unstructured-ingest 1.0.17__tar.gz → 1.0.19__tar.gz

{unstructured_ingest-1.0.17 → unstructured_ingest-1.0.19}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: unstructured_ingest
-Version: 1.0.17
+Version: 1.0.19
 Summary: Local ETL data pipeline to get data RAG ready
 Author-email: Unstructured Technologies <devops@unstructuredai.io>
 License-Expression: Apache-2.0

unstructured_ingest-1.0.19/unstructured_ingest/__version__.py

@@ -0,0 +1 @@
+__version__ = "1.0.19"  # pragma: no cover

{unstructured_ingest-1.0.17 → unstructured_ingest-1.0.19}/unstructured_ingest/embed/azure_openai.py

@@ -25,9 +25,8 @@ class AzureOpenAIEmbeddingConfig(OpenAIEmbeddingConfig):
     def get_client(self) -> "AzureOpenAI":
         from openai import AzureOpenAI
 
-        api_key = self.api_key.get_secret_value() if self.api_key else None
         return AzureOpenAI(
-            api_key=api_key,
+            api_key=self.api_key.get_secret_value(),
             api_version=self.api_version,
             azure_endpoint=self.azure_endpoint,
         )
@@ -36,9 +35,8 @@ class AzureOpenAIEmbeddingConfig(OpenAIEmbeddingConfig):
     def get_async_client(self) -> "AsyncAzureOpenAI":
         from openai import AsyncAzureOpenAI
 
-        api_key = self.api_key.get_secret_value() if self.api_key else None
         return AsyncAzureOpenAI(
-            api_key=api_key,
+            api_key=self.api_key.get_secret_value(),
             api_version=self.api_version,
             azure_endpoint=self.azure_endpoint,
         )

{unstructured_ingest-1.0.17 → unstructured_ingest-1.0.19}/unstructured_ingest/embed/octoai.py

@@ -1,5 +1,5 @@
 from dataclasses import dataclass
-from typing import TYPE_CHECKING, Optional
+from typing import TYPE_CHECKING
 
 from pydantic import Field, SecretStr
 
@@ -24,7 +24,7 @@ if TYPE_CHECKING:
 
 
 class OctoAiEmbeddingConfig(EmbeddingConfig):
-    api_key: Optional[SecretStr] = Field(description="API key for OctoAI", default=None)
+    api_key: SecretStr = Field(description="API key for OctoAI")
     embedder_model_name: str = Field(
         default="thenlper/gte-large", alias="model_name", description="octoai model name"
     )
@@ -77,8 +77,7 @@ class OctoAiEmbeddingConfig(EmbeddingConfig):
         """Creates an OpenAI python client to embed elements. Uses the OpenAI SDK."""
         from openai import OpenAI
 
-        api_key = self.api_key.get_secret_value() if self.api_key else None
-        return OpenAI(api_key=api_key, base_url=self.base_url)
+        return OpenAI(api_key=self.api_key.get_secret_value(), base_url=self.base_url)
 
     @requires_dependencies(
         ["openai", "tiktoken"],
@@ -88,8 +87,7 @@ class OctoAiEmbeddingConfig(EmbeddingConfig):
         """Creates an OpenAI python client to embed elements. Uses the OpenAI SDK."""
         from openai import AsyncOpenAI
 
-        api_key = self.api_key.get_secret_value() if self.api_key else None
-        return AsyncOpenAI(api_key=api_key, base_url=self.base_url)
+        return AsyncOpenAI(api_key=self.api_key.get_secret_value(), base_url=self.base_url)
 
 
 @dataclass

{unstructured_ingest-1.0.17 → unstructured_ingest-1.0.19}/unstructured_ingest/embed/openai.py

@@ -24,7 +24,7 @@ if TYPE_CHECKING:
 
 
 class OpenAIEmbeddingConfig(EmbeddingConfig):
-    api_key: Optional[SecretStr] = Field(description="API key for OpenAI", default=None)
+    api_key: SecretStr = Field(description="API key for OpenAI")
     embedder_model_name: str = Field(
         default="text-embedding-ada-002", alias="model_name", description="OpenAI model name"
     )
@@ -88,15 +88,13 @@ class OpenAIEmbeddingConfig(EmbeddingConfig):
     def get_client(self) -> "OpenAI":
         from openai import OpenAI
 
-        api_key = self.api_key.get_secret_value() if self.api_key else None
-        return OpenAI(api_key=api_key, base_url=self.base_url)
+        return OpenAI(api_key=self.api_key.get_secret_value(), base_url=self.base_url)
 
     @requires_dependencies(["openai"], extras="openai")
     def get_async_client(self) -> "AsyncOpenAI":
         from openai import AsyncOpenAI
 
-        api_key = self.api_key.get_secret_value() if self.api_key else None
-        return AsyncOpenAI(api_key=api_key, base_url=self.base_url)
+        return AsyncOpenAI(api_key=self.api_key.get_secret_value(), base_url=self.base_url)
 
 
 @dataclass

{unstructured_ingest-1.0.17 → unstructured_ingest-1.0.19}/unstructured_ingest/embed/togetherai.py

@@ -1,5 +1,5 @@
 from dataclasses import dataclass
-from typing import TYPE_CHECKING, Any, Optional
+from typing import TYPE_CHECKING, Any
 
 from pydantic import Field, SecretStr
 
@@ -20,7 +20,7 @@ if TYPE_CHECKING:
 
 
 class TogetherAIEmbeddingConfig(EmbeddingConfig):
-    api_key: Optional[SecretStr] = Field(description="API key for Together AI", default=None)
+    api_key: SecretStr = Field(description="API key for Together AI")
     embedder_model_name: str = Field(
         default="togethercomputer/m2-bert-80M-8k-retrieval",
         alias="model_name",
@@ -58,15 +58,13 @@ class TogetherAIEmbeddingConfig(EmbeddingConfig):
     def get_client(self) -> "Together":
         from together import Together
 
-        api_key = self.api_key.get_secret_value() if self.api_key else None
-        return Together(api_key=api_key)
+        return Together(api_key=self.api_key.get_secret_value())
 
     @requires_dependencies(["together"], extras="togetherai")
     def get_async_client(self) -> "AsyncTogether":
         from together import AsyncTogether
 
-        api_key = self.api_key.get_secret_value() if self.api_key else None
-        return AsyncTogether(api_key=api_key)
+        return AsyncTogether(api_key=self.api_key.get_secret_value())
 
 
 @dataclass

{unstructured_ingest-1.0.17 → unstructured_ingest-1.0.19}/unstructured_ingest/embed/voyageai.py

@@ -26,7 +26,7 @@ class VoyageAIEmbeddingConfig(EmbeddingConfig):
         le=128,
         description="Batch size for embedding requests. VoyageAI has a limit of 128.",
     )
-    api_key: Optional[SecretStr] = Field(description="API key for VoyageAI", default=None)
+    api_key: SecretStr = Field(description="API key for VoyageAI")
     embedder_model_name: str = Field(
         default="voyage-3", alias="model_name", description="VoyageAI model name"
     )
@@ -65,9 +65,8 @@ class VoyageAIEmbeddingConfig(EmbeddingConfig):
         """Creates a VoyageAI python client to embed elements."""
         from voyageai import Client as VoyageAIClient
 
-        api_key = self.api_key.get_secret_value() if self.api_key else None
         client = VoyageAIClient(
-            api_key=api_key,
+            api_key=self.api_key.get_secret_value(),
             max_retries=self.max_retries,
             timeout=self.timeout_in_seconds,
         )
@@ -81,9 +80,8 @@ class VoyageAIEmbeddingConfig(EmbeddingConfig):
         """Creates a VoyageAI python client to embed elements."""
         from voyageai import AsyncClient as AsyncVoyageAIClient
 
-        api_key = self.api_key.get_secret_value() if self.api_key else None
         client = AsyncVoyageAIClient(
-            api_key=api_key,
+            api_key=self.api_key.get_secret_value(),
             max_retries=self.max_retries,
             timeout=self.timeout_in_seconds,
         )

{unstructured_ingest-1.0.17 → unstructured_ingest-1.0.19}/unstructured_ingest/processes/connectors/assets/databricks_delta_table_schema.sql

@@ -1,4 +1,4 @@
-CREATE TABLE elements (
+CREATE TABLE IF NOT EXISTS `elements` (
     id STRING NOT NULL PRIMARY KEY,
     record_id STRING NOT NULL,
     element_id STRING NOT NULL,
@@ -7,4 +7,3 @@ CREATE TABLE elements (
     type STRING,
     metadata VARIANT
 );
-

{unstructured_ingest-1.0.17 → unstructured_ingest-1.0.19}/unstructured_ingest/processes/connectors/databricks/volumes_table.py

@@ -136,7 +136,7 @@ class DatabricksVolumeDeltaTableUploader(Uploader):
     def get_table_columns(self) -> dict[str, str]:
         if self._columns is None:
             with self.get_cursor() as cursor:
-                cursor.execute(f"SELECT * from {self.upload_config.table_name} LIMIT 1")
+                cursor.execute(f"SELECT * from `{self.upload_config.table_name}` LIMIT 1")
                 self._columns = {desc[0]: desc[1] for desc in cursor.description}
         return self._columns
 
@@ -152,7 +152,7 @@ class DatabricksVolumeDeltaTableUploader(Uploader):
         )
         with self.get_cursor() as cursor:
             cursor.execute(
-                f"DELETE FROM {self.upload_config.table_name} WHERE {RECORD_ID_LABEL} = '{file_data.identifier}'"  # noqa: E501
+                f"DELETE FROM `{self.upload_config.table_name}` WHERE {RECORD_ID_LABEL} = '{file_data.identifier}'"  # noqa: E501
             )
             results = cursor.fetchall()
             deleted_rows = results[0][0]

unstructured_ingest-1.0.17/unstructured_ingest/__version__.py

@@ -1 +0,0 @@
-__version__ = "1.0.17"  # pragma: no cover