llama-cloud 0.1.4__py3-none-any.whl → 0.1.6__py3-none-any.whl

llama_cloud/types/plan.py

@@ -0,0 +1,40 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class Plan(pydantic.BaseModel):
+    total_users: typing.Optional[int]
+    total_indexes: typing.Optional[int]
+    total_indexed_pages: typing.Optional[int]
+    credits: typing.Optional[int]
+    has_payment_method: typing.Optional[bool]
+    free: typing.Optional[bool] = pydantic.Field(description="If is a free plan")
+    allowed_index: typing.Optional[bool] = pydantic.Field(description="If is allowed to use indexes")
+    allowed_external_index: typing.Optional[bool] = pydantic.Field(
+        description="If is allowed to use external data sources or sinks in indexes"
+    )
+
+    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)
+
+    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}

llama_cloud/types/playground_session.py

@@ -23,8 +23,8 @@ class PlaygroundSession(pydantic.BaseModel):
     """
 
     id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime]
-    updated_at: typing.Optional[dt.datetime]
+    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
+    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
     pipeline_id: str
     user_id: str
     llm_params_id: str

llama_cloud/types/preset_retrieval_params.py

@@ -21,13 +21,20 @@ class PresetRetrievalParams(pydantic.BaseModel):
     Schema for the search params for an retrieval execution that can be preset for a pipeline.
     """
 
-    dense_similarity_top_k: typing.Optional[int]
-    sparse_similarity_top_k: typing.Optional[int]
-    enable_reranking: typing.Optional[bool]
-    rerank_top_n: typing.Optional[int]
-    alpha: typing.Optional[float]
-    search_filters: typing.Optional[MetadataFilters]
-    files_top_k: typing.Optional[int]
+    dense_similarity_top_k: typing.Optional[int] = pydantic.Field(description="Number of nodes for dense retrieval.")
+    dense_similarity_cutoff: typing.Optional[float] = pydantic.Field(
+        description="Minimum similarity score wrt query for retrieval"
+    )
+    sparse_similarity_top_k: typing.Optional[int] = pydantic.Field(description="Number of nodes for sparse retrieval.")
+    enable_reranking: typing.Optional[bool] = pydantic.Field(description="Enable reranking for retrieval")
+    rerank_top_n: typing.Optional[int] = pydantic.Field(description="Number of reranked nodes for returning.")
+    alpha: typing.Optional[float] = pydantic.Field(
+        description="Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval."
+    )
+    search_filters: typing.Optional[MetadataFilters] = pydantic.Field(description="Search filters for retrieval.")
+    files_top_k: typing.Optional[int] = pydantic.Field(
+        description="Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content)."
+    )
     retrieval_mode: typing.Optional[RetrievalMode] = pydantic.Field(description="The retrieval mode for the query.")
     retrieve_image_nodes: typing.Optional[bool] = pydantic.Field(description="Whether to retrieve image nodes.")
     class_name: typing.Optional[str]

llama_cloud/types/presigned_url.py

@@ -21,7 +21,9 @@ class PresignedUrl(pydantic.BaseModel):
 
     url: str = pydantic.Field(description="A presigned URL for IO operations against a private file")
     expires_at: dt.datetime = pydantic.Field(description="The time at which the presigned URL expires")
-    form_fields: typing.Optional[typing.Dict[str, typing.Optional[str]]]
+    form_fields: typing.Optional[typing.Dict[str, typing.Optional[str]]] = pydantic.Field(
+        description="Form fields for a presigned POST request"
+    )
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/project.py

@@ -21,8 +21,8 @@ class Project(pydantic.BaseModel):
 
     name: str
     id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime]
-    updated_at: typing.Optional[dt.datetime]
+    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
+    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
     ad_hoc_eval_dataset_id: typing.Optional[str]
     organization_id: str = pydantic.Field(description="The Organization ID the project is under.")
     is_default: typing.Optional[bool] = pydantic.Field(

llama_cloud/types/prompt_mixin_prompts.py

@@ -21,7 +21,7 @@ class PromptMixinPrompts(pydantic.BaseModel):
     """
 
     project_id: str = pydantic.Field(description="The ID of the project.")
-    id: typing.Optional[str]
+    id: typing.Optional[str] = pydantic.Field(description="The ID of the prompt set.")
     name: str = pydantic.Field(description="The name of the prompt set.")
     prompts: typing.List[PromptSpec] = pydantic.Field(description="The prompts.")
 

llama_cloud/types/prompt_spec.py

@@ -19,8 +19,10 @@ class PromptSpec(pydantic.BaseModel):
     prompt_key: str = pydantic.Field(description="The key of the prompt in the PromptMixin.")
     prompt_class: str = pydantic.Field(description="The class of the prompt (PromptTemplate or ChatPromptTemplate).")
     prompt_type: str = pydantic.Field(description="The type of prompt.")
-    template: typing.Optional[str]
-    message_templates: typing.Optional[typing.List[ChatMessage]]
+    template: typing.Optional[str] = pydantic.Field(description="The template of the prompt.")
+    message_templates: typing.Optional[typing.List[ChatMessage]] = pydantic.Field(
+        description="The chat message templates of the prompt."
+    )
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/role.py

@@ -21,10 +21,10 @@ class Role(pydantic.BaseModel):
     """
 
     id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime]
-    updated_at: typing.Optional[dt.datetime]
+    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
+    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
     name: str = pydantic.Field(description="A name for the role.")
-    organization_id: typing.Optional[str]
+    organization_id: typing.Optional[str] = pydantic.Field(description="The organization's ID.")
     permissions: typing.List[Permission] = pydantic.Field(description="The actual permissions of the role.")
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/sentence_splitter.py

@@ -28,12 +28,14 @@ class SentenceSplitter(pydantic.BaseModel):
     )
     include_prev_next_rel: typing.Optional[bool] = pydantic.Field(description="Include prev/next node relationships.")
     callback_manager: typing.Optional[typing.Any]
-    id_func: typing.Optional[str]
+    id_func: typing.Optional[str] = pydantic.Field(description="Function to generate node IDs.")
     chunk_size: typing.Optional[int] = pydantic.Field(description="The token chunk size for each chunk.")
     chunk_overlap: typing.Optional[int] = pydantic.Field(description="The token overlap of each chunk when splitting.")
     separator: typing.Optional[str] = pydantic.Field(description="Default separator for splitting into words")
     paragraph_separator: typing.Optional[str] = pydantic.Field(description="Separator between paragraphs.")
-    secondary_chunking_regex: typing.Optional[str]
+    secondary_chunking_regex: typing.Optional[str] = pydantic.Field(
+        description="Backup regex for splitting into sentences."
+    )
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/text_node.py

@@ -17,7 +17,7 @@ except ImportError:
 
 class TextNode(pydantic.BaseModel):
     id: typing.Optional[str] = pydantic.Field(alias="id_", description="Unique ID of the node.")
-    embedding: typing.Optional[typing.List[float]]
+    embedding: typing.Optional[typing.List[float]] = pydantic.Field(description="Embedding of the node.")
     extra_info: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(
         description="A flat dictionary of metadata fields"
     )
@@ -32,8 +32,8 @@ class TextNode(pydantic.BaseModel):
     )
     text: typing.Optional[str] = pydantic.Field(description="Text content of the node.")
     mimetype: typing.Optional[str] = pydantic.Field(description="MIME type of the node content.")
-    start_char_idx: typing.Optional[int]
-    end_char_idx: typing.Optional[int]
+    start_char_idx: typing.Optional[int] = pydantic.Field(description="Start char index of the node.")
+    end_char_idx: typing.Optional[int] = pydantic.Field(description="End char index of the node.")
     text_template: typing.Optional[str] = pydantic.Field(
         description="Template for how text is formatted, with {content} and {metadata_str} placeholders."
     )

llama_cloud/types/{hugging_face_inference_api_embedding_token.py → token.py}

@@ -2,4 +2,4 @@
 
 import typing
 
-HuggingFaceInferenceApiEmbeddingToken = typing.Union[str, bool]
+Token = typing.Union[str, bool]

llama_cloud/types/token_text_splitter.py

@@ -24,7 +24,7 @@ class TokenTextSplitter(pydantic.BaseModel):
     )
     include_prev_next_rel: typing.Optional[bool] = pydantic.Field(description="Include prev/next node relationships.")
     callback_manager: typing.Optional[typing.Any]
-    id_func: typing.Optional[str]
+    id_func: typing.Optional[str] = pydantic.Field(description="Function to generate node IDs.")
     chunk_size: typing.Optional[int] = pydantic.Field(description="The token chunk size for each chunk.")
     chunk_overlap: typing.Optional[int] = pydantic.Field(description="The token overlap of each chunk when splitting.")
     separator: typing.Optional[str] = pydantic.Field(description="Default separator for splitting into words")

llama_cloud/types/usage.py

@@ -0,0 +1,41 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+
+try:
+    import pydantic
+    if pydantic.__version__.startswith("1."):
+        raise ImportError
+    import pydantic.v1 as pydantic  # type: ignore
+except ImportError:
+    import pydantic  # type: ignore
+
+
+class Usage(pydantic.BaseModel):
+    """
+    Response model; use UsageSubmission for tracking
+    """
+
+    total_users: typing.Optional[int]
+    total_indexes: typing.Optional[int]
+    total_indexed_pages: typing.Optional[int]
+    extract_pages: typing.Optional[int]
+    parse_pages: typing.Optional[int]
+    index_pages: typing.Optional[int]
+    credits: typing.Optional[int]
+
+    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)
+
+    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}

llama_cloud/types/user_organization.py

@@ -21,16 +21,20 @@ class UserOrganization(pydantic.BaseModel):
     """
 
     id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime]
-    updated_at: typing.Optional[dt.datetime]
+    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
+    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
     email: str = pydantic.Field(description="The user's email address.")
-    user_id: typing.Optional[str]
+    user_id: typing.Optional[str] = pydantic.Field(description="The user's ID.")
     organization_id: str = pydantic.Field(description="The organization's ID.")
     pending: typing.Optional[bool] = pydantic.Field(
         description="Whether the user's membership is pending account signup."
     )
-    invited_by_user_id: typing.Optional[str]
-    invited_by_user_email: typing.Optional[str]
+    invited_by_user_id: typing.Optional[str] = pydantic.Field(
+        description="The user ID of the user who added the user to the organization."
+    )
+    invited_by_user_email: typing.Optional[str] = pydantic.Field(
+        description="The email address of the user who added the user to the organization."
+    )
     roles: typing.List[UserOrganizationRole] = pydantic.Field(description="The roles of the user in the organization.")
 
     def json(self, **kwargs: typing.Any) -> str:

llama_cloud/types/user_organization_create.py

@@ -19,10 +19,10 @@ class UserOrganizationCreate(pydantic.BaseModel):
     Schema for creating a user's membership to an organization.
     """
 
-    user_id: typing.Optional[str]
-    email: typing.Optional[str]
-    project_ids: typing.Optional[typing.List[str]]
-    role_id: typing.Optional[str]
+    user_id: typing.Optional[str] = pydantic.Field(description="The user's ID.")
+    email: typing.Optional[str] = pydantic.Field(description="The user's email address.")
+    project_ids: typing.Optional[typing.List[str]] = pydantic.Field(description="The project IDs to add the user to.")
+    role_id: typing.Optional[str] = pydantic.Field(description="The role ID to assign to the user.")
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/user_organization_delete.py

@@ -19,8 +19,8 @@ class UserOrganizationDelete(pydantic.BaseModel):
     Schema for deleting a user's membership to an organization.
     """
 
-    user_id: typing.Optional[str]
-    email: typing.Optional[str]
+    user_id: typing.Optional[str] = pydantic.Field(description="The user's ID.")
+    email: typing.Optional[str] = pydantic.Field(description="The user's email address.")
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

llama_cloud/types/user_organization_role.py

@@ -21,8 +21,8 @@ class UserOrganizationRole(pydantic.BaseModel):
     """
 
     id: str = pydantic.Field(description="Unique identifier")
-    created_at: typing.Optional[dt.datetime]
-    updated_at: typing.Optional[dt.datetime]
+    created_at: typing.Optional[dt.datetime] = pydantic.Field(description="Creation datetime")
+    updated_at: typing.Optional[dt.datetime] = pydantic.Field(description="Update datetime")
     user_id: str = pydantic.Field(description="The user's ID.")
     organization_id: str = pydantic.Field(description="The organization's ID.")
     role_id: str = pydantic.Field(description="The role's ID.")

llama_cloud/types/value.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+Value = typing.Union[int, float, str, typing.List[str], typing.List[float], typing.List[int]]

llama_cloud/types/vertex_text_embedding.py

@@ -18,17 +18,21 @@ except ImportError:
 class VertexTextEmbedding(pydantic.BaseModel):
     model_name: typing.Optional[str] = pydantic.Field(description="The modelId of the VertexAI model to use.")
     embed_batch_size: typing.Optional[int] = pydantic.Field(description="The batch size for embedding calls.")
-    num_workers: typing.Optional[int]
+    num_workers: typing.Optional[int] = pydantic.Field(
+        description="The number of workers to use for async embedding calls."
+    )
     location: str = pydantic.Field(description="The default location to use when making API calls.")
     project: str = pydantic.Field(description="The default GCP project to use when making Vertex API calls.")
     embed_mode: typing.Optional[VertexEmbeddingMode] = pydantic.Field(description="The embedding mode to use.")
     additional_kwargs: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(
         description="Additional kwargs for the Vertex."
     )
-    client_email: typing.Optional[str]
-    token_uri: typing.Optional[str]
-    private_key_id: typing.Optional[str]
-    private_key: typing.Optional[str]
+    client_email: typing.Optional[str] = pydantic.Field(description="The client email for the VertexAI credentials.")
+    token_uri: typing.Optional[str] = pydantic.Field(description="The token URI for the VertexAI credentials.")
+    private_key_id: typing.Optional[str] = pydantic.Field(
+        description="The private key ID for the VertexAI credentials."
+    )
+    private_key: typing.Optional[str] = pydantic.Field(description="The private key for the VertexAI credentials.")
     class_name: typing.Optional[str]
 
     def json(self, **kwargs: typing.Any) -> str:

{llama_cloud-0.1.4.dist-info → llama_cloud-0.1.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: llama-cloud
-Version: 0.1.4
+Version: 0.1.6
 Summary: 
 License: MIT
 Author: Logan Markewich