pulse-python-sdk 1.0.6__tar.gz → 1.0.7__tar.gz

{pulse_python_sdk-1.0.6 → pulse_python_sdk-1.0.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pulse-python-sdk
-Version: 1.0.6
+Version: 1.0.7
 Summary: 
 Requires-Python: >=3.8,<4.0
 Classifier: Intended Audience :: Developers

{pulse_python_sdk-1.0.6 → pulse_python_sdk-1.0.7}/pyproject.toml

@@ -4,7 +4,7 @@ dynamic = ["version"]
 
 [tool.poetry]
 name = "pulse-python-sdk"
-version = "1.0.6"
+version = "1.0.7"
 description = ""
 readme = "README.md"
 authors = []

{pulse_python_sdk-1.0.6 → pulse_python_sdk-1.0.7}/src/pulse/client.py

@@ -460,6 +460,7 @@ class Pulse:
         self,
         *,
         extraction_id: typing.Optional[str] = OMIT,
+        extraction_ids: typing.Optional[typing.Sequence[str]] = OMIT,
         split_id: typing.Optional[str] = OMIT,
         schema_config: typing.Optional[SchemaConfig] = OMIT,
         schema_config_id: typing.Optional[str] = OMIT,
@@ -474,10 +475,20 @@ class Pulse:
         **Single mode** — Provide `extraction_id` + `schema_config` (or
         `schema_config_id`) to apply one schema to the entire document.
 
+        **Multi-extraction mode** — Provide a batch extract ID as `extraction_id`
+        (auto-detected) or an explicit `extraction_ids` list. The content from all
+        extractions is combined and the schema is applied to the composite. Citations
+        use `extraction_id-bb_id` format to disambiguate across source documents.
+
         **Split mode** — Provide `split_id` + `split_schema_config` to apply
         different schemas to different page groups from a prior `/split` call.
         Each topic can have its own schema, prompt, and effort setting.
 
+        **Excel template mode** — Provide `excel_template` (base64 .xlsx) in
+        `schema_config` instead of `input_schema`. The schema is auto-generated
+        from the template's column headers, and a filled copy is returned as
+        `excel_output_url`.
+
         Creates a versioned schema record that can be retrieved later.
         Set `async: true` to return immediately with a job_id for polling.
 
@@ -488,7 +499,10 @@ class Pulse:
         Parameters
         ----------
         extraction_id : typing.Optional[str]
-            ID of saved extraction to apply the schema to. Use for single-mode schema extraction.
+            ID of a saved extraction OR a batch extract job. When a batch extract ID is provided, the system auto-detects it and combines all completed child extractions into a single schema application.
+
+        extraction_ids : typing.Optional[typing.Sequence[str]]
+            Explicit list of extraction IDs to combine. The markdown and bounding boxes from all extractions are merged and the schema is applied to the composite content. Citations use `extraction_id-bb_id` format to disambiguate across source documents.
 
         split_id : typing.Optional[str]
             ID of saved split (from a prior `/split` call). Use for split-mode schema extraction.
@@ -524,6 +538,7 @@ class Pulse:
         """
         _response = self._raw_client.schema(
             extraction_id=extraction_id,
+            extraction_ids=extraction_ids,
             split_id=split_id,
             schema_config=schema_config,
             schema_config_id=schema_config_id,
@@ -533,6 +548,42 @@ class Pulse:
         )
         return _response.data
 
+    def download_schema_excel(
+        self, schema_id: str, *, request_options: typing.Optional[RequestOptions] = None
+    ) -> typing.Iterator[bytes]:
+        """
+        Download the filled Excel template produced by a schema extraction that
+        used `excel_template` in its `schema_config`. Requires the same API key
+        authentication as other endpoints. The caller must belong to the org
+        that owns the underlying extraction.
+
+        Parameters
+        ----------
+        schema_id : str
+            The schema ID returned from a prior `POST /schema` call.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration. You can pass in configuration such as `chunk_size`, and more to customize the request and response.
+
+        Returns
+        -------
+        typing.Iterator[bytes]
+            Filled Excel file
+
+        Examples
+        --------
+        from pulse import Pulse
+
+        client = Pulse(
+            api_key="YOUR_API_KEY",
+        )
+        client.download_schema_excel(
+            schema_id="schemaId",
+        )
+        """
+        with self._raw_client.download_schema_excel(schema_id, request_options=request_options) as r:
+            yield from r.data
+
     def tables(
         self,
         *,
@@ -1057,6 +1108,7 @@ class AsyncPulse:
         self,
         *,
         extraction_id: typing.Optional[str] = OMIT,
+        extraction_ids: typing.Optional[typing.Sequence[str]] = OMIT,
         split_id: typing.Optional[str] = OMIT,
         schema_config: typing.Optional[SchemaConfig] = OMIT,
         schema_config_id: typing.Optional[str] = OMIT,
@@ -1071,10 +1123,20 @@ class AsyncPulse:
         **Single mode** — Provide `extraction_id` + `schema_config` (or
         `schema_config_id`) to apply one schema to the entire document.
 
+        **Multi-extraction mode** — Provide a batch extract ID as `extraction_id`
+        (auto-detected) or an explicit `extraction_ids` list. The content from all
+        extractions is combined and the schema is applied to the composite. Citations
+        use `extraction_id-bb_id` format to disambiguate across source documents.
+
         **Split mode** — Provide `split_id` + `split_schema_config` to apply
         different schemas to different page groups from a prior `/split` call.
         Each topic can have its own schema, prompt, and effort setting.
 
+        **Excel template mode** — Provide `excel_template` (base64 .xlsx) in
+        `schema_config` instead of `input_schema`. The schema is auto-generated
+        from the template's column headers, and a filled copy is returned as
+        `excel_output_url`.
+
         Creates a versioned schema record that can be retrieved later.
         Set `async: true` to return immediately with a job_id for polling.
 
@@ -1085,7 +1147,10 @@ class AsyncPulse:
         Parameters
         ----------
         extraction_id : typing.Optional[str]
-            ID of saved extraction to apply the schema to. Use for single-mode schema extraction.
+            ID of a saved extraction OR a batch extract job. When a batch extract ID is provided, the system auto-detects it and combines all completed child extractions into a single schema application.
+
+        extraction_ids : typing.Optional[typing.Sequence[str]]
+            Explicit list of extraction IDs to combine. The markdown and bounding boxes from all extractions are merged and the schema is applied to the composite content. Citations use `extraction_id-bb_id` format to disambiguate across source documents.
 
         split_id : typing.Optional[str]
             ID of saved split (from a prior `/split` call). Use for split-mode schema extraction.
@@ -1129,6 +1194,7 @@ class AsyncPulse:
         """
         _response = await self._raw_client.schema(
             extraction_id=extraction_id,
+            extraction_ids=extraction_ids,
             split_id=split_id,
             schema_config=schema_config,
             schema_config_id=schema_config_id,
@@ -1138,6 +1204,51 @@ class AsyncPulse:
         )
         return _response.data
 
+    async def download_schema_excel(
+        self, schema_id: str, *, request_options: typing.Optional[RequestOptions] = None
+    ) -> typing.AsyncIterator[bytes]:
+        """
+        Download the filled Excel template produced by a schema extraction that
+        used `excel_template` in its `schema_config`. Requires the same API key
+        authentication as other endpoints. The caller must belong to the org
+        that owns the underlying extraction.
+
+        Parameters
+        ----------
+        schema_id : str
+            The schema ID returned from a prior `POST /schema` call.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration. You can pass in configuration such as `chunk_size`, and more to customize the request and response.
+
+        Returns
+        -------
+        typing.AsyncIterator[bytes]
+            Filled Excel file
+
+        Examples
+        --------
+        import asyncio
+
+        from pulse import AsyncPulse
+
+        client = AsyncPulse(
+            api_key="YOUR_API_KEY",
+        )
+
+
+        async def main() -> None:
+            await client.download_schema_excel(
+                schema_id="schemaId",
+            )
+
+
+        asyncio.run(main())
+        """
+        async with self._raw_client.download_schema_excel(schema_id, request_options=request_options) as r:
+            async for _chunk in r.data:
+                yield _chunk
+
     async def tables(
         self,
         *,

{pulse_python_sdk-1.0.6 → pulse_python_sdk-1.0.7}/src/pulse/core/client_wrapper.py

@@ -22,10 +22,10 @@ class BaseClientWrapper:
 
     def get_headers(self) -> typing.Dict[str, str]:
         headers: typing.Dict[str, str] = {
-            "User-Agent": "pulse-python-sdk/1.0.6",
+            "User-Agent": "pulse-python-sdk/1.0.7",
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "pulse-python-sdk",
-            "X-Fern-SDK-Version": "1.0.6",
+            "X-Fern-SDK-Version": "1.0.7",
             **(self.get_custom_headers() or {}),
         }
         headers["x-api-key"] = self.api_key

{pulse_python_sdk-1.0.6 → pulse_python_sdk-1.0.7}/src/pulse/raw_client.py

@@ -1,5 +1,6 @@
 # This file was auto-generated by Fern from our API Definition.
 
+import contextlib
 import typing
 from json.decoder import JSONDecodeError
 
@@ -7,6 +8,7 @@ from . import core
 from .core.api_error import ApiError
 from .core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
 from .core.http_response import AsyncHttpResponse, HttpResponse
+from .core.jsonable_encoder import jsonable_encoder
 from .core.request_options import RequestOptions
 from .core.serialization import convert_and_respect_annotation_metadata
 from .core.unchecked_base_model import construct_type
@@ -538,6 +540,7 @@ class RawPulse:
         self,
         *,
         extraction_id: typing.Optional[str] = OMIT,
+        extraction_ids: typing.Optional[typing.Sequence[str]] = OMIT,
         split_id: typing.Optional[str] = OMIT,
         schema_config: typing.Optional[SchemaConfig] = OMIT,
         schema_config_id: typing.Optional[str] = OMIT,
@@ -552,10 +555,20 @@ class RawPulse:
         **Single mode** — Provide `extraction_id` + `schema_config` (or
         `schema_config_id`) to apply one schema to the entire document.
 
+        **Multi-extraction mode** — Provide a batch extract ID as `extraction_id`
+        (auto-detected) or an explicit `extraction_ids` list. The content from all
+        extractions is combined and the schema is applied to the composite. Citations
+        use `extraction_id-bb_id` format to disambiguate across source documents.
+
         **Split mode** — Provide `split_id` + `split_schema_config` to apply
         different schemas to different page groups from a prior `/split` call.
         Each topic can have its own schema, prompt, and effort setting.
 
+        **Excel template mode** — Provide `excel_template` (base64 .xlsx) in
+        `schema_config` instead of `input_schema`. The schema is auto-generated
+        from the template's column headers, and a filled copy is returned as
+        `excel_output_url`.
+
         Creates a versioned schema record that can be retrieved later.
         Set `async: true` to return immediately with a job_id for polling.
 
@@ -566,7 +579,10 @@ class RawPulse:
         Parameters
         ----------
         extraction_id : typing.Optional[str]
-            ID of saved extraction to apply the schema to. Use for single-mode schema extraction.
+            ID of a saved extraction OR a batch extract job. When a batch extract ID is provided, the system auto-detects it and combines all completed child extractions into a single schema application.
+
+        extraction_ids : typing.Optional[typing.Sequence[str]]
+            Explicit list of extraction IDs to combine. The markdown and bounding boxes from all extractions are merged and the schema is applied to the composite content. Citations use `extraction_id-bb_id` format to disambiguate across source documents.
 
         split_id : typing.Optional[str]
             ID of saved split (from a prior `/split` call). Use for split-mode schema extraction.
@@ -596,6 +612,7 @@ class RawPulse:
             method="POST",
             json={
                 "extraction_id": extraction_id,
+                "extraction_ids": extraction_ids,
                 "split_id": split_id,
                 "schema_config": convert_and_respect_annotation_metadata(
                     object_=schema_config, annotation=SchemaConfig, direction="write"
@@ -682,6 +699,74 @@ class RawPulse:
             raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
         raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
 
+    @contextlib.contextmanager
+    def download_schema_excel(
+        self, schema_id: str, *, request_options: typing.Optional[RequestOptions] = None
+    ) -> typing.Iterator[HttpResponse[typing.Iterator[bytes]]]:
+        """
+        Download the filled Excel template produced by a schema extraction that
+        used `excel_template` in its `schema_config`. Requires the same API key
+        authentication as other endpoints. The caller must belong to the org
+        that owns the underlying extraction.
+
+        Parameters
+        ----------
+        schema_id : str
+            The schema ID returned from a prior `POST /schema` call.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration. You can pass in configuration such as `chunk_size`, and more to customize the request and response.
+
+        Returns
+        -------
+        typing.Iterator[HttpResponse[typing.Iterator[bytes]]]
+            Filled Excel file
+        """
+        with self._client_wrapper.httpx_client.stream(
+            f"schema/{jsonable_encoder(schema_id)}/excel",
+            method="GET",
+            request_options=request_options,
+        ) as _response:
+
+            def _stream() -> HttpResponse[typing.Iterator[bytes]]:
+                try:
+                    if 200 <= _response.status_code < 300:
+                        _chunk_size = request_options.get("chunk_size", None) if request_options is not None else None
+                        return HttpResponse(
+                            response=_response, data=(_chunk for _chunk in _response.iter_bytes(chunk_size=_chunk_size))
+                        )
+                    _response.read()
+                    if _response.status_code == 401:
+                        raise UnauthorizedError(
+                            headers=dict(_response.headers),
+                            body=typing.cast(
+                                typing.Any,
+                                construct_type(
+                                    type_=typing.Any,  # type: ignore
+                                    object_=_response.json(),
+                                ),
+                            ),
+                        )
+                    if _response.status_code == 404:
+                        raise NotFoundError(
+                            headers=dict(_response.headers),
+                            body=typing.cast(
+                                typing.Any,
+                                construct_type(
+                                    type_=typing.Any,  # type: ignore
+                                    object_=_response.json(),
+                                ),
+                            ),
+                        )
+                    _response_json = _response.json()
+                except JSONDecodeError:
+                    raise ApiError(
+                        status_code=_response.status_code, headers=dict(_response.headers), body=_response.text
+                    )
+                raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+            yield _stream()
+
     def tables(
         self,
         *,
@@ -1317,6 +1402,7 @@ class AsyncRawPulse:
         self,
         *,
         extraction_id: typing.Optional[str] = OMIT,
+        extraction_ids: typing.Optional[typing.Sequence[str]] = OMIT,
         split_id: typing.Optional[str] = OMIT,
         schema_config: typing.Optional[SchemaConfig] = OMIT,
         schema_config_id: typing.Optional[str] = OMIT,
@@ -1331,10 +1417,20 @@ class AsyncRawPulse:
         **Single mode** — Provide `extraction_id` + `schema_config` (or
         `schema_config_id`) to apply one schema to the entire document.
 
+        **Multi-extraction mode** — Provide a batch extract ID as `extraction_id`
+        (auto-detected) or an explicit `extraction_ids` list. The content from all
+        extractions is combined and the schema is applied to the composite. Citations
+        use `extraction_id-bb_id` format to disambiguate across source documents.
+
         **Split mode** — Provide `split_id` + `split_schema_config` to apply
         different schemas to different page groups from a prior `/split` call.
         Each topic can have its own schema, prompt, and effort setting.
 
+        **Excel template mode** — Provide `excel_template` (base64 .xlsx) in
+        `schema_config` instead of `input_schema`. The schema is auto-generated
+        from the template's column headers, and a filled copy is returned as
+        `excel_output_url`.
+
         Creates a versioned schema record that can be retrieved later.
         Set `async: true` to return immediately with a job_id for polling.
 
@@ -1345,7 +1441,10 @@ class AsyncRawPulse:
         Parameters
         ----------
         extraction_id : typing.Optional[str]
-            ID of saved extraction to apply the schema to. Use for single-mode schema extraction.
+            ID of a saved extraction OR a batch extract job. When a batch extract ID is provided, the system auto-detects it and combines all completed child extractions into a single schema application.
+
+        extraction_ids : typing.Optional[typing.Sequence[str]]
+            Explicit list of extraction IDs to combine. The markdown and bounding boxes from all extractions are merged and the schema is applied to the composite content. Citations use `extraction_id-bb_id` format to disambiguate across source documents.
 
         split_id : typing.Optional[str]
             ID of saved split (from a prior `/split` call). Use for split-mode schema extraction.
@@ -1375,6 +1474,7 @@ class AsyncRawPulse:
             method="POST",
             json={
                 "extraction_id": extraction_id,
+                "extraction_ids": extraction_ids,
                 "split_id": split_id,
                 "schema_config": convert_and_respect_annotation_metadata(
                     object_=schema_config, annotation=SchemaConfig, direction="write"
@@ -1461,6 +1561,75 @@ class AsyncRawPulse:
             raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
         raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
 
+    @contextlib.asynccontextmanager
+    async def download_schema_excel(
+        self, schema_id: str, *, request_options: typing.Optional[RequestOptions] = None
+    ) -> typing.AsyncIterator[AsyncHttpResponse[typing.AsyncIterator[bytes]]]:
+        """
+        Download the filled Excel template produced by a schema extraction that
+        used `excel_template` in its `schema_config`. Requires the same API key
+        authentication as other endpoints. The caller must belong to the org
+        that owns the underlying extraction.
+
+        Parameters
+        ----------
+        schema_id : str
+            The schema ID returned from a prior `POST /schema` call.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration. You can pass in configuration such as `chunk_size`, and more to customize the request and response.
+
+        Returns
+        -------
+        typing.AsyncIterator[AsyncHttpResponse[typing.AsyncIterator[bytes]]]
+            Filled Excel file
+        """
+        async with self._client_wrapper.httpx_client.stream(
+            f"schema/{jsonable_encoder(schema_id)}/excel",
+            method="GET",
+            request_options=request_options,
+        ) as _response:
+
+            async def _stream() -> AsyncHttpResponse[typing.AsyncIterator[bytes]]:
+                try:
+                    if 200 <= _response.status_code < 300:
+                        _chunk_size = request_options.get("chunk_size", None) if request_options is not None else None
+                        return AsyncHttpResponse(
+                            response=_response,
+                            data=(_chunk async for _chunk in _response.aiter_bytes(chunk_size=_chunk_size)),
+                        )
+                    await _response.aread()
+                    if _response.status_code == 401:
+                        raise UnauthorizedError(
+                            headers=dict(_response.headers),
+                            body=typing.cast(
+                                typing.Any,
+                                construct_type(
+                                    type_=typing.Any,  # type: ignore
+                                    object_=_response.json(),
+                                ),
+                            ),
+                        )
+                    if _response.status_code == 404:
+                        raise NotFoundError(
+                            headers=dict(_response.headers),
+                            body=typing.cast(
+                                typing.Any,
+                                construct_type(
+                                    type_=typing.Any,  # type: ignore
+                                    object_=_response.json(),
+                                ),
+                            ),
+                        )
+                    _response_json = _response.json()
+                except JSONDecodeError:
+                    raise ApiError(
+                        status_code=_response.status_code, headers=dict(_response.headers), body=_response.text
+                    )
+                raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+            yield await _stream()
+
     async def tables(
         self,
         *,

{pulse_python_sdk-1.0.6 → pulse_python_sdk-1.0.7}/src/pulse/types/schema_config.py

@@ -9,12 +9,17 @@ from ..core.unchecked_base_model import UncheckedBaseModel
 
 class SchemaConfig(UncheckedBaseModel):
     """
-    Inline schema configuration.
+    Inline schema configuration. Provide `input_schema` (JSON Schema) OR `excel_template` (base64 .xlsx) — not both. When `excel_template` is provided, the JSON Schema is auto-generated from the spreadsheet's column headers.
     """
 
-    input_schema: typing.Dict[str, typing.Any] = pydantic.Field()
+    input_schema: typing.Optional[typing.Dict[str, typing.Any]] = pydantic.Field(default=None)
     """
-    JSON Schema defining the structured data to extract.
+    JSON Schema defining the structured data to extract. Required unless `excel_template` is provided.
+    """
+
+    excel_template: typing.Optional[str] = pydantic.Field(default=None)
+    """
+    Base64-encoded Excel template (.xlsx). When provided, the template's column headers are used to auto-generate the JSON Schema and a filled copy of the template is returned in the response as `excel_output_url`. Mutually exclusive with `input_schema`.
     """
 
     schema_prompt: typing.Optional[str] = pydantic.Field(default=None)

{pulse_python_sdk-1.0.6 → pulse_python_sdk-1.0.7}/src/pulse/types/single_schema_response.py

@@ -28,6 +28,16 @@ class SingleSchemaResponse(UncheckedBaseModel):
     Extracted values and citations.
     """
 
+    extraction_ids: typing.Optional[typing.List[str]] = pydantic.Field(default=None)
+    """
+    Present when multiple extractions were combined (via batch extract auto-detection or explicit `extraction_ids` input). Lists all source extraction IDs that contributed to the result.
+    """
+
+    excel_output_url: typing.Optional[str] = pydantic.Field(default=None)
+    """
+    API path to download the filled Excel template (e.g. `/schema/{schema_id}/excel`). Requires the same API key authentication. Only present when `excel_template` was provided in the request.
+    """
+
     if IS_PYDANTIC_V2:
         model_config: typing.ClassVar[pydantic.ConfigDict] = pydantic.ConfigDict(extra="allow", frozen=True)  # type: ignore # Pydantic v2
     else: