[Bug]: [int8_vector] Insert failed reporting "{float_vector} field should be a INT8_VECTOR, but got a {<class 'numpy.ndarray'>} instead." when insert INT8_VECTOR through column ways

[binbinlv]

Is there an existing issue for this?

• I have searched the existing issues

Environment

- Milvus version: master-20250421-ac1e0437-amd64
- Deployment mode(standalone or cluster): both
- MQ type(rocksmq, pulsar or kafka):   all  
- SDK version(e.g. pymilvus v2.0.0rc2): 2.6.0rc115
- OS(Ubuntu or CentOS): 
- CPU/Memory: 
- GPU: 
- Others:

Current Behavior

Insert failed reporting "{float_vector} field should be a INT8_VECTOR, but got a {<class 'numpy.ndarray'>} instead." when insert INT8_VECTOR through column ways

>>> res = collection.insert([[i for i in range(nb)], vectors])
2025-04-23 16:41:26,585 [ERROR][handler]: RPC error: [batch_insert], <DataNotMatchException: (code=1, message=The Input data type is inconsistent with defined schema, {float_vector} field should be a INT8_VECTOR, but got a {<class 'numpy.ndarray'>} instead.)>, <Time:{'RPC start': '2025-04-23 16:41:26.417898', 'RPC error': '2025-04-23 16:41:26.585700'}> (decorators.py:140)
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/Users/binbin/milvus_latest_env_3.11/lib/python3.11/site-packages/pymilvus/orm/collection.py", line 518, in insert
    return conn.batch_insert(
           ^^^^^^^^^^^^^^^^^^
  File "/Users/binbin/milvus_latest_env_3.11/lib/python3.11/site-packages/pymilvus/decorators.py", line 141, in handler
    raise e from e
  File "/Users/binbin/milvus_latest_env_3.11/lib/python3.11/site-packages/pymilvus/decorators.py", line 137, in handler
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/Users/binbin/milvus_latest_env_3.11/lib/python3.11/site-packages/pymilvus/decorators.py", line 176, in handler
    return func(self, *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/binbin/milvus_latest_env_3.11/lib/python3.11/site-packages/pymilvus/decorators.py", line 116, in handler
    raise e from e
  File "/Users/binbin/milvus_latest_env_3.11/lib/python3.11/site-packages/pymilvus/decorators.py", line 86, in handler
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/Users/binbin/milvus_latest_env_3.11/lib/python3.11/site-packages/pymilvus/client/grpc_handler.py", line 685, in batch_insert
    raise err from err
  File "/Users/binbin/milvus_latest_env_3.11/lib/python3.11/site-packages/pymilvus/client/grpc_handler.py", line 668, in batch_insert
    request = self._prepare_batch_insert_request(
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/binbin/milvus_latest_env_3.11/lib/python3.11/site-packages/pymilvus/client/grpc_handler.py", line 652, in _prepare_batch_insert_request
    else Prepare.batch_insert_param(collection_name, entities, partition_name, fields_info)
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/binbin/milvus_latest_env_3.11/lib/python3.11/site-packages/pymilvus/client/prepare.py", line 773, in batch_insert_param
    return cls._parse_batch_request(request, entities, fields_info, location)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/binbin/milvus_latest_env_3.11/lib/python3.11/site-packages/pymilvus/client/prepare.py", line 749, in _parse_batch_request
    field_data = entity_helper.entity_to_field_data(
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/binbin/milvus_latest_env_3.11/lib/python3.11/site-packages/pymilvus/client/entity_helper.py", line 515, in entity_to_field_data
    raise DataNotMatchException(
pymilvus.exceptions.DataNotMatchException: <DataNotMatchException: (code=1, message=The Input data type is inconsistent with defined schema, {float_vector} field should be a INT8_VECTOR, but got a {<class 'numpy.ndarray'>} instead.)>

Expected Behavior

Insert successfully

Steps To Reproduce

from pymilvus import CollectionSchema, FieldSchema
from pymilvus import Collection
from pymilvus import connections
from pymilvus import DataType
from pymilvus import Partition
from pymilvus import utility
import json

connections.connect()
int64_field = FieldSchema(name="int64", dtype=DataType.INT64, is_primary=True)
float_vector = FieldSchema(name="float_vector", dtype=DataType.INT8_VECTOR, dim=dim)
schema = CollectionSchema(fields=[int64_field, float_vector])

import numpy as np
import random

collection = Collection("test_search_collection_binbin_tmp_0", schema=schema)

nb=10

def gen_int8_vectors(num, dim):
     raw_vectors = []
     int8_vectors = []
     for _ in range(num):
        raw_vector = [random.randint(-128, 127) for _ in range(dim)]
        raw_vectors.append(raw_vector)
        int8_vector = np.array(raw_vector, dtype=np.int8)
        int8_vectors.append(int8_vector)
     return raw_vectors, int8_vectors
vectors = gen_int8_vectors(nb, dim)[1]
res = collection.insert([[i for i in range(nb)], vectors])

Milvus Log

https://grafana-4am.zilliz.cc/explore?orgId=1&panes=%7B%22RSh%22:%7B%22datasource%22:%22vhI6Vw67k%22,%22queries%22:%5B%7B%22refId%22:%22A%22,%22expr%22:%22%7Bcluster%3D%5C%22devops%5C%22,namespace%3D%5C%22chaos-testing%5C%22,pod%3D~%5C%22master-try-binbin-kgwjl.%2A%5C%22%7D%22,%22datasource%22:%7B%22type%22:%22loki%22,%22uid%22:%22vhI6Vw67k%22%7D%7D%5D,%22range%22:%7B%22from%22:%22now-1h%22,%22to%22:%22now%22%7D%7D%7D&schemaVersion=1

Anything else?

No response

[binbinlv]

The rows insert is OK

[binbinlv]

And the column insert is OK for both BFLOAT16_VECTOR and FLOAT16_VECTOR.

for example: FLOAT16_VECTOR

>>> dim = 128
>>> int64_field = FieldSchema(name="int64", dtype=DataType.INT64, is_primary=True)
>>> float_vector = FieldSchema(name="float_vector", dtype=DataType.FLOAT16_VECTOR, dim=dim)
>>> schema = CollectionSchema(fields=[int64_field, float_vector])
>>> collection = Collection("test_search_collection_binbin_tmp_1", schema=schema)
>>> def gen_fp16_vectors(num, dim):
...    raw_vectors = []
...    fp16_vectors = []
...    for _ in range(num):
...         raw_vector = [random.random() for _ in range(dim)]
...         raw_vectors.append(raw_vector)
...         fp16_vector = np.array(raw_vector, dtype=np.float16)
...         fp16_vectors.append(fp16_vector)
...    return raw_vectors, fp16_vectors
...
>>> vectors = gen_fp16_vectors(nb, dim)[1]
>>> res = collection.insert([[i for i in range(nb)], vectors])
>>> res
(insert count: 10, delete count: 0, upsert count: 0, timestamp: 457545571062775827, success count: 10, err count: 0
>>> vectors

[binbinlv]

/assign @foxspy

[foxspy]

assign@binbinlv
fixed, please use the latest sdk

[foxspy]

/assign @binbinlv