File size: 5,477 Bytes
f3d315e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
from pymilvus import MilvusClient, DataType
import numpy as np
import concurrent.futures


class MilvusManager:
    def __init__(self, milvus_uri, collection_name, create_collection, dim=128):
        self.client = MilvusClient(uri=milvus_uri)
        self.collection_name = collection_name
        if self.client.has_collection(collection_name=self.collection_name):
            self.client.load_collection(collection_name)
        self.dim = dim

        if create_collection:
            self.create_collection()
            self.create_index()


    def create_collection(self):
        if self.client.has_collection(collection_name=self.collection_name):
            self.client.drop_collection(collection_name=self.collection_name)
        schema = self.client.create_schema(
            auto_id=True,
            enable_dynamic_fields=True,
        )
        schema.add_field(field_name="pk", datatype=DataType.INT64, is_primary=True)
        schema.add_field(
            field_name="vector", datatype=DataType.FLOAT_VECTOR, dim=self.dim
        )
        schema.add_field(field_name="seq_id", datatype=DataType.INT16)
        schema.add_field(field_name="doc_id", datatype=DataType.INT64)
        schema.add_field(field_name="doc", datatype=DataType.VARCHAR, max_length=65535)

        self.client.create_collection(
            collection_name=self.collection_name, schema=schema
        )

    def create_index(self):
        self.client.release_collection(collection_name=self.collection_name)
        self.client.drop_index(
            collection_name=self.collection_name, index_name="vector"
        )
        index_params = self.client.prepare_index_params()
        index_params.add_index(
            field_name="vector",
            index_name="vector_index",
            index_type="HNSW", 
            metric_type="IP", 
            params={
                "M": 16,
                "efConstruction": 500,
            },
        )

        self.client.create_index(
            collection_name=self.collection_name, index_params=index_params, sync=True
        )

    def create_scalar_index(self):
        self.client.release_collection(collection_name=self.collection_name)

        index_params = self.client.prepare_index_params()
        index_params.add_index(
            field_name="doc_id",
            index_name="int32_index",
            index_type="INVERTED",
        )

        self.client.create_index(
            collection_name=self.collection_name, index_params=index_params, sync=True
        )

    def search(self, data, topk):
        search_params = {"metric_type": "IP", "params": {}}
        results = self.client.search(
            self.collection_name,
            data,
            limit=int(50),
            output_fields=["vector", "seq_id", "doc_id"],
            search_params=search_params,
        )
        doc_ids = set()
        for r_id in range(len(results)):
            for r in range(len(results[r_id])):
                doc_ids.add(results[r_id][r]["entity"]["doc_id"])

        scores = []

        def rerank_single_doc(doc_id, data, client, collection_name):
            doc_colbert_vecs = client.query(
                collection_name=collection_name,
                filter=f"doc_id in [{doc_id}, {doc_id + 1}]",
                output_fields=["seq_id", "vector", "doc"],
                limit=1000,
            )
            doc_vecs = np.vstack(
                [doc_colbert_vecs[i]["vector"] for i in range(len(doc_colbert_vecs))]
            )
            score = np.dot(data, doc_vecs.T).max(1).sum()
            return (score, doc_id)

        with concurrent.futures.ThreadPoolExecutor(max_workers=300) as executor:
            futures = {
                executor.submit(
                    rerank_single_doc, doc_id, data, self.client, self.collection_name
                ): doc_id
                for doc_id in doc_ids
            }
            for future in concurrent.futures.as_completed(futures):
                score, doc_id = future.result()
                scores.append((score, doc_id))

        scores.sort(key=lambda x: x[0], reverse=True)
        if len(scores) >= topk:
            return scores[:topk]
        else:
            return scores

    def insert(self, data):
        colbert_vecs = [vec for vec in data["colbert_vecs"]]
        seq_length = len(colbert_vecs)
        doc_ids = [data["doc_id"] for i in range(seq_length)]
        seq_ids = list(range(seq_length))
        docs = [""] * seq_length
        docs[0] = data["filepath"]

        self.client.insert(
            self.collection_name,
            [
                {
                    "vector": colbert_vecs[i],
                    "seq_id": seq_ids[i],
                    "doc_id": doc_ids[i],
                    "doc": docs[i],
                }
                for i in range(seq_length)
            ],
        )


    def get_images_as_doc(self, images_with_vectors:list):
        
        images_data = []

        for i in range(len(images_with_vectors)):
            data = {
                "colbert_vecs": images_with_vectors[i]["colbert_vecs"],
                "doc_id": i,
                "filepath": images_with_vectors[i]["filepath"],
            }
            images_data.append(data)

        return images_data


    def insert_images_data(self, image_data):
        data = self.get_images_as_doc(image_data)

        for i in range(len(data)):
            self.insert(data[i])