unstructured-ingest 0.5.25__py3-none-any.whl → 0.6.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of unstructured-ingest might be problematic. Click here for more details.

Files changed (105) hide show
  1. test/integration/connectors/databricks/test_volumes_native.py +1 -1
  2. test/integration/connectors/duckdb/test_duckdb.py +1 -1
  3. test/integration/connectors/duckdb/test_motherduck.py +1 -1
  4. test/integration/connectors/elasticsearch/test_elasticsearch.py +1 -1
  5. test/integration/connectors/elasticsearch/test_opensearch.py +1 -1
  6. test/integration/connectors/sql/test_databricks_delta_tables.py +1 -1
  7. test/integration/connectors/sql/test_postgres.py +1 -1
  8. test/integration/connectors/sql/test_singlestore.py +1 -1
  9. test/integration/connectors/sql/test_snowflake.py +1 -1
  10. test/integration/connectors/sql/test_sqlite.py +1 -1
  11. test/integration/connectors/test_astradb.py +1 -1
  12. test/integration/connectors/test_azure_ai_search.py +1 -1
  13. test/integration/connectors/test_chroma.py +1 -1
  14. test/integration/connectors/test_delta_table.py +1 -1
  15. test/integration/connectors/test_lancedb.py +1 -1
  16. test/integration/connectors/test_milvus.py +1 -1
  17. test/integration/connectors/test_mongodb.py +1 -1
  18. test/integration/connectors/test_neo4j.py +5 -5
  19. test/integration/connectors/test_onedrive.py +1 -1
  20. test/integration/connectors/test_pinecone.py +1 -1
  21. test/integration/connectors/test_qdrant.py +1 -1
  22. test/integration/connectors/test_redis.py +1 -1
  23. test/integration/connectors/test_s3.py +1 -1
  24. test/integration/connectors/test_vectara.py +1 -1
  25. test/integration/connectors/utils/validation/destination.py +2 -1
  26. test/integration/connectors/utils/validation/source.py +2 -1
  27. test/integration/connectors/weaviate/test_local.py +1 -1
  28. test/unit/test_html.py +1 -1
  29. test/unit/v2/connectors/ibm_watsonx/test_ibm_watsonx_s3.py +1 -1
  30. test/unit/v2/connectors/motherduck/test_base.py +1 -2
  31. test/unit/v2/connectors/sql/test_sql.py +1 -1
  32. unstructured_ingest/__version__.py +1 -1
  33. unstructured_ingest/utils/html.py +2 -1
  34. unstructured_ingest/v2/interfaces/__init__.py +0 -13
  35. unstructured_ingest/v2/interfaces/downloader.py +1 -1
  36. unstructured_ingest/v2/interfaces/indexer.py +1 -1
  37. unstructured_ingest/v2/interfaces/upload_stager.py +2 -2
  38. unstructured_ingest/v2/interfaces/uploader.py +2 -3
  39. unstructured_ingest/v2/pipeline/steps/chunk.py +1 -2
  40. unstructured_ingest/v2/pipeline/steps/download.py +2 -3
  41. unstructured_ingest/v2/pipeline/steps/embed.py +1 -2
  42. unstructured_ingest/v2/pipeline/steps/filter.py +1 -1
  43. unstructured_ingest/v2/pipeline/steps/partition.py +1 -2
  44. unstructured_ingest/v2/pipeline/steps/stage.py +2 -2
  45. unstructured_ingest/v2/pipeline/steps/uncompress.py +1 -1
  46. unstructured_ingest/v2/pipeline/steps/upload.py +2 -2
  47. unstructured_ingest/v2/processes/connectors/airtable.py +1 -2
  48. unstructured_ingest/v2/processes/connectors/astradb.py +7 -5
  49. unstructured_ingest/v2/processes/connectors/azure_ai_search.py +1 -1
  50. unstructured_ingest/v2/processes/connectors/chroma.py +1 -1
  51. unstructured_ingest/v2/processes/connectors/confluence.py +5 -3
  52. unstructured_ingest/v2/processes/connectors/couchbase.py +7 -5
  53. unstructured_ingest/v2/processes/connectors/databricks/volumes.py +5 -3
  54. unstructured_ingest/v2/processes/connectors/databricks/volumes_table.py +2 -1
  55. unstructured_ingest/v2/processes/connectors/delta_table.py +1 -1
  56. unstructured_ingest/v2/processes/connectors/discord.py +5 -3
  57. unstructured_ingest/v2/processes/connectors/duckdb/base.py +2 -1
  58. unstructured_ingest/v2/processes/connectors/duckdb/duckdb.py +1 -1
  59. unstructured_ingest/v2/processes/connectors/duckdb/motherduck.py +1 -1
  60. unstructured_ingest/v2/processes/connectors/elasticsearch/elasticsearch.py +7 -5
  61. unstructured_ingest/v2/processes/connectors/fsspec/azure.py +1 -1
  62. unstructured_ingest/v2/processes/connectors/fsspec/box.py +1 -1
  63. unstructured_ingest/v2/processes/connectors/fsspec/dropbox.py +1 -1
  64. unstructured_ingest/v2/processes/connectors/fsspec/fsspec.py +5 -3
  65. unstructured_ingest/v2/processes/connectors/fsspec/gcs.py +1 -1
  66. unstructured_ingest/v2/processes/connectors/fsspec/s3.py +3 -3
  67. unstructured_ingest/v2/processes/connectors/fsspec/sftp.py +1 -1
  68. unstructured_ingest/v2/processes/connectors/gitlab.py +5 -3
  69. unstructured_ingest/v2/processes/connectors/google_drive.py +5 -3
  70. unstructured_ingest/v2/processes/connectors/ibm_watsonx/ibm_watsonx_s3.py +1 -1
  71. unstructured_ingest/v2/processes/connectors/jira.py +5 -3
  72. unstructured_ingest/v2/processes/connectors/kafka/kafka.py +5 -3
  73. unstructured_ingest/v2/processes/connectors/kdbai.py +1 -1
  74. unstructured_ingest/v2/processes/connectors/lancedb/lancedb.py +8 -4
  75. unstructured_ingest/v2/processes/connectors/local.py +5 -3
  76. unstructured_ingest/v2/processes/connectors/milvus.py +1 -1
  77. unstructured_ingest/v2/processes/connectors/mongodb.py +7 -5
  78. unstructured_ingest/v2/processes/connectors/neo4j.py +1 -1
  79. unstructured_ingest/v2/processes/connectors/notion/connector.py +5 -3
  80. unstructured_ingest/v2/processes/connectors/onedrive.py +5 -3
  81. unstructured_ingest/v2/processes/connectors/outlook.py +5 -2
  82. unstructured_ingest/v2/processes/connectors/pinecone.py +1 -1
  83. unstructured_ingest/v2/processes/connectors/qdrant/qdrant.py +1 -1
  84. unstructured_ingest/v2/processes/connectors/redisdb.py +1 -1
  85. unstructured_ingest/v2/processes/connectors/salesforce.py +5 -3
  86. unstructured_ingest/v2/processes/connectors/sharepoint.py +3 -3
  87. unstructured_ingest/v2/processes/connectors/slack.py +2 -2
  88. unstructured_ingest/v2/processes/connectors/sql/databricks_delta_tables.py +1 -1
  89. unstructured_ingest/v2/processes/connectors/sql/snowflake.py +1 -1
  90. unstructured_ingest/v2/processes/connectors/sql/sql.py +7 -5
  91. unstructured_ingest/v2/processes/connectors/sql/vastdb.py +3 -3
  92. unstructured_ingest/v2/processes/connectors/vectara.py +1 -1
  93. unstructured_ingest/v2/processes/connectors/weaviate/weaviate.py +1 -1
  94. unstructured_ingest/v2/processes/connectors/zendesk/zendesk.py +5 -3
  95. unstructured_ingest/v2/processes/filter.py +1 -1
  96. unstructured_ingest/v2/processes/uncompress.py +1 -1
  97. unstructured_ingest/v2/processes/utils/blob_storage.py +2 -1
  98. unstructured_ingest/v2/utils.py +1 -1
  99. {unstructured_ingest-0.5.25.dist-info → unstructured_ingest-0.6.0.dist-info}/METADATA +94 -94
  100. {unstructured_ingest-0.5.25.dist-info → unstructured_ingest-0.6.0.dist-info}/RECORD +104 -105
  101. unstructured_ingest/v2/interfaces/file_data.py +0 -13
  102. {unstructured_ingest-0.5.25.dist-info → unstructured_ingest-0.6.0.dist-info}/LICENSE.md +0 -0
  103. {unstructured_ingest-0.5.25.dist-info → unstructured_ingest-0.6.0.dist-info}/WHEEL +0 -0
  104. {unstructured_ingest-0.5.25.dist-info → unstructured_ingest-0.6.0.dist-info}/entry_points.txt +0 -0
  105. {unstructured_ingest-0.5.25.dist-info → unstructured_ingest-0.6.0.dist-info}/top_level.txt +0 -0
@@ -21,7 +21,6 @@ from test.integration.connectors.utils.validation.source import (
21
21
  )
22
22
  from test.integration.utils import requires_env
23
23
  from unstructured_ingest.v2.errors import UserAuthError, UserError
24
- from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
25
24
  from unstructured_ingest.v2.processes.connectors.databricks.volumes_native import (
26
25
  CONNECTOR_TYPE,
27
26
  DatabricksNativeVolumesAccessConfig,
@@ -33,6 +32,7 @@ from unstructured_ingest.v2.processes.connectors.databricks.volumes_native impor
33
32
  DatabricksNativeVolumesUploader,
34
33
  DatabricksNativeVolumesUploaderConfig,
35
34
  )
35
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
36
36
 
37
37
 
38
38
  @dataclass
@@ -10,7 +10,6 @@ from test.integration.connectors.utils.validation.destination import (
10
10
  StagerValidationConfigs,
11
11
  stager_validation,
12
12
  )
13
- from unstructured_ingest.v2.interfaces.file_data import FileData, SourceIdentifiers
14
13
  from unstructured_ingest.v2.processes.connectors.duckdb.duckdb import (
15
14
  CONNECTOR_TYPE,
16
15
  DuckDBConnectionConfig,
@@ -18,6 +17,7 @@ from unstructured_ingest.v2.processes.connectors.duckdb.duckdb import (
18
17
  DuckDBUploaderConfig,
19
18
  DuckDBUploadStager,
20
19
  )
20
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
21
21
 
22
22
 
23
23
  @pytest.fixture
@@ -9,7 +9,6 @@ import pytest
9
9
 
10
10
  from test.integration.connectors.utils.constants import DESTINATION_TAG, SQL_TAG
11
11
  from test.integration.utils import requires_env
12
- from unstructured_ingest.v2.interfaces.file_data import FileData, SourceIdentifiers
13
12
  from unstructured_ingest.v2.processes.connectors.duckdb.motherduck import (
14
13
  CONNECTOR_TYPE,
15
14
  MotherDuckAccessConfig,
@@ -18,6 +17,7 @@ from unstructured_ingest.v2.processes.connectors.duckdb.motherduck import (
18
17
  MotherDuckUploaderConfig,
19
18
  MotherDuckUploadStager,
20
19
  )
20
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
21
21
 
22
22
 
23
23
  @pytest.fixture
@@ -22,7 +22,7 @@ from test.integration.connectors.utils.validation.source import (
22
22
  source_connector_validation,
23
23
  )
24
24
  from unstructured_ingest.error import DestinationConnectionError, SourceConnectionError
25
- from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
25
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
26
26
  from unstructured_ingest.v2.processes.connectors.elasticsearch.elasticsearch import (
27
27
  CONNECTOR_TYPE,
28
28
  ElasticsearchAccessConfig,
@@ -24,7 +24,6 @@ from unstructured_ingest.error import (
24
24
  DestinationConnectionError,
25
25
  SourceConnectionError,
26
26
  )
27
- from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
28
27
  from unstructured_ingest.v2.processes.connectors.elasticsearch.opensearch import (
29
28
  CONNECTOR_TYPE,
30
29
  OpenSearchAccessConfig,
@@ -38,6 +37,7 @@ from unstructured_ingest.v2.processes.connectors.elasticsearch.opensearch import
38
37
  OpenSearchUploadStager,
39
38
  OpenSearchUploadStagerConfig,
40
39
  )
40
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
41
41
 
42
42
  SOURCE_INDEX_NAME = "movies"
43
43
  DESTINATION_INDEX_NAME = "elements"
@@ -14,7 +14,6 @@ from pytest_mock import MockerFixture
14
14
 
15
15
  from test.integration.connectors.utils.constants import DESTINATION_TAG, SQL_TAG, env_setup_path
16
16
  from test.integration.utils import requires_env
17
- from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
18
17
  from unstructured_ingest.v2.logger import logger
19
18
  from unstructured_ingest.v2.processes.connectors.sql.databricks_delta_tables import (
20
19
  CONNECTOR_TYPE,
@@ -24,6 +23,7 @@ from unstructured_ingest.v2.processes.connectors.sql.databricks_delta_tables imp
24
23
  DatabricksDeltaTablesUploaderConfig,
25
24
  DatabricksDeltaTablesUploadStager,
26
25
  )
26
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
27
27
 
28
28
  CATALOG = "utic-dev-tech-fixtures"
29
29
 
@@ -20,7 +20,6 @@ from test.integration.connectors.utils.validation.source import (
20
20
  SourceValidationConfigs,
21
21
  source_connector_validation,
22
22
  )
23
- from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
24
23
  from unstructured_ingest.v2.processes.connectors.sql.postgres import (
25
24
  CONNECTOR_TYPE,
26
25
  PostgresAccessConfig,
@@ -32,6 +31,7 @@ from unstructured_ingest.v2.processes.connectors.sql.postgres import (
32
31
  PostgresUploader,
33
32
  PostgresUploadStager,
34
33
  )
34
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
35
35
 
36
36
  SEED_DATA_ROWS = 10
37
37
 
@@ -20,7 +20,6 @@ from test.integration.connectors.utils.validation.source import (
20
20
  SourceValidationConfigs,
21
21
  source_connector_validation,
22
22
  )
23
- from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
24
23
  from unstructured_ingest.v2.processes.connectors.sql.singlestore import (
25
24
  CONNECTOR_TYPE,
26
25
  SingleStoreAccessConfig,
@@ -33,6 +32,7 @@ from unstructured_ingest.v2.processes.connectors.sql.singlestore import (
33
32
  SingleStoreUploaderConfig,
34
33
  SingleStoreUploadStager,
35
34
  )
35
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
36
36
 
37
37
  SEED_DATA_ROWS = 10
38
38
 
@@ -22,7 +22,6 @@ from test.integration.connectors.utils.validation.source import (
22
22
  source_connector_validation,
23
23
  )
24
24
  from test.integration.utils import requires_env
25
- from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
26
25
  from unstructured_ingest.v2.processes.connectors.sql.snowflake import (
27
26
  CONNECTOR_TYPE,
28
27
  SnowflakeAccessConfig,
@@ -34,6 +33,7 @@ from unstructured_ingest.v2.processes.connectors.sql.snowflake import (
34
33
  SnowflakeUploader,
35
34
  SnowflakeUploadStager,
36
35
  )
36
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
37
37
 
38
38
  SEED_DATA_ROWS = 20
39
39
 
@@ -20,7 +20,6 @@ from test.integration.connectors.utils.validation.source import (
20
20
  SourceValidationConfigs,
21
21
  source_connector_validation,
22
22
  )
23
- from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
24
23
  from unstructured_ingest.v2.processes.connectors.sql.sqlite import (
25
24
  CONNECTOR_TYPE,
26
25
  SQLiteConnectionConfig,
@@ -31,6 +30,7 @@ from unstructured_ingest.v2.processes.connectors.sql.sqlite import (
31
30
  SQLiteUploader,
32
31
  SQLiteUploadStager,
33
32
  )
33
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
34
34
 
35
35
  SEED_DATA_ROWS = 10
36
36
 
@@ -20,7 +20,6 @@ from test.integration.connectors.utils.validation.source import (
20
20
  source_connector_validation,
21
21
  )
22
22
  from test.integration.utils import requires_env
23
- from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
24
23
  from unstructured_ingest.v2.processes.connectors.astradb import (
25
24
  CONNECTOR_TYPE,
26
25
  AstraDBAccessConfig,
@@ -36,6 +35,7 @@ from unstructured_ingest.v2.processes.connectors.astradb import (
36
35
  DestinationConnectionError,
37
36
  SourceConnectionError,
38
37
  )
38
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
39
39
 
40
40
  EXISTENT_COLLECTION_NAME = "ingest_test_src"
41
41
  NONEXISTENT_COLLECTION_NAME = "nonexistant"
@@ -29,7 +29,6 @@ from test.integration.connectors.utils.validation.destination import (
29
29
  stager_validation,
30
30
  )
31
31
  from test.integration.utils import requires_env
32
- from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
33
32
  from unstructured_ingest.v2.processes.connectors.azure_ai_search import (
34
33
  CONNECTOR_TYPE,
35
34
  RECORD_ID_LABEL,
@@ -40,6 +39,7 @@ from unstructured_ingest.v2.processes.connectors.azure_ai_search import (
40
39
  AzureAISearchUploadStager,
41
40
  AzureAISearchUploadStagerConfig,
42
41
  )
42
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
43
43
 
44
44
  repo_path = Path(__file__).parent.resolve()
45
45
 
@@ -27,7 +27,7 @@ from test.integration.connectors.utils.validation.destination import (
27
27
  StagerValidationConfigs,
28
28
  stager_validation,
29
29
  )
30
- from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
30
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
31
31
  from unstructured_ingest.v2.processes.connectors.chroma import (
32
32
  CONNECTOR_TYPE,
33
33
  ChromaConnectionConfig,
@@ -8,7 +8,6 @@ from fsspec import get_filesystem_class
8
8
 
9
9
  from test.integration.connectors.utils.constants import DESTINATION_TAG, SQL_TAG
10
10
  from test.integration.utils import requires_env
11
- from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
12
11
  from unstructured_ingest.v2.processes.connectors.delta_table import (
13
12
  CONNECTOR_TYPE,
14
13
  DeltaTableAccessConfig,
@@ -18,6 +17,7 @@ from unstructured_ingest.v2.processes.connectors.delta_table import (
18
17
  DeltaTableUploadStager,
19
18
  DeltaTableUploadStagerConfig,
20
19
  )
20
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
21
21
 
22
22
  multiprocessing.set_start_method("spawn")
23
23
 
@@ -13,7 +13,6 @@ from upath import UPath
13
13
 
14
14
  from test.integration.connectors.utils.constants import DESTINATION_TAG, VECTOR_DB_TAG
15
15
  from unstructured_ingest.v2.constants import RECORD_ID_LABEL
16
- from unstructured_ingest.v2.interfaces.file_data import FileData, SourceIdentifiers
17
16
  from unstructured_ingest.v2.processes.connectors.lancedb.aws import (
18
17
  LanceDBAwsAccessConfig,
19
18
  LanceDBAwsConnectionConfig,
@@ -39,6 +38,7 @@ from unstructured_ingest.v2.processes.connectors.lancedb.local import (
39
38
  LanceDBLocalConnectionConfig,
40
39
  LanceDBLocalUploader,
41
40
  )
41
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
42
42
 
43
43
  DATABASE_NAME = "database"
44
44
  TABLE_NAME = "elements"
@@ -25,7 +25,6 @@ from test.integration.connectors.utils.validation.destination import (
25
25
  stager_validation,
26
26
  )
27
27
  from unstructured_ingest.error import DestinationConnectionError
28
- from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
29
28
  from unstructured_ingest.v2.processes.connectors.milvus import (
30
29
  CONNECTOR_TYPE,
31
30
  MilvusConnectionConfig,
@@ -33,6 +32,7 @@ from unstructured_ingest.v2.processes.connectors.milvus import (
33
32
  MilvusUploaderConfig,
34
33
  MilvusUploadStager,
35
34
  )
35
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
36
36
 
37
37
  DB_NAME = "test_database"
38
38
  EXISTENT_COLLECTION_NAME = "test_collection"
@@ -20,7 +20,6 @@ from test.integration.connectors.utils.validation.source import (
20
20
  )
21
21
  from test.integration.utils import requires_env
22
22
  from unstructured_ingest.error import DestinationConnectionError, SourceConnectionError
23
- from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
24
23
  from unstructured_ingest.v2.processes.connectors.mongodb import (
25
24
  CONNECTOR_TYPE,
26
25
  MongoDBAccessConfig,
@@ -32,6 +31,7 @@ from unstructured_ingest.v2.processes.connectors.mongodb import (
32
31
  MongoDBUploader,
33
32
  MongoDBUploaderConfig,
34
33
  )
34
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
35
35
 
36
36
  SOURCE_COLLECTION = "sample-mongodb-data"
37
37
 
@@ -13,11 +13,6 @@ from test.integration.connectors.utils.constants import DESTINATION_TAG, GRAPH_D
13
13
  from test.integration.connectors.utils.docker import container_context
14
14
  from unstructured_ingest.error import DestinationConnectionError
15
15
  from unstructured_ingest.utils.chunking import elements_from_base64_gzipped_json
16
- from unstructured_ingest.v2.interfaces.file_data import (
17
- FileData,
18
- FileDataSourceMetadata,
19
- SourceIdentifiers,
20
- )
21
16
  from unstructured_ingest.v2.processes.connectors.neo4j import (
22
17
  CONNECTOR_TYPE,
23
18
  Label,
@@ -28,6 +23,11 @@ from unstructured_ingest.v2.processes.connectors.neo4j import (
28
23
  Neo4jUploadStager,
29
24
  Relationship,
30
25
  )
26
+ from unstructured_ingest.v2.types.file_data import (
27
+ FileData,
28
+ FileDataSourceMetadata,
29
+ SourceIdentifiers,
30
+ )
31
31
 
32
32
  USERNAME = "neo4j"
33
33
  PASSWORD = "password"
@@ -15,7 +15,6 @@ from test.integration.connectors.utils.validation.source import (
15
15
  source_connector_validation,
16
16
  )
17
17
  from test.integration.utils import requires_env
18
- from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
19
18
  from unstructured_ingest.v2.processes.connectors.onedrive import (
20
19
  CONNECTOR_TYPE,
21
20
  OnedriveAccessConfig,
@@ -27,6 +26,7 @@ from unstructured_ingest.v2.processes.connectors.onedrive import (
27
26
  OnedriveUploader,
28
27
  OnedriveUploaderConfig,
29
28
  )
29
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
30
30
 
31
31
 
32
32
  @pytest.fixture
@@ -19,7 +19,6 @@ from test.integration.connectors.utils.validation.destination import (
19
19
  )
20
20
  from test.integration.utils import requires_env
21
21
  from unstructured_ingest.error import DestinationConnectionError
22
- from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
23
22
  from unstructured_ingest.v2.logger import logger
24
23
  from unstructured_ingest.v2.processes.connectors.pinecone import (
25
24
  CONNECTOR_TYPE,
@@ -31,6 +30,7 @@ from unstructured_ingest.v2.processes.connectors.pinecone import (
31
30
  PineconeUploadStager,
32
31
  PineconeUploadStagerConfig,
33
32
  )
33
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
34
34
 
35
35
  METADATA_BYTES_LIMIT = (
36
36
  40960 # 40KB https://docs.pinecone.io/reference/quotas-and-limits#hard-limits
@@ -16,7 +16,6 @@ from test.integration.connectors.utils.validation.destination import (
16
16
  stager_validation,
17
17
  )
18
18
  from test.integration.utils import requires_env
19
- from unstructured_ingest.v2.interfaces.file_data import FileData, SourceIdentifiers
20
19
  from unstructured_ingest.v2.processes.connectors.qdrant.cloud import (
21
20
  CloudQdrantAccessConfig,
22
21
  CloudQdrantConnectionConfig,
@@ -45,6 +44,7 @@ from unstructured_ingest.v2.processes.connectors.qdrant.server import (
45
44
  ServerQdrantUploadStager,
46
45
  ServerQdrantUploadStagerConfig,
47
46
  )
47
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
48
48
 
49
49
  COLLECTION_NAME = f"test-coll-{uuid.uuid4().hex[:12]}"
50
50
  VECTORS_CONFIG = {"size": 384, "distance": "Cosine"}
@@ -11,7 +11,6 @@ from redis.asyncio import Redis, from_url
11
11
 
12
12
  from test.integration.connectors.utils.constants import DESTINATION_TAG, NOSQL_TAG
13
13
  from test.integration.utils import requires_env
14
- from unstructured_ingest.v2.interfaces.file_data import FileData, SourceIdentifiers
15
14
  from unstructured_ingest.v2.processes.connectors.redisdb import (
16
15
  CONNECTOR_TYPE as REDIS_CONNECTOR_TYPE,
17
16
  )
@@ -21,6 +20,7 @@ from unstructured_ingest.v2.processes.connectors.redisdb import (
21
20
  RedisUploader,
22
21
  RedisUploaderConfig,
23
22
  )
23
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
24
24
 
25
25
 
26
26
  async def delete_record(client: Redis, element_id: str, key_prefix: str) -> None:
@@ -18,7 +18,6 @@ from test.integration.connectors.utils.validation.source import (
18
18
  )
19
19
  from test.integration.utils import requires_env
20
20
  from unstructured_ingest.v2.errors import UserAuthError, UserError
21
- from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
22
21
  from unstructured_ingest.v2.processes.connectors.fsspec.s3 import (
23
22
  CONNECTOR_TYPE,
24
23
  S3AccessConfig,
@@ -30,6 +29,7 @@ from unstructured_ingest.v2.processes.connectors.fsspec.s3 import (
30
29
  S3Uploader,
31
30
  S3UploaderConfig,
32
31
  )
32
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
33
33
 
34
34
 
35
35
  def validate_predownload_file_data(file_data: FileData):
@@ -11,7 +11,6 @@ import requests
11
11
 
12
12
  from test.integration.connectors.utils.constants import DESTINATION_TAG, NOSQL_TAG
13
13
  from test.integration.utils import requires_env
14
- from unstructured_ingest.v2.interfaces.file_data import FileData, SourceIdentifiers
15
14
  from unstructured_ingest.v2.logger import logger
16
15
  from unstructured_ingest.v2.processes.connectors.vectara import (
17
16
  CONNECTOR_TYPE as VECTARA_CONNECTOR_TYPE,
@@ -24,6 +23,7 @@ from unstructured_ingest.v2.processes.connectors.vectara import (
24
23
  VectaraUploadStager,
25
24
  VectaraUploadStagerConfig,
26
25
  )
26
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
27
27
 
28
28
 
29
29
  def validate_upload(document: dict, expected_data: dict):
@@ -4,7 +4,8 @@ from pathlib import Path
4
4
 
5
5
  from test.integration.connectors.utils.validation.utils import ValidationConfig
6
6
  from unstructured_ingest.utils.data_prep import get_data
7
- from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers, UploadStager
7
+ from unstructured_ingest.v2.interfaces import UploadStager
8
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
8
9
 
9
10
 
10
11
  class StagerValidationConfigs(ValidationConfig):
@@ -8,7 +8,8 @@ from deepdiff import DeepDiff
8
8
  from pydantic import Field
9
9
 
10
10
  from test.integration.connectors.utils.validation.utils import ValidationConfig
11
- from unstructured_ingest.v2.interfaces import Downloader, FileData, Indexer
11
+ from unstructured_ingest.v2.interfaces import Downloader, Indexer
12
+ from unstructured_ingest.v2.types.file_data import FileData
12
13
 
13
14
  NONSTANDARD_METADATA_FIELDS = {
14
15
  "additional_metadata.@microsoft.graph.downloadUrl": [
@@ -9,7 +9,6 @@ from weaviate.client import WeaviateClient
9
9
 
10
10
  from test.integration.connectors.utils.constants import DESTINATION_TAG, VECTOR_DB_TAG
11
11
  from test.integration.connectors.utils.docker import container_context
12
- from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
13
12
  from unstructured_ingest.v2.processes.connectors.weaviate.local import (
14
13
  CONNECTOR_TYPE,
15
14
  LocalWeaviateConnectionConfig,
@@ -17,6 +16,7 @@ from unstructured_ingest.v2.processes.connectors.weaviate.local import (
17
16
  LocalWeaviateUploaderConfig,
18
17
  LocalWeaviateUploadStager,
19
18
  )
19
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
20
20
 
21
21
  COLLECTION_NAME = "elements"
22
22
 
test/unit/test_html.py CHANGED
@@ -5,7 +5,7 @@ from bs4 import BeautifulSoup
5
5
  from pytest_mock import MockerFixture
6
6
 
7
7
  from unstructured_ingest.utils.html import HtmlMixin
8
- from unstructured_ingest.v2.interfaces import FileData, SourceIdentifiers
8
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
9
9
 
10
10
 
11
11
  def test_extract_images(mocker: MockerFixture):
@@ -8,7 +8,6 @@ from pyiceberg.exceptions import CommitFailedException
8
8
  from pytest_mock import MockerFixture
9
9
 
10
10
  from unstructured_ingest.v2.errors import ProviderError, UserError
11
- from unstructured_ingest.v2.interfaces.file_data import FileData, SourceIdentifiers
12
11
  from unstructured_ingest.v2.processes.connectors.ibm_watsonx import IBM_WATSONX_S3_CONNECTOR_TYPE
13
12
  from unstructured_ingest.v2.processes.connectors.ibm_watsonx.ibm_watsonx_s3 import (
14
13
  IbmWatsonxAccessConfig,
@@ -16,6 +15,7 @@ from unstructured_ingest.v2.processes.connectors.ibm_watsonx.ibm_watsonx_s3 impo
16
15
  IbmWatsonxUploader,
17
16
  IbmWatsonxUploaderConfig,
18
17
  )
18
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
19
19
 
20
20
 
21
21
  @pytest.fixture
@@ -3,10 +3,9 @@ from pathlib import Path
3
3
  import pytest
4
4
  from pytest_mock import MockerFixture
5
5
 
6
- from unstructured_ingest.v2.interfaces import FileData
7
- from unstructured_ingest.v2.interfaces.file_data import SourceIdentifiers
8
6
  from unstructured_ingest.v2.interfaces.upload_stager import UploadStagerConfig
9
7
  from unstructured_ingest.v2.processes.connectors.duckdb.base import BaseDuckDBUploadStager
8
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
10
9
 
11
10
 
12
11
  @pytest.fixture
@@ -4,13 +4,13 @@ import pandas as pd
4
4
  import pytest
5
5
  from pytest_mock import MockerFixture
6
6
 
7
- from unstructured_ingest.v2.interfaces.file_data import FileData, SourceIdentifiers
8
7
  from unstructured_ingest.v2.processes.connectors.sql.sql import (
9
8
  SQLConnectionConfig,
10
9
  SQLUploader,
11
10
  SQLUploaderConfig,
12
11
  SQLUploadStager,
13
12
  )
13
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
14
14
 
15
15
 
16
16
  @pytest.fixture
@@ -1 +1 @@
1
- __version__ = "0.5.25" # pragma: no cover
1
+ __version__ = "0.6.0" # pragma: no cover
@@ -7,8 +7,9 @@ from uuid import NAMESPACE_DNS, uuid5
7
7
  from pydantic import BaseModel, Field
8
8
 
9
9
  from unstructured_ingest.utils.dep_check import requires_dependencies
10
- from unstructured_ingest.v2.interfaces import DownloadResponse, FileData, SourceIdentifiers
10
+ from unstructured_ingest.v2.interfaces import DownloadResponse
11
11
  from unstructured_ingest.v2.logger import logger
12
+ from unstructured_ingest.v2.types.file_data import FileData, SourceIdentifiers
12
13
 
13
14
  if TYPE_CHECKING:
14
15
  from bs4.element import Tag
@@ -1,11 +1,3 @@
1
- from unstructured_ingest.v2.types.file_data import (
2
- BatchFileData,
3
- BatchItem,
4
- FileData,
5
- FileDataSourceMetadata,
6
- SourceIdentifiers,
7
- )
8
-
9
1
  from .connector import AccessConfig, BaseConnector, ConnectionConfig
10
2
  from .downloader import Downloader, DownloaderConfig, DownloadResponse, download_responses
11
3
  from .indexer import Indexer, IndexerConfig
@@ -19,7 +11,6 @@ __all__ = [
19
11
  "download_responses",
20
12
  "Downloader",
21
13
  "DownloaderConfig",
22
- "FileData",
23
14
  "Indexer",
24
15
  "IndexerConfig",
25
16
  "BaseProcess",
@@ -28,13 +19,9 @@ __all__ = [
28
19
  "UploadStagerConfig",
29
20
  "Uploader",
30
21
  "UploaderConfig",
31
- "SourceIdentifiers",
32
22
  "UploadContent",
33
23
  "AccessConfig",
34
24
  "ConnectionConfig",
35
25
  "BaseConnector",
36
- "FileDataSourceMetadata",
37
- "BatchFileData",
38
- "BatchItem",
39
26
  "VectorDBUploader",
40
27
  ]
@@ -6,8 +6,8 @@ from typing import Any, Optional, TypedDict, TypeVar, Union
6
6
  from pydantic import BaseModel, Field
7
7
 
8
8
  from unstructured_ingest.v2.interfaces.connector import BaseConnector
9
- from unstructured_ingest.v2.interfaces.file_data import FileData
10
9
  from unstructured_ingest.v2.interfaces.process import BaseProcess
10
+ from unstructured_ingest.v2.types.file_data import FileData
11
11
 
12
12
 
13
13
  class DownloaderConfig(BaseModel):
@@ -4,8 +4,8 @@ from typing import Any, AsyncGenerator, Generator, Optional, TypeVar
4
4
  from pydantic import BaseModel
5
5
 
6
6
  from unstructured_ingest.v2.interfaces.connector import BaseConnector
7
- from unstructured_ingest.v2.interfaces.file_data import FileData
8
7
  from unstructured_ingest.v2.interfaces.process import BaseProcess
8
+ from unstructured_ingest.v2.types.file_data import FileData
9
9
 
10
10
 
11
11
  class IndexerConfig(BaseModel):
@@ -7,8 +7,8 @@ from pydantic import BaseModel
7
7
 
8
8
  from unstructured_ingest.utils import ndjson
9
9
  from unstructured_ingest.utils.data_prep import get_data, write_data
10
- from unstructured_ingest.v2.interfaces.file_data import FileData
11
- from unstructured_ingest.v2.interfaces.process import BaseProcess
10
+ from unstructured_ingest.v2.interfaces import BaseProcess
11
+ from unstructured_ingest.v2.types.file_data import FileData
12
12
 
13
13
 
14
14
  class UploadStagerConfig(BaseModel):
@@ -6,9 +6,8 @@ from typing import Any, TypeVar
6
6
  from pydantic import BaseModel
7
7
 
8
8
  from unstructured_ingest.utils.data_prep import get_data
9
- from unstructured_ingest.v2.interfaces.connector import BaseConnector
10
- from unstructured_ingest.v2.interfaces.file_data import FileData
11
- from unstructured_ingest.v2.interfaces.process import BaseProcess
9
+ from unstructured_ingest.v2.interfaces import BaseConnector, BaseProcess
10
+ from unstructured_ingest.v2.types.file_data import FileData
12
11
 
13
12
 
14
13
  class UploaderConfig(BaseModel):
@@ -5,11 +5,10 @@ from pathlib import Path
5
5
  from typing import Callable, Optional, TypedDict
6
6
 
7
7
  from unstructured_ingest.utils.data_prep import write_data
8
- from unstructured_ingest.v2.interfaces import FileData
9
- from unstructured_ingest.v2.interfaces.file_data import file_data_from_file
10
8
  from unstructured_ingest.v2.logger import logger
11
9
  from unstructured_ingest.v2.pipeline.interfaces import PipelineStep
12
10
  from unstructured_ingest.v2.processes.chunker import Chunker
11
+ from unstructured_ingest.v2.types.file_data import FileData, file_data_from_file
13
12
  from unstructured_ingest.v2.utils import serialize_base_model_json
14
13
 
15
14
  STEP_ID = "chunk"
@@ -6,11 +6,10 @@ from dataclasses import dataclass
6
6
  from pathlib import Path
7
7
  from typing import Callable, Optional, TypedDict, TypeVar
8
8
 
9
- from unstructured_ingest.v2.interfaces import FileData, download_responses
10
- from unstructured_ingest.v2.interfaces.downloader import Downloader
11
- from unstructured_ingest.v2.interfaces.file_data import file_data_from_file
9
+ from unstructured_ingest.v2.interfaces import Downloader, download_responses
12
10
  from unstructured_ingest.v2.logger import logger
13
11
  from unstructured_ingest.v2.pipeline.interfaces import PipelineStep
12
+ from unstructured_ingest.v2.types.file_data import FileData, file_data_from_file
14
13
  from unstructured_ingest.v2.utils import serialize_base_model_json
15
14
 
16
15
  DownloaderT = TypeVar("DownloaderT", bound=Downloader)
@@ -5,11 +5,10 @@ from pathlib import Path
5
5
  from typing import Callable, Optional, TypedDict
6
6
 
7
7
  from unstructured_ingest.utils.data_prep import write_data
8
- from unstructured_ingest.v2.interfaces import FileData
9
- from unstructured_ingest.v2.interfaces.file_data import file_data_from_file
10
8
  from unstructured_ingest.v2.logger import logger
11
9
  from unstructured_ingest.v2.pipeline.interfaces import PipelineStep
12
10
  from unstructured_ingest.v2.processes.embedder import Embedder
11
+ from unstructured_ingest.v2.types.file_data import FileData, file_data_from_file
13
12
  from unstructured_ingest.v2.utils import serialize_base_model_json
14
13
 
15
14
  STEP_ID = "embed"
@@ -2,10 +2,10 @@ import asyncio
2
2
  from dataclasses import dataclass
3
3
  from typing import Callable, Optional
4
4
 
5
- from unstructured_ingest.v2.interfaces.file_data import file_data_from_file
6
5
  from unstructured_ingest.v2.logger import logger
7
6
  from unstructured_ingest.v2.pipeline.interfaces import PipelineStep
8
7
  from unstructured_ingest.v2.processes.filter import Filterer
8
+ from unstructured_ingest.v2.types.file_data import file_data_from_file
9
9
 
10
10
  STEP_ID = "filter"
11
11