File size: 22,707 Bytes
f71c799 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 |
import json
from flask import request
from flask_restful import marshal, reqparse # type: ignore
from sqlalchemy import desc
from werkzeug.exceptions import NotFound
import services.dataset_service
from controllers.common.errors import FilenameNotExistsError
from controllers.service_api import api
from controllers.service_api.app.error import (
FileTooLargeError,
NoFileUploadedError,
ProviderNotInitializeError,
TooManyFilesError,
UnsupportedFileTypeError,
)
from controllers.service_api.dataset.error import (
ArchivedDocumentImmutableError,
DocumentIndexingError,
InvalidMetadataError,
)
from controllers.service_api.wraps import DatasetApiResource, cloud_edition_billing_resource_check
from core.errors.error import ProviderTokenNotInitError
from extensions.ext_database import db
from fields.document_fields import document_fields, document_status_fields
from libs.login import current_user
from models.dataset import Dataset, Document, DocumentSegment
from services.dataset_service import DocumentService
from services.entities.knowledge_entities.knowledge_entities import KnowledgeConfig
from services.file_service import FileService
class DocumentAddByTextApi(DatasetApiResource):
"""Resource for documents."""
@cloud_edition_billing_resource_check("vector_space", "dataset")
@cloud_edition_billing_resource_check("documents", "dataset")
def post(self, tenant_id, dataset_id):
"""Create document by text."""
parser = reqparse.RequestParser()
parser.add_argument("name", type=str, required=True, nullable=False, location="json")
parser.add_argument("text", type=str, required=True, nullable=False, location="json")
parser.add_argument("process_rule", type=dict, required=False, nullable=True, location="json")
parser.add_argument("original_document_id", type=str, required=False, location="json")
parser.add_argument("doc_form", type=str, default="text_model", required=False, nullable=False, location="json")
parser.add_argument(
"doc_language", type=str, default="English", required=False, nullable=False, location="json"
)
parser.add_argument(
"indexing_technique", type=str, choices=Dataset.INDEXING_TECHNIQUE_LIST, nullable=False, location="json"
)
parser.add_argument("retrieval_model", type=dict, required=False, nullable=False, location="json")
parser.add_argument("doc_type", type=str, required=False, nullable=True, location="json")
parser.add_argument("doc_metadata", type=dict, required=False, nullable=True, location="json")
args = parser.parse_args()
dataset_id = str(dataset_id)
tenant_id = str(tenant_id)
dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
if not dataset:
raise ValueError("Dataset is not exist.")
if not dataset.indexing_technique and not args["indexing_technique"]:
raise ValueError("indexing_technique is required.")
# Validate metadata if provided
if args.get("doc_type") or args.get("doc_metadata"):
if not args.get("doc_type") or not args.get("doc_metadata"):
raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
raise InvalidMetadataError(
"Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
)
if not isinstance(args["doc_metadata"], dict):
raise InvalidMetadataError("doc_metadata must be a dictionary")
# Validate metadata schema based on doc_type
if args["doc_type"] != "others":
metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
for key, value in args["doc_metadata"].items():
if key in metadata_schema and not isinstance(value, metadata_schema[key]):
raise InvalidMetadataError(f"Invalid type for metadata field {key}")
# set to MetaDataConfig
args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
text = args.get("text")
name = args.get("name")
if text is None or name is None:
raise ValueError("Both 'text' and 'name' must be non-null values.")
upload_file = FileService.upload_text(text=str(text), text_name=str(name))
data_source = {
"type": "upload_file",
"info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
}
args["data_source"] = data_source
knowledge_config = KnowledgeConfig(**args)
# validate args
DocumentService.document_create_args_validate(knowledge_config)
try:
documents, batch = DocumentService.save_document_with_dataset_id(
dataset=dataset,
knowledge_config=knowledge_config,
account=current_user,
dataset_process_rule=dataset.latest_process_rule if "process_rule" not in args else None,
created_from="api",
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
document = documents[0]
documents_and_batch_fields = {"document": marshal(document, document_fields), "batch": batch}
return documents_and_batch_fields, 200
class DocumentUpdateByTextApi(DatasetApiResource):
"""Resource for update documents."""
@cloud_edition_billing_resource_check("vector_space", "dataset")
def post(self, tenant_id, dataset_id, document_id):
"""Update document by text."""
parser = reqparse.RequestParser()
parser.add_argument("name", type=str, required=False, nullable=True, location="json")
parser.add_argument("text", type=str, required=False, nullable=True, location="json")
parser.add_argument("process_rule", type=dict, required=False, nullable=True, location="json")
parser.add_argument("doc_form", type=str, default="text_model", required=False, nullable=False, location="json")
parser.add_argument(
"doc_language", type=str, default="English", required=False, nullable=False, location="json"
)
parser.add_argument("retrieval_model", type=dict, required=False, nullable=False, location="json")
parser.add_argument("doc_type", type=str, required=False, nullable=True, location="json")
parser.add_argument("doc_metadata", type=dict, required=False, nullable=True, location="json")
args = parser.parse_args()
dataset_id = str(dataset_id)
tenant_id = str(tenant_id)
dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
if not dataset:
raise ValueError("Dataset is not exist.")
# indexing_technique is already set in dataset since this is an update
args["indexing_technique"] = dataset.indexing_technique
# Validate metadata if provided
if args.get("doc_type") or args.get("doc_metadata"):
if not args.get("doc_type") or not args.get("doc_metadata"):
raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
raise InvalidMetadataError(
"Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
)
if not isinstance(args["doc_metadata"], dict):
raise InvalidMetadataError("doc_metadata must be a dictionary")
# Validate metadata schema based on doc_type
if args["doc_type"] != "others":
metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
for key, value in args["doc_metadata"].items():
if key in metadata_schema and not isinstance(value, metadata_schema[key]):
raise InvalidMetadataError(f"Invalid type for metadata field {key}")
# set to MetaDataConfig
args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
if args["text"]:
text = args.get("text")
name = args.get("name")
if text is None or name is None:
raise ValueError("Both text and name must be strings.")
upload_file = FileService.upload_text(text=str(text), text_name=str(name))
data_source = {
"type": "upload_file",
"info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
}
args["data_source"] = data_source
# validate args
args["original_document_id"] = str(document_id)
knowledge_config = KnowledgeConfig(**args)
DocumentService.document_create_args_validate(knowledge_config)
try:
documents, batch = DocumentService.save_document_with_dataset_id(
dataset=dataset,
knowledge_config=knowledge_config,
account=current_user,
dataset_process_rule=dataset.latest_process_rule if "process_rule" not in args else None,
created_from="api",
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
document = documents[0]
documents_and_batch_fields = {"document": marshal(document, document_fields), "batch": batch}
return documents_and_batch_fields, 200
class DocumentAddByFileApi(DatasetApiResource):
"""Resource for documents."""
@cloud_edition_billing_resource_check("vector_space", "dataset")
@cloud_edition_billing_resource_check("documents", "dataset")
def post(self, tenant_id, dataset_id):
"""Create document by upload file."""
args = {}
if "data" in request.form:
args = json.loads(request.form["data"])
if "doc_form" not in args:
args["doc_form"] = "text_model"
if "doc_language" not in args:
args["doc_language"] = "English"
# Validate metadata if provided
if args.get("doc_type") or args.get("doc_metadata"):
if not args.get("doc_type") or not args.get("doc_metadata"):
raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
raise InvalidMetadataError(
"Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
)
if not isinstance(args["doc_metadata"], dict):
raise InvalidMetadataError("doc_metadata must be a dictionary")
# Validate metadata schema based on doc_type
if args["doc_type"] != "others":
metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
for key, value in args["doc_metadata"].items():
if key in metadata_schema and not isinstance(value, metadata_schema[key]):
raise InvalidMetadataError(f"Invalid type for metadata field {key}")
# set to MetaDataConfig
args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
# get dataset info
dataset_id = str(dataset_id)
tenant_id = str(tenant_id)
dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
if not dataset:
raise ValueError("Dataset is not exist.")
if not dataset.indexing_technique and not args.get("indexing_technique"):
raise ValueError("indexing_technique is required.")
# save file info
file = request.files["file"]
# check file
if "file" not in request.files:
raise NoFileUploadedError()
if len(request.files) > 1:
raise TooManyFilesError()
if not file.filename:
raise FilenameNotExistsError
upload_file = FileService.upload_file(
filename=file.filename,
content=file.read(),
mimetype=file.mimetype,
user=current_user,
source="datasets",
)
data_source = {
"type": "upload_file",
"info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
}
args["data_source"] = data_source
# validate args
knowledge_config = KnowledgeConfig(**args)
DocumentService.document_create_args_validate(knowledge_config)
try:
documents, batch = DocumentService.save_document_with_dataset_id(
dataset=dataset,
knowledge_config=knowledge_config,
account=dataset.created_by_account,
dataset_process_rule=dataset.latest_process_rule if "process_rule" not in args else None,
created_from="api",
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
document = documents[0]
documents_and_batch_fields = {"document": marshal(document, document_fields), "batch": batch}
return documents_and_batch_fields, 200
class DocumentUpdateByFileApi(DatasetApiResource):
"""Resource for update documents."""
@cloud_edition_billing_resource_check("vector_space", "dataset")
def post(self, tenant_id, dataset_id, document_id):
"""Update document by upload file."""
args = {}
if "data" in request.form:
args = json.loads(request.form["data"])
if "doc_form" not in args:
args["doc_form"] = "text_model"
if "doc_language" not in args:
args["doc_language"] = "English"
# Validate metadata if provided
if args.get("doc_type") or args.get("doc_metadata"):
if not args.get("doc_type") or not args.get("doc_metadata"):
raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
raise InvalidMetadataError(
"Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
)
if not isinstance(args["doc_metadata"], dict):
raise InvalidMetadataError("doc_metadata must be a dictionary")
# Validate metadata schema based on doc_type
if args["doc_type"] != "others":
metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
for key, value in args["doc_metadata"].items():
if key in metadata_schema and not isinstance(value, metadata_schema[key]):
raise InvalidMetadataError(f"Invalid type for metadata field {key}")
# set to MetaDataConfig
args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
# get dataset info
dataset_id = str(dataset_id)
tenant_id = str(tenant_id)
dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
if not dataset:
raise ValueError("Dataset is not exist.")
if "file" in request.files:
# save file info
file = request.files["file"]
if len(request.files) > 1:
raise TooManyFilesError()
if not file.filename:
raise FilenameNotExistsError
try:
upload_file = FileService.upload_file(
filename=file.filename,
content=file.read(),
mimetype=file.mimetype,
user=current_user,
source="datasets",
)
except services.errors.file.FileTooLargeError as file_too_large_error:
raise FileTooLargeError(file_too_large_error.description)
except services.errors.file.UnsupportedFileTypeError:
raise UnsupportedFileTypeError()
data_source = {
"type": "upload_file",
"info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
}
args["data_source"] = data_source
# validate args
args["original_document_id"] = str(document_id)
knowledge_config = KnowledgeConfig(**args)
DocumentService.document_create_args_validate(knowledge_config)
try:
documents, batch = DocumentService.save_document_with_dataset_id(
dataset=dataset,
knowledge_config=knowledge_config,
account=dataset.created_by_account,
dataset_process_rule=dataset.latest_process_rule if "process_rule" not in args else None,
created_from="api",
)
except ProviderTokenNotInitError as ex:
raise ProviderNotInitializeError(ex.description)
document = documents[0]
documents_and_batch_fields = {"document": marshal(document, document_fields), "batch": document.batch}
return documents_and_batch_fields, 200
class DocumentDeleteApi(DatasetApiResource):
def delete(self, tenant_id, dataset_id, document_id):
"""Delete document."""
document_id = str(document_id)
dataset_id = str(dataset_id)
tenant_id = str(tenant_id)
# get dataset info
dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
if not dataset:
raise ValueError("Dataset is not exist.")
document = DocumentService.get_document(dataset.id, document_id)
# 404 if document not found
if document is None:
raise NotFound("Document Not Exists.")
# 403 if document is archived
if DocumentService.check_archived(document):
raise ArchivedDocumentImmutableError()
try:
# delete document
DocumentService.delete_document(document)
except services.errors.document.DocumentIndexingError:
raise DocumentIndexingError("Cannot delete document during indexing.")
return {"result": "success"}, 200
class DocumentListApi(DatasetApiResource):
def get(self, tenant_id, dataset_id):
dataset_id = str(dataset_id)
tenant_id = str(tenant_id)
page = request.args.get("page", default=1, type=int)
limit = request.args.get("limit", default=20, type=int)
search = request.args.get("keyword", default=None, type=str)
dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
if not dataset:
raise NotFound("Dataset not found.")
query = Document.query.filter_by(dataset_id=str(dataset_id), tenant_id=tenant_id)
if search:
search = f"%{search}%"
query = query.filter(Document.name.like(search))
query = query.order_by(desc(Document.created_at))
paginated_documents = query.paginate(page=page, per_page=limit, max_per_page=100, error_out=False)
documents = paginated_documents.items
response = {
"data": marshal(documents, document_fields),
"has_more": len(documents) == limit,
"limit": limit,
"total": paginated_documents.total,
"page": page,
}
return response
class DocumentIndexingStatusApi(DatasetApiResource):
def get(self, tenant_id, dataset_id, batch):
dataset_id = str(dataset_id)
batch = str(batch)
tenant_id = str(tenant_id)
# get dataset
dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
if not dataset:
raise NotFound("Dataset not found.")
# get documents
documents = DocumentService.get_batch_documents(dataset_id, batch)
if not documents:
raise NotFound("Documents not found.")
documents_status = []
for document in documents:
completed_segments = DocumentSegment.query.filter(
DocumentSegment.completed_at.isnot(None),
DocumentSegment.document_id == str(document.id),
DocumentSegment.status != "re_segment",
).count()
total_segments = DocumentSegment.query.filter(
DocumentSegment.document_id == str(document.id), DocumentSegment.status != "re_segment"
).count()
document.completed_segments = completed_segments
document.total_segments = total_segments
if document.is_paused:
document.indexing_status = "paused"
documents_status.append(marshal(document, document_status_fields))
data = {"data": documents_status}
return data
api.add_resource(
DocumentAddByTextApi,
"/datasets/<uuid:dataset_id>/document/create_by_text",
"/datasets/<uuid:dataset_id>/document/create-by-text",
)
api.add_resource(
DocumentAddByFileApi,
"/datasets/<uuid:dataset_id>/document/create_by_file",
"/datasets/<uuid:dataset_id>/document/create-by-file",
)
api.add_resource(
DocumentUpdateByTextApi,
"/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_text",
"/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update-by-text",
)
api.add_resource(
DocumentUpdateByFileApi,
"/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_file",
"/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update-by-file",
)
api.add_resource(DocumentDeleteApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>")
api.add_resource(DocumentListApi, "/datasets/<uuid:dataset_id>/documents")
api.add_resource(DocumentIndexingStatusApi, "/datasets/<uuid:dataset_id>/documents/<string:batch>/indexing-status")
|