f2d5c820e7f2dbad7d48e3338c824e7ac4d2a12da3dc6061cc39c8e6"}, - {file = "ujson-5.10.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:c66962ca7565605b355a9ed478292da628b8f18c0f2793021ca4425abf8b01e5"}, - {file = "ujson-5.10.0-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:ba43cc34cce49cf2d4bc76401a754a81202d8aa926d0e2b79f0ee258cb15d3a4"}, - {file = "ujson-5.10.0-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:ac56eb983edce27e7f51d05bc8dd820586c6e6be1c5216a6809b0c668bb312b8"}, - {file = "ujson-5.10.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f44bd4b23a0e723bf8b10628288c2c7c335161d6840013d4d5de20e48551773b"}, - {file = "ujson-5.10.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7c10f4654e5326ec14a46bcdeb2b685d4ada6911050aa8baaf3501e57024b804"}, - {file = "ujson-5.10.0-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0de4971a89a762398006e844ae394bd46991f7c385d7a6a3b93ba229e6dac17e"}, - {file = "ujson-5.10.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:e1402f0564a97d2a52310ae10a64d25bcef94f8dd643fcf5d310219d915484f7"}, - {file = "ujson-5.10.0.tar.gz", hash = "sha256:b3cd8f3c5d8c7738257f1018880444f7b7d9b66232c64649f562d7ba86ad4bc1"}, + {file = "ujson-5.9.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:ab71bf27b002eaf7d047c54a68e60230fbd5cd9da60de7ca0aa87d0bccead8fa"}, + {file = "ujson-5.9.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:7a365eac66f5aa7a7fdf57e5066ada6226700884fc7dce2ba5483538bc16c8c5"}, + {file = "ujson-5.9.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e015122b337858dba5a3dc3533af2a8fc0410ee9e2374092f6a5b88b182e9fcc"}, + {file = "ujson-5.9.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:779a2a88c53039bebfbccca934430dabb5c62cc179e09a9c27a322023f363e0d"}, + {file = "ujson-5.9.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:10ca3c41e80509fd9805f7c149068fa8dbee18872bbdc03d7cca928926a358d5"}, + {file = "ujson-5.9.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:4a566e465cb2fcfdf040c2447b7dd9718799d0d90134b37a20dff1e27c0e9096"}, + {file = "ujson-5.9.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:f833c529e922577226a05bc25b6a8b3eb6c4fb155b72dd88d33de99d53113124"}, + {file = "ujson-5.9.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b68a0caab33f359b4cbbc10065c88e3758c9f73a11a65a91f024b2e7a1257106"}, + {file = "ujson-5.9.0-cp310-cp310-win32.whl", hash = "sha256:7cc7e605d2aa6ae6b7321c3ae250d2e050f06082e71ab1a4200b4ae64d25863c"}, + {file = "ujson-5.9.0-cp310-cp310-win_amd64.whl", hash = "sha256:a6d3f10eb8ccba4316a6b5465b705ed70a06011c6f82418b59278fbc919bef6f"}, + {file = "ujson-5.9.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:3b23bbb46334ce51ddb5dded60c662fbf7bb74a37b8f87221c5b0fec1ec6454b"}, + {file = "ujson-5.9.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:6974b3a7c17bbf829e6c3bfdc5823c67922e44ff169851a755eab79a3dd31ec0"}, + {file = "ujson-5.9.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b5964ea916edfe24af1f4cc68488448fbb1ec27a3ddcddc2b236da575c12c8ae"}, + {file = "ujson-5.9.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8ba7cac47dd65ff88571eceeff48bf30ed5eb9c67b34b88cb22869b7aa19600d"}, + {file = "ujson-5.9.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6bbd91a151a8f3358c29355a491e915eb203f607267a25e6ab10531b3b157c5e"}, + {file = "ujson-5.9.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:829a69d451a49c0de14a9fecb2a2d544a9b2c884c2b542adb243b683a6f15908"}, + {file = "ujson-5.9.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:a807ae73c46ad5db161a7e883eec0fbe1bebc6a54890152ccc63072c4884823b"}, + {file = "ujson-5.9.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:8fc2aa18b13d97b3c8ccecdf1a3c405f411a6e96adeee94233058c44ff92617d"}, + {file = "ujson-5.9.0-cp311-cp311-win32.whl", hash = "sha256:70e06849dfeb2548be48fdd3ceb53300640bc8100c379d6e19d78045e9c26120"}, + {file = "ujson-5.9.0-cp311-cp311-win_amd64.whl", hash = "sha256:7309d063cd392811acc49b5016728a5e1b46ab9907d321ebbe1c2156bc3c0b99"}, + {file = "ujson-5.9.0-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:20509a8c9f775b3a511e308bbe0b72897ba6b800767a7c90c5cca59d20d7c42c"}, + {file = "ujson-5.9.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:b28407cfe315bd1b34f1ebe65d3bd735d6b36d409b334100be8cdffae2177b2f"}, + {file = "ujson-5.9.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9d302bd17989b6bd90d49bade66943c78f9e3670407dbc53ebcf61271cadc399"}, + {file = "ujson-5.9.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9f21315f51e0db8ee245e33a649dd2d9dce0594522de6f278d62f15f998e050e"}, + {file = "ujson-5.9.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5635b78b636a54a86fdbf6f027e461aa6c6b948363bdf8d4fbb56a42b7388320"}, + {file = "ujson-5.9.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:82b5a56609f1235d72835ee109163c7041b30920d70fe7dac9176c64df87c164"}, + {file = "ujson-5.9.0-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:5ca35f484622fd208f55041b042d9d94f3b2c9c5add4e9af5ee9946d2d30db01"}, + {file = "ujson-5.9.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:829b824953ebad76d46e4ae709e940bb229e8999e40881338b3cc94c771b876c"}, + {file = "ujson-5.9.0-cp312-cp312-win32.whl", hash = "sha256:25fa46e4ff0a2deecbcf7100af3a5d70090b461906f2299506485ff31d9ec437"}, + {file = "ujson-5.9.0-cp312-cp312-win_amd64.whl", hash = "sha256:60718f1720a61560618eff3b56fd517d107518d3c0160ca7a5a66ac949c6cf1c"}, + {file = "ujson-5.9.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:d581db9db9e41d8ea0b2705c90518ba623cbdc74f8d644d7eb0d107be0d85d9c"}, + {file = "ujson-5.9.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:ff741a5b4be2d08fceaab681c9d4bc89abf3c9db600ab435e20b9b6d4dfef12e"}, + {file = "ujson-5.9.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cdcb02cabcb1e44381221840a7af04433c1dc3297af76fde924a50c3054c708c"}, + {file = "ujson-5.9.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e208d3bf02c6963e6ef7324dadf1d73239fb7008491fdf523208f60be6437402"}, + {file = "ujson-5.9.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f4b3917296630a075e04d3d07601ce2a176479c23af838b6cf90a2d6b39b0d95"}, + {file = "ujson-5.9.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:0c4d6adb2c7bb9eb7c71ad6f6f612e13b264942e841f8cc3314a21a289a76c4e"}, + {file = "ujson-5.9.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:0b159efece9ab5c01f70b9d10bbb77241ce111a45bc8d21a44c219a2aec8ddfd"}, + {file = "ujson-5.9.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:f0cb4a7814940ddd6619bdce6be637a4b37a8c4760de9373bac54bb7b229698b"}, + {file = "ujson-5.9.0-cp38-cp38-win32.whl", hash = "sha256:dc80f0f5abf33bd7099f7ac94ab1206730a3c0a2d17549911ed2cb6b7aa36d2d"}, + {file = "ujson-5.9.0-cp38-cp38-win_amd64.whl", hash = "sha256:506a45e5fcbb2d46f1a51fead991c39529fc3737c0f5d47c9b4a1d762578fc30"}, + {file = "ujson-5.9.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:d0fd2eba664a22447102062814bd13e63c6130540222c0aa620701dd01f4be81"}, + {file = "ujson-5.9.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:bdf7fc21a03bafe4ba208dafa84ae38e04e5d36c0e1c746726edf5392e9f9f36"}, + {file = "ujson-5.9.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e2f909bc08ce01f122fd9c24bc6f9876aa087188dfaf3c4116fe6e4daf7e194f"}, + {file = "ujson-5.9.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bd4ea86c2afd41429751d22a3ccd03311c067bd6aeee2d054f83f97e41e11d8f"}, + {file = "ujson-5.9.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:63fb2e6599d96fdffdb553af0ed3f76b85fda63281063f1cb5b1141a6fcd0617"}, + {file = "ujson-5.9.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:32bba5870c8fa2a97f4a68f6401038d3f1922e66c34280d710af00b14a3ca562"}, + {file = "ujson-5.9.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:37ef92e42535a81bf72179d0e252c9af42a4ed966dc6be6967ebfb929a87bc60"}, + {file = "ujson-5.9.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:f69f16b8f1c69da00e38dc5f2d08a86b0e781d0ad3e4cc6a13ea033a439c4844"}, + {file = "ujson-5.9.0-cp39-cp39-win32.whl", hash = "sha256:3382a3ce0ccc0558b1c1668950008cece9bf463ebb17463ebf6a8bfc060dae34"}, + {file = "ujson-5.9.0-cp39-cp39-win_amd64.whl", hash = "sha256:6adef377ed583477cf005b58c3025051b5faa6b8cc25876e594afbb772578f21"}, + {file = "ujson-5.9.0-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:ffdfebd819f492e48e4f31c97cb593b9c1a8251933d8f8972e81697f00326ff1"}, + {file = "ujson-5.9.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c4eec2ddc046360d087cf35659c7ba0cbd101f32035e19047013162274e71fcf"}, + {file = "ujson-5.9.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2fbb90aa5c23cb3d4b803c12aa220d26778c31b6e4b7a13a1f49971f6c7d088e"}, + {file = "ujson-5.9.0-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ba0823cb70866f0d6a4ad48d998dd338dce7314598721bc1b7986d054d782dfd"}, + {file = "ujson-5.9.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:4e35d7885ed612feb6b3dd1b7de28e89baaba4011ecdf995e88be9ac614765e9"}, + {file = "ujson-5.9.0-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:b048aa93eace8571eedbd67b3766623e7f0acbf08ee291bef7d8106210432427"}, + {file = "ujson-5.9.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:323279e68c195110ef85cbe5edce885219e3d4a48705448720ad925d88c9f851"}, + {file = "ujson-5.9.0-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9ac92d86ff34296f881e12aa955f7014d276895e0e4e868ba7fddebbde38e378"}, + {file = "ujson-5.9.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:6eecbd09b316cea1fd929b1e25f70382917542ab11b692cb46ec9b0a26c7427f"}, + {file = "ujson-5.9.0-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:473fb8dff1d58f49912323d7cb0859df5585cfc932e4b9c053bf8cf7f2d7c5c4"}, + {file = "ujson-5.9.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f91719c6abafe429c1a144cfe27883eace9fb1c09a9c5ef1bcb3ae80a3076a4e"}, + {file = "ujson-5.9.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7b1c0991c4fe256f5fdb19758f7eac7f47caac29a6c57d0de16a19048eb86bad"}, + {file = "ujson-5.9.0-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2a8ea0f55a1396708e564595aaa6696c0d8af532340f477162ff6927ecc46e21"}, + {file = "ujson-5.9.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:07e0cfdde5fd91f54cd2d7ffb3482c8ff1bf558abf32a8b953a5d169575ae1cd"}, + {file = "ujson-5.9.0.tar.gz", hash = "sha256:89cc92e73d5501b8a7f48575eeb14ad27156ad092c2e9fc7e3cf949f07e75532"}, ] [[package]] @@ -9941,4 +9996,4 @@ cffi = ["cffi (>=1.11)"] [metadata] lock-version = "2.1" python-versions = ">=3.11,<3.13" -content-hash = "f724eea7b0b065c002f52bdc22f5ff1c1fb57986d0c7baaf2aad0b3d2e098edb" +content-hash = "5ee6591e61f05986ab0bb50e5a540ef4eee4b086e8da8e9f01ac1176730ad051" diff --git a/api/pyproject.toml b/api/pyproject.toml index 4284118e54..4b5ec05e9a 100644 --- a/api/pyproject.toml +++ b/api/pyproject.toml @@ -130,7 +130,7 @@ pymilvus = "~2.5.0" pymochow = "1.3.1" pyobvector = "~0.1.6" qdrant-client = "1.7.3" -tcvectordb = "1.3.2" +tcvectordb = "~1.6.4" tidb-vector = "0.0.9" upstash-vector = "0.6.0" volcengine-compat = "~1.0.156" diff --git a/api/tests/integration_tests/vdb/__mock/tcvectordb.py b/api/tests/integration_tests/vdb/__mock/tcvectordb.py index 68a1e290ad..4c16f27732 100644 --- a/api/tests/integration_tests/vdb/__mock/tcvectordb.py +++ b/api/tests/integration_tests/vdb/__mock/tcvectordb.py @@ -1,58 +1,65 @@ import os -from typing import Optional +from typing import Optional, Union import pytest from _pytest.monkeypatch import MonkeyPatch from requests.adapters import HTTPAdapter -from tcvectordb import VectorDBClient # type: ignore -from tcvectordb.model.database import Collection, Database # type: ignore +from tcvectordb import RPCVectorDBClient # type: ignore +from tcvectordb.model.collection import FilterIndexConfig from tcvectordb.model.document import Document, Filter # type: ignore from tcvectordb.model.enum import ReadConsistency # type: ignore -from tcvectordb.model.index import Index # type: ignore +from tcvectordb.model.index import Index, IndexField # type: ignore +from tcvectordb.rpc.model.collection import RPCCollection +from tcvectordb.rpc.model.database import RPCDatabase from xinference_client.types import Embedding # type: ignore class MockTcvectordbClass: def mock_vector_db_client( self, - url=None, + url: str, username="", key="", read_consistency: ReadConsistency = ReadConsistency.EVENTUAL_CONSISTENCY, - timeout=5, + timeout=10, adapter: HTTPAdapter = None, + pool_size: int = 2, + proxies: Optional[dict] = None, + password: Optional[str] = None, + **kwargs, ): self._conn = None self._read_consistency = read_consistency - def list_databases(self) -> list[Database]: - return [ - Database( - conn=self._conn, - read_consistency=self._read_consistency, - name="dify", - ) - ] + def create_database_if_not_exists(self, database_name: str, timeout: Optional[float] = None) -> RPCDatabase: + return RPCDatabase( + name="dify", + read_consistency=self._read_consistency, + ) - def list_collections(self, timeout: Optional[float] = None) -> list[Collection]: - return [] - - def drop_collection(self, name: str, timeout: Optional[float] = None): - return {"code": 0, "msg": "operation success"} + def exists_collection(self, database_name: str, collection_name: str) -> bool: + return True def create_collection( self, - name: str, + database_name: str, + collection_name: str, shard: int, replicas: int, - description: str, - index: Index, + description: Optional[str] = None, + index: Index = None, embedding: Embedding = None, timeout: Optional[float] = None, - ) -> Collection: - return Collection( - self, - name, + ttl_config: Optional[dict] = None, + filter_index_config: FilterIndexConfig = None, + indexes: Optional[list[IndexField]] = None, + ) -> RPCCollection: + return RPCCollection( + RPCDatabase( + name="dify", + read_consistency=self._read_consistency, + ), + collection_name, shard, replicas, description, @@ -60,19 +67,26 @@ class MockTcvectordbClass: embedding=embedding, read_consistency=self._read_consistency, timeout=timeout, + ttl_config=ttl_config, + filter_index_config=filter_index_config, + indexes=indexes, ) - def describe_collection(self, name: str, timeout: Optional[float] = None) -> Collection: - collection = Collection(self, name, shard=1, replicas=2, description=name, timeout=timeout) - return collection - def collection_upsert( - self, documents: list[Document], timeout: Optional[float] = None, build_index: bool = True, **kwargs + self, + database_name: str, + collection_name: str, + documents: list[Union[Document, dict]], + timeout: Optional[float] = None, + build_index: bool = True, + **kwargs, ): return {"code": 0, "msg": "operation success"} def collection_search( self, + database_name: str, + collection_name: str, vectors: list[list[float]], filter: Filter = None, params=None, @@ -81,10 +95,12 @@ class MockTcvectordbClass: output_fields: Optional[list[str]] = None, timeout: Optional[float] = None, ) -> list[list[dict]]: - return [[{"metadata": '{"doc_id":"foo1"}', "text": "text", "doc_id": "foo1", "score": 0.1}]] + return [[{"metadata": {"doc_id": "foo1"}, "text": "text", "doc_id": "foo1", "score": 0.1}]] def collection_query( self, + database_name: str, + collection_name: str, document_ids: Optional[list] = None, retrieve_vector: bool = False, limit: Optional[int] = None, @@ -97,12 +113,17 @@ class MockTcvectordbClass: def collection_delete( self, + database_name: str, + collection_name: str, document_ids: Optional[list[str]] = None, filter: Filter = None, timeout: Optional[float] = None, ): return {"code": 0, "msg": "operation success"} + def drop_collection(self, database_name: str, collection_name: str, timeout: Optional[float] = None) -> dict: + return {"code": 0, "msg": "operation success"} + MOCK = os.getenv("MOCK_SWITCH", "false").lower() == "true" @@ -110,16 +131,17 @@ MOCK = os.getenv("MOCK_SWITCH", "false").lower() == "true" @pytest.fixture def setup_tcvectordb_mock(request, monkeypatch: MonkeyPatch): if MOCK: - monkeypatch.setattr(VectorDBClient, "__init__", MockTcvectordbClass.mock_vector_db_client) - monkeypatch.setattr(VectorDBClient, "list_databases", MockTcvectordbClass.list_databases) - monkeypatch.setattr(Database, "collection", MockTcvectordbClass.describe_collection) - monkeypatch.setattr(Database, "list_collections", MockTcvectordbClass.list_collections) - monkeypatch.setattr(Database, "drop_collection", MockTcvectordbClass.drop_collection) - monkeypatch.setattr(Database, "create_collection", MockTcvectordbClass.create_collection) - monkeypatch.setattr(Collection, "upsert", MockTcvectordbClass.collection_upsert) - monkeypatch.setattr(Collection, "search", MockTcvectordbClass.collection_search) - monkeypatch.setattr(Collection, "query", MockTcvectordbClass.collection_query) - monkeypatch.setattr(Collection, "delete", MockTcvectordbClass.collection_delete) + monkeypatch.setattr(RPCVectorDBClient, "__init__", MockTcvectordbClass.mock_vector_db_client) + monkeypatch.setattr( + RPCVectorDBClient, "create_database_if_not_exists", MockTcvectordbClass.create_database_if_not_exists + ) + monkeypatch.setattr(RPCVectorDBClient, "exists_collection", MockTcvectordbClass.exists_collection) + monkeypatch.setattr(RPCVectorDBClient, "create_collection", MockTcvectordbClass.create_collection) + monkeypatch.setattr(RPCVectorDBClient, "upsert", MockTcvectordbClass.collection_upsert) + monkeypatch.setattr(RPCVectorDBClient, "search", MockTcvectordbClass.collection_search) + monkeypatch.setattr(RPCVectorDBClient, "query", MockTcvectordbClass.collection_query) + monkeypatch.setattr(RPCVectorDBClient, "delete", MockTcvectordbClass.collection_delete) + monkeypatch.setattr(RPCVectorDBClient, "drop_collection", MockTcvectordbClass.drop_collection) yield