Hologres
HologresVectorStore #
Bases: BasePydanticVectorStore
Hologres Vector Store.
Hologres is a one-stop real-time data warehouse, which can support high performance OLAP analysis and high QPS online services. Hologres supports vector processing and allows you to use vector data to show the characteristics of unstructured data. https://www.alibabacloud.com/help/en/hologres/user-guide/introduction-to-vector-processing
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-hologres/llama_index/vector_stores/hologres/base.py
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 |
|
from_connection_string
classmethod
#
from_connection_string(connection_string: str, table_name: str, table_schema: Dict[str, str] = {'document': 'text'}, embedding_dimension: int = 1536, pre_delete_table: bool = False) -> HologresVectorStore
Create Hologres Vector Store from connection string.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
connection_string |
str
|
connection string of hologres database |
required |
table_name |
str
|
table name to persist data |
required |
table_schema |
Dict[str, str]
|
table column schemam |
{'document': 'text'}
|
embedding_dimension |
int
|
dimension size of embedding vector |
1536
|
pre_delete_table |
bool
|
whether to erase data from table on creation |
False
|
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-hologres/llama_index/vector_stores/hologres/base.py
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 |
|
from_param
classmethod
#
from_param(host: str, port: int, user: str, password: str, database: str, table_name: str, table_schema: Dict[str, str] = {'document': 'text'}, embedding_dimension: int = 1536, pre_delete_table: bool = False) -> HologresVectorStore
Create Hologres Vector Store from database configurations.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
host |
str
|
host |
required |
port |
int
|
port number |
required |
user |
str
|
hologres user |
required |
password |
str
|
hologres password |
required |
database |
str
|
hologres database |
required |
table_name |
str
|
hologres table name |
required |
table_schema |
Dict[str, str]
|
table column schemam |
{'document': 'text'}
|
embedding_dimension |
int
|
dimension size of embedding vector |
1536
|
pre_delete_table |
bool
|
whether to erase data from table on creation |
False
|
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-hologres/llama_index/vector_stores/hologres/base.py
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 |
|
add #
add(nodes: List[BaseNode], **add_kwargs: Any) -> List[str]
Add nodes to hologres index.
Embedding data will be saved to vector
column and text will be saved to document
column.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
nodes |
List[BaseNode]
|
List[BaseNode]: list of nodes with embeddings |
required |
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-hologres/llama_index/vector_stores/hologres/base.py
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 |
|
query #
query(query: VectorStoreQuery, **kwargs: Any) -> VectorStoreQueryResult
Query index for top k most similar nodes.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
query_embedding |
List[float]
|
query embedding |
required |
similarity_top_k |
int
|
top k most similar nodes |
required |
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-hologres/llama_index/vector_stores/hologres/base.py
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 |
|
delete #
delete(ref_doc_id: str, **delete_kwargs: Any) -> None
Delete nodes using with ref_doc_id.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
ref_doc_id |
str
|
The doc_id of the document to delete. |
required |
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-hologres/llama_index/vector_stores/hologres/base.py
192 193 194 195 196 197 198 199 200 |
|