From 595f00831a7791a2d86ddcf7a06f4eea99bf2b33 Mon Sep 17 00:00:00 2001 From: Sarah Wooders Date: Sat, 25 May 2024 21:36:46 -0700 Subject: [PATCH] feat: Milvus storage connector (#1198) (#1400) Signed-off-by: ChengZi Co-authored-by: ChengZi --- .github/workflows/tests.yml | 1 - docs/storage.md | 20 +++ memgpt/agent_store/milvus.py | 198 ++++++++++++++++++++++++++ memgpt/agent_store/storage.py | 3 + memgpt/cli/cli_config.py | 9 +- poetry.lock | 261 ++++++++++++++++++++++++++-------- pyproject.toml | 2 + tests/test_load_archival.py | 6 +- tests/test_storage.py | 9 +- 9 files changed, 447 insertions(+), 62 deletions(-) create mode 100644 memgpt/agent_store/milvus.py diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml index d0ab9354..4eee7198 100644 --- a/.github/workflows/tests.yml +++ b/.github/workflows/tests.yml @@ -21,7 +21,6 @@ jobs: - name: Build and run container run: bash db/run_postgres.sh - - name: "Setup Python, Poetry and Dependencies" uses: packetcoders/action-setup-cache-python-poetry@main with: diff --git a/docs/storage.md b/docs/storage.md index 7e7b27ae..cde9056c 100644 --- a/docs/storage.md +++ b/docs/storage.md @@ -104,3 +104,23 @@ memgpt configure ``` and selecting `lancedb` for archival storage, and database URI (e.g. `./.lancedb`"), Empty archival uri is also handled and default uri is set at `./.lancedb`. For more checkout [lancedb docs](https://lancedb.github.io/lancedb/) + + +## Milvus + +To enable the Milvus backend, make sure to install the required dependencies with: + +```sh +pip install 'pymemgpt[milvus]' +``` +You can configure Milvus connection via command `memgpt configure`. + +```sh +... +? Select storage backend for archival data: milvus +? Enter the Milvus connection URI (Default: ~/.memgpt/milvus.db): ~/.memgpt/milvus.db +``` +You just set the URI to the local file path, e.g. `~/.memgpt/milvus.db`, which will automatically invoke the local Milvus service instance through Milvus Lite. + +If you have large scale of data such as more than a million docs, we recommend setting up a more performant Milvus server on [docker or kubenetes](https://milvus.io/docs/quickstart.md). +And in this case, your URI should be the server URI, e.g. `http://localhost:19530`. diff --git a/memgpt/agent_store/milvus.py b/memgpt/agent_store/milvus.py new file mode 100644 index 00000000..04495863 --- /dev/null +++ b/memgpt/agent_store/milvus.py @@ -0,0 +1,198 @@ +import uuid +from copy import deepcopy +from typing import Dict, Iterator, List, Optional, cast + +from pymilvus import DataType, MilvusClient +from pymilvus.client.constants import ConsistencyLevel + +from memgpt.agent_store.storage import StorageConnector, TableType +from memgpt.config import MemGPTConfig +from memgpt.constants import MAX_EMBEDDING_DIM +from memgpt.data_types import Passage, Record, RecordType +from memgpt.utils import datetime_to_timestamp, printd, timestamp_to_datetime + + +class MilvusStorageConnector(StorageConnector): + """Storage via Milvus""" + + def __init__(self, table_type: str, config: MemGPTConfig, user_id, agent_id=None): + super().__init__(table_type=table_type, config=config, user_id=user_id, agent_id=agent_id) + + assert table_type in [TableType.ARCHIVAL_MEMORY, TableType.PASSAGES], "Milvus only supports archival memory" + if config.archival_storage_uri: + self.client = MilvusClient(uri=config.archival_storage_uri) + self._create_collection() + else: + raise ValueError("Please set `archival_storage_uri` in the config file when using Milvus.") + + # need to be converted to strings + self.uuid_fields = ["id", "user_id", "agent_id", "source_id", "doc_id"] + + def _create_collection(self): + schema = MilvusClient.create_schema( + auto_id=False, + enable_dynamic_field=True, + ) + schema.add_field(field_name="id", datatype=DataType.VARCHAR, is_primary=True, max_length=65_535) + schema.add_field(field_name="text", datatype=DataType.VARCHAR, is_primary=False, max_length=65_535) + schema.add_field(field_name="embedding", datatype=DataType.FLOAT_VECTOR, dim=MAX_EMBEDDING_DIM) + index_params = self.client.prepare_index_params() + index_params.add_index(field_name="id") + index_params.add_index(field_name="embedding", index_type="AUTOINDEX", metric_type="IP") + self.client.create_collection( + collection_name=self.table_name, schema=schema, index_params=index_params, consistency_level=ConsistencyLevel.Strong + ) + + def get_milvus_filter(self, filters: Optional[Dict] = {}) -> str: + filter_conditions = {**self.filters, **filters} if filters is not None else self.filters + if not filter_conditions: + return "" + conditions = [] + for key, value in filter_conditions.items(): + if key in self.uuid_fields or isinstance(key, str): + condition = f'({key} == "{value}")' + else: + condition = f"({key} == {value})" + conditions.append(condition) + filter_expr = " and ".join(conditions) + if len(conditions) == 1: + filter_expr = filter_expr[1:-1] + return filter_expr + + def get_all_paginated(self, filters: Optional[Dict] = {}, page_size: int = 1000) -> Iterator[List[RecordType]]: + if not self.client.has_collection(collection_name=self.table_name): + yield [] + filter_expr = self.get_milvus_filter(filters) + offset = 0 + while True: + # Retrieve a chunk of records with the given page_size + query_res = self.client.query( + collection_name=self.table_name, + filter=filter_expr, + offset=offset, + limit=page_size, + ) + if not query_res: + break + # Yield a list of Record objects converted from the chunk + yield self._list_to_records(query_res) + + # Increment the offset to get the next chunk in the next iteration + offset += page_size + + def get_all(self, filters: Optional[Dict] = {}, limit=None) -> List[RecordType]: + if not self.client.has_collection(collection_name=self.table_name): + return [] + filter_expr = self.get_milvus_filter(filters) + query_res = self.client.query( + collection_name=self.table_name, + filter=filter_expr, + limit=limit, + ) + return self._list_to_records(query_res) + + def get(self, id: uuid.UUID) -> Optional[RecordType]: + res = self.client.get(collection_name=self.table_name, ids=str(id)) + return self._list_to_records(res)[0] if res else None + + def size(self, filters: Optional[Dict] = {}) -> int: + if not self.client.has_collection(collection_name=self.table_name): + return 0 + filter_expr = self.get_milvus_filter(filters) + count_expr = "count(*)" + query_res = self.client.query( + collection_name=self.table_name, + filter=filter_expr, + output_fields=[count_expr], + ) + doc_num = query_res[0][count_expr] + return doc_num + + def insert(self, record: RecordType): + self.insert_many([record]) + + def insert_many(self, records: List[RecordType], show_progress=False): + if not records: + return + + # Milvus lite currently does not support upsert, so we delete and insert instead + # self.client.upsert(collection_name=self.table_name, data=self._records_to_list(records)) + ids = [str(record.id) for record in records] + self.client.delete(collection_name=self.table_name, ids=ids) + data = self._records_to_list(records) + self.client.insert(collection_name=self.table_name, data=data) + + def query(self, query: str, query_vec: List[float], top_k: int = 10, filters: Optional[Dict] = {}) -> List[RecordType]: + if not self.client.has_collection(self.table_name): + return [] + search_res = self.client.search( + collection_name=self.table_name, data=[query_vec], filter=self.get_milvus_filter(filters), limit=top_k, output_fields=["*"] + )[0] + entity_res = [res["entity"] for res in search_res] + return self._list_to_records(entity_res) + + def delete_table(self): + self.client.drop_collection(collection_name=self.table_name) + + def delete(self, filters: Optional[Dict] = {}): + if not self.client.has_collection(collection_name=self.table_name): + return + filter_expr = self.get_milvus_filter(filters) + self.client.delete(collection_name=self.table_name, filter=filter_expr) + + def save(self): + # save to persistence file (nothing needs to be done) + printd("Saving milvus") + + def _records_to_list(self, records: List[Record]) -> List[Dict]: + if records == []: + return [] + assert all(isinstance(r, Passage) for r in records) + record_list = [] + records = list(set(records)) + for record in records: + record_vars = deepcopy(vars(record)) + _id = record_vars.pop("id") + text = record_vars.pop("text", "") + embedding = record_vars.pop("embedding") + record_metadata = record_vars.pop("metadata_", None) or {} + if "created_at" in record_vars: + record_vars["created_at"] = datetime_to_timestamp(record_vars["created_at"]) + record_dict = {key: value for key, value in record_vars.items() if value is not None} + record_dict = { + **record_dict, + **record_metadata, + "id": str(_id), + "text": text, + "embedding": embedding, + } + for key, value in record_dict.items(): + if key in self.uuid_fields: + record_dict[key] = str(value) + record_list.append(record_dict) + return record_list + + def _list_to_records(self, query_res: List[Dict]) -> List[RecordType]: + records = [] + for res_dict in query_res: + _id = res_dict.pop("id") + embedding = res_dict.pop("embedding") + text = res_dict.pop("text") + metadata = deepcopy(res_dict) + for key, value in metadata.items(): + if key in self.uuid_fields: + metadata[key] = uuid.UUID(value) + elif key == "created_at": + metadata[key] = timestamp_to_datetime(value) + records.append( + cast( + RecordType, + self.type( + text=text, + embedding=embedding, + id=uuid.UUID(_id), + **metadata, + ), + ) + ) + return records diff --git a/memgpt/agent_store/storage.py b/memgpt/agent_store/storage.py index a780a8ef..31d6e4d3 100644 --- a/memgpt/agent_store/storage.py +++ b/memgpt/agent_store/storage.py @@ -110,7 +110,10 @@ class StorageConnector: from memgpt.agent_store.db import SQLLiteStorageConnector return SQLLiteStorageConnector(table_type, config, user_id, agent_id) + elif storage_type == "milvus": + from memgpt.agent_store.milvus import MilvusStorageConnector + return MilvusStorageConnector(table_type, config, user_id, agent_id) else: raise NotImplementedError(f"Storage type {storage_type} not implemented") diff --git a/memgpt/cli/cli_config.py b/memgpt/cli/cli_config.py index 86d3da36..94bec9ab 100644 --- a/memgpt/cli/cli_config.py +++ b/memgpt/cli/cli_config.py @@ -877,7 +877,7 @@ def configure_embedding_endpoint(config: MemGPTConfig, credentials: MemGPTCreden def configure_archival_storage(config: MemGPTConfig, credentials: MemGPTCredentials): # Configure archival storage backend - archival_storage_options = ["postgres", "chroma"] + archival_storage_options = ["postgres", "chroma", "milvus"] archival_storage_type = questionary.select( "Select storage backend for archival data:", archival_storage_options, default=config.archival_storage_type ).ask() @@ -914,6 +914,13 @@ def configure_archival_storage(config: MemGPTConfig, credentials: MemGPTCredenti if chroma_type == "persistent": archival_storage_path = os.path.join(MEMGPT_DIR, "chroma") + if archival_storage_type == "milvus": + default_milvus_uri = archival_storage_path = os.path.join(MEMGPT_DIR, "milvus.db") + archival_storage_uri = questionary.text( + f"Enter the Milvus connection URI (Default: {default_milvus_uri}):", default=default_milvus_uri + ).ask() + if archival_storage_uri is None: + raise KeyboardInterrupt return archival_storage_type, archival_storage_uri, archival_storage_path # TODO: allow configuring embedding model diff --git a/poetry.lock b/poetry.lock index 623042d1..b2fcde98 100644 --- a/poetry.lock +++ b/poetry.lock @@ -996,6 +996,27 @@ files = [ {file = "docx2txt-0.8.tar.gz", hash = "sha256:2c06d98d7cfe2d3947e5760a57d924e3ff07745b379c8737723922e7009236e5"}, ] +[[package]] +name = "environs" +version = "9.5.0" +description = "simplified environment variable parsing" +optional = true +python-versions = ">=3.6" +files = [ + {file = "environs-9.5.0-py2.py3-none-any.whl", hash = "sha256:1e549569a3de49c05f856f40bce86979e7d5ffbbc4398e7f338574c220189124"}, + {file = "environs-9.5.0.tar.gz", hash = "sha256:a76307b36fbe856bdca7ee9161e6c466fd7fcffc297109a118c59b54e27e30c9"}, +] + +[package.dependencies] +marshmallow = ">=3.0.0" +python-dotenv = "*" + +[package.extras] +dev = ["dj-database-url", "dj-email-url", "django-cache-url", "flake8 (==4.0.1)", "flake8-bugbear (==21.9.2)", "mypy (==0.910)", "pre-commit (>=2.4,<3.0)", "pytest", "tox"] +django = ["dj-database-url", "dj-email-url", "django-cache-url"] +lint = ["flake8 (==4.0.1)", "flake8-bugbear (==21.9.2)", "mypy (==0.910)", "pre-commit (>=2.4,<3.0)"] +tests = ["dj-database-url", "dj-email-url", "django-cache-url", "pytest"] + [[package]] name = "exceptiongroup" version = "1.2.1" @@ -1345,69 +1366,69 @@ test = ["objgraph", "psutil"] [[package]] name = "grpcio" -version = "1.62.2" +version = "1.60.0" description = "HTTP/2-based RPC framework" optional = false python-versions = ">=3.7" files = [ - {file = "grpcio-1.62.2-cp310-cp310-linux_armv7l.whl", hash = "sha256:66344ea741124c38588a664237ac2fa16dfd226964cca23ddc96bd4accccbde5"}, - {file = "grpcio-1.62.2-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:5dab7ac2c1e7cb6179c6bfad6b63174851102cbe0682294e6b1d6f0981ad7138"}, - {file = "grpcio-1.62.2-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:3ad00f3f0718894749d5a8bb0fa125a7980a2f49523731a9b1fabf2b3522aa43"}, - {file = "grpcio-1.62.2-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2e72ddfee62430ea80133d2cbe788e0d06b12f865765cb24a40009668bd8ea05"}, - {file = "grpcio-1.62.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:53d3a59a10af4c2558a8e563aed9f256259d2992ae0d3037817b2155f0341de1"}, - {file = "grpcio-1.62.2-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:a1511a303f8074f67af4119275b4f954189e8313541da7b88b1b3a71425cdb10"}, - {file = "grpcio-1.62.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b94d41b7412ef149743fbc3178e59d95228a7064c5ab4760ae82b562bdffb199"}, - {file = "grpcio-1.62.2-cp310-cp310-win32.whl", hash = "sha256:a75af2fc7cb1fe25785be7bed1ab18cef959a376cdae7c6870184307614caa3f"}, - {file = "grpcio-1.62.2-cp310-cp310-win_amd64.whl", hash = "sha256:80407bc007754f108dc2061e37480238b0dc1952c855e86a4fc283501ee6bb5d"}, - {file = "grpcio-1.62.2-cp311-cp311-linux_armv7l.whl", hash = "sha256:c1624aa686d4b36790ed1c2e2306cc3498778dffaf7b8dd47066cf819028c3ad"}, - {file = "grpcio-1.62.2-cp311-cp311-macosx_10_10_universal2.whl", hash = "sha256:1c1bb80299bdef33309dff03932264636450c8fdb142ea39f47e06a7153d3063"}, - {file = "grpcio-1.62.2-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:db068bbc9b1fa16479a82e1ecf172a93874540cb84be69f0b9cb9b7ac3c82670"}, - {file = "grpcio-1.62.2-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e2cc8a308780edbe2c4913d6a49dbdb5befacdf72d489a368566be44cadaef1a"}, - {file = "grpcio-1.62.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d0695ae31a89f1a8fc8256050329a91a9995b549a88619263a594ca31b76d756"}, - {file = "grpcio-1.62.2-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:88b4f9ee77191dcdd8810241e89340a12cbe050be3e0d5f2f091c15571cd3930"}, - {file = "grpcio-1.62.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:2a0204532aa2f1afd467024b02b4069246320405bc18abec7babab03e2644e75"}, - {file = "grpcio-1.62.2-cp311-cp311-win32.whl", hash = "sha256:6e784f60e575a0de554ef9251cbc2ceb8790914fe324f11e28450047f264ee6f"}, - {file = "grpcio-1.62.2-cp311-cp311-win_amd64.whl", hash = "sha256:112eaa7865dd9e6d7c0556c8b04ae3c3a2dc35d62ad3373ab7f6a562d8199200"}, - {file = "grpcio-1.62.2-cp312-cp312-linux_armv7l.whl", hash = "sha256:65034473fc09628a02fb85f26e73885cf1ed39ebd9cf270247b38689ff5942c5"}, - {file = "grpcio-1.62.2-cp312-cp312-macosx_10_10_universal2.whl", hash = "sha256:d2c1771d0ee3cf72d69bb5e82c6a82f27fbd504c8c782575eddb7839729fbaad"}, - {file = "grpcio-1.62.2-cp312-cp312-manylinux_2_17_aarch64.whl", hash = "sha256:3abe6838196da518863b5d549938ce3159d809218936851b395b09cad9b5d64a"}, - {file = "grpcio-1.62.2-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c5ffeb269f10cedb4f33142b89a061acda9f672fd1357331dbfd043422c94e9e"}, - {file = "grpcio-1.62.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:404d3b4b6b142b99ba1cff0b2177d26b623101ea2ce51c25ef6e53d9d0d87bcc"}, - {file = "grpcio-1.62.2-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:262cda97efdabb20853d3b5a4c546a535347c14b64c017f628ca0cc7fa780cc6"}, - {file = "grpcio-1.62.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:17708db5b11b966373e21519c4c73e5a750555f02fde82276ea2a267077c68ad"}, - {file = "grpcio-1.62.2-cp312-cp312-win32.whl", hash = "sha256:b7ec9e2f8ffc8436f6b642a10019fc513722858f295f7efc28de135d336ac189"}, - {file = "grpcio-1.62.2-cp312-cp312-win_amd64.whl", hash = "sha256:aa787b83a3cd5e482e5c79be030e2b4a122ecc6c5c6c4c42a023a2b581fdf17b"}, - {file = "grpcio-1.62.2-cp37-cp37m-linux_armv7l.whl", hash = "sha256:cfd23ad29bfa13fd4188433b0e250f84ec2c8ba66b14a9877e8bce05b524cf54"}, - {file = "grpcio-1.62.2-cp37-cp37m-macosx_10_10_universal2.whl", hash = "sha256:af15e9efa4d776dfcecd1d083f3ccfb04f876d613e90ef8432432efbeeac689d"}, - {file = "grpcio-1.62.2-cp37-cp37m-manylinux_2_17_aarch64.whl", hash = "sha256:f4aa94361bb5141a45ca9187464ae81a92a2a135ce2800b2203134f7a1a1d479"}, - {file = "grpcio-1.62.2-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:82af3613a219512a28ee5c95578eb38d44dd03bca02fd918aa05603c41018051"}, - {file = "grpcio-1.62.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:55ddaf53474e8caeb29eb03e3202f9d827ad3110475a21245f3c7712022882a9"}, - {file = "grpcio-1.62.2-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:c79b518c56dddeec79e5500a53d8a4db90da995dfe1738c3ac57fe46348be049"}, - {file = "grpcio-1.62.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:a5eb4844e5e60bf2c446ef38c5b40d7752c6effdee882f716eb57ae87255d20a"}, - {file = "grpcio-1.62.2-cp37-cp37m-win_amd64.whl", hash = "sha256:aaae70364a2d1fb238afd6cc9fcb10442b66e397fd559d3f0968d28cc3ac929c"}, - {file = "grpcio-1.62.2-cp38-cp38-linux_armv7l.whl", hash = "sha256:1bcfe5070e4406f489e39325b76caeadab28c32bf9252d3ae960c79935a4cc36"}, - {file = "grpcio-1.62.2-cp38-cp38-macosx_10_10_universal2.whl", hash = "sha256:da6a7b6b938c15fa0f0568e482efaae9c3af31963eec2da4ff13a6d8ec2888e4"}, - {file = "grpcio-1.62.2-cp38-cp38-manylinux_2_17_aarch64.whl", hash = "sha256:41955b641c34db7d84db8d306937b72bc4968eef1c401bea73081a8d6c3d8033"}, - {file = "grpcio-1.62.2-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c772f225483905f675cb36a025969eef9712f4698364ecd3a63093760deea1bc"}, - {file = "grpcio-1.62.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:07ce1f775d37ca18c7a141300e5b71539690efa1f51fe17f812ca85b5e73262f"}, - {file = "grpcio-1.62.2-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:26f415f40f4a93579fd648f48dca1c13dfacdfd0290f4a30f9b9aeb745026811"}, - {file = "grpcio-1.62.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:db707e3685ff16fc1eccad68527d072ac8bdd2e390f6daa97bc394ea7de4acea"}, - {file = "grpcio-1.62.2-cp38-cp38-win32.whl", hash = "sha256:589ea8e75de5fd6df387de53af6c9189c5231e212b9aa306b6b0d4f07520fbb9"}, - {file = "grpcio-1.62.2-cp38-cp38-win_amd64.whl", hash = "sha256:3c3ed41f4d7a3aabf0f01ecc70d6b5d00ce1800d4af652a549de3f7cf35c4abd"}, - {file = "grpcio-1.62.2-cp39-cp39-linux_armv7l.whl", hash = "sha256:162ccf61499c893831b8437120600290a99c0bc1ce7b51f2c8d21ec87ff6af8b"}, - {file = "grpcio-1.62.2-cp39-cp39-macosx_10_10_universal2.whl", hash = "sha256:f27246d7da7d7e3bd8612f63785a7b0c39a244cf14b8dd9dd2f2fab939f2d7f1"}, - {file = "grpcio-1.62.2-cp39-cp39-manylinux_2_17_aarch64.whl", hash = "sha256:2507006c8a478f19e99b6fe36a2464696b89d40d88f34e4b709abe57e1337467"}, - {file = "grpcio-1.62.2-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a90ac47a8ce934e2c8d71e317d2f9e7e6aaceb2d199de940ce2c2eb611b8c0f4"}, - {file = "grpcio-1.62.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:99701979bcaaa7de8d5f60476487c5df8f27483624f1f7e300ff4669ee44d1f2"}, - {file = "grpcio-1.62.2-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:af7dc3f7a44f10863b1b0ecab4078f0a00f561aae1edbd01fd03ad4dcf61c9e9"}, - {file = "grpcio-1.62.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:fa63245271920786f4cb44dcada4983a3516be8f470924528cf658731864c14b"}, - {file = "grpcio-1.62.2-cp39-cp39-win32.whl", hash = "sha256:c6ad9c39704256ed91a1cffc1379d63f7d0278d6a0bad06b0330f5d30291e3a3"}, - {file = "grpcio-1.62.2-cp39-cp39-win_amd64.whl", hash = "sha256:16da954692fd61aa4941fbeda405a756cd96b97b5d95ca58a92547bba2c1624f"}, - {file = "grpcio-1.62.2.tar.gz", hash = "sha256:c77618071d96b7a8be2c10701a98537823b9c65ba256c0b9067e0594cdbd954d"}, + {file = "grpcio-1.60.0-cp310-cp310-linux_armv7l.whl", hash = "sha256:d020cfa595d1f8f5c6b343530cd3ca16ae5aefdd1e832b777f9f0eb105f5b139"}, + {file = "grpcio-1.60.0-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:b98f43fcdb16172dec5f4b49f2fece4b16a99fd284d81c6bbac1b3b69fcbe0ff"}, + {file = "grpcio-1.60.0-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:20e7a4f7ded59097c84059d28230907cd97130fa74f4a8bfd1d8e5ba18c81491"}, + {file = "grpcio-1.60.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:452ca5b4afed30e7274445dd9b441a35ece656ec1600b77fff8c216fdf07df43"}, + {file = "grpcio-1.60.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:43e636dc2ce9ece583b3e2ca41df5c983f4302eabc6d5f9cd04f0562ee8ec1ae"}, + {file = "grpcio-1.60.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:6e306b97966369b889985a562ede9d99180def39ad42c8014628dd3cc343f508"}, + {file = "grpcio-1.60.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:f897c3b127532e6befdcf961c415c97f320d45614daf84deba0a54e64ea2457b"}, + {file = "grpcio-1.60.0-cp310-cp310-win32.whl", hash = "sha256:b87efe4a380887425bb15f220079aa8336276398dc33fce38c64d278164f963d"}, + {file = "grpcio-1.60.0-cp310-cp310-win_amd64.whl", hash = "sha256:a9c7b71211f066908e518a2ef7a5e211670761651039f0d6a80d8d40054047df"}, + {file = "grpcio-1.60.0-cp311-cp311-linux_armv7l.whl", hash = "sha256:fb464479934778d7cc5baf463d959d361954d6533ad34c3a4f1d267e86ee25fd"}, + {file = "grpcio-1.60.0-cp311-cp311-macosx_10_10_universal2.whl", hash = "sha256:4b44d7e39964e808b071714666a812049765b26b3ea48c4434a3b317bac82f14"}, + {file = "grpcio-1.60.0-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:90bdd76b3f04bdb21de5398b8a7c629676c81dfac290f5f19883857e9371d28c"}, + {file = "grpcio-1.60.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:91229d7203f1ef0ab420c9b53fe2ca5c1fbeb34f69b3bc1b5089466237a4a134"}, + {file = "grpcio-1.60.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3b36a2c6d4920ba88fa98075fdd58ff94ebeb8acc1215ae07d01a418af4c0253"}, + {file = "grpcio-1.60.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:297eef542156d6b15174a1231c2493ea9ea54af8d016b8ca7d5d9cc65cfcc444"}, + {file = "grpcio-1.60.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:87c9224acba0ad8bacddf427a1c2772e17ce50b3042a789547af27099c5f751d"}, + {file = "grpcio-1.60.0-cp311-cp311-win32.whl", hash = "sha256:95ae3e8e2c1b9bf671817f86f155c5da7d49a2289c5cf27a319458c3e025c320"}, + {file = "grpcio-1.60.0-cp311-cp311-win_amd64.whl", hash = "sha256:467a7d31554892eed2aa6c2d47ded1079fc40ea0b9601d9f79204afa8902274b"}, + {file = "grpcio-1.60.0-cp312-cp312-linux_armv7l.whl", hash = "sha256:a7152fa6e597c20cb97923407cf0934e14224af42c2b8d915f48bc3ad2d9ac18"}, + {file = "grpcio-1.60.0-cp312-cp312-macosx_10_10_universal2.whl", hash = "sha256:7db16dd4ea1b05ada504f08d0dca1cd9b926bed3770f50e715d087c6f00ad748"}, + {file = "grpcio-1.60.0-cp312-cp312-manylinux_2_17_aarch64.whl", hash = "sha256:b0571a5aef36ba9177e262dc88a9240c866d903a62799e44fd4aae3f9a2ec17e"}, + {file = "grpcio-1.60.0-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6fd9584bf1bccdfff1512719316efa77be235469e1e3295dce64538c4773840b"}, + {file = "grpcio-1.60.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d6a478581b1a1a8fdf3318ecb5f4d0cda41cacdffe2b527c23707c9c1b8fdb55"}, + {file = "grpcio-1.60.0-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:77c8a317f0fd5a0a2be8ed5cbe5341537d5c00bb79b3bb27ba7c5378ba77dbca"}, + {file = "grpcio-1.60.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:1c30bb23a41df95109db130a6cc1b974844300ae2e5d68dd4947aacba5985aa5"}, + {file = "grpcio-1.60.0-cp312-cp312-win32.whl", hash = "sha256:2aef56e85901c2397bd557c5ba514f84de1f0ae5dd132f5d5fed042858115951"}, + {file = "grpcio-1.60.0-cp312-cp312-win_amd64.whl", hash = "sha256:e381fe0c2aa6c03b056ad8f52f8efca7be29fb4d9ae2f8873520843b6039612a"}, + {file = "grpcio-1.60.0-cp37-cp37m-linux_armv7l.whl", hash = "sha256:92f88ca1b956eb8427a11bb8b4a0c0b2b03377235fc5102cb05e533b8693a415"}, + {file = "grpcio-1.60.0-cp37-cp37m-macosx_10_10_universal2.whl", hash = "sha256:e278eafb406f7e1b1b637c2cf51d3ad45883bb5bd1ca56bc05e4fc135dfdaa65"}, + {file = "grpcio-1.60.0-cp37-cp37m-manylinux_2_17_aarch64.whl", hash = "sha256:a48edde788b99214613e440fce495bbe2b1e142a7f214cce9e0832146c41e324"}, + {file = "grpcio-1.60.0-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:de2ad69c9a094bf37c1102b5744c9aec6cf74d2b635558b779085d0263166454"}, + {file = "grpcio-1.60.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:073f959c6f570797272f4ee9464a9997eaf1e98c27cb680225b82b53390d61e6"}, + {file = "grpcio-1.60.0-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:c826f93050c73e7769806f92e601e0efdb83ec8d7c76ddf45d514fee54e8e619"}, + {file = "grpcio-1.60.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:9e30be89a75ee66aec7f9e60086fadb37ff8c0ba49a022887c28c134341f7179"}, + {file = "grpcio-1.60.0-cp37-cp37m-win_amd64.whl", hash = "sha256:b0fb2d4801546598ac5cd18e3ec79c1a9af8b8f2a86283c55a5337c5aeca4b1b"}, + {file = "grpcio-1.60.0-cp38-cp38-linux_armv7l.whl", hash = "sha256:9073513ec380434eb8d21970e1ab3161041de121f4018bbed3146839451a6d8e"}, + {file = "grpcio-1.60.0-cp38-cp38-macosx_10_10_universal2.whl", hash = "sha256:74d7d9fa97809c5b892449b28a65ec2bfa458a4735ddad46074f9f7d9550ad13"}, + {file = "grpcio-1.60.0-cp38-cp38-manylinux_2_17_aarch64.whl", hash = "sha256:1434ca77d6fed4ea312901122dc8da6c4389738bf5788f43efb19a838ac03ead"}, + {file = "grpcio-1.60.0-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e61e76020e0c332a98290323ecfec721c9544f5b739fab925b6e8cbe1944cf19"}, + {file = "grpcio-1.60.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:675997222f2e2f22928fbba640824aebd43791116034f62006e19730715166c0"}, + {file = "grpcio-1.60.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:5208a57eae445ae84a219dfd8b56e04313445d146873117b5fa75f3245bc1390"}, + {file = "grpcio-1.60.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:428d699c8553c27e98f4d29fdc0f0edc50e9a8a7590bfd294d2edb0da7be3629"}, + {file = "grpcio-1.60.0-cp38-cp38-win32.whl", hash = "sha256:83f2292ae292ed5a47cdcb9821039ca8e88902923198f2193f13959360c01860"}, + {file = "grpcio-1.60.0-cp38-cp38-win_amd64.whl", hash = "sha256:705a68a973c4c76db5d369ed573fec3367d7d196673fa86614b33d8c8e9ebb08"}, + {file = "grpcio-1.60.0-cp39-cp39-linux_armv7l.whl", hash = "sha256:c193109ca4070cdcaa6eff00fdb5a56233dc7610216d58fb81638f89f02e4968"}, + {file = "grpcio-1.60.0-cp39-cp39-macosx_10_10_universal2.whl", hash = "sha256:676e4a44e740deaba0f4d95ba1d8c5c89a2fcc43d02c39f69450b1fa19d39590"}, + {file = "grpcio-1.60.0-cp39-cp39-manylinux_2_17_aarch64.whl", hash = "sha256:5ff21e000ff2f658430bde5288cb1ac440ff15c0d7d18b5fb222f941b46cb0d2"}, + {file = "grpcio-1.60.0-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4c86343cf9ff7b2514dd229bdd88ebba760bd8973dac192ae687ff75e39ebfab"}, + {file = "grpcio-1.60.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0fd3b3968ffe7643144580f260f04d39d869fcc2cddb745deef078b09fd2b328"}, + {file = "grpcio-1.60.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:30943b9530fe3620e3b195c03130396cd0ee3a0d10a66c1bee715d1819001eaf"}, + {file = "grpcio-1.60.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:b10241250cb77657ab315270b064a6c7f1add58af94befa20687e7c8d8603ae6"}, + {file = "grpcio-1.60.0-cp39-cp39-win32.whl", hash = "sha256:79a050889eb8d57a93ed21d9585bb63fca881666fc709f5d9f7f9372f5e7fd03"}, + {file = "grpcio-1.60.0-cp39-cp39-win_amd64.whl", hash = "sha256:8a97a681e82bc11a42d4372fe57898d270a2707f36c45c6676e49ce0d5c41353"}, + {file = "grpcio-1.60.0.tar.gz", hash = "sha256:2199165a1affb666aa24adf0c97436686d0a61bc5fc113c037701fb7c7fceb96"}, ] [package.extras] -protobuf = ["grpcio-tools (>=1.62.2)"] +protobuf = ["grpcio-tools (>=1.60.0)"] [[package]] name = "h11" @@ -2306,6 +2327,18 @@ files = [ {file = "mdurl-0.1.2.tar.gz", hash = "sha256:bb413d29f5eea38f31dd4754dd7377d4465116fb207585f97bf925588687c1ba"}, ] +[[package]] +name = "milvus-lite" +version = "2.4.5" +description = "A lightweight version of Milvus wrapped with Python." +optional = true +python-versions = ">=3.7" +files = [ + {file = "milvus_lite-2.4.5-py3-none-macosx_10_9_x86_64.whl", hash = "sha256:343d5f4df801def14eb711048de8fdf24a216704e591c261cd0827770772a7ee"}, + {file = "milvus_lite-2.4.5-py3-none-macosx_11_0_arm64.whl", hash = "sha256:73f154a82d60f933e2c991b53dd795683b196c0f5b6d36f8464422bdedddb857"}, + {file = "milvus_lite-2.4.5-py3-none-manylinux2014_x86_64.whl", hash = "sha256:22d70c87494442882b3fceeba38ef131d1186c9b9bc363fb9550e8494b2fdaba"}, +] + [[package]] name = "minijinja" version = "1.0.16" @@ -3995,6 +4028,31 @@ benchmarks = ["pytest-benchmark"] tests = ["duckdb", "ml_dtypes", "pandas (>=1.4,<2.1)", "polars[pandas,pyarrow]", "pytest", "semver", "tensorflow", "tqdm"] torch = ["torch"] +[[package]] +name = "pymilvus" +version = "2.4.3" +description = "Python Sdk for Milvus" +optional = true +python-versions = ">=3.8" +files = [ + {file = "pymilvus-2.4.3-py3-none-any.whl", hash = "sha256:38239e89f8d739f665141d0b80908990b5f59681e889e135c234a4a45669a5c8"}, + {file = "pymilvus-2.4.3.tar.gz", hash = "sha256:703ac29296cdce03d6dc2aaebbe959e57745c141a94150e371dc36c61c226cc1"}, +] + +[package.dependencies] +environs = "<=9.5.0" +grpcio = ">=1.49.1,<=1.63.0" +milvus-lite = ">=2.4.0,<2.5.0" +pandas = ">=1.2.4" +protobuf = ">=3.20.0" +setuptools = ">=67" +ujson = ">=2.0.0" + +[package.extras] +bulk-writer = ["azure-storage-blob", "minio (>=7.0.0)", "pyarrow (>=12.0.0)", "requests"] +dev = ["black", "grpcio (==1.62.2)", "grpcio-testing (==1.62.2)", "grpcio-tools (==1.62.2)", "pytest (>=5.3.4)", "pytest-cov (>=2.8.1)", "pytest-timeout (>=1.3.4)", "ruff (>0.4.0)"] +model = ["milvus-model (>=0.1.0)"] + [[package]] name = "pypdf" version = "4.2.0" @@ -4256,6 +4314,7 @@ files = [ {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"}, {file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"}, {file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"}, + {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a08c6f0fe150303c1c6b71ebcd7213c2858041a7e01975da3a99aed1e7a378ef"}, {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"}, {file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"}, {file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"}, @@ -5513,6 +5572,93 @@ files = [ {file = "tzdata-2024.1.tar.gz", hash = "sha256:2674120f8d891909751c38abcdfd386ac0a5a1127954fbc332af6b5ceae07efd"}, ] +[[package]] +name = "ujson" +version = "5.10.0" +description = "Ultra fast JSON encoder and decoder for Python" +optional = true +python-versions = ">=3.8" +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"}, +] + [[package]] name = "urllib3" version = "2.2.1" @@ -6133,10 +6279,11 @@ testing = ["big-O", "jaraco.functools", "jaraco.itertools", "more-itertools", "p autogen = ["pyautogen"] dev = ["autoflake", "black", "datasets", "isort", "pexpect", "pre-commit", "pyright", "pytest", "pytest-asyncio", "pytest-order"] local = ["llama-index-embeddings-huggingface"] +milvus = ["pymilvus"] postgres = ["pg8000", "pgvector"] server = ["fastapi", "uvicorn", "websockets"] [metadata] lock-version = "2.0" python-versions = "<3.13,>=3.10" -content-hash = "03cc31f8b43801bf2e932b43eaaf0ed14d85bd905cf329a55392195bfdd76da3" +content-hash = "3b09972bb581ee7efa283cf4d70be0ad2efd27314d974d7635f0c1f35a4b38f5" diff --git a/pyproject.toml b/pyproject.toml index 27f22dac..0e552ee4 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -46,6 +46,7 @@ docx2txt = "^0.8" sqlalchemy = "^2.0.25" pexpect = {version = "^4.9.0", optional = true} pyright = {version = "^1.1.347", optional = true} +pymilvus = {version ="^2.4.3", optional = true} python-box = "^7.1.1" sqlmodel = "^0.0.16" autoflake = {version = "^2.3.0", optional = true} @@ -65,6 +66,7 @@ isort = { version = "^5.13.2", optional = true } [tool.poetry.extras] local = ["llama-index-embeddings-huggingface"] postgres = ["pgvector", "pg8000", "psycopg2-binary"] +milvus = ["pymilvus"] dev = ["pytest", "pytest-asyncio", "pexpect", "black", "pre-commit", "datasets", "pyright", "pytest-order", "autoflake", "isort"] server = ["websockets", "fastapi", "uvicorn"] autogen = ["pyautogen"] diff --git a/tests/test_load_archival.py b/tests/test_load_archival.py index ba5679c6..19338a49 100644 --- a/tests/test_load_archival.py +++ b/tests/test_load_archival.py @@ -38,7 +38,7 @@ def recreate_declarative_base(): @pytest.mark.parametrize("metadata_storage_connector", ["sqlite", "postgres"]) -@pytest.mark.parametrize("passage_storage_connector", ["chroma", "postgres"]) +@pytest.mark.parametrize("passage_storage_connector", ["chroma", "postgres", "milvus"]) def test_load_directory( metadata_storage_connector, passage_storage_connector, @@ -73,6 +73,10 @@ def test_load_directory( elif passage_storage_connector == "chroma": print("testing chroma passage storage") # nothing to do (should be config defaults) + elif passage_storage_connector == "milvus": + print("Testing Milvus passage storage") + TEST_MEMGPT_CONFIG.archival_storage_type = "milvus" + TEST_MEMGPT_CONFIG.archival_storage_uri = "./milvus.db" else: raise NotImplementedError(f"Storage type {passage_storage_connector} not implemented") TEST_MEMGPT_CONFIG.save() diff --git a/tests/test_storage.py b/tests/test_storage.py index 3fda760f..6933ab42 100644 --- a/tests/test_storage.py +++ b/tests/test_storage.py @@ -106,7 +106,7 @@ def recreate_declarative_base(): Base.metadata.clear() -@pytest.mark.parametrize("storage_connector", ["postgres", "chroma", "sqlite"]) +@pytest.mark.parametrize("storage_connector", ["postgres", "chroma", "sqlite", "milvus"]) # @pytest.mark.parametrize("storage_connector", ["sqlite", "chroma"]) # @pytest.mark.parametrize("storage_connector", ["postgres"]) @pytest.mark.parametrize("table_type", [TableType.RECALL_MEMORY, TableType.ARCHIVAL_MEMORY]) @@ -160,7 +160,12 @@ def test_storage( print("Skipping test, sqlite only supported for recall memory") return TEST_MEMGPT_CONFIG.recall_storage_type = "sqlite" - + if storage_connector == "milvus": + if table_type == TableType.RECALL_MEMORY: + print("Skipping test, Milvus only supports archival memory") + return + TEST_MEMGPT_CONFIG.archival_storage_type = "milvus" + TEST_MEMGPT_CONFIG.archival_storage_uri = "./milvus.db" # get embedding model embed_model = None if os.getenv("OPENAI_API_KEY"):