unstructured-ingest 0.5.17__tar.gz → 0.5.19__tar.gz

{unstructured_ingest-0.5.17/unstructured_ingest.egg-info → unstructured_ingest-0.5.19}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: unstructured-ingest
-Version: 0.5.17
+Version: 0.5.19
 Summary: A library that prepares raw documents for downstream ML tasks.
 Home-page: https://github.com/Unstructured-IO/unstructured-ingest
 Author: Unstructured Technologies
@@ -22,13 +22,13 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9.0,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
-Requires-Dist: opentelemetry-sdk
-Requires-Dist: pydantic>=2.7
-Requires-Dist: dataclasses_json
 Requires-Dist: pandas
-Requires-Dist: python-dateutil
 Requires-Dist: tqdm
+Requires-Dist: python-dateutil
+Requires-Dist: pydantic>=2.7
 Requires-Dist: click
+Requires-Dist: opentelemetry-sdk
+Requires-Dist: dataclasses_json
 Provides-Extra: remote
 Requires-Dist: unstructured-client>=0.30.0; extra == "remote"
 Provides-Extra: csv
@@ -81,8 +81,8 @@ Requires-Dist: chromadb; extra == "chroma"
 Provides-Extra: clarifai
 Requires-Dist: clarifai; extra == "clarifai"
 Provides-Extra: confluence
-Requires-Dist: requests; extra == "confluence"
 Requires-Dist: atlassian-python-api; extra == "confluence"
+Requires-Dist: requests; extra == "confluence"
 Provides-Extra: couchbase
 Requires-Dist: couchbase; extra == "couchbase"
 Provides-Extra: delta-table
@@ -99,11 +99,11 @@ Provides-Extra: elasticsearch
 Requires-Dist: elasticsearch[async]; extra == "elasticsearch"
 Provides-Extra: gcs
 Requires-Dist: gcsfs; extra == "gcs"
-Requires-Dist: bs4; extra == "gcs"
 Requires-Dist: fsspec; extra == "gcs"
+Requires-Dist: bs4; extra == "gcs"
 Provides-Extra: github
-Requires-Dist: requests; extra == "github"
 Requires-Dist: pygithub>1.58.0; extra == "github"
+Requires-Dist: requests; extra == "github"
 Provides-Extra: gitlab
 Requires-Dist: python-gitlab; extra == "gitlab"
 Provides-Extra: google-drive
@@ -124,14 +124,14 @@ Requires-Dist: pymilvus; extra == "milvus"
 Provides-Extra: mongodb
 Requires-Dist: pymongo; extra == "mongodb"
 Provides-Extra: neo4j
-Requires-Dist: networkx; extra == "neo4j"
 Requires-Dist: neo4j-rust-ext; extra == "neo4j"
 Requires-Dist: cymple; extra == "neo4j"
+Requires-Dist: networkx; extra == "neo4j"
 Provides-Extra: notion
-Requires-Dist: backoff; extra == "notion"
-Requires-Dist: httpx; extra == "notion"
 Requires-Dist: notion-client; extra == "notion"
 Requires-Dist: htmlBuilder; extra == "notion"
+Requires-Dist: backoff; extra == "notion"
+Requires-Dist: httpx; extra == "notion"
 Provides-Extra: onedrive
 Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
 Requires-Dist: msal; extra == "onedrive"
@@ -165,8 +165,8 @@ Requires-Dist: fsspec; extra == "sftp"
 Provides-Extra: slack
 Requires-Dist: slack_sdk[optional]; extra == "slack"
 Provides-Extra: snowflake
-Requires-Dist: psycopg2-binary; extra == "snowflake"
 Requires-Dist: snowflake-connector-python; extra == "snowflake"
+Requires-Dist: psycopg2-binary; extra == "snowflake"
 Provides-Extra: wikipedia
 Requires-Dist: wikipedia; extra == "wikipedia"
 Provides-Extra: weaviate
@@ -178,22 +178,22 @@ Requires-Dist: databricks-sql-connector; extra == "databricks-delta-tables"
 Provides-Extra: singlestore
 Requires-Dist: singlestoredb; extra == "singlestore"
 Provides-Extra: vectara
-Requires-Dist: requests; extra == "vectara"
 Requires-Dist: aiofiles; extra == "vectara"
+Requires-Dist: requests; extra == "vectara"
 Requires-Dist: httpx; extra == "vectara"
 Provides-Extra: vastdb
-Requires-Dist: vastdb; extra == "vastdb"
-Requires-Dist: ibis; extra == "vastdb"
 Requires-Dist: pyarrow; extra == "vastdb"
+Requires-Dist: ibis; extra == "vastdb"
+Requires-Dist: vastdb; extra == "vastdb"
 Provides-Extra: zendesk
 Requires-Dist: httpx; extra == "zendesk"
-Requires-Dist: bs4; extra == "zendesk"
 Requires-Dist: aiofiles; extra == "zendesk"
+Requires-Dist: bs4; extra == "zendesk"
 Provides-Extra: embed-huggingface
 Requires-Dist: sentence-transformers; extra == "embed-huggingface"
 Provides-Extra: embed-octoai
-Requires-Dist: openai; extra == "embed-octoai"
 Requires-Dist: tiktoken; extra == "embed-octoai"
+Requires-Dist: openai; extra == "embed-octoai"
 Provides-Extra: embed-vertexai
 Requires-Dist: vertexai; extra == "embed-vertexai"
 Provides-Extra: embed-voyageai
@@ -201,8 +201,8 @@ Requires-Dist: voyageai; extra == "embed-voyageai"
 Provides-Extra: embed-mixedbreadai
 Requires-Dist: mixedbread-ai; extra == "embed-mixedbreadai"
 Provides-Extra: openai
-Requires-Dist: openai; extra == "openai"
 Requires-Dist: tiktoken; extra == "openai"
+Requires-Dist: openai; extra == "openai"
 Provides-Extra: bedrock
 Requires-Dist: aioboto3; extra == "bedrock"
 Requires-Dist: boto3; extra == "bedrock"

{unstructured_ingest-0.5.17 → unstructured_ingest-0.5.19}/test/integration/connectors/test_redis.py

@@ -23,20 +23,22 @@ from unstructured_ingest.v2.processes.connectors.redisdb import (
 )
 
 
-async def delete_record(client: Redis, element_id: str) -> None:
-    await client.delete(element_id)
+async def delete_record(client: Redis, element_id: str, key_prefix: str) -> None:
+    key_with_prefix = f"{key_prefix}{element_id}"
+    await client.delete(key_with_prefix)
 
 
-async def validate_upload(client: Redis, first_element: dict):
+async def validate_upload(client: Redis, first_element: dict, key_prefix: str) -> None:
     element_id = first_element["element_id"]
+    key_with_prefix = f"{key_prefix}{element_id}"
     expected_text = first_element["text"]
     expected_embeddings = first_element["embeddings"]
     async with client.pipeline(transaction=True) as pipe:
         try:
-            response = await pipe.json().get(element_id, "$").execute()
+            response = await pipe.json().get(key_with_prefix, "$").execute()
             response = response[0][0]
         except redis_exceptions.ResponseError:
-            response = await pipe.get(element_id).execute()
+            response = await pipe.get(key_with_prefix).execute()
             response = json.loads(response[0])
 
     embedding_similarity = np.linalg.norm(
@@ -53,6 +55,7 @@ async def redis_destination_test(
     upload_file: Path,
     tmp_path: Path,
     connection_kwargs: dict,
+    uploader_config: dict,
     uri: Optional[str] = None,
     password: Optional[str] = None,
 ):
@@ -60,8 +63,9 @@ async def redis_destination_test(
         connection_config=RedisConnectionConfig(
             **connection_kwargs, access_config=RedisAccessConfig(uri=uri, password=password)
         ),
-        upload_config=RedisUploaderConfig(batch_size=10),
+        upload_config=RedisUploaderConfig(batch_size=10, **uploader_config),
     )
+    key_prefix = uploader.upload_config.key_prefix
 
     file_data = FileData(
         source_identifiers=SourceIdentifiers(fullpath=upload_file.name, filename=upload_file.name),
@@ -78,20 +82,32 @@ async def redis_destination_test(
 
         if uri:
             async with from_url(uri) as client:
-                await validate_upload(client=client, first_element=first_element)
+                await validate_upload(
+                    client=client,
+                    first_element=first_element,
+                    key_prefix=key_prefix,
+                )
         else:
             async with Redis(**connection_kwargs, password=password) as client:
-                await validate_upload(client=client, first_element=first_element)
+                await validate_upload(
+                    client=client,
+                    first_element=first_element,
+                    key_prefix=key_prefix,
+                )
     except Exception as e:
         raise e
     finally:
         if uri:
             async with from_url(uri) as client:
-                tasks = [delete_record(client, element["element_id"]) for element in elements]
+                tasks = [
+                    delete_record(client, element["element_id"], key_prefix) for element in elements
+                ]
                 await asyncio.gather(*tasks)
         else:
             async with Redis(**connection_kwargs, password=password) as client:
-                tasks = [delete_record(client, element["element_id"]) for element in elements]
+                tasks = [
+                    delete_record(client, element["element_id"], key_prefix) for element in elements
+                ]
                 await asyncio.gather(*tasks)
 
 
@@ -105,8 +121,13 @@ async def test_redis_destination_azure_with_password(upload_file: Path, tmp_path
         "db": 0,
         "ssl": True,
     }
+    uploader_config = {
+        "key_prefix": "test_ingest:",
+    }
     redis_pw = os.environ["AZURE_REDIS_INGEST_TEST_PASSWORD"]
-    await redis_destination_test(upload_file, tmp_path, connection_kwargs, password=redis_pw)
+    await redis_destination_test(
+        upload_file, tmp_path, connection_kwargs, uploader_config, password=redis_pw
+    )
 
 
 @pytest.mark.asyncio
@@ -114,6 +135,9 @@ async def test_redis_destination_azure_with_password(upload_file: Path, tmp_path
 @requires_env("AZURE_REDIS_INGEST_TEST_PASSWORD")
 async def test_redis_destination_azure_with_uri(upload_file: Path, tmp_path: Path):
     connection_kwargs = {}
+    uploader_config = {
+        "key_prefix": "test_ingest:",
+    }
     redis_pw = os.environ["AZURE_REDIS_INGEST_TEST_PASSWORD"]
     uri = f"rediss://:{redis_pw}@utic-dashboard-dev.redis.cache.windows.net:6380/0"
-    await redis_destination_test(upload_file, tmp_path, connection_kwargs, uri=uri)
+    await redis_destination_test(upload_file, tmp_path, connection_kwargs, uploader_config, uri=uri)

unstructured_ingest-0.5.19/unstructured_ingest/__version__.py

@@ -0,0 +1 @@
+__version__ = "0.5.19"  # pragma: no cover

{unstructured_ingest-0.5.17 → unstructured_ingest-0.5.19}/unstructured_ingest/utils/data_prep.py

@@ -192,6 +192,16 @@ def get_data(path: Union[Path, str]) -> list[dict]:
             logger.warning(f"failed to read {path} as parquet: {e}")
 
 
+def get_json_data(path: Path) -> list[dict]:
+    with path.open() as f:
+        if path.suffix == ".json":
+            return json.load(f)
+        elif path.suffix == ".ndjson":
+            return ndjson.load(f)
+        else:
+            raise ValueError(f"Unsupported file type: {path}")
+
+
 def get_data_df(path: Path) -> pd.DataFrame:
     with path.open() as f:
         if path.suffix == ".json":

{unstructured_ingest-0.5.17 → unstructured_ingest-0.5.19}/unstructured_ingest/v2/processes/connectors/delta_table.py

@@ -1,4 +1,3 @@
-import json
 import os
 import traceback
 from dataclasses import dataclass, field
@@ -11,7 +10,7 @@ import pandas as pd
 from pydantic import Field, Secret
 
 from unstructured_ingest.error import DestinationConnectionError
-from unstructured_ingest.utils.data_prep import get_data_df
+from unstructured_ingest.utils.data_prep import get_data_df, get_json_data
 from unstructured_ingest.utils.dep_check import requires_dependencies
 from unstructured_ingest.utils.table import convert_to_pandas_dataframe
 from unstructured_ingest.v2.interfaces import (
@@ -86,9 +85,7 @@ class DeltaTableUploadStager(UploadStager):
         output_filename: str,
         **kwargs: Any,
     ) -> Path:
-        with open(elements_filepath) as elements_file:
-            elements_contents = json.load(elements_file)
-
+        elements_contents = get_json_data(elements_filepath)
         output_path = Path(output_dir) / Path(f"{output_filename}.parquet")
 
         df = convert_to_pandas_dataframe(elements_dict=elements_contents)

{unstructured_ingest-0.5.17 → unstructured_ingest-0.5.19}/unstructured_ingest/v2/processes/connectors/neo4j.py

@@ -1,7 +1,6 @@
 from __future__ import annotations
 
 import asyncio
-import json
 import uuid
 from collections import defaultdict
 from contextlib import asynccontextmanager
@@ -14,7 +13,7 @@ from pydantic import BaseModel, ConfigDict, Field, Secret, field_validator
 
 from unstructured_ingest.error import DestinationConnectionError
 from unstructured_ingest.logger import logger
-from unstructured_ingest.utils.data_prep import batch_generator
+from unstructured_ingest.utils.data_prep import batch_generator, get_json_data
 from unstructured_ingest.utils.dep_check import requires_dependencies
 from unstructured_ingest.v2.interfaces import (
     AccessConfig,
@@ -97,8 +96,7 @@ class Neo4jUploadStager(UploadStager):
         output_filename: str,
         **kwargs: Any,
     ) -> Path:
-        with elements_filepath.open() as file:
-            elements = json.load(file)
+        elements = get_json_data(elements_filepath)
 
         nx_graph = self._create_lexical_graph(
             elements, self._create_document_node(file_data=file_data)
@@ -294,8 +292,7 @@ class Neo4jUploader(Uploader):
         return True
 
     async def run_async(self, path: Path, file_data: FileData, **kwargs) -> None:  # type: ignore
-        with path.open() as file:
-            staged_data = json.load(file)
+        staged_data = get_json_data(path)
 
         graph_data = _GraphData.model_validate(staged_data)
         async with self.connection_config.get_client() as client:

{unstructured_ingest-0.5.17 → unstructured_ingest-0.5.19}/unstructured_ingest/v2/processes/connectors/onedrive.py

@@ -35,6 +35,10 @@ from unstructured_ingest.v2.processes.connector_registry import (
     DestinationRegistryEntry,
     SourceRegistryEntry,
 )
+from unstructured_ingest.v2.processes.utils.blob_storage import (
+    BlobStoreUploadStager,
+    BlobStoreUploadStagerConfig,
+)
 
 if TYPE_CHECKING:
     from office365.graph_client import GraphClient
@@ -428,4 +432,6 @@ onedrive_destination_entry = DestinationRegistryEntry(
     connection_config=OnedriveConnectionConfig,
     uploader=OnedriveUploader,
     uploader_config=OnedriveUploaderConfig,
+    upload_stager_config=BlobStoreUploadStagerConfig,
+    upload_stager=BlobStoreUploadStager,
 )

{unstructured_ingest-0.5.17 → unstructured_ingest-0.5.19}/unstructured_ingest/v2/processes/connectors/redisdb.py

@@ -110,6 +110,7 @@ class RedisConnectionConfig(ConnectionConfig):
 
 class RedisUploaderConfig(UploaderConfig):
     batch_size: int = Field(default=100, description="Number of records per batch")
+    key_prefix: str = Field(default="", description="Prefix for Redis keys")
 
 
 @dataclass
@@ -145,11 +146,11 @@ class RedisUploader(Uploader):
         async with self.connection_config.create_async_client() as async_client:
             async with async_client.pipeline(transaction=True) as pipe:
                 for element in batch:
-                    element_id = element["element_id"]
+                    key_with_prefix = f"{self.upload_config.key_prefix}{element['element_id']}"
                     if redis_stack:
-                        pipe.json().set(element_id, "$", element)
+                        pipe.json().set(key_with_prefix, "$", element)
                     else:
-                        pipe.set(element_id, json.dumps(element))
+                        pipe.set(key_with_prefix, json.dumps(element))
                 await pipe.execute()
 
     @requires_dependencies(["redis"], extras="redis")
@@ -159,16 +160,16 @@ class RedisUploader(Uploader):
         redis_stack = True
         async with self.connection_config.create_async_client() as async_client:
             async with async_client.pipeline(transaction=True) as pipe:
-                element_id = element["element_id"]
+                key_with_prefix = f"{self.upload_config.key_prefix}{element['element_id']}"
                 try:
                     # Redis with stack extension supports JSON type
-                    await pipe.json().set(element_id, "$", element).execute()
+                    await pipe.json().set(key_with_prefix, "$", element).execute()
                 except redis_exceptions.ResponseError as e:
                     message = str(e)
                     if "unknown command `JSON.SET`" in message:
                         # if this error occurs, Redis server doesn't support JSON type,
                         # so save as string type instead
-                        await pipe.set(element_id, json.dumps(element)).execute()
+                        await pipe.set(key_with_prefix, json.dumps(element)).execute()
                         redis_stack = False
                     else:
                         raise e

{unstructured_ingest-0.5.17 → unstructured_ingest-0.5.19/unstructured_ingest.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: unstructured-ingest
-Version: 0.5.17
+Version: 0.5.19
 Summary: A library that prepares raw documents for downstream ML tasks.
 Home-page: https://github.com/Unstructured-IO/unstructured-ingest
 Author: Unstructured Technologies
@@ -22,13 +22,13 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9.0,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
-Requires-Dist: opentelemetry-sdk
-Requires-Dist: pydantic>=2.7
-Requires-Dist: dataclasses_json
 Requires-Dist: pandas
-Requires-Dist: python-dateutil
 Requires-Dist: tqdm
+Requires-Dist: python-dateutil
+Requires-Dist: pydantic>=2.7
 Requires-Dist: click
+Requires-Dist: opentelemetry-sdk
+Requires-Dist: dataclasses_json
 Provides-Extra: remote
 Requires-Dist: unstructured-client>=0.30.0; extra == "remote"
 Provides-Extra: csv
@@ -81,8 +81,8 @@ Requires-Dist: chromadb; extra == "chroma"
 Provides-Extra: clarifai
 Requires-Dist: clarifai; extra == "clarifai"
 Provides-Extra: confluence
-Requires-Dist: requests; extra == "confluence"
 Requires-Dist: atlassian-python-api; extra == "confluence"
+Requires-Dist: requests; extra == "confluence"
 Provides-Extra: couchbase
 Requires-Dist: couchbase; extra == "couchbase"
 Provides-Extra: delta-table
@@ -99,11 +99,11 @@ Provides-Extra: elasticsearch
 Requires-Dist: elasticsearch[async]; extra == "elasticsearch"
 Provides-Extra: gcs
 Requires-Dist: gcsfs; extra == "gcs"
-Requires-Dist: bs4; extra == "gcs"
 Requires-Dist: fsspec; extra == "gcs"
+Requires-Dist: bs4; extra == "gcs"
 Provides-Extra: github
-Requires-Dist: requests; extra == "github"
 Requires-Dist: pygithub>1.58.0; extra == "github"
+Requires-Dist: requests; extra == "github"
 Provides-Extra: gitlab
 Requires-Dist: python-gitlab; extra == "gitlab"
 Provides-Extra: google-drive
@@ -124,14 +124,14 @@ Requires-Dist: pymilvus; extra == "milvus"
 Provides-Extra: mongodb
 Requires-Dist: pymongo; extra == "mongodb"
 Provides-Extra: neo4j
-Requires-Dist: networkx; extra == "neo4j"
 Requires-Dist: neo4j-rust-ext; extra == "neo4j"
 Requires-Dist: cymple; extra == "neo4j"
+Requires-Dist: networkx; extra == "neo4j"
 Provides-Extra: notion
-Requires-Dist: backoff; extra == "notion"
-Requires-Dist: httpx; extra == "notion"
 Requires-Dist: notion-client; extra == "notion"
 Requires-Dist: htmlBuilder; extra == "notion"
+Requires-Dist: backoff; extra == "notion"
+Requires-Dist: httpx; extra == "notion"
 Provides-Extra: onedrive
 Requires-Dist: Office365-REST-Python-Client; extra == "onedrive"
 Requires-Dist: msal; extra == "onedrive"
@@ -165,8 +165,8 @@ Requires-Dist: fsspec; extra == "sftp"
 Provides-Extra: slack
 Requires-Dist: slack_sdk[optional]; extra == "slack"
 Provides-Extra: snowflake
-Requires-Dist: psycopg2-binary; extra == "snowflake"
 Requires-Dist: snowflake-connector-python; extra == "snowflake"
+Requires-Dist: psycopg2-binary; extra == "snowflake"
 Provides-Extra: wikipedia
 Requires-Dist: wikipedia; extra == "wikipedia"
 Provides-Extra: weaviate
@@ -178,22 +178,22 @@ Requires-Dist: databricks-sql-connector; extra == "databricks-delta-tables"
 Provides-Extra: singlestore
 Requires-Dist: singlestoredb; extra == "singlestore"
 Provides-Extra: vectara
-Requires-Dist: requests; extra == "vectara"
 Requires-Dist: aiofiles; extra == "vectara"
+Requires-Dist: requests; extra == "vectara"
 Requires-Dist: httpx; extra == "vectara"
 Provides-Extra: vastdb
-Requires-Dist: vastdb; extra == "vastdb"
-Requires-Dist: ibis; extra == "vastdb"
 Requires-Dist: pyarrow; extra == "vastdb"
+Requires-Dist: ibis; extra == "vastdb"
+Requires-Dist: vastdb; extra == "vastdb"
 Provides-Extra: zendesk
 Requires-Dist: httpx; extra == "zendesk"
-Requires-Dist: bs4; extra == "zendesk"
 Requires-Dist: aiofiles; extra == "zendesk"
+Requires-Dist: bs4; extra == "zendesk"
 Provides-Extra: embed-huggingface
 Requires-Dist: sentence-transformers; extra == "embed-huggingface"
 Provides-Extra: embed-octoai
-Requires-Dist: openai; extra == "embed-octoai"
 Requires-Dist: tiktoken; extra == "embed-octoai"
+Requires-Dist: openai; extra == "embed-octoai"
 Provides-Extra: embed-vertexai
 Requires-Dist: vertexai; extra == "embed-vertexai"
 Provides-Extra: embed-voyageai
@@ -201,8 +201,8 @@ Requires-Dist: voyageai; extra == "embed-voyageai"
 Provides-Extra: embed-mixedbreadai
 Requires-Dist: mixedbread-ai; extra == "embed-mixedbreadai"
 Provides-Extra: openai
-Requires-Dist: openai; extra == "openai"
 Requires-Dist: tiktoken; extra == "openai"
+Requires-Dist: openai; extra == "openai"
 Provides-Extra: bedrock
 Requires-Dist: aioboto3; extra == "bedrock"
 Requires-Dist: boto3; extra == "bedrock"

unstructured_ingest-0.5.17/unstructured_ingest/__version__.py

@@ -1 +0,0 @@
-__version__ = "0.5.17"  # pragma: no cover