llama-cloud 0.1.41__py3-none-any.whl → 1.0.0b4__py3-none-any.whl

llama_cloud/types/shared_params/cloud_confluence_data_source.py

@@ -0,0 +1,58 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Optional
+from typing_extensions import Required, TypedDict
+
+from .failure_handling_config import FailureHandlingConfig
+
+__all__ = ["CloudConfluenceDataSource"]
+
+
+class CloudConfluenceDataSource(TypedDict, total=False):
+    authentication_mechanism: Required[str]
+    """Type of Authentication for connecting to Confluence APIs."""
+
+    server_url: Required[str]
+    """The server URL of the Confluence instance."""
+
+    api_token: Optional[str]
+    """The API token to use for authentication."""
+
+    class_name: str
+
+    cql: Optional[str]
+    """The CQL query to use for fetching pages."""
+
+    failure_handling: FailureHandlingConfig
+    """Configuration for handling failures during processing.
+
+    Key-value object controlling failure handling behaviors.
+
+    Example: { "skip_list_failures": true }
+
+    Currently supports:
+
+    - skip_list_failures: Skip failed batches/lists and continue processing
+    """
+
+    index_restricted_pages: bool
+    """Whether to index restricted pages."""
+
+    keep_markdown_format: bool
+    """Whether to keep the markdown format."""
+
+    label: Optional[str]
+    """The label to use for fetching pages."""
+
+    page_ids: Optional[str]
+    """The page IDs of the Confluence to read from."""
+
+    space_key: Optional[str]
+    """The space key to read from."""
+
+    supports_access_control: bool
+
+    user_name: Optional[str]
+    """The username to use for authentication."""

llama_cloud/types/shared_params/cloud_jira_data_source.py

@@ -0,0 +1,34 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Optional
+from typing_extensions import Required, TypedDict
+
+__all__ = ["CloudJiraDataSource"]
+
+
+class CloudJiraDataSource(TypedDict, total=False):
+    """Cloud Jira Data Source integrating JiraReader."""
+
+    authentication_mechanism: Required[str]
+    """Type of Authentication for connecting to Jira APIs."""
+
+    query: Required[str]
+    """JQL (Jira Query Language) query to search."""
+
+    api_token: Optional[str]
+    """The API/ Access Token used for Basic, PAT and OAuth2 authentication."""
+
+    class_name: str
+
+    cloud_id: Optional[str]
+    """The cloud ID, used in case of OAuth2."""
+
+    email: Optional[str]
+    """The email address to use for authentication."""
+
+    server_url: Optional[str]
+    """The server url for Jira Cloud."""
+
+    supports_access_control: bool

llama_cloud/types/shared_params/cloud_jira_data_source_v2.py

@@ -0,0 +1,54 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Optional
+from typing_extensions import Literal, Required, TypedDict
+
+from ..._types import SequenceNotStr
+
+__all__ = ["CloudJiraDataSourceV2"]
+
+
+class CloudJiraDataSourceV2(TypedDict, total=False):
+    """Cloud Jira Data Source integrating JiraReaderV2."""
+
+    authentication_mechanism: Required[str]
+    """Type of Authentication for connecting to Jira APIs."""
+
+    query: Required[str]
+    """JQL (Jira Query Language) query to search."""
+
+    server_url: Required[str]
+    """The server url for Jira Cloud."""
+
+    api_token: Optional[str]
+    """The API Access Token used for Basic, PAT and OAuth2 authentication."""
+
+    api_version: Literal["2", "3"]
+    """Jira REST API version to use (2 or 3).
+
+    3 supports Atlassian Document Format (ADF).
+    """
+
+    class_name: str
+
+    cloud_id: Optional[str]
+    """The cloud ID, used in case of OAuth2."""
+
+    email: Optional[str]
+    """The email address to use for authentication."""
+
+    expand: Optional[str]
+    """Fields to expand in the response."""
+
+    fields: Optional[SequenceNotStr[str]]
+    """List of fields to retrieve from Jira. If None, retrieves all fields."""
+
+    get_permissions: bool
+    """Whether to fetch project role permissions and issue-level security"""
+
+    requests_per_minute: Optional[int]
+    """Rate limit for Jira API requests per minute."""
+
+    supports_access_control: bool

llama_cloud/types/shared_params/cloud_milvus_vector_store.py

@@ -0,0 +1,24 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Optional
+from typing_extensions import Required, TypedDict
+
+__all__ = ["CloudMilvusVectorStore"]
+
+
+class CloudMilvusVectorStore(TypedDict, total=False):
+    """Cloud Milvus Vector Store."""
+
+    uri: Required[str]
+
+    token: Optional[str]
+
+    class_name: str
+
+    collection_name: Optional[str]
+
+    embedding_dimension: Optional[int]
+
+    supports_nested_metadata_filters: bool

llama_cloud/types/shared_params/cloud_mongodb_atlas_vector_search.py

@@ -0,0 +1,39 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Optional
+from typing_extensions import Required, TypedDict
+
+__all__ = ["CloudMongoDBAtlasVectorSearch"]
+
+
+class CloudMongoDBAtlasVectorSearch(TypedDict, total=False):
+    """Cloud MongoDB Atlas Vector Store.
+
+    This class is used to store the configuration for a MongoDB Atlas vector store,
+    so that it can be created and used in LlamaCloud.
+
+    Args:
+        mongodb_uri (str): URI for connecting to MongoDB Atlas
+        db_name (str): name of the MongoDB database
+        collection_name (str): name of the MongoDB collection
+        vector_index_name (str): name of the MongoDB Atlas vector index
+        fulltext_index_name (str): name of the MongoDB Atlas full-text index
+    """
+
+    collection_name: Required[str]
+
+    db_name: Required[str]
+
+    mongodb_uri: Required[str]
+
+    class_name: str
+
+    embedding_dimension: Optional[int]
+
+    fulltext_index_name: Optional[str]
+
+    supports_nested_metadata_filters: bool
+
+    vector_index_name: Optional[str]

llama_cloud/types/shared_params/cloud_notion_page_data_source.py

@@ -0,0 +1,23 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Optional
+from typing_extensions import Required, TypedDict
+
+__all__ = ["CloudNotionPageDataSource"]
+
+
+class CloudNotionPageDataSource(TypedDict, total=False):
+    integration_token: Required[str]
+    """The integration token to use for authentication."""
+
+    class_name: str
+
+    database_ids: Optional[str]
+    """The Notion Database Id to read content from."""
+
+    page_ids: Optional[str]
+    """The Page ID's of the Notion to read from."""
+
+    supports_access_control: bool

llama_cloud/types/shared_params/cloud_one_drive_data_source.py

@@ -0,0 +1,37 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Optional
+from typing_extensions import Literal, Required, TypedDict
+
+from ..._types import SequenceNotStr
+
+__all__ = ["CloudOneDriveDataSource"]
+
+
+class CloudOneDriveDataSource(TypedDict, total=False):
+    client_id: Required[str]
+    """The client ID to use for authentication."""
+
+    client_secret: Required[str]
+    """The client secret to use for authentication."""
+
+    tenant_id: Required[str]
+    """The tenant ID to use for authentication."""
+
+    user_principal_name: Required[str]
+    """The user principal name to use for authentication."""
+
+    class_name: str
+
+    folder_id: Optional[str]
+    """The ID of the OneDrive folder to read from."""
+
+    folder_path: Optional[str]
+    """The path of the OneDrive folder to read from."""
+
+    required_exts: Optional[SequenceNotStr[str]]
+    """The list of required file extensions."""
+
+    supports_access_control: Literal[True]

llama_cloud/types/shared_params/cloud_pinecone_vector_store.py

@@ -0,0 +1,35 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict, Optional
+from typing_extensions import Literal, Required, TypedDict
+
+__all__ = ["CloudPineconeVectorStore"]
+
+
+class CloudPineconeVectorStore(TypedDict, total=False):
+    """Cloud Pinecone Vector Store.
+
+    This class is used to store the configuration for a Pinecone vector store, so that it can be
+    created and used in LlamaCloud.
+
+    Args:
+        api_key (str): API key for authenticating with Pinecone
+        index_name (str): name of the Pinecone index
+        namespace (optional[str]): namespace to use in the Pinecone index
+        insert_kwargs (optional[dict]): additional kwargs to pass during insertion
+    """
+
+    api_key: Required[str]
+    """The API key for authenticating with Pinecone"""
+
+    index_name: Required[str]
+
+    class_name: str
+
+    insert_kwargs: Optional[Dict[str, object]]
+
+    namespace: Optional[str]
+
+    supports_nested_metadata_filters: Literal[True]

llama_cloud/types/shared_params/cloud_postgres_vector_store.py

@@ -0,0 +1,39 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Optional
+from typing_extensions import Required, TypedDict
+
+from .pg_vector_hnsw_settings import PgVectorHnswSettings
+
+__all__ = ["CloudPostgresVectorStore"]
+
+
+class CloudPostgresVectorStore(TypedDict, total=False):
+    database: Required[str]
+
+    embed_dim: Required[int]
+
+    host: Required[str]
+
+    password: Required[str]
+
+    port: Required[int]
+
+    schema_name: Required[str]
+
+    table_name: Required[str]
+
+    user: Required[str]
+
+    class_name: str
+
+    hnsw_settings: Optional[PgVectorHnswSettings]
+    """HNSW settings for PGVector."""
+
+    hybrid_search: Optional[bool]
+
+    perform_setup: bool
+
+    supports_nested_metadata_filters: bool

llama_cloud/types/shared_params/cloud_qdrant_vector_store.py

@@ -0,0 +1,37 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Dict
+from typing_extensions import Literal, Required, TypedDict
+
+__all__ = ["CloudQdrantVectorStore"]
+
+
+class CloudQdrantVectorStore(TypedDict, total=False):
+    """Cloud Qdrant Vector Store.
+
+    This class is used to store the configuration for a Qdrant vector store, so that it can be
+    created and used in LlamaCloud.
+
+    Args:
+        collection_name (str): name of the Qdrant collection
+        url (str): url of the Qdrant instance
+        api_key (str): API key for authenticating with Qdrant
+        max_retries (int): maximum number of retries in case of a failure. Defaults to 3
+        client_kwargs (dict): additional kwargs to pass to the Qdrant client
+    """
+
+    api_key: Required[str]
+
+    collection_name: Required[str]
+
+    url: Required[str]
+
+    class_name: str
+
+    client_kwargs: Dict[str, object]
+
+    max_retries: int
+
+    supports_nested_metadata_filters: Literal[True]

llama_cloud/types/shared_params/cloud_s3_data_source.py

@@ -0,0 +1,32 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Optional
+from typing_extensions import Required, TypedDict
+
+__all__ = ["CloudS3DataSource"]
+
+
+class CloudS3DataSource(TypedDict, total=False):
+    bucket: Required[str]
+    """The name of the S3 bucket to read from."""
+
+    aws_access_id: Optional[str]
+    """The AWS access ID to use for authentication."""
+
+    aws_access_secret: Optional[str]
+    """The AWS access secret to use for authentication."""
+
+    class_name: str
+
+    prefix: Optional[str]
+    """The prefix of the S3 objects to read from."""
+
+    regex_pattern: Optional[str]
+    """The regex pattern to filter S3 objects. Must be a valid regex pattern."""
+
+    s3_endpoint_url: Optional[str]
+    """The S3 endpoint URL to use for authentication."""
+
+    supports_access_control: bool

llama_cloud/types/shared_params/cloud_sharepoint_data_source.py

@@ -0,0 +1,60 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Optional
+from typing_extensions import Literal, Required, TypedDict
+
+from ..._types import SequenceNotStr
+
+__all__ = ["CloudSharepointDataSource"]
+
+
+class CloudSharepointDataSource(TypedDict, total=False):
+    client_id: Required[str]
+    """The client ID to use for authentication."""
+
+    client_secret: Required[str]
+    """The client secret to use for authentication."""
+
+    tenant_id: Required[str]
+    """The tenant ID to use for authentication."""
+
+    class_name: str
+
+    drive_name: Optional[str]
+    """The name of the Sharepoint drive to read from."""
+
+    exclude_path_patterns: Optional[SequenceNotStr[str]]
+    """List of regex patterns for file paths to exclude.
+
+    Files whose paths (including filename) match any pattern will be excluded.
+    Example: ['/temp/', '/backup/', '\\..git/', '\\..tmp$', '^~']
+    """
+
+    folder_id: Optional[str]
+    """The ID of the Sharepoint folder to read from."""
+
+    folder_path: Optional[str]
+    """The path of the Sharepoint folder to read from."""
+
+    get_permissions: Optional[bool]
+    """Whether to get permissions for the sharepoint site."""
+
+    include_path_patterns: Optional[SequenceNotStr[str]]
+    """List of regex patterns for file paths to include.
+
+    Full paths (including filename) must match at least one pattern to be included.
+    Example: ['/reports/', '/docs/.*\\..pdf$', '^Report.*\\..pdf$']
+    """
+
+    required_exts: Optional[SequenceNotStr[str]]
+    """The list of required file extensions."""
+
+    site_id: Optional[str]
+    """The ID of the SharePoint site to download from."""
+
+    site_name: Optional[str]
+    """The name of the SharePoint site to download from."""
+
+    supports_access_control: Literal[True]

llama_cloud/types/shared_params/cloud_slack_data_source.py

@@ -0,0 +1,35 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing import Optional
+from typing_extensions import Required, TypedDict
+
+__all__ = ["CloudSlackDataSource"]
+
+
+class CloudSlackDataSource(TypedDict, total=False):
+    slack_token: Required[str]
+    """Slack Bot Token."""
+
+    channel_ids: Optional[str]
+    """Slack Channel."""
+
+    channel_patterns: Optional[str]
+    """Slack Channel name pattern."""
+
+    class_name: str
+
+    earliest_date: Optional[str]
+    """Earliest date."""
+
+    earliest_date_timestamp: Optional[float]
+    """Earliest date timestamp."""
+
+    latest_date: Optional[str]
+    """Latest date."""
+
+    latest_date_timestamp: Optional[float]
+    """Latest date timestamp."""
+
+    supports_access_control: bool

llama_cloud/types/shared_params/failure_handling_config.py

@@ -0,0 +1,16 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing_extensions import TypedDict
+
+__all__ = ["FailureHandlingConfig"]
+
+
+class FailureHandlingConfig(TypedDict, total=False):
+    """
+    Configuration for handling different types of failures during data source processing.
+    """
+
+    skip_list_failures: bool
+    """Whether to skip failed batches/lists and continue processing"""

llama_cloud/types/shared_params/pg_vector_hnsw_settings.py

@@ -0,0 +1,26 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing_extensions import Literal, TypedDict
+
+__all__ = ["PgVectorHnswSettings"]
+
+
+class PgVectorHnswSettings(TypedDict, total=False):
+    """HNSW settings for PGVector."""
+
+    distance_method: Literal["l2", "ip", "cosine", "l1", "hamming", "jaccard"]
+    """The distance method to use."""
+
+    ef_construction: int
+    """The number of edges to use during the construction phase."""
+
+    ef_search: int
+    """The number of edges to use during the search phase."""
+
+    m: int
+    """The number of bi-directional links created for each new element."""
+
+    vector_type: Literal["vector", "half_vec", "bit", "sparse_vec"]
+    """The type of vector to use."""

llama_cloud/types/sparse_model_config.py

@@ -1,42 +1,28 @@
-# This file was auto-generated by Fern from our API Definition.
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
-import datetime as dt
-import typing
+from typing import Optional
+from typing_extensions import Literal
 
-from ..core.datetime_utils import serialize_datetime
-from .sparse_model_type import SparseModelType
+from pydantic import Field as FieldInfo
 
-try:
-    import pydantic
-    if pydantic.__version__.startswith("1."):
-        raise ImportError
-    import pydantic.v1 as pydantic  # type: ignore
-except ImportError:
-    import pydantic  # type: ignore
+from .._models import BaseModel
 
+__all__ = ["SparseModelConfig"]
 
-class SparseModelConfig(pydantic.BaseModel):
-    """
-    Configuration for sparse embedding models used in hybrid search.
+
+class SparseModelConfig(BaseModel):
+    """Configuration for sparse embedding models used in hybrid search.
 
     This allows users to choose between Splade and BM25 models for
     sparse retrieval in managed data sinks.
     """
 
-    model_type: typing.Optional[SparseModelType] = pydantic.Field(
-        description="The sparse model type to use. 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade), 'splade' uses HuggingFace Splade model, 'bm25' uses Qdrant's FastEmbed BM25 model."
-    )
-    class_name: typing.Optional[str]
+    class_name: Optional[str] = None
 
-    def json(self, **kwargs: typing.Any) -> str:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().json(**kwargs_with_defaults)
+    api_model_type: Optional[Literal["splade", "bm25", "auto"]] = FieldInfo(alias="model_type", default=None)
+    """The sparse model type to use.
 
-    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
-        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
-        return super().dict(**kwargs_with_defaults)
-
-    class Config:
-        frozen = True
-        smart_union = True
-        json_encoders = {dt.datetime: serialize_datetime}
+    'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade'
+    uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC
+    uses term frequency, Cloud uses Splade).
+    """

llama_cloud/types/sparse_model_config_param.py

@@ -0,0 +1,25 @@
+# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+from __future__ import annotations
+
+from typing_extensions import Literal, TypedDict
+
+__all__ = ["SparseModelConfigParam"]
+
+
+class SparseModelConfigParam(TypedDict, total=False):
+    """Configuration for sparse embedding models used in hybrid search.
+
+    This allows users to choose between Splade and BM25 models for
+    sparse retrieval in managed data sinks.
+    """
+
+    class_name: str
+
+    model_type: Literal["splade", "bm25", "auto"]
+    """The sparse model type to use.
+
+    'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade'
+    uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC
+    uses term frequency, Cloud uses Splade).
+    """