llama-cloud 0.1.0__tar.gz → 0.1.2__tar.gz

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/PKG-INFO

@@ -1,16 +1,17 @@
 Metadata-Version: 2.1
 Name: llama-cloud
-Version: 0.1.0
+Version: 0.1.2
 Summary: 
+License: MIT
 Author: Logan Markewich
 Author-email: logan@runllama.ai
 Requires-Python: >=3.8,<4
+Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
 Requires-Dist: httpx (>=0.20.0)
 Requires-Dist: pydantic (>=1.10)
 Description-Content-Type: text/markdown

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/llama_cloud/__init__.py

@@ -27,7 +27,6 @@ from .types import (
     CloudAzStorageBlobDataSource,
     CloudAzureAiSearchVectorStore,
     CloudBoxDataSource,
-    CloudChromaVectorStore,
     CloudConfluenceDataSource,
     CloudDocument,
     CloudDocumentCreate,
@@ -43,7 +42,6 @@ from .types import (
     CloudS3DataSource,
     CloudSharepointDataSource,
     CloudSlackDataSource,
-    CloudWeaviateVectorStore,
     CodeSplitter,
     CohereEmbedding,
     CohereEmbeddingConfig,
@@ -75,7 +73,6 @@ from .types import (
     EvalQuestion,
     EvalQuestionCreate,
     EvalQuestionResult,
-    ExtendVertexTextEmbedding,
     ExtractionJob,
     ExtractionResult,
     ExtractionResultDataValue,
@@ -200,6 +197,7 @@ from .types import (
     ValidationErrorLocItem,
     VertexAiEmbeddingConfig,
     VertexEmbeddingMode,
+    VertexTextEmbedding,
 )
 from .errors import UnprocessableEntityError
 from .resources import (
@@ -259,7 +257,6 @@ __all__ = [
     "CloudAzStorageBlobDataSource",
     "CloudAzureAiSearchVectorStore",
     "CloudBoxDataSource",
-    "CloudChromaVectorStore",
     "CloudConfluenceDataSource",
     "CloudDocument",
     "CloudDocumentCreate",
@@ -275,7 +272,6 @@ __all__ = [
     "CloudS3DataSource",
     "CloudSharepointDataSource",
     "CloudSlackDataSource",
-    "CloudWeaviateVectorStore",
     "CodeSplitter",
     "CohereEmbedding",
     "CohereEmbeddingConfig",
@@ -310,7 +306,6 @@ __all__ = [
     "EvalQuestion",
     "EvalQuestionCreate",
     "EvalQuestionResult",
-    "ExtendVertexTextEmbedding",
     "ExtractionJob",
     "ExtractionResult",
     "ExtractionResultDataValue",
@@ -450,6 +445,7 @@ __all__ = [
     "ValidationErrorLocItem",
     "VertexAiEmbeddingConfig",
     "VertexEmbeddingMode",
+    "VertexTextEmbedding",
     "component_definitions",
     "data_sinks",
     "data_sources",

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/llama_cloud/resources/data_sinks/client.py

@@ -89,7 +89,7 @@ class DataSinksClient:
         client.data_sinks.create_data_sink(
             request=DataSinkCreate(
                 name="string",
-                sink_type=ConfigurableDataSinkNames.CHROMA,
+                sink_type=ConfigurableDataSinkNames.PINECONE,
             ),
         )
         """
@@ -138,7 +138,7 @@ class DataSinksClient:
         client.data_sinks.upsert_data_sink(
             request=DataSinkCreate(
                 name="string",
-                sink_type=ConfigurableDataSinkNames.CHROMA,
+                sink_type=ConfigurableDataSinkNames.PINECONE,
             ),
         )
         """
@@ -220,7 +220,7 @@ class DataSinksClient:
         )
         client.data_sinks.update_data_sink(
             data_sink_id="string",
-            sink_type=ConfigurableDataSinkNames.CHROMA,
+            sink_type=ConfigurableDataSinkNames.PINECONE,
         )
         """
         _request: typing.Dict[str, typing.Any] = {"sink_type": sink_type}
@@ -340,7 +340,7 @@ class AsyncDataSinksClient:
         await client.data_sinks.create_data_sink(
             request=DataSinkCreate(
                 name="string",
-                sink_type=ConfigurableDataSinkNames.CHROMA,
+                sink_type=ConfigurableDataSinkNames.PINECONE,
             ),
         )
         """
@@ -389,7 +389,7 @@ class AsyncDataSinksClient:
         await client.data_sinks.upsert_data_sink(
             request=DataSinkCreate(
                 name="string",
-                sink_type=ConfigurableDataSinkNames.CHROMA,
+                sink_type=ConfigurableDataSinkNames.PINECONE,
             ),
         )
         """
@@ -471,7 +471,7 @@ class AsyncDataSinksClient:
         )
         await client.data_sinks.update_data_sink(
             data_sink_id="string",
-            sink_type=ConfigurableDataSinkNames.CHROMA,
+            sink_type=ConfigurableDataSinkNames.PINECONE,
         )
         """
         _request: typing.Dict[str, typing.Any] = {"sink_type": sink_type}

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/llama_cloud/resources/data_sinks/types/data_sink_update_component.py

@@ -3,21 +3,17 @@
 import typing
 
 from ....types.cloud_azure_ai_search_vector_store import CloudAzureAiSearchVectorStore
-from ....types.cloud_chroma_vector_store import CloudChromaVectorStore
 from ....types.cloud_milvus_vector_store import CloudMilvusVectorStore
 from ....types.cloud_mongo_db_atlas_vector_search import CloudMongoDbAtlasVectorSearch
 from ....types.cloud_pinecone_vector_store import CloudPineconeVectorStore
 from ....types.cloud_postgres_vector_store import CloudPostgresVectorStore
 from ....types.cloud_qdrant_vector_store import CloudQdrantVectorStore
-from ....types.cloud_weaviate_vector_store import CloudWeaviateVectorStore
 
 DataSinkUpdateComponent = typing.Union[
     typing.Dict[str, typing.Any],
-    CloudChromaVectorStore,
     CloudPineconeVectorStore,
     CloudPostgresVectorStore,
     CloudQdrantVectorStore,
-    CloudWeaviateVectorStore,
     CloudAzureAiSearchVectorStore,
     CloudMongoDbAtlasVectorSearch,
     CloudMilvusVectorStore,

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/llama_cloud/resources/parsing/client.py

@@ -125,6 +125,10 @@ class ParsingClient:
         disable_reconstruction: bool,
         input_s_3_path: str,
         output_s_3_path_prefix: str,
+        azure_openai_deployment_name: str,
+        azure_openai_endpoint: str,
+        azure_openai_api_version: str,
+        azure_openai_key: str,
         file: typing.Optional[str] = OMIT,
     ) -> ParsingJob:
         """
@@ -179,6 +183,14 @@ class ParsingClient:
 
             - output_s_3_path_prefix: str.
 
+            - azure_openai_deployment_name: str.
+
+            - azure_openai_endpoint: str.
+
+            - azure_openai_api_version: str.
+
+            - azure_openai_key: str.
+
             - file: typing.Optional[str].
         """
         _request: typing.Dict[str, typing.Any] = {
@@ -206,6 +218,10 @@ class ParsingClient:
             "disable_reconstruction": disable_reconstruction,
             "input_s3_path": input_s_3_path,
             "output_s3_path_prefix": output_s_3_path_prefix,
+            "azure_openai_deployment_name": azure_openai_deployment_name,
+            "azure_openai_endpoint": azure_openai_endpoint,
+            "azure_openai_api_version": azure_openai_api_version,
+            "azure_openai_key": azure_openai_key,
         }
         if file is not OMIT:
             _request["file"] = file
@@ -678,6 +694,10 @@ class AsyncParsingClient:
         disable_reconstruction: bool,
         input_s_3_path: str,
         output_s_3_path_prefix: str,
+        azure_openai_deployment_name: str,
+        azure_openai_endpoint: str,
+        azure_openai_api_version: str,
+        azure_openai_key: str,
         file: typing.Optional[str] = OMIT,
     ) -> ParsingJob:
         """
@@ -732,6 +752,14 @@ class AsyncParsingClient:
 
             - output_s_3_path_prefix: str.
 
+            - azure_openai_deployment_name: str.
+
+            - azure_openai_endpoint: str.
+
+            - azure_openai_api_version: str.
+
+            - azure_openai_key: str.
+
             - file: typing.Optional[str].
         """
         _request: typing.Dict[str, typing.Any] = {
@@ -759,6 +787,10 @@ class AsyncParsingClient:
             "disable_reconstruction": disable_reconstruction,
             "input_s3_path": input_s_3_path,
             "output_s3_path_prefix": output_s_3_path_prefix,
+            "azure_openai_deployment_name": azure_openai_deployment_name,
+            "azure_openai_endpoint": azure_openai_endpoint,
+            "azure_openai_api_version": azure_openai_api_version,
+            "azure_openai_key": azure_openai_key,
         }
         if file is not OMIT:
             _request["file"] = file

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/llama_cloud/types/__init__.py

@@ -30,7 +30,6 @@ from .chat_message import ChatMessage
 from .cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
 from .cloud_azure_ai_search_vector_store import CloudAzureAiSearchVectorStore
 from .cloud_box_data_source import CloudBoxDataSource
-from .cloud_chroma_vector_store import CloudChromaVectorStore
 from .cloud_confluence_data_source import CloudConfluenceDataSource
 from .cloud_document import CloudDocument
 from .cloud_document_create import CloudDocumentCreate
@@ -46,7 +45,6 @@ from .cloud_qdrant_vector_store import CloudQdrantVectorStore
 from .cloud_s_3_data_source import CloudS3DataSource
 from .cloud_sharepoint_data_source import CloudSharepointDataSource
 from .cloud_slack_data_source import CloudSlackDataSource
-from .cloud_weaviate_vector_store import CloudWeaviateVectorStore
 from .code_splitter import CodeSplitter
 from .cohere_embedding import CohereEmbedding
 from .cohere_embedding_config import CohereEmbeddingConfig
@@ -78,7 +76,6 @@ from .eval_metric import EvalMetric
 from .eval_question import EvalQuestion
 from .eval_question_create import EvalQuestionCreate
 from .eval_question_result import EvalQuestionResult
-from .extend_vertex_text_embedding import ExtendVertexTextEmbedding
 from .extraction_job import ExtractionJob
 from .extraction_result import ExtractionResult
 from .extraction_result_data_value import ExtractionResultDataValue
@@ -209,6 +206,7 @@ from .validation_error import ValidationError
 from .validation_error_loc_item import ValidationErrorLocItem
 from .vertex_ai_embedding_config import VertexAiEmbeddingConfig
 from .vertex_embedding_mode import VertexEmbeddingMode
+from .vertex_text_embedding import VertexTextEmbedding
 
 __all__ = [
     "AdvancedModeTransformConfig",
@@ -237,7 +235,6 @@ __all__ = [
     "CloudAzStorageBlobDataSource",
     "CloudAzureAiSearchVectorStore",
     "CloudBoxDataSource",
-    "CloudChromaVectorStore",
     "CloudConfluenceDataSource",
     "CloudDocument",
     "CloudDocumentCreate",
@@ -253,7 +250,6 @@ __all__ = [
     "CloudS3DataSource",
     "CloudSharepointDataSource",
     "CloudSlackDataSource",
-    "CloudWeaviateVectorStore",
     "CodeSplitter",
     "CohereEmbedding",
     "CohereEmbeddingConfig",
@@ -285,7 +281,6 @@ __all__ = [
     "EvalQuestion",
     "EvalQuestionCreate",
     "EvalQuestionResult",
-    "ExtendVertexTextEmbedding",
     "ExtractionJob",
     "ExtractionResult",
     "ExtractionResultDataValue",
@@ -410,4 +405,5 @@ __all__ = [
     "ValidationErrorLocItem",
     "VertexAiEmbeddingConfig",
     "VertexEmbeddingMode",
+    "VertexTextEmbedding",
 ]

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/llama_cloud/types/azure_open_ai_embedding.py

@@ -15,14 +15,13 @@ except ImportError:
 
 
 class AzureOpenAiEmbedding(pydantic.BaseModel):
-    model_name: typing.Optional[str] = pydantic.Field(description="The name of the embedding model.")
+    model_name: typing.Optional[str] = pydantic.Field(description="The name of the OpenAI embedding model.")
     embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    callback_manager: typing.Optional[typing.Any]
     num_workers: typing.Optional[int]
     additional_kwargs: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(
         description="Additional kwargs for the OpenAI API."
     )
-    api_key: str = pydantic.Field(description="The OpenAI API key.")
+    api_key: typing.Optional[str]
     api_base: typing.Optional[str] = pydantic.Field(description="The base URL for Azure deployment.")
     api_version: typing.Optional[str] = pydantic.Field(description="The version for Azure OpenAI API.")
     max_retries: typing.Optional[int] = pydantic.Field(description="Maximum number of retries.")
@@ -34,10 +33,6 @@ class AzureOpenAiEmbedding(pydantic.BaseModel):
     dimensions: typing.Optional[int]
     azure_endpoint: typing.Optional[str]
     azure_deployment: typing.Optional[str]
-    azure_ad_token_provider: typing.Optional[str]
-    use_azure_ad: bool = pydantic.Field(
-        description="Indicates if Microsoft Entra ID (former Azure AD) is used for token authentication"
-    )
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/llama_cloud/types/bedrock_embedding.py

@@ -15,17 +15,14 @@ except ImportError:
 
 
 class BedrockEmbedding(pydantic.BaseModel):
-    model_name: str = pydantic.Field(description="The modelId of the Bedrock model to use.")
+    model_name: typing.Optional[str] = pydantic.Field(description="The modelId of the Bedrock model to use.")
     embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    callback_manager: typing.Optional[typing.Any]
     num_workers: typing.Optional[int]
     profile_name: typing.Optional[str]
     aws_access_key_id: typing.Optional[str]
     aws_secret_access_key: typing.Optional[str]
     aws_session_token: typing.Optional[str]
     region_name: typing.Optional[str]
-    botocore_session: typing.Optional[typing.Any]
-    botocore_config: typing.Optional[typing.Any]
     max_retries: typing.Optional[int] = pydantic.Field(description="The maximum number of API retries.")
     timeout: typing.Optional[float] = pydantic.Field(
         description="The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts."

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/llama_cloud/types/cloud_pinecone_vector_store.py

@@ -29,7 +29,7 @@ class CloudPineconeVectorStore(pydantic.BaseModel):
     """
 
     supports_nested_metadata_filters: typing.Optional[bool]
-    api_key: str
+    api_key: str = pydantic.Field(description="The API key for authenticating with Pinecone")
     index_name: str
     namespace: typing.Optional[str]
     insert_kwargs: typing.Optional[typing.Dict[str, typing.Any]]

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/llama_cloud/types/cohere_embedding.py

@@ -15,18 +15,13 @@ except ImportError:
 
 
 class CohereEmbedding(pydantic.BaseModel):
-    """
-    CohereEmbedding uses the Cohere API to generate embeddings for text.
-    """
-
-    model_name: typing.Optional[str] = pydantic.Field(description="The name of the embedding model.")
+    model_name: typing.Optional[str] = pydantic.Field(description="The modelId of the Cohere model to use.")
     embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    callback_manager: typing.Optional[typing.Any]
     num_workers: typing.Optional[int]
-    api_key: str = pydantic.Field(description="The Cohere API key.")
-    truncate: str = pydantic.Field(description="Truncation type - START/ END/ NONE")
+    api_key: typing.Optional[str]
+    truncate: typing.Optional[str] = pydantic.Field(description="Truncation type - START/ END/ NONE")
     input_type: typing.Optional[str]
-    embedding_type: str = pydantic.Field(
+    embedding_type: typing.Optional[str] = pydantic.Field(
         description="Embedding type. If not provided float embedding_type is used when needed."
     )
     class_name: typing.Optional[str]

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/llama_cloud/types/configurable_data_sink_names.py

@@ -7,36 +7,28 @@ T_Result = typing.TypeVar("T_Result")
 
 
 class ConfigurableDataSinkNames(str, enum.Enum):
-    CHROMA = "CHROMA"
     PINECONE = "PINECONE"
     POSTGRES = "POSTGRES"
     QDRANT = "QDRANT"
-    WEAVIATE = "WEAVIATE"
     AZUREAI_SEARCH = "AZUREAI_SEARCH"
     MONGODB_ATLAS = "MONGODB_ATLAS"
     MILVUS = "MILVUS"
 
     def visit(
         self,
-        chroma: typing.Callable[[], T_Result],
         pinecone: typing.Callable[[], T_Result],
         postgres: typing.Callable[[], T_Result],
         qdrant: typing.Callable[[], T_Result],
-        weaviate: typing.Callable[[], T_Result],
         azureai_search: typing.Callable[[], T_Result],
         mongodb_atlas: typing.Callable[[], T_Result],
         milvus: typing.Callable[[], T_Result],
     ) -> T_Result:
-        if self is ConfigurableDataSinkNames.CHROMA:
-            return chroma()
         if self is ConfigurableDataSinkNames.PINECONE:
             return pinecone()
         if self is ConfigurableDataSinkNames.POSTGRES:
             return postgres()
         if self is ConfigurableDataSinkNames.QDRANT:
             return qdrant()
-        if self is ConfigurableDataSinkNames.WEAVIATE:
-            return weaviate()
         if self is ConfigurableDataSinkNames.AZUREAI_SEARCH:
             return azureai_search()
         if self is ConfigurableDataSinkNames.MONGODB_ATLAS:

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/llama_cloud/types/configurable_transformation_names.py

@@ -14,13 +14,6 @@ class ConfigurableTransformationNames(str, enum.Enum):
     TOKEN_AWARE_NODE_PARSER = "TOKEN_AWARE_NODE_PARSER"
     MARKDOWN_NODE_PARSER = "MARKDOWN_NODE_PARSER"
     MARKDOWN_ELEMENT_NODE_PARSER = "MARKDOWN_ELEMENT_NODE_PARSER"
-    OPENAI_EMBEDDING = "OPENAI_EMBEDDING"
-    AZURE_EMBEDDING = "AZURE_EMBEDDING"
-    COHERE_EMBEDDING = "COHERE_EMBEDDING"
-    BEDROCK_EMBEDDING = "BEDROCK_EMBEDDING"
-    HUGGINGFACE_API_EMBEDDING = "HUGGINGFACE_API_EMBEDDING"
-    GEMINI_EMBEDDING = "GEMINI_EMBEDDING"
-    VERTEXAI_EMBEDDING = "VERTEXAI_EMBEDDING"
 
     def visit(
         self,
@@ -31,13 +24,6 @@ class ConfigurableTransformationNames(str, enum.Enum):
         token_aware_node_parser: typing.Callable[[], T_Result],
         markdown_node_parser: typing.Callable[[], T_Result],
         markdown_element_node_parser: typing.Callable[[], T_Result],
-        openai_embedding: typing.Callable[[], T_Result],
-        azure_embedding: typing.Callable[[], T_Result],
-        cohere_embedding: typing.Callable[[], T_Result],
-        bedrock_embedding: typing.Callable[[], T_Result],
-        huggingface_api_embedding: typing.Callable[[], T_Result],
-        gemini_embedding: typing.Callable[[], T_Result],
-        vertexai_embedding: typing.Callable[[], T_Result],
     ) -> T_Result:
         if self is ConfigurableTransformationNames.CHARACTER_SPLITTER:
             return character_splitter()
@@ -53,17 +39,3 @@ class ConfigurableTransformationNames(str, enum.Enum):
             return markdown_node_parser()
         if self is ConfigurableTransformationNames.MARKDOWN_ELEMENT_NODE_PARSER:
             return markdown_element_node_parser()
-        if self is ConfigurableTransformationNames.OPENAI_EMBEDDING:
-            return openai_embedding()
-        if self is ConfigurableTransformationNames.AZURE_EMBEDDING:
-            return azure_embedding()
-        if self is ConfigurableTransformationNames.COHERE_EMBEDDING:
-            return cohere_embedding()
-        if self is ConfigurableTransformationNames.BEDROCK_EMBEDDING:
-            return bedrock_embedding()
-        if self is ConfigurableTransformationNames.HUGGINGFACE_API_EMBEDDING:
-            return huggingface_api_embedding()
-        if self is ConfigurableTransformationNames.GEMINI_EMBEDDING:
-            return gemini_embedding()
-        if self is ConfigurableTransformationNames.VERTEXAI_EMBEDDING:
-            return vertexai_embedding()

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/llama_cloud/types/configured_transformation_item_component.py

@@ -2,17 +2,10 @@
 
 import typing
 
-from .azure_open_ai_embedding import AzureOpenAiEmbedding
-from .bedrock_embedding import BedrockEmbedding
 from .character_splitter import CharacterSplitter
 from .code_splitter import CodeSplitter
-from .cohere_embedding import CohereEmbedding
-from .extend_vertex_text_embedding import ExtendVertexTextEmbedding
-from .gemini_embedding import GeminiEmbedding
-from .hugging_face_inference_api_embedding import HuggingFaceInferenceApiEmbedding
 from .markdown_element_node_parser import MarkdownElementNodeParser
 from .markdown_node_parser import MarkdownNodeParser
-from .open_ai_embedding import OpenAiEmbedding
 from .page_splitter_node_parser import PageSplitterNodeParser
 from .sentence_splitter import SentenceSplitter
 from .token_text_splitter import TokenTextSplitter
@@ -26,11 +19,4 @@ ConfiguredTransformationItemComponent = typing.Union[
     TokenTextSplitter,
     MarkdownNodeParser,
     MarkdownElementNodeParser,
-    OpenAiEmbedding,
-    AzureOpenAiEmbedding,
-    CohereEmbedding,
-    BedrockEmbedding,
-    HuggingFaceInferenceApiEmbedding,
-    GeminiEmbedding,
-    ExtendVertexTextEmbedding,
 ]

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/llama_cloud/types/data_sink_component.py

@@ -3,21 +3,17 @@
 import typing
 
 from .cloud_azure_ai_search_vector_store import CloudAzureAiSearchVectorStore
-from .cloud_chroma_vector_store import CloudChromaVectorStore
 from .cloud_milvus_vector_store import CloudMilvusVectorStore
 from .cloud_mongo_db_atlas_vector_search import CloudMongoDbAtlasVectorSearch
 from .cloud_pinecone_vector_store import CloudPineconeVectorStore
 from .cloud_postgres_vector_store import CloudPostgresVectorStore
 from .cloud_qdrant_vector_store import CloudQdrantVectorStore
-from .cloud_weaviate_vector_store import CloudWeaviateVectorStore
 
 DataSinkComponent = typing.Union[
     typing.Dict[str, typing.Any],
-    CloudChromaVectorStore,
     CloudPineconeVectorStore,
     CloudPostgresVectorStore,
     CloudQdrantVectorStore,
-    CloudWeaviateVectorStore,
     CloudAzureAiSearchVectorStore,
     CloudMongoDbAtlasVectorSearch,
     CloudMilvusVectorStore,

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/llama_cloud/types/data_sink_create_component.py

@@ -3,21 +3,17 @@
 import typing
 
 from .cloud_azure_ai_search_vector_store import CloudAzureAiSearchVectorStore
-from .cloud_chroma_vector_store import CloudChromaVectorStore
 from .cloud_milvus_vector_store import CloudMilvusVectorStore
 from .cloud_mongo_db_atlas_vector_search import CloudMongoDbAtlasVectorSearch
 from .cloud_pinecone_vector_store import CloudPineconeVectorStore
 from .cloud_postgres_vector_store import CloudPostgresVectorStore
 from .cloud_qdrant_vector_store import CloudQdrantVectorStore
-from .cloud_weaviate_vector_store import CloudWeaviateVectorStore
 
 DataSinkCreateComponent = typing.Union[
     typing.Dict[str, typing.Any],
-    CloudChromaVectorStore,
     CloudPineconeVectorStore,
     CloudPostgresVectorStore,
     CloudQdrantVectorStore,
-    CloudWeaviateVectorStore,
     CloudAzureAiSearchVectorStore,
     CloudMongoDbAtlasVectorSearch,
     CloudMilvusVectorStore,

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/llama_cloud/types/gemini_embedding.py

@@ -15,25 +15,14 @@ except ImportError:
 
 
 class GeminiEmbedding(pydantic.BaseModel):
-    """
-    Google Gemini embeddings.
-
-    Args:
-    model_name (str): Model for embedding.
-    Defaults to "models/embedding-001".
-
-        api_key (Optional[str]): API key to access the model. Defaults to None.
-        api_base (Optional[str]): API base to access the model. Defaults to Official Base.
-        transport (Optional[str]): Transport to access the model.
-    """
-
-    model_name: typing.Optional[str] = pydantic.Field(description="The name of the embedding model.")
+    model_name: typing.Optional[str] = pydantic.Field(description="The modelId of the Gemini model to use.")
     embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    callback_manager: typing.Optional[typing.Any]
     num_workers: typing.Optional[int]
     title: typing.Optional[str]
     task_type: typing.Optional[str]
     api_key: typing.Optional[str]
+    api_base: typing.Optional[str]
+    transport: typing.Optional[str]
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/llama_cloud/types/hugging_face_inference_api_embedding.py

@@ -17,17 +17,8 @@ except ImportError:
 
 
 class HuggingFaceInferenceApiEmbedding(pydantic.BaseModel):
-    """
-    Wrapper on the Hugging Face's Inference API for embeddings.
-
-    Overview of the design:
-
-    - Uses the feature extraction task: https://huggingface.co/tasks/feature-extraction
-    """
-
     model_name: typing.Optional[str]
     embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    callback_manager: typing.Optional[typing.Any]
     num_workers: typing.Optional[int]
     pooling: typing.Optional[Pooling]
     query_instruction: typing.Optional[str]

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/llama_cloud/types/input_message.py

@@ -20,7 +20,7 @@ class InputMessage(pydantic.BaseModel):
     This is distinct from a ChatMessage because this schema is enforced by the AI Chat library used in the frontend
     """
 
-    id: typing.Optional[str]
+    id: str = pydantic.Field(description="ID of the message, if any. a UUID.")
     role: MessageRole
     content: str
     data: typing.Optional[typing.Dict[str, typing.Any]]

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/llama_cloud/types/llama_parse_parameters.py

@@ -44,6 +44,10 @@ class LlamaParseParameters(pydantic.BaseModel):
     premium_mode: typing.Optional[bool]
     s_3_input_path: typing.Optional[str] = pydantic.Field(alias="s3_input_path")
     s_3_output_path_prefix: typing.Optional[str] = pydantic.Field(alias="s3_output_path_prefix")
+    azure_openai_deployment_name: typing.Optional[str]
+    azure_openai_endpoint: typing.Optional[str]
+    azure_openai_api_version: typing.Optional[str]
+    azure_openai_key: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/llama_cloud/types/open_ai_embedding.py

@@ -15,36 +15,13 @@ except ImportError:
 
 
 class OpenAiEmbedding(pydantic.BaseModel):
-    """
-    OpenAI class for embeddings.
-
-    Args:
-    mode (str): Mode for embedding.
-    Defaults to OpenAIEmbeddingMode.TEXT_SEARCH_MODE.
-    Options are:
-
-            - OpenAIEmbeddingMode.SIMILARITY_MODE
-            - OpenAIEmbeddingMode.TEXT_SEARCH_MODE
-
-        model (str): Model for embedding.
-            Defaults to OpenAIEmbeddingModelType.TEXT_EMBED_ADA_002.
-            Options are:
-
-            - OpenAIEmbeddingModelType.DAVINCI
-            - OpenAIEmbeddingModelType.CURIE
-            - OpenAIEmbeddingModelType.BABBAGE
-            - OpenAIEmbeddingModelType.ADA
-            - OpenAIEmbeddingModelType.TEXT_EMBED_ADA_002
-    """
-
-    model_name: typing.Optional[str] = pydantic.Field(description="The name of the embedding model.")
+    model_name: typing.Optional[str] = pydantic.Field(description="The name of the OpenAI embedding model.")
     embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    callback_manager: typing.Optional[typing.Any]
     num_workers: typing.Optional[int]
     additional_kwargs: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(
         description="Additional kwargs for the OpenAI API."
     )
-    api_key: str = pydantic.Field(description="The OpenAI API key.")
+    api_key: typing.Optional[str]
     api_base: typing.Optional[str]
     api_version: typing.Optional[str]
     max_retries: typing.Optional[int] = pydantic.Field(description="Maximum number of retries.")

{llama_cloud-0.1.0 → llama_cloud-0.1.2}/llama_cloud/types/vertex_ai_embedding_config.py

@@ -4,7 +4,7 @@ import datetime as dt
 import typing
 
 from ..core.datetime_utils import serialize_datetime
-from .extend_vertex_text_embedding import ExtendVertexTextEmbedding
+from .vertex_text_embedding import VertexTextEmbedding
 
 try:
     import pydantic
@@ -16,7 +16,7 @@ except ImportError:
 
 
 class VertexAiEmbeddingConfig(pydantic.BaseModel):
-    component: typing.Optional[ExtendVertexTextEmbedding] = pydantic.Field(
+    component: typing.Optional[VertexTextEmbedding] = pydantic.Field(
         description="Configuration for the VertexAI embedding model."
     )