What's Changed
* Delete some third-party dependencies in https://github.com/milvus-io/milvus-lite/pull/222 https://github.com/milvus-io/milvus-lite/pull/226 https://github.com/milvus-io/milvus-lite/pull/236
* Support Android Presburger in https://github.com/milvus-io/milvus-lite/pull/229
* Support IVF_FLAT index by junjiejiangjjj in https://github.com/milvus-io/milvus-lite/pull/234
After creating the IVF_FLAT index, the index will be built when the data exceeds 10,000
example:
python
from pymilvus import MilvusClient, DataType
1. Set up a Milvus client
client = MilvusClient(
uri="./milvus_demo.db"
)
2. Create schema
2.1. Create schema
schema = MilvusClient.create_schema(
auto_id=False,
enable_dynamic_field=True,
)
2.2. Add fields to schema
schema.add_field(field_name="id", datatype=DataType.INT64, is_primary=True)
schema.add_field(field_name="vector", datatype=DataType.FLOAT_VECTOR, dim=5)
3. Create collection
client.create_collection(
collection_name="customized_setup",
schema=schema,
)
4.1. Set up the index parameters
index_params = MilvusClient.prepare_index_params()
4.2. Add an index on the vector field.
index_params.add_index(
field_name="vector",
metric_type="COSINE",
index_type="IVF_FLAT",
index_name="vector_index",
params={ "nlist": 128 }
)
4.3. Create an index file
client.create_index(
collection_name="customized_setup",
index_params=index_params
)
* Fix some bugs
New Contributors
* 982945902 made their first contribution in https://github.com/milvus-io/milvus-lite/pull/224
**Full Changelog**: https://github.com/milvus-io/milvus-lite/compare/v2.4.10...v2.4.11