Bigquery
BigQueryVectorStore #
Bases: BasePydanticVectorStore
Vector store index using Google BigQuery.
Provides integration with BigQuery for storing and querying vector embeddings. For more information, visit: https://cloud.google.com/bigquery/docs/vector-search-intro
Examples:
pip install llama-index-vector-stores-bigquery
from google.cloud.bigquery import Client
from llama_index.vector_stores.bigquery import BigQueryVectorStore
client = Client()
vector_store = BigQueryVectorStore(
table_id="my_bigquery_table",
dataset_id="my_bigquery_dataset",
bigquery_client=client,
)
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-bigquery/llama_index/vector_stores/bigquery/base.py
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 |
|
from_params
classmethod
#
from_params(table_id: str, dataset_id: str, project_id: Optional[str] = None, region: Optional[str] = None, distance_type: Optional[DistanceType] = EUCLIDEAN, auth_credentials: Optional[Credentials] = None, bigquery_client: Optional[Client] = None) -> BigQueryVectorStore
Initialize a BigQuery Vector store.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
table_id
|
str
|
The ID of the BigQuery table to use for vector storage. |
required |
dataset_id
|
str
|
The ID of the dataset containing the table. |
required |
project_id
|
Optional[str]
|
The GCP project ID. If not provided, it will be inferred from the client or environment. |
None
|
region
|
Optional[str]
|
Optionally specify a default location for datasets / tables. |
None
|
distance_type
|
Optional[DistanceType]
|
Optionally specify a distance type to use |
EUCLIDEAN
|
auth_credentials
|
Optional[Credentials]
|
Optional credentials object used to authenticate with BigQuery. |
None
|
bigquery_client
|
Optional[Client]
|
An existing BigQuery client instance. If not provided, one will be created. |
None
|
Returns:
Type | Description |
---|---|
BigQueryVectorStore
|
BigQueryVectorStore |
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-bigquery/llama_index/vector_stores/bigquery/base.py
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 |
|
add #
add(nodes: List[BaseNode], **add_kwargs: Any) -> List[str]
Add nodes to index.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
nodes
|
List[BaseNode]
|
List of nodes with embeddings. |
required |
Returns:
Type | Description |
---|---|
List[str]
|
List of node IDs that were added. |
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-bigquery/llama_index/vector_stores/bigquery/base.py
285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 |
|
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
|
The doc_id of the document to delete. |
required |
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-bigquery/llama_index/vector_stores/bigquery/base.py
319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 |
|
query #
query(query: VectorStoreQuery, **kwargs: Any) -> VectorStoreQueryResult
Query the vector store using BigQuery's VECTOR_SEARCH to retrieve the top-k most similar nodes.
When MetadataFilters
are provided and the table is indexed on relevant columns, BigQuery attempts to optimize
the search with pre-filtering before nearest neighbor search. If filters don't align with an index,
post-filtering is applied after similarity search, potentially returning fewer than similarity_top_k results
.
Consider increasing similarity_top_k
when post-filtering is expected.
For more information on pre-filtering and post-filtering, see: https://cloud.google.com/bigquery/docs/vector-index#pre-filters_and_post-filters
Assumes embeddings are normalized for similarity scoring.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
query
|
VectorStoreQuery
|
Contains the query embedding, similarity_top_k value, and optional metadata filters. |
required |
Returns:
Type | Description |
---|---|
VectorStoreQueryResult
|
VectorStoreQueryResult |
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-bigquery/llama_index/vector_stores/bigquery/base.py
341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 |
|
get_nodes #
get_nodes(node_ids: Optional[List[str]] = None, filters: Optional[MetadataFilters] = None) -> List[BaseNode]
Retrieve nodes from BigQuery using node IDs, metadata filters, or both.
If both node_ids
and filters
are provided, only nodes that satisfy
both conditions will be returned.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
node_ids
|
Optional[List[str]]
|
Optional list of node IDs for retrieval. |
None
|
filters
|
Optional MetadataFilters filters for retrieval. |
None
|
Returns:
Type | Description |
---|---|
List[BaseNode]
|
A list of matching nodes. |
Raises:
Type | Description |
---|---|
ValueError
|
If neither |
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-bigquery/llama_index/vector_stores/bigquery/base.py
441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 |
|
delete_nodes #
delete_nodes(node_ids: Optional[List[str]] = None, filters: Optional[MetadataFilters] = None, **delete_kwargs: Any) -> None
Delete nodes from BigQuery based on node IDs, metadata filters, or both.
If both node_ids
and filters
are provided, only nodes matching both
criteria will be deleted.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
node_ids
|
Optional[List[str]]
|
Optional list of node IDs to delete. |
None
|
filters
|
Optional MetadataFilters filters for deletion. |
None
|
Raises:
Type | Description |
---|---|
ValueError
|
If neither |
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-bigquery/llama_index/vector_stores/bigquery/base.py
502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 |
|
clear #
clear() -> None
Clears the index.
This truncates the underlying table in BigQuery.
Source code in llama-index-integrations/vector_stores/llama-index-vector-stores-bigquery/llama_index/vector_stores/bigquery/base.py
540 541 542 543 544 545 546 547 |
|