Qdrant
step
¶
containing the DVCStep sending embedding data into Qdrant.
Classes¶
QdrantConnectorStep
¶
Bases: TypedStep[QdrantSettings, DataFrame[EmbeddingResult], DataFrame[QdrantResult]]
Qdrant connector step. It consumes embedding csv files, creates a new schema and inserts the embeddings.
Source code in wurzel/steps/qdrant/step.py
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 |
|
Functions¶
get_available_hashes(text, encoding='utf-8')
staticmethod
¶
Compute n
hashes for a given input text based. The number n
depends on the optionally installed python libs. For now only TLSH (Trend Micro Locality Sensitive Hash) is supported
TLSH¶
Given a byte stream with a minimum length of 50 bytes TLSH generates a hash value which can be used for similarity comparisons.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
text | str | Input text | required |
encoding | str | Input text will encoded to bytes using this encoding. Defaults to "utf-8". | 'utf-8' |
Returns:
Type | Description |
---|---|
dict | dict[str, str]: keys: |
Source code in wurzel/steps/qdrant/step.py
step_multi_vector
¶
containing the DVCStep sending embedding data into Qdrant.
Classes¶
QdrantConnectorMultiVectorStep
¶
Bases: QdrantConnectorStep
, TypedStep[QdrantSettings, DataFrame[EmbeddingMultiVectorResult], DataFrame[QdrantMultiVectorResult]]
Qdrant connector step. It consumes embedding csv files, creates a new schema and inserts the embeddings.
Source code in wurzel/steps/qdrant/step_multi_vector.py
settings
¶
Classes¶
QdrantSettings
¶
Bases: Settings
QdrantSettings is a configuration class for managing settings related to the Qdrant database.
Attributes:
Name | Type | Description |
---|---|---|
DISTANCE | Distance | The distance metric to be used, default is Distance.DOT. |
URI | str | The URI for the Qdrant database, default is "http://localhost:6333". |
COLLECTION | str | The name of the collection in the Qdrant database. |
COLLECTION_HISTORY_LEN | int | The length of the collection history, default is 10. |
SEARCH_PARAMS | dict | Parameters for search operations, default is {"metric_type": "IP", "params": {}}. |
INDEX_PARAMS | dict | Parameters for index creation, default includes "index_type", "field_name", "distance", and "params". |
APIKEY | SecretStr | The API key for authentication, default is an empty SecretStr. |
REPLICATION_FACTOR | int | The replication factor for the database, default is 3, must be greater than 0. |
BATCH_SIZE | int | The batch size for operations, default is 1024, must be greater than 0. |
Methods:
Name | Description |
---|---|
parse_json | Validates and parses JSON strings into Python objects for SEARCH_PARAMS and INDEX_PARAMS. |