unstructured-ingest 0.0.3__tar.gz → 0.0.4__tar.gz

{unstructured-ingest-0.0.3 → unstructured-ingest-0.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: unstructured-ingest
-Version: 0.0.3
+Version: 0.0.4
 Summary: A library that prepares raw documents for downstream ML tasks.
 Home-page: https://github.com/Unstructured-IO/unstructured-ingest
 Author: Unstructured Technologies
@@ -21,6 +21,7 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.9.0,<3.13
 Description-Content-Type: text/markdown
+Provides-Extra: remote
 Provides-Extra: csv
 Provides-Extra: doc
 Provides-Extra: docx
@@ -37,7 +38,7 @@ Provides-Extra: rst
 Provides-Extra: tsv
 Provides-Extra: xlsx
 Provides-Extra: airtable
-Provides-Extra: astra
+Provides-Extra: astradb
 Provides-Extra: azure
 Provides-Extra: azure-cognitive-search
 Provides-Extra: biomed
@@ -45,6 +46,7 @@ Provides-Extra: box
 Provides-Extra: chroma
 Provides-Extra: clarifai
 Provides-Extra: confluence
+Provides-Extra: couchbase
 Provides-Extra: delta-table
 Provides-Extra: discord
 Provides-Extra: dropbox
@@ -75,6 +77,7 @@ Provides-Extra: wikipedia
 Provides-Extra: weaviate
 Provides-Extra: databricks-volumes
 Provides-Extra: singlestore
+Provides-Extra: vectara
 Provides-Extra: embed-huggingface
 Provides-Extra: embed-octoai
 Provides-Extra: embed-vertexai

{unstructured-ingest-0.0.3 → unstructured-ingest-0.0.4}/setup.py

@@ -81,7 +81,7 @@ all_doc_reqs = list(
 )
 connectors_reqs = {
     "airtable": load_requirements("requirements/connectors/airtable.in"),
-    "astra": load_requirements("requirements/connectors/astra.in"),
+    "astradb": load_requirements("requirements/connectors/astradb.in"),
     "azure": load_requirements("requirements/connectors/azure.in"),
     "azure-cognitive-search": load_requirements(
         "requirements/connectors/azure-cognitive-search.in",
@@ -91,6 +91,7 @@ connectors_reqs = {
     "chroma": load_requirements("requirements/connectors/chroma.in"),
     "clarifai": load_requirements("requirements/connectors/clarifai.in"),
     "confluence": load_requirements("requirements/connectors/confluence.in"),
+    "couchbase": load_requirements("requirements/connectors/couchbase.in"),
     "delta-table": load_requirements("requirements/connectors/delta-table.in"),
     "discord": load_requirements("requirements/connectors/discord.in"),
     "dropbox": load_requirements("requirements/connectors/dropbox.in"),
@@ -121,6 +122,7 @@ connectors_reqs = {
     "weaviate": load_requirements("requirements/connectors/weaviate.in"),
     "databricks-volumes": load_requirements("requirements/connectors/databricks-volumes.in"),
     "singlestore": load_requirements("requirements/connectors/singlestore.in"),
+    "vectara": load_requirements("requirements/connectors/vectara.in"),
 }
 
 embed_reqs = {
@@ -150,7 +152,9 @@ docs_reqs = {
     "xlsx": xlsx_reqs,
 }
 
-extras_require = {}
+extras_require = {
+    "remote": load_requirements("requirements/remote/client.in"),
+}
 for d in [docs_reqs, connectors_reqs, embed_reqs]:
     extras_require.update(d)
 

unstructured-ingest-0.0.4/test/test_chunking_utils.py

@@ -0,0 +1,36 @@
+from pathlib import Path
+
+import pytest
+from unstructured.chunking import dispatch
+from unstructured.documents.elements import assign_and_map_hash_ids
+from unstructured.partition.auto import partition
+
+from unstructured_ingest.utils.chunking import (
+    assign_and_map_hash_ids as new_assign_and_map_hash_ids,
+)
+
+test_file_path = Path(__file__).resolve()
+project_root = test_file_path.parent.parent
+docs_path = project_root / "example-docs"
+
+
+@pytest.mark.parametrize(
+    "chunking_strategy",
+    ["basic", "by_title"],
+)
+def test_assign_and_map_hash_ids(chunking_strategy):
+    # Make sure the new logic working on dict content matches the
+    # results if using the unstructured version
+    file_path = docs_path / "book-war-and-peace-1p.txt"
+    elements = partition(filename=str(file_path.resolve()), strategy="fast")
+    chunked_elements = dispatch.chunk(elements=elements, chunking_strategy=chunking_strategy)
+    chunked_elements_copy = chunked_elements.copy()
+
+    hashed_chunked_elements = assign_and_map_hash_ids(chunked_elements)
+    og_chunked_elements_dicts = [e.to_dict() for e in hashed_chunked_elements]
+
+    new_chunked_elements_dicts = [e.to_dict() for e in chunked_elements_copy]
+    new_chunked_elements_dicts = new_assign_and_map_hash_ids(new_chunked_elements_dicts)
+
+    for e1, e2 in zip(og_chunked_elements_dicts, new_chunked_elements_dicts):
+        assert e1 == e2

{unstructured-ingest-0.0.3 → unstructured-ingest-0.0.4}/test/test_interfaces.py

@@ -90,7 +90,7 @@ class ExampleIngestDoc(BaseSingleIngestDoc):
         pass
 
 
-@pytest.fixture()
+@pytest.fixture
 def partition_test_results():
     # Reusable partition test results, calculated only once
     result = partition(
@@ -107,7 +107,7 @@ def partition_test_results():
     return result
 
 
-@pytest.fixture()
+@pytest.fixture
 def partition_file_test_results(partition_test_results):
     # Reusable partition_file test results, calculated only once
     return elements_to_dicts(partition_test_results)

unstructured-ingest-0.0.4/test/test_utils_v2.py

@@ -0,0 +1,82 @@
+import json
+from typing import Any
+
+from pydantic import BaseModel, Field, Secret, SecretStr
+from pydantic.types import _SecretBase
+
+from unstructured_ingest.v2.utils import serialize_base_model, serialize_base_model_json
+
+
+class MockChildBaseModel(BaseModel):
+    child_secret_str: SecretStr
+    child_secret_float: Secret[float]
+    child_not_secret_dict: dict[str, Any] = Field(default_factory=dict)
+
+
+class MockBaseModel(BaseModel):
+    secret_str: SecretStr
+    not_secret_bool: bool
+    secret_child_base: Secret[MockChildBaseModel]
+    not_secret_list: list[int] = Field(default_factory=list)
+
+
+model = MockBaseModel(
+    secret_str="secret string",
+    not_secret_bool=False,
+    secret_child_base=MockChildBaseModel(
+        child_secret_str="child secret string",
+        child_secret_float=3.14,
+        child_not_secret_dict={"key": "value"},
+    ),
+    not_secret_list=[1, 2, 3],
+)
+
+
+def test_serialize_base_model():
+
+    serialized_dict = model.dict()
+    assert isinstance(serialized_dict["secret_str"], _SecretBase)
+    assert isinstance(serialized_dict["secret_child_base"], _SecretBase)
+
+    serialized_dict_w_secrets = serialize_base_model(model=model)
+    assert not isinstance(serialized_dict_w_secrets["secret_str"], _SecretBase)
+    assert not isinstance(serialized_dict_w_secrets["secret_child_base"], _SecretBase)
+
+    expected_dict = {
+        "secret_str": "secret string",
+        "not_secret_bool": False,
+        "secret_child_base": {
+            "child_secret_str": "child secret string",
+            "child_secret_float": 3.14,
+            "child_not_secret_dict": {"key": "value"},
+        },
+        "not_secret_list": [1, 2, 3],
+    }
+
+    assert serialized_dict_w_secrets == expected_dict
+
+
+def test_serialize_base_model_json():
+    serialized_json = model.json()
+    serialized_dict = json.loads(serialized_json)
+    expected_dict = {
+        "secret_str": "**********",
+        "not_secret_bool": False,
+        "secret_child_base": "**********",
+        "not_secret_list": [1, 2, 3],
+    }
+    assert expected_dict == serialized_dict
+
+    serialized_json_w_secrets = serialize_base_model_json(model=model)
+    serialized_dict_w_secrets = json.loads(serialized_json_w_secrets)
+    expected_dict_w_secrets = {
+        "secret_str": "secret string",
+        "not_secret_bool": False,
+        "secret_child_base": {
+            "child_secret_str": "child secret string",
+            "child_secret_float": 3.14,
+            "child_not_secret_dict": {"key": "value"},
+        },
+        "not_secret_list": [1, 2, 3],
+    }
+    assert expected_dict_w_secrets == serialized_dict_w_secrets

unstructured-ingest-0.0.4/unstructured_ingest/__version__.py

@@ -0,0 +1 @@
+__version__ = "0.0.4"  # pragma: no cover

{unstructured-ingest-0.0.3 → unstructured-ingest-0.0.4}/unstructured_ingest/cli/cli.py

@@ -1,16 +1,21 @@
+from typing import TYPE_CHECKING
+
 import click
 
 from unstructured_ingest.cli import dest, src
 from unstructured_ingest.v2.cli.cmds import dest as dest_v2
 from unstructured_ingest.v2.cli.cmds import src as src_v2
 
+if TYPE_CHECKING:
+    from click import Command
+
 
 @click.group()
 def ingest():
     pass
 
 
-def get_cmd() -> click.Command:
+def get_cmd() -> "Command":
     """Construct and return a Click command object representing the main command for the CLI.
 
     This function adds all dest_subcommand(s) to each src_subcommand, and adds all of those

{unstructured-ingest-0.0.3 → unstructured-ingest-0.0.4}/unstructured_ingest/cli/cmds/__init__.py

@@ -7,8 +7,8 @@ from unstructured_ingest.cli.base.src import BaseSrcCmd
 from unstructured_ingest.cli.cmds.fsspec.sftp import get_base_src_cmd as sftp_base_src_cmd
 
 from .airtable import get_base_src_cmd as airtable_base_src_cmd
-from .astra import get_base_dest_cmd as astra_base_dest_cmd
-from .astra import get_base_src_cmd as astra_base_src_cmd
+from .astradb import get_base_dest_cmd as astradb_base_dest_cmd
+from .astradb import get_base_src_cmd as astradb_base_src_cmd
 from .azure_cognitive_search import get_base_dest_cmd as azure_cognitive_search_base_dest_cmd
 from .biomed import get_base_src_cmd as biomed_base_src_cmd
 from .chroma import get_base_dest_cmd as chroma_base_dest_cmd
@@ -63,7 +63,7 @@ if t.TYPE_CHECKING:
 
 base_src_cmd_fns: t.List[t.Callable[[], BaseSrcCmd]] = [
     airtable_base_src_cmd,
-    astra_base_src_cmd,
+    astradb_base_src_cmd,
     azure_base_src_cmd,
     biomed_base_src_cmd,
     box_base_src_cmd,
@@ -106,7 +106,7 @@ if src_duplicates:
     )
 
 base_dest_cmd_fns: t.List[t.Callable[[], "BaseDestCmd"]] = [
-    astra_base_dest_cmd,
+    astradb_base_dest_cmd,
     azure_base_dest_cmd,
     box_base_dest_cmd,
     chroma_base_dest_cmd,

unstructured-ingest-0.0.3/unstructured_ingest/cli/cmds/astra.py → unstructured-ingest-0.0.4/unstructured_ingest/cli/cmds/astradb.py

@@ -4,11 +4,11 @@ from dataclasses import dataclass
 import click
 
 from unstructured_ingest.cli.interfaces import CliConfig, Dict
-from unstructured_ingest.connector.astra import AstraWriteConfig, SimpleAstraConfig
+from unstructured_ingest.connector.astradb import AstraDBWriteConfig, SimpleAstraDBConfig
 
 
 @dataclass
-class AstraCliConfig(SimpleAstraConfig, CliConfig):
+class AstraDBCliConfig(SimpleAstraDBConfig, CliConfig):
     @staticmethod
     def get_cli_options() -> t.List[click.Option]:
         options = [
@@ -48,7 +48,7 @@ class AstraCliConfig(SimpleAstraConfig, CliConfig):
 
 
 @dataclass
-class AstraCliWriteConfig(AstraWriteConfig, CliConfig):
+class AstraDBCliWriteConfig(AstraDBWriteConfig, CliConfig):
     @staticmethod
     def get_cli_options() -> t.List[click.Option]:
         options = [
@@ -81,8 +81,8 @@ def get_base_src_cmd():
     from unstructured_ingest.cli.base.src import BaseSrcCmd
 
     cmd_cls = BaseSrcCmd(
-        cmd_name="astra",
-        cli_config=AstraCliConfig,
+        cmd_name="astradb",
+        cli_config=AstraDBCliConfig,
     )
     return cmd_cls
 
@@ -91,9 +91,9 @@ def get_base_dest_cmd():
     from unstructured_ingest.cli.base.dest import BaseDestCmd
 
     cmd_cls = BaseDestCmd(
-        cmd_name="astra",
-        cli_config=AstraCliConfig,
-        additional_cli_options=[AstraCliWriteConfig],
-        write_config=AstraWriteConfig,
+        cmd_name="astradb",
+        cli_config=AstraDBCliConfig,
+        additional_cli_options=[AstraDBCliWriteConfig],
+        write_config=AstraDBWriteConfig,
     )
     return cmd_cls

{unstructured-ingest-0.0.3 → unstructured-ingest-0.0.4}/unstructured_ingest/cli/interfaces.py

@@ -11,7 +11,6 @@ from pathlib import Path
 import click
 from dataclasses_json.core import Json
 from typing_extensions import Self
-from unstructured.chunking import CHUNK_MAX_CHARS_DEFAULT, CHUNK_MULTI_PAGE_DEFAULT
 
 from unstructured_ingest.interfaces import (
     BaseConfig,
@@ -25,6 +24,9 @@ from unstructured_ingest.interfaces import (
     RetryStrategyConfig,
 )
 
+CHUNK_MAX_CHARS_DEFAULT: int = 500
+CHUNK_MULTI_PAGE_DEFAULT: bool = True
+
 
 class Dict(click.ParamType):
     name = "dict"
@@ -412,14 +414,19 @@ class CliFilesStorageConfig(FileStorageConfig, CliMixin):
 class CliEmbeddingConfig(EmbeddingConfig, CliMixin):
     @staticmethod
     def get_cli_options() -> t.List[click.Option]:
-        from unstructured.embed import EMBEDDING_PROVIDER_TO_CLASS_MAP
-
+        embed_providers = [
+            "langchain-openai",
+            "langchain-huggingface",
+            "langchain-aws-bedrock",
+            "langchain-vertexai",
+            "langchain-voyageai",
+            "octoai",
+        ]
         options = [
             click.Option(
                 ["--embedding-provider"],
-                help="Type of the embedding class to be used. Can be one of: "
-                f"{list(EMBEDDING_PROVIDER_TO_CLASS_MAP)}",
-                type=click.Choice(list(EMBEDDING_PROVIDER_TO_CLASS_MAP)),
+                help="Type of the embedding class to be used.",
+                type=click.Choice(embed_providers),
             ),
             click.Option(
                 ["--embedding-api-key"],

unstructured-ingest-0.0.3/unstructured_ingest/connector/astra.py → unstructured-ingest-0.0.4/unstructured_ingest/connector/astradb.py

@@ -30,23 +30,23 @@ NON_INDEXED_FIELDS = ["metadata._node_content", "content"]
 
 
 @dataclass
-class AstraAccessConfig(AccessConfig):
+class AstraDBAccessConfig(AccessConfig):
     token: str = enhanced_field(sensitive=True)
     api_endpoint: str = enhanced_field(sensitive=True)
 
 
 @dataclass
-class SimpleAstraConfig(BaseConnectorConfig):
-    access_config: AstraAccessConfig
+class SimpleAstraDBConfig(BaseConnectorConfig):
+    access_config: AstraDBAccessConfig
     collection_name: str
     namespace: t.Optional[str] = None
 
 
 @dataclass
-class AstraIngestDoc(IngestDocCleanupMixin, BaseSingleIngestDoc):
-    connector_config: SimpleAstraConfig
+class AstraDBIngestDoc(IngestDocCleanupMixin, BaseSingleIngestDoc):
+    connector_config: SimpleAstraDBConfig
     metadata: t.Dict[str, str] = field(default_factory=dict)
-    registry_name: str = "astra"
+    registry_name: str = "astradb"
 
     @property
     def filename(self):
@@ -75,7 +75,7 @@ class AstraIngestDoc(IngestDocCleanupMixin, BaseSingleIngestDoc):
         )
 
     @SourceConnectionError.wrap
-    @requires_dependencies(["astrapy"], extras="astra")
+    @requires_dependencies(["astrapy"], extras="astradb")
     @BaseSingleIngestDoc.skip_if_file_exists
     def get_file(self):
         self.filename.parent.mkdir(parents=True, exist_ok=True)
@@ -89,19 +89,19 @@ class AstraIngestDoc(IngestDocCleanupMixin, BaseSingleIngestDoc):
 
 
 @dataclass
-class AstraSourceConnector(SourceConnectorCleanupMixin, BaseSourceConnector):
-    connector_config: SimpleAstraConfig
+class AstraDBSourceConnector(SourceConnectorCleanupMixin, BaseSourceConnector):
+    connector_config: SimpleAstraDBConfig
     _astra_db: t.Optional["AstraDB"] = field(init=False, default=None)
     _astra_db_collection: t.Optional["AstraDBCollection"] = field(init=False, default=None)
 
     @property
-    @requires_dependencies(["astrapy"], extras="astra")
+    @requires_dependencies(["astrapy"], extras="astradb")
     def astra_db_collection(self) -> "AstraDBCollection":
         if self._astra_db_collection is None:
             from astrapy.db import AstraDB
 
             # Build the Astra DB object.
-            # caller_name/version for AstraDB tracking
+            # caller_name/version for Astra DB tracking
             self._astra_db = AstraDB(
                 api_endpoint=self.connector_config.access_config.api_endpoint,
                 token=self.connector_config.access_config.token,
@@ -116,12 +116,12 @@ class AstraSourceConnector(SourceConnectorCleanupMixin, BaseSourceConnector):
             )
         return self._astra_db_collection  # type: ignore
 
-    @requires_dependencies(["astrapy"], extras="astra")
+    @requires_dependencies(["astrapy"], extras="astradb")
     @SourceConnectionError.wrap  # type: ignore
     def initialize(self):
         _ = self.astra_db_collection
 
-    @requires_dependencies(["astrapy"], extras="astra")
+    @requires_dependencies(["astrapy"], extras="astradb")
     def check_connection(self):
         try:
             _ = self.astra_db_collection
@@ -129,14 +129,14 @@ class AstraSourceConnector(SourceConnectorCleanupMixin, BaseSourceConnector):
             logger.error(f"Failed to validate connection {e}", exc_info=True)
             raise SourceConnectionError(f"failed to validate connection: {e}")
 
-    @requires_dependencies(["astrapy"], extras="astra")
+    @requires_dependencies(["astrapy"], extras="astradb")
     def get_ingest_docs(self):  # type: ignore
         # Perform the find operation
-        astra_docs = list(self.astra_db_collection.paginated_find())
+        astra_db_docs = list(self.astra_db_collection.paginated_find())
 
         doc_list = []
-        for record in astra_docs:
-            doc = AstraIngestDoc(
+        for record in astra_db_docs:
+            doc = AstraDBIngestDoc(
                 connector_config=self.connector_config,
                 processor_config=self.processor_config,
                 read_config=self.read_config,
@@ -151,16 +151,16 @@ class AstraSourceConnector(SourceConnectorCleanupMixin, BaseSourceConnector):
 
 
 @dataclass
-class AstraWriteConfig(WriteConfig):
+class AstraDBWriteConfig(WriteConfig):
     embedding_dimension: int
     requested_indexing_policy: t.Optional[t.Dict[str, t.Any]] = None
     batch_size: int = 20
 
 
 @dataclass
-class AstraDestinationConnector(BaseDestinationConnector):
-    write_config: AstraWriteConfig
-    connector_config: SimpleAstraConfig
+class AstraDBDestinationConnector(BaseDestinationConnector):
+    write_config: AstraDBWriteConfig
+    connector_config: SimpleAstraDBConfig
     _astra_db: t.Optional["AstraDB"] = field(init=False, default=None)
     _astra_db_collection: t.Optional["AstraDBCollection"] = field(init=False, default=None)
 
@@ -179,7 +179,7 @@ class AstraDestinationConnector(BaseDestinationConnector):
         return _asdict(self_cp, **kwargs)
 
     @property
-    @requires_dependencies(["astrapy"], extras="astra")
+    @requires_dependencies(["astrapy"], extras="astradb")
     def astra_db_collection(self) -> "AstraDBCollection":
         if self._astra_db_collection is None:
             from astrapy.db import AstraDB
@@ -187,11 +187,11 @@ class AstraDestinationConnector(BaseDestinationConnector):
             collection_name = self.connector_config.collection_name
             embedding_dimension = self.write_config.embedding_dimension
 
-            # If the user has requested an indexing policy, pass it to the AstraDB
+            # If the user has requested an indexing policy, pass it to the Astra DB
             requested_indexing_policy = self.write_config.requested_indexing_policy
             options = {"indexing": requested_indexing_policy} if requested_indexing_policy else None
 
-            # caller_name/version for AstraDB tracking
+            # caller_name/version for Astra DB tracking
             self._astra_db = AstraDB(
                 api_endpoint=self.connector_config.access_config.api_endpoint,
                 token=self.connector_config.access_config.token,
@@ -208,12 +208,12 @@ class AstraDestinationConnector(BaseDestinationConnector):
             )
         return self._astra_db_collection
 
-    @requires_dependencies(["astrapy"], extras="astra")
+    @requires_dependencies(["astrapy"], extras="astradb")
     @DestinationConnectionError.wrap
     def initialize(self):
         _ = self.astra_db_collection
 
-    @requires_dependencies(["astrapy"], extras="astra")
+    @requires_dependencies(["astrapy"], extras="astradb")
     def check_connection(self):
         try:
             _ = self.astra_db_collection
@@ -222,11 +222,11 @@ class AstraDestinationConnector(BaseDestinationConnector):
             raise DestinationConnectionError(f"failed to validate connection: {e}")
 
     def write_dict(self, *args, elements_dict: t.List[t.Dict[str, t.Any]], **kwargs) -> None:
-        logger.info(f"Inserting / updating {len(elements_dict)} documents to Astra.")
+        logger.info(f"Inserting / updating {len(elements_dict)} documents to Astra DB.")
 
-        astra_batch_size = self.write_config.batch_size
+        astra_db_batch_size = self.write_config.batch_size
 
-        for batch in batch_generator(elements_dict, astra_batch_size):
+        for batch in batch_generator(elements_dict, astra_db_batch_size):
             self._astra_db_collection.insert_many(batch)
 
     def normalize_dict(self, element_dict: dict) -> dict:

{unstructured-ingest-0.0.3 → unstructured-ingest-0.0.4}/unstructured_ingest/connector/biomed.py

@@ -5,9 +5,6 @@ from dataclasses import dataclass
 from ftplib import FTP, error_perm
 from pathlib import Path
 
-import requests
-from requests.adapters import HTTPAdapter
-
 from unstructured_ingest.error import SourceConnectionError, SourceConnectionNetworkError
 from unstructured_ingest.interfaces import (
     BaseConnectorConfig,
@@ -20,6 +17,10 @@ from unstructured_ingest.logger import logger
 from unstructured_ingest.utils.data_prep import (
     validate_date_args,
 )
+from unstructured_ingest.utils.dep_check import requires_dependencies
+
+if t.TYPE_CHECKING:
+    from requests import Response, Session
 
 DOMAIN = "ftp.ncbi.nlm.nih.gov"
 FTP_DOMAIN = f"ftp://{DOMAIN}"
@@ -165,8 +166,11 @@ class BiomedSourceConnector(SourceConnectorCleanupMixin, BaseSourceConnector):
 
         return endpoint_url
 
+    @requires_dependencies(["requests"], extras="biomed")
     def _list_objects_api(self) -> t.List[BiomedFileMeta]:
         from bs4 import BeautifulSoup
+        from requests import Session
+        from requests.adapters import HTTPAdapter
 
         def urls_to_metadata(urls):
             files = []
@@ -193,7 +197,7 @@ class BiomedSourceConnector(SourceConnectorCleanupMixin, BaseSourceConnector):
         endpoint_url = self.get_base_endpoints_url()
 
         while endpoint_url:
-            session = requests.Session()
+            session = Session()
             adapter = HTTPAdapter()
             session.mount("http://", adapter)
             session.mount("https://", adapter)
@@ -213,7 +217,7 @@ class BiomedSourceConnector(SourceConnectorCleanupMixin, BaseSourceConnector):
         return files
 
     @SourceConnectionNetworkError.wrap
-    def _get_request(self, session: requests.Session, endpoint_url: str) -> requests.Response:
+    def _get_request(self, session: "Session", endpoint_url: str) -> "Response":
         return session.get(endpoint_url, timeout=self.connector_config.max_request_time)
 
     def _list_objects(self) -> t.List[BiomedFileMeta]:
@@ -293,7 +297,10 @@ class BiomedSourceConnector(SourceConnectorCleanupMixin, BaseSourceConnector):
     def initialize(self):
         pass
 
+    @requires_dependencies(["requests"], extras="biomed")
     def check_connection(self):
+        import requests
+
         resp = requests.head(self.get_base_endpoints_url())
         try:
             resp.raise_for_status()

{unstructured-ingest-0.0.3 → unstructured-ingest-0.0.4}/unstructured_ingest/connector/confluence.py

@@ -4,8 +4,6 @@ from dataclasses import dataclass, field
 from datetime import datetime
 from pathlib import Path
 
-import requests
-
 from unstructured_ingest.enhanced_dataclass import enhanced_field
 from unstructured_ingest.error import SourceConnectionError, SourceConnectionNetworkError
 from unstructured_ingest.interfaces import (
@@ -208,8 +206,10 @@ class ConfluenceSourceConnector(SourceConnectorCleanupMixin, BaseSourceConnector
             )
         return self._confluence
 
-    @requires_dependencies(["atlassian"], extras="Confluence")
+    @requires_dependencies(["atlassian", "requests"], extras="Confluence")
     def check_connection(self):
+        import requests
+
         url = "rest/api/space"
         try:
             self.confluence.request(method="HEAD", path=url)

{unstructured-ingest-0.0.3 → unstructured-ingest-0.0.4}/unstructured_ingest/connector/github.py

@@ -3,8 +3,6 @@ from dataclasses import dataclass
 from datetime import datetime
 from urllib.parse import urlparse
 
-import requests
-
 from unstructured_ingest.connector.git import (
     GitIngestDoc,
     GitSourceConnector,
@@ -71,7 +69,10 @@ class GitHubIngestDoc(GitIngestDoc):
         return content_file
 
     @SourceConnectionNetworkError.wrap
+    @requires_dependencies(["requests"], extras="github")
     def _fetch_content(self, content_file):
+        import requests
+
         contents = b""
         if (
             not content_file.content  # type: ignore

{unstructured-ingest-0.0.3 → unstructured-ingest-0.0.4}/unstructured_ingest/connector/google_drive.py

@@ -7,8 +7,6 @@ from datetime import datetime
 from mimetypes import guess_extension
 from pathlib import Path
 
-from unstructured.file_utils.google_filetype import GOOGLE_DRIVE_EXPORT_TYPES
-
 from unstructured_ingest.enhanced_dataclass import enhanced_field
 from unstructured_ingest.error import SourceConnectionError, SourceConnectionNetworkError
 from unstructured_ingest.interfaces import (
@@ -25,6 +23,7 @@ from unstructured_ingest.interfaces import (
 )
 from unstructured_ingest.logger import logger
 from unstructured_ingest.utils.dep_check import requires_dependencies
+from unstructured_ingest.utils.google_filetype import GOOGLE_DRIVE_EXPORT_TYPES
 from unstructured_ingest.utils.string_and_date_utils import json_to_dict
 
 if t.TYPE_CHECKING:

{unstructured-ingest-0.0.3 → unstructured-ingest-0.0.4}/unstructured_ingest/connector/mongodb.py

@@ -3,8 +3,7 @@ import typing as t
 from dataclasses import dataclass, field
 from pathlib import Path
 
-from unstructured.__version__ import __version__ as unstructured_version
-
+from unstructured_ingest.__version__ import __version__ as unstructured_version
 from unstructured_ingest.enhanced_dataclass import enhanced_field
 from unstructured_ingest.enhanced_dataclass.core import _asdict
 from unstructured_ingest.error import DestinationConnectionError, SourceConnectionError, WriteError