unstructured-ingest 1.0.15__tar.gz → 1.0.16__tar.gz

{unstructured_ingest-1.0.15 → unstructured_ingest-1.0.16}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: unstructured_ingest
-Version: 1.0.15
+Version: 1.0.16
 Summary: Local ETL data pipeline to get data RAG ready
 Author-email: Unstructured Technologies <devops@unstructuredai.io>
 License-Expression: Apache-2.0
@@ -19,7 +19,6 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: <3.13,>=3.9
 Requires-Dist: click
-Requires-Dist: dataclasses-json
 Requires-Dist: opentelemetry-sdk
 Requires-Dist: pydantic>=2.7
 Requires-Dist: python-dateutil

unstructured_ingest-1.0.16/unstructured_ingest/__version__.py

@@ -0,0 +1 @@
+__version__ = "1.0.16"  # pragma: no cover

{unstructured_ingest-1.0.15 → unstructured_ingest-1.0.16}/unstructured_ingest/embed/azure_openai.py

@@ -16,8 +16,10 @@ if TYPE_CHECKING:
 
 class AzureOpenAIEmbeddingConfig(OpenAIEmbeddingConfig):
     api_version: str = Field(description="Azure API version", default="2024-06-01")
-    azure_endpoint: str
-    embedder_model_name: str = Field(default="text-embedding-ada-002", alias="model_name")
+    azure_endpoint: str = Field(description="Azure endpoint")
+    embedder_model_name: str = Field(
+        default="text-embedding-ada-002", alias="model_name", description="Azure OpenAI model name"
+    )
 
     @requires_dependencies(["openai"], extras="openai")
     def get_client(self) -> "AzureOpenAI":

{unstructured_ingest-1.0.15 → unstructured_ingest-1.0.16}/unstructured_ingest/embed/bedrock.py

@@ -58,10 +58,14 @@ def conform_query(query: str, provider: str) -> dict:
 
 
 class BedrockEmbeddingConfig(EmbeddingConfig):
-    aws_access_key_id: SecretStr
-    aws_secret_access_key: SecretStr
-    region_name: str = "us-west-2"
-    embedder_model_name: str = Field(default="amazon.titan-embed-text-v1", alias="model_name")
+    aws_access_key_id: SecretStr = Field(description="aws access key id")
+    aws_secret_access_key: SecretStr = Field(description="aws secret access key")
+    region_name: str = Field(description="aws region name", default="us-west-2")
+    embedder_model_name: str = Field(
+        default="amazon.titan-embed-text-v1",
+        alias="model_name",
+        description="AWS Bedrock model name",
+    )
 
     def wrap_error(self, e: Exception) -> Exception:
         if is_internal_error(e=e):

{unstructured_ingest-1.0.15 → unstructured_ingest-1.0.16}/unstructured_ingest/embed/huggingface.py

@@ -15,11 +15,18 @@ if TYPE_CHECKING:
 
 
 class HuggingFaceEmbeddingConfig(EmbeddingConfig):
-    embedder_model_name: Optional[str] = Field(default="all-MiniLM-L6-v2", alias="model_name")
+    embedder_model_name: Optional[str] = Field(
+        default="all-MiniLM-L6-v2", alias="model_name", description="HuggingFace model name"
+    )
     embedder_model_kwargs: Optional[dict] = Field(
-        default_factory=lambda: {"device": "cpu"}, alias="model_kwargs"
+        default_factory=lambda: {"device": "cpu"},
+        alias="model_kwargs",
+        description="additional model parameters",
+    )
+    encode_kwargs: Optional[dict] = Field(
+        default_factory=lambda: {"normalize_embeddings": False},
+        description="additional embedding parameters",
     )
-    encode_kwargs: Optional[dict] = Field(default_factory=lambda: {"normalize_embeddings": False})
 
     @requires_dependencies(
         ["sentence_transformers"],

{unstructured_ingest-1.0.15 → unstructured_ingest-1.0.16}/unstructured_ingest/embed/mixedbreadai.py

@@ -34,10 +34,13 @@ class MixedbreadAIEmbeddingConfig(EmbeddingConfig):
 
     api_key: SecretStr = Field(
         default_factory=lambda: SecretStr(os.environ.get("MXBAI_API_KEY")),
+        description="API key for Mixedbread AI",
     )
 
     embedder_model_name: str = Field(
-        default="mixedbread-ai/mxbai-embed-large-v1", alias="model_name"
+        default="mixedbread-ai/mxbai-embed-large-v1",
+        alias="model_name",
+        description="Mixedbread AI model name",
     )
 
     @requires_dependencies(

{unstructured_ingest-1.0.15 → unstructured_ingest-1.0.16}/unstructured_ingest/embed/octoai.py

@@ -25,8 +25,12 @@ if TYPE_CHECKING:
 
 class OctoAiEmbeddingConfig(EmbeddingConfig):
     api_key: SecretStr
-    embedder_model_name: str = Field(default="thenlper/gte-large", alias="model_name")
-    base_url: str = Field(default="https://text.octoai.run/v1")
+    embedder_model_name: str = Field(
+        default="thenlper/gte-large", alias="model_name", description="octoai model name"
+    )
+    base_url: str = Field(
+        default="https://text.octoai.run/v1", description="optional override for the base url"
+    )
 
     def wrap_error(self, e: Exception) -> Exception:
         if is_internal_error(e=e):

{unstructured_ingest-1.0.15 → unstructured_ingest-1.0.16}/unstructured_ingest/embed/openai.py

@@ -24,9 +24,11 @@ if TYPE_CHECKING:
 
 
 class OpenAIEmbeddingConfig(EmbeddingConfig):
-    api_key: SecretStr
-    embedder_model_name: str = Field(default="text-embedding-ada-002", alias="model_name")
-    base_url: Optional[str] = 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"
+    )
+    base_url: Optional[str] = Field(default=None, description="optional override for the base url")
 
     @requires_dependencies(["openai"], extras="openai")
     def wrap_error(self, e: Exception) -> Exception:

{unstructured_ingest-1.0.15 → unstructured_ingest-1.0.16}/unstructured_ingest/embed/togetherai.py

@@ -20,9 +20,11 @@ if TYPE_CHECKING:
 
 
 class TogetherAIEmbeddingConfig(EmbeddingConfig):
-    api_key: SecretStr
+    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"
+        default="togethercomputer/m2-bert-80M-8k-retrieval",
+        alias="model_name",
+        description="Together AI model name",
     )
 
     def wrap_error(self, e: Exception) -> Exception:

{unstructured_ingest-1.0.15 → unstructured_ingest-1.0.16}/unstructured_ingest/embed/vertexai.py

@@ -32,9 +32,9 @@ ApiKeyType = Secret[Annotated[dict, BeforeValidator(conform_string_to_dict)]]
 
 
 class VertexAIEmbeddingConfig(EmbeddingConfig):
-    api_key: ApiKeyType
+    api_key: ApiKeyType = Field(description="API key for Vertex AI")
     embedder_model_name: Optional[str] = Field(
-        default="textembedding-gecko@001", alias="model_name"
+        default="textembedding-gecko@001", alias="model_name", description="Vertex AI model name"
     )
 
     def wrap_error(self, e: Exception) -> Exception:

{unstructured_ingest-1.0.15 → unstructured_ingest-1.0.16}/unstructured_ingest/embed/voyageai.py

@@ -26,11 +26,14 @@ class VoyageAIEmbeddingConfig(EmbeddingConfig):
         le=128,
         description="Batch size for embedding requests. VoyageAI has a limit of 128.",
     )
-    api_key: SecretStr
-    embedder_model_name: str = Field(default="voyage-3", alias="model_name")
-    truncation: Optional[bool] = Field(default=None)
-    max_retries: int = 0
-    timeout_in_seconds: Optional[int] = 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"
+    )
+    max_retries: int = Field(default=0, description="Max retries for embedding requests.")
+    timeout_in_seconds: Optional[int] = Field(
+        default=None, description="Optional timeout in seconds for embedding requests."
+    )
 
     def wrap_error(self, e: Exception) -> Exception:
         if is_internal_error(e=e):

unstructured_ingest-1.0.15/unstructured_ingest/__version__.py

@@ -1 +0,0 @@
-__version__ = "1.0.15"  # pragma: no cover