Skip to content

Awadb

AwaDBVectorStore #

Bases: BasePydanticVectorStore

AwaDB向量存储。

在这个向量存储中，嵌入被存储在AwaDB表中。

在查询时，索引使用AwaDB查询前k个最相似的节点。

示例

pip install llama-index-vector-stores-awadb

from llama_index.vector_stores.awadb import AwaDBVectorStore

vector_store = AwaDBVectorStore(table_name="llamaindex")
Source code in llama_index/vector_stores/awadb/base.py 
 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
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
class AwaDBVectorStore(BasePydanticVectorStore):
    """AwaDB向量存储。

    在这个向量存储中，嵌入被存储在AwaDB表中。

    在查询时，索引使用AwaDB查询前k个最相似的节点。

    示例:
        `pip install llama-index-vector-stores-awadb`

        ```python
        from llama_index.vector_stores.awadb import AwaDBVectorStore

        vector_store = AwaDBVectorStore(table_name="llamaindex")
        ```"""

    flat_metadata: bool = True
    stores_text: bool = True
    DEFAULT_TABLE_NAME = "llamaindex_awadb"

    _awadb_client: Any = PrivateAttr()

    @property
    def client(self) -> Any:
        """获取AwaDB客户端。"""
        return self._awadb_client

    def __init__(
        self,
        table_name: str = DEFAULT_TABLE_NAME,
        log_and_data_dir: Optional[str] = None,
        **kwargs: Any,
    ) -> None:
        """使用AwaDB客户端进行初始化。
如果未指定table_name，
将自动创建一个随机的表名`DEFAULT_TABLE_NAME + uuid的最后一段`。

Args:
    table_name：创建的表的名称，默认为DEFAULT_TABLE_NAME。
    log_and_data_dir：可选的日志和数据的根目录。
    kwargs：将来可能的任何扩展参数。

Returns:
    无。
"""
        super().__init__()

        import_err_msg = "`awadb` package not found, please run `pip install awadb`"
        try:
            import awadb
        except ImportError:
            raise ImportError(import_err_msg)
        if log_and_data_dir is not None:
            self._awadb_client = awadb.Client(log_and_data_dir)
        else:
            self._awadb_client = awadb.Client()

        if table_name == self.DEFAULT_TABLE_NAME:
            table_name += "_"
            table_name += str(uuid.uuid4()).split("-")[-1]

        self._awadb_client.Create(table_name)

    @classmethod
    def class_name(cls) -> str:
        return "AwaDBVectorStore"

    def add(
        self,
        nodes: List[BaseNode],
        **add_kwargs: Any,
    ) -> List[str]:
        """将节点添加到AwaDB。

Args:
    节点：List[BaseNode]：带有嵌入的节点列表

Returns:
    已添加的节点ID
"""
        if not self._awadb_client:
            raise ValueError("AwaDB client not initialized")

        embeddings = []
        metadatas = []
        ids = []
        texts = []
        for node in nodes:
            embeddings.append(node.get_embedding())
            metadatas.append(
                node_to_metadata_dict(
                    node, remove_text=True, flat_metadata=self.flat_metadata
                )
            )
            ids.append(node.node_id)
            texts.append(node.get_content(metadata_mode=MetadataMode.NONE) or "")

        self._awadb_client.AddTexts(
            "embedding_text",
            "text_embedding",
            texts,
            embeddings,
            metadatas,
            is_duplicate_texts=False,
            ids=ids,
        )

        return ids

    def delete(self, ref_doc_id: str, **delete_kwargs: Any) -> None:
        """使用ref_doc_id删除节点。

Args:
    ref_doc_id（str）：要删除的文档的doc_id。

Returns:
    无
"""
        if len(ref_doc_id) == 0:
            return
        ids: List[str] = []
        ids.append(ref_doc_id)
        self._awadb_client.Delete(ids)

    def query(self, query: VectorStoreQuery, **kwargs: Any) -> VectorStoreQueryResult:
        """查询前k个最相似节点的索引。

Args:
    query：存储查询的向量

Returns:
    VectorStoreQueryResult：查询结果
"""
        meta_filters = {}
        if query.filters is not None:
            for filter in query.filters.legacy_filters():
                meta_filters[filter.key] = filter.value

        not_include_fields: Set[str] = {"text_embedding"}
        results = self._awadb_client.Search(
            query=query.query_embedding,
            topn=query.similarity_top_k,
            meta_filter=meta_filters,
            not_include_fields=not_include_fields,
        )

        nodes = []
        similarities = []
        ids = []

        for item_detail in results[0]["ResultItems"]:
            content = ""
            meta_data = {}
            node_id = ""
            for item_key in item_detail:
                if item_key == "embedding_text":
                    content = item_detail[item_key]
                    continue
                elif item_key == "_id":
                    node_id = item_detail[item_key]
                    ids.append(node_id)
                    continue
                elif item_key == "score":
                    similarities.append(item_detail[item_key])
                    continue
                meta_data[item_key] = item_detail[item_key]

            try:
                node = metadata_dict_to_node(meta_data)
                node.set_content(content)
            except Exception:
                # NOTE: deprecated legacy logic for backward compatibility
                metadata, node_info, relationships = legacy_metadata_dict_to_node(
                    meta_data
                )

                node = TextNode(
                    text=content,
                    id_=node_id,
                    metadata=metadata,
                    start_char_idx=node_info.get("start", None),
                    end_char_idx=node_info.get("end", None),
                    relationships=relationships,
                )

            nodes.append(node)

        return VectorStoreQueryResult(nodes=nodes, similarities=similarities, ids=ids)

client property #

client: Any

获取AwaDB客户端。

add #

add(nodes: List[BaseNode], **add_kwargs: Any) -> List[str]

将节点添加到AwaDB。

Returns:

Type Description
List[str]

已添加的节点ID
Source code in llama_index/vector_stores/awadb/base.py 
 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
    def add(
        self,
        nodes: List[BaseNode],
        **add_kwargs: Any,
    ) -> List[str]:
        """将节点添加到AwaDB。

Args:
    节点：List[BaseNode]：带有嵌入的节点列表

Returns:
    已添加的节点ID
"""
        if not self._awadb_client:
            raise ValueError("AwaDB client not initialized")

        embeddings = []
        metadatas = []
        ids = []
        texts = []
        for node in nodes:
            embeddings.append(node.get_embedding())
            metadatas.append(
                node_to_metadata_dict(
                    node, remove_text=True, flat_metadata=self.flat_metadata
                )
            )
            ids.append(node.node_id)
            texts.append(node.get_content(metadata_mode=MetadataMode.NONE) or "")

        self._awadb_client.AddTexts(
            "embedding_text",
            "text_embedding",
            texts,
            embeddings,
            metadatas,
            is_duplicate_texts=False,
            ids=ids,
        )

        return ids

delete #

delete(ref_doc_id: str, **delete_kwargs: Any) -> None

使用ref_doc_id删除节点。

Returns:

Type Description
None

无
Source code in llama_index/vector_stores/awadb/base.py 
136
137
138
139
140
141
142
143
144
145
146
147
148
149
    def delete(self, ref_doc_id: str, **delete_kwargs: Any) -> None:
        """使用ref_doc_id删除节点。

Args:
    ref_doc_id（str）：要删除的文档的doc_id。

Returns:
    无
"""
        if len(ref_doc_id) == 0:
            return
        ids: List[str] = []
        ids.append(ref_doc_id)
        self._awadb_client.Delete(ids)

query #

query(
    query: VectorStoreQuery, **kwargs: Any
) -> VectorStoreQueryResult

查询前k个最相似节点的索引。

Returns:

Type Description
VectorStoreQueryResult

VectorStoreQueryResult：查询结果
Source code in llama_index/vector_stores/awadb/base.py 
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
    def query(self, query: VectorStoreQuery, **kwargs: Any) -> VectorStoreQueryResult:
        """查询前k个最相似节点的索引。

Args:
    query：存储查询的向量

Returns:
    VectorStoreQueryResult：查询结果
"""
        meta_filters = {}
        if query.filters is not None:
            for filter in query.filters.legacy_filters():
                meta_filters[filter.key] = filter.value

        not_include_fields: Set[str] = {"text_embedding"}
        results = self._awadb_client.Search(
            query=query.query_embedding,
            topn=query.similarity_top_k,
            meta_filter=meta_filters,
            not_include_fields=not_include_fields,
        )

        nodes = []
        similarities = []
        ids = []

        for item_detail in results[0]["ResultItems"]:
            content = ""
            meta_data = {}
            node_id = ""
            for item_key in item_detail:
                if item_key == "embedding_text":
                    content = item_detail[item_key]
                    continue
                elif item_key == "_id":
                    node_id = item_detail[item_key]
                    ids.append(node_id)
                    continue
                elif item_key == "score":
                    similarities.append(item_detail[item_key])
                    continue
                meta_data[item_key] = item_detail[item_key]

            try:
                node = metadata_dict_to_node(meta_data)
                node.set_content(content)
            except Exception:
                # NOTE: deprecated legacy logic for backward compatibility
                metadata, node_info, relationships = legacy_metadata_dict_to_node(
                    meta_data
                )

                node = TextNode(
                    text=content,
                    id_=node_id,
                    metadata=metadata,
                    start_char_idx=node_info.get("start", None),
                    end_char_idx=node_info.get("end", None),
                    relationships=relationships,
                )

            nodes.append(node)

        return VectorStoreQueryResult(nodes=nodes, similarities=similarities, ids=ids)