supermemory 3.7.0__py3-none-any.whl → 3.19.0__py3-none-any.whl

supermemory/resources/documents.py

@@ -2,12 +2,19 @@
 
 from __future__ import annotations
 
-from typing import Dict, Union, Mapping, cast
+from typing import Dict, Union, Mapping, Iterable, cast
 from typing_extensions import Literal
 
 import httpx
 
-from ..types import document_add_params, document_list_params, document_update_params, document_upload_file_params
+from ..types import (
+    document_add_params,
+    document_list_params,
+    document_update_params,
+    document_batch_add_params,
+    document_delete_bulk_params,
+    document_upload_file_params,
+)
 from .._types import Body, Omit, Query, Headers, NoneType, NotGiven, FileTypes, SequenceNotStr, omit, not_given
 from .._utils import extract_files, maybe_transform, deepcopy_minimal, async_maybe_transform
 from .._compat import cached_property
@@ -23,7 +30,10 @@ from ..types.document_add_response import DocumentAddResponse
 from ..types.document_get_response import DocumentGetResponse
 from ..types.document_list_response import DocumentListResponse
 from ..types.document_update_response import DocumentUpdateResponse
+from ..types.document_batch_add_response import DocumentBatchAddResponse
+from ..types.document_delete_bulk_response import DocumentDeleteBulkResponse
 from ..types.document_upload_file_response import DocumentUploadFileResponse
+from ..types.document_list_processing_response import DocumentListProcessingResponse
 
 __all__ = ["DocumentsResource", "AsyncDocumentsResource"]
 
@@ -278,6 +288,110 @@ class DocumentsResource(SyncAPIResource):
             cast_to=DocumentAddResponse,
         )
 
+    def batch_add(
+        self,
+        *,
+        documents: Union[Iterable[document_batch_add_params.DocumentsUnionMember0], SequenceNotStr[str]],
+        container_tag: str | Omit = omit,
+        container_tags: SequenceNotStr[str] | Omit = omit,
+        content: None | Omit = omit,
+        metadata: Dict[str, Union[str, float, bool, SequenceNotStr[str]]] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> DocumentBatchAddResponse:
+        """Add multiple documents in a single request.
+
+        Each document can have any content
+        type (text, url, file, etc.) and metadata
+
+        Args:
+          container_tag: Optional tag this document should be containerized by. This can be an ID for
+              your user, a project ID, or any other identifier you wish to use to group
+              documents.
+
+          container_tags: (DEPRECATED: Use containerTag instead) Optional tags this document should be
+              containerized by. This can be an ID for your user, a project ID, or any other
+              identifier you wish to use to group documents.
+
+          metadata: Optional metadata for the document. This is used to store additional information
+              about the document. You can use this to store any additional information you
+              need about the document. Metadata can be filtered through. Keys must be strings
+              and are case sensitive. Values can be strings, numbers, or booleans. You cannot
+              nest objects.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        return self._post(
+            "/v3/documents/batch",
+            body=maybe_transform(
+                {
+                    "documents": documents,
+                    "container_tag": container_tag,
+                    "container_tags": container_tags,
+                    "content": content,
+                    "metadata": metadata,
+                },
+                document_batch_add_params.DocumentBatchAddParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=DocumentBatchAddResponse,
+        )
+
+    def delete_bulk(
+        self,
+        *,
+        container_tags: SequenceNotStr[str] | Omit = omit,
+        ids: SequenceNotStr[str] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> DocumentDeleteBulkResponse:
+        """
+        Bulk delete documents by IDs or container tags
+
+        Args:
+          container_tags: Array of container tags - all documents in these containers will be deleted
+
+          ids: Array of document IDs to delete (max 100 at once)
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        return self._delete(
+            "/v3/documents/bulk",
+            body=maybe_transform(
+                {
+                    "container_tags": container_tags,
+                    "ids": ids,
+                },
+                document_delete_bulk_params.DocumentDeleteBulkParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=DocumentDeleteBulkResponse,
+        )
+
     def get(
         self,
         id: str,
@@ -311,6 +425,25 @@ class DocumentsResource(SyncAPIResource):
             cast_to=DocumentGetResponse,
         )
 
+    def list_processing(
+        self,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> DocumentListProcessingResponse:
+        """Get documents that are currently being processed"""
+        return self._get(
+            "/v3/documents/processing",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=DocumentListProcessingResponse,
+        )
+
     def upload_file(
         self,
         *,
@@ -319,6 +452,7 @@ class DocumentsResource(SyncAPIResource):
         file_type: str | Omit = omit,
         metadata: str | Omit = omit,
         mime_type: str | Omit = omit,
+        use_advanced_processing: str | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -348,6 +482,10 @@ class DocumentsResource(SyncAPIResource):
           mime_type: Required when fileType is 'image' or 'video'. Specifies the exact MIME type to
               use (e.g., 'image/png', 'image/jpeg', 'video/mp4', 'video/webm')
 
+          use_advanced_processing: DEPRECATED: This field is no longer used. Advanced PDF processing is now
+              automatic with our hybrid Mistral OCR + Gemini pipeline. This parameter will be
+              accepted but ignored for backwards compatibility.
+
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -363,6 +501,7 @@ class DocumentsResource(SyncAPIResource):
                 "file_type": file_type,
                 "metadata": metadata,
                 "mime_type": mime_type,
+                "use_advanced_processing": use_advanced_processing,
             }
         )
         files = extract_files(cast(Mapping[str, object], body), paths=[["file"]])
@@ -631,6 +770,110 @@ class AsyncDocumentsResource(AsyncAPIResource):
             cast_to=DocumentAddResponse,
         )
 
+    async def batch_add(
+        self,
+        *,
+        documents: Union[Iterable[document_batch_add_params.DocumentsUnionMember0], SequenceNotStr[str]],
+        container_tag: str | Omit = omit,
+        container_tags: SequenceNotStr[str] | Omit = omit,
+        content: None | Omit = omit,
+        metadata: Dict[str, Union[str, float, bool, SequenceNotStr[str]]] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> DocumentBatchAddResponse:
+        """Add multiple documents in a single request.
+
+        Each document can have any content
+        type (text, url, file, etc.) and metadata
+
+        Args:
+          container_tag: Optional tag this document should be containerized by. This can be an ID for
+              your user, a project ID, or any other identifier you wish to use to group
+              documents.
+
+          container_tags: (DEPRECATED: Use containerTag instead) Optional tags this document should be
+              containerized by. This can be an ID for your user, a project ID, or any other
+              identifier you wish to use to group documents.
+
+          metadata: Optional metadata for the document. This is used to store additional information
+              about the document. You can use this to store any additional information you
+              need about the document. Metadata can be filtered through. Keys must be strings
+              and are case sensitive. Values can be strings, numbers, or booleans. You cannot
+              nest objects.
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        return await self._post(
+            "/v3/documents/batch",
+            body=await async_maybe_transform(
+                {
+                    "documents": documents,
+                    "container_tag": container_tag,
+                    "container_tags": container_tags,
+                    "content": content,
+                    "metadata": metadata,
+                },
+                document_batch_add_params.DocumentBatchAddParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=DocumentBatchAddResponse,
+        )
+
+    async def delete_bulk(
+        self,
+        *,
+        container_tags: SequenceNotStr[str] | Omit = omit,
+        ids: SequenceNotStr[str] | Omit = omit,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> DocumentDeleteBulkResponse:
+        """
+        Bulk delete documents by IDs or container tags
+
+        Args:
+          container_tags: Array of container tags - all documents in these containers will be deleted
+
+          ids: Array of document IDs to delete (max 100 at once)
+
+          extra_headers: Send extra headers
+
+          extra_query: Add additional query parameters to the request
+
+          extra_body: Add additional JSON properties to the request
+
+          timeout: Override the client-level default timeout for this request, in seconds
+        """
+        return await self._delete(
+            "/v3/documents/bulk",
+            body=await async_maybe_transform(
+                {
+                    "container_tags": container_tags,
+                    "ids": ids,
+                },
+                document_delete_bulk_params.DocumentDeleteBulkParams,
+            ),
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=DocumentDeleteBulkResponse,
+        )
+
     async def get(
         self,
         id: str,
@@ -664,6 +907,25 @@ class AsyncDocumentsResource(AsyncAPIResource):
             cast_to=DocumentGetResponse,
         )
 
+    async def list_processing(
+        self,
+        *,
+        # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
+        # The extra values given here take precedence over values defined on the client or passed to this method.
+        extra_headers: Headers | None = None,
+        extra_query: Query | None = None,
+        extra_body: Body | None = None,
+        timeout: float | httpx.Timeout | None | NotGiven = not_given,
+    ) -> DocumentListProcessingResponse:
+        """Get documents that are currently being processed"""
+        return await self._get(
+            "/v3/documents/processing",
+            options=make_request_options(
+                extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
+            ),
+            cast_to=DocumentListProcessingResponse,
+        )
+
     async def upload_file(
         self,
         *,
@@ -672,6 +934,7 @@ class AsyncDocumentsResource(AsyncAPIResource):
         file_type: str | Omit = omit,
         metadata: str | Omit = omit,
         mime_type: str | Omit = omit,
+        use_advanced_processing: str | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -701,6 +964,10 @@ class AsyncDocumentsResource(AsyncAPIResource):
           mime_type: Required when fileType is 'image' or 'video'. Specifies the exact MIME type to
               use (e.g., 'image/png', 'image/jpeg', 'video/mp4', 'video/webm')
 
+          use_advanced_processing: DEPRECATED: This field is no longer used. Advanced PDF processing is now
+              automatic with our hybrid Mistral OCR + Gemini pipeline. This parameter will be
+              accepted but ignored for backwards compatibility.
+
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -716,6 +983,7 @@ class AsyncDocumentsResource(AsyncAPIResource):
                 "file_type": file_type,
                 "metadata": metadata,
                 "mime_type": mime_type,
+                "use_advanced_processing": use_advanced_processing,
             }
         )
         files = extract_files(cast(Mapping[str, object], body), paths=[["file"]])
@@ -750,9 +1018,18 @@ class DocumentsResourceWithRawResponse:
         self.add = to_raw_response_wrapper(
             documents.add,
         )
+        self.batch_add = to_raw_response_wrapper(
+            documents.batch_add,
+        )
+        self.delete_bulk = to_raw_response_wrapper(
+            documents.delete_bulk,
+        )
         self.get = to_raw_response_wrapper(
             documents.get,
         )
+        self.list_processing = to_raw_response_wrapper(
+            documents.list_processing,
+        )
         self.upload_file = to_raw_response_wrapper(
             documents.upload_file,
         )
@@ -774,9 +1051,18 @@ class AsyncDocumentsResourceWithRawResponse:
         self.add = async_to_raw_response_wrapper(
             documents.add,
         )
+        self.batch_add = async_to_raw_response_wrapper(
+            documents.batch_add,
+        )
+        self.delete_bulk = async_to_raw_response_wrapper(
+            documents.delete_bulk,
+        )
         self.get = async_to_raw_response_wrapper(
             documents.get,
         )
+        self.list_processing = async_to_raw_response_wrapper(
+            documents.list_processing,
+        )
         self.upload_file = async_to_raw_response_wrapper(
             documents.upload_file,
         )
@@ -798,9 +1084,18 @@ class DocumentsResourceWithStreamingResponse:
         self.add = to_streamed_response_wrapper(
             documents.add,
         )
+        self.batch_add = to_streamed_response_wrapper(
+            documents.batch_add,
+        )
+        self.delete_bulk = to_streamed_response_wrapper(
+            documents.delete_bulk,
+        )
         self.get = to_streamed_response_wrapper(
             documents.get,
         )
+        self.list_processing = to_streamed_response_wrapper(
+            documents.list_processing,
+        )
         self.upload_file = to_streamed_response_wrapper(
             documents.upload_file,
         )
@@ -822,9 +1117,18 @@ class AsyncDocumentsResourceWithStreamingResponse:
         self.add = async_to_streamed_response_wrapper(
             documents.add,
         )
+        self.batch_add = async_to_streamed_response_wrapper(
+            documents.batch_add,
+        )
+        self.delete_bulk = async_to_streamed_response_wrapper(
+            documents.delete_bulk,
+        )
         self.get = async_to_streamed_response_wrapper(
             documents.get,
         )
+        self.list_processing = async_to_streamed_response_wrapper(
+            documents.list_processing,
+        )
         self.upload_file = async_to_streamed_response_wrapper(
             documents.upload_file,
         )