Generated

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "0.20.0"
+  ".": "0.21.0"
 }

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 17
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/reducto%2Freductoai-1b16fbf5337f188d0b66a5992f0d241be80c46c45412ef9830cb19b11437d1c6.yml
-openapi_spec_hash: 88f89b5803058bfa20d5da05c2bcf754
-config_hash: 9dd1f73da997aefc8516b226e0e7fed7
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/reducto/reductoai-b36868a5180fdbbf68e1ec04645b9f3cafae6e8149be90e2b57a249fc8e5f070.yml
+openapi_spec_hash: 22a35f1691ac8540ee6141d7c800119a
+config_hash: 9fa10baf03f994be027bf73b29ac8572

README.md

@@ -9,6 +9,15 @@ and offers both synchronous and asynchronous clients powered by [httpx](https://
 
 It is generated with [Stainless](https://www.stainless.com/).
 
+## MCP Server
+
+Use the Reducto MCP Server to enable AI assistants to interact with this API, allowing them to explore endpoints, make test requests, and use documentation to help integrate this SDK into your application.
+
+[![Add to Cursor](https://cursor.com/deeplink/mcp-install-dark.svg)](https://cursor.com/en-US/install-mcp?name=reductoai-mcp&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsInJlZHVjdG9haS1tY3AiXSwiZW52Ijp7IlJFRFVDVE9fQVBJX0tFWSI6Ik15IEFQSSBLZXkifX0)
+[![Install in VS Code](https://img.shields.io/badge/_-Add_to_VS_Code-blue?style=for-the-badge&logo=data:image/svg%2bxml;base64,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)](https://vscode.stainless.com/mcp/%7B%22name%22%3A%22reductoai-mcp%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22reductoai-mcp%22%5D%2C%22env%22%3A%7B%22REDUCTO_API_KEY%22%3A%22My%20API%20Key%22%7D%7D)
+
+> Note: You may need to set environment variables in your MCP client.
+
 ## Documentation
 
 The REST API documentation can be found on [docs.reductoai.com](https://docs.reductoai.com). The full API of this library can be found in [api.md](api.md).
@@ -129,6 +138,23 @@ response = client.parse.run(
 print(response.enhance)
 ```
 
+## File uploads
+
+Request parameters that correspond to file uploads can be passed as `bytes`, or a [`PathLike`](https://docs.python.org/3/library/os.html#os.PathLike) instance or a tuple of `(filename, contents, media type)`.
+
+```python
+from pathlib import Path
+from reducto import Reducto
+
+client = Reducto()
+
+client.upload(
+    file=Path("/path/to/file"),
+)
+```
+
+The async client uses the exact same interface. If you pass a [`PathLike`](https://docs.python.org/3/library/os.html#os.PathLike) instance, the file contents will be read asynchronously automatically.
+
 ## Handling errors
 
 When the library is unable to connect to the API (for example, due to network connection problems or a timeout), a subclass of `reducto.APIConnectionError` is raised.

api.md

@@ -1,7 +1,39 @@
 # Shared Types
 
 ```python
-from reducto.types import Upload
+from reducto.types import (
+    AdvancedCitationsConfig,
+    AdvancedProcessingOptions,
+    ArrayExtractConfig,
+    AsyncEditResponse,
+    AsyncExtractResponse,
+    AsyncParseResponse,
+    AsyncPipelineResponse,
+    AsyncSplitResponse,
+    BaseProcessingOptions,
+    Chunking,
+    ChunkingConfig,
+    ClassifyResponse,
+    DirectWebhookConfig,
+    EditResponse,
+    EnrichConfig,
+    ExperimentalProcessingOptions,
+    ExtractResponse,
+    FigureAgentic,
+    FigureSummaryConfig,
+    LargeTableChunkingConfig,
+    PageRange,
+    ParseResponse,
+    PipelineResponse,
+    SplitLargeTables,
+    SplitResponse,
+    SvixWebhookConfig,
+    TableAgentic,
+    TableSummaryConfig,
+    TextAgentic,
+    Upload,
+    WebhookConfigNew,
+)
 ```
 
 # Reducto
@@ -25,10 +57,8 @@ Types:
 from reducto.types import (
     AsyncConfigV3,
     AsyncParseConfig,
-    AsyncParseResponse,
     Enhance,
     Formatting,
-    ParseResponse,
     Retrieval,
     Settings,
     Spreadsheet,
@@ -39,7 +69,7 @@ from reducto.types import (
 Methods:
 
 - <code title="post /parse">client.parse.<a href="./src/reducto/resources/parse.py">run</a>(\*\*<a href="src/reducto/types/parse_run_params.py">params</a>) -> <a href="./src/reducto/types/parse_run_response.py">ParseRunResponse</a></code>
-- <code title="post /parse_async">client.parse.<a href="./src/reducto/resources/parse.py">run_job</a>(\*\*<a href="src/reducto/types/parse_run_job_params.py">params</a>) -> <a href="./src/reducto/types/async_parse_response.py">AsyncParseResponse</a></code>
+- <code title="post /parse_async">client.parse.<a href="./src/reducto/resources/parse.py">run_job</a>(\*\*<a href="src/reducto/types/parse_run_job_params.py">params</a>) -> <a href="./src/reducto/types/shared/async_parse_response.py">AsyncParseResponse</a></code>
 
 # Extract
 
@@ -48,7 +78,6 @@ Types:
 ```python
 from reducto.types import (
     AsyncExtractConfig,
-    AsyncExtractResponse,
     ExtractSettings,
     ExtractUsage,
     Instructions,
@@ -61,65 +90,52 @@ from reducto.types import (
 Methods:
 
 - <code title="post /extract">client.extract.<a href="./src/reducto/resources/extract.py">run</a>(\*\*<a href="src/reducto/types/extract_run_params.py">params</a>) -> <a href="./src/reducto/types/extract_run_response.py">ExtractRunResponse</a></code>
-- <code title="post /extract_async">client.extract.<a href="./src/reducto/resources/extract.py">run_job</a>(\*\*<a href="src/reducto/types/extract_run_job_params.py">params</a>) -> <a href="./src/reducto/types/async_extract_response.py">AsyncExtractResponse</a></code>
+- <code title="post /extract_async">client.extract.<a href="./src/reducto/resources/extract.py">run_job</a>(\*\*<a href="src/reducto/types/extract_run_job_params.py">params</a>) -> <a href="./src/reducto/types/shared/async_extract_response.py">AsyncExtractResponse</a></code>
 
 # Split
 
 Types:
 
 ```python
-from reducto.types import (
-    DeepSplitPageEvidence,
-    ParseUsage,
-    SplitCategory,
-    SplitResponse,
-    SplitTableOptions,
-    SplitRunJobResponse,
-)
+from reducto.types import DeepSplitPageEvidence, ParseUsage, SplitCategory, SplitTableOptions
 ```
 
 Methods:
 
-- <code title="post /split">client.split.<a href="./src/reducto/resources/split.py">run</a>(\*\*<a href="src/reducto/types/split_run_params.py">params</a>) -> <a href="./src/reducto/types/split_response.py">SplitResponse</a></code>
-- <code title="post /split_async">client.split.<a href="./src/reducto/resources/split.py">run_job</a>(\*\*<a href="src/reducto/types/split_run_job_params.py">params</a>) -> <a href="./src/reducto/types/split_run_job_response.py">SplitRunJobResponse</a></code>
+- <code title="post /split">client.split.<a href="./src/reducto/resources/split.py">run</a>(\*\*<a href="src/reducto/types/split_run_params.py">params</a>) -> <a href="./src/reducto/types/shared/split_response.py">SplitResponse</a></code>
+- <code title="post /split_async">client.split.<a href="./src/reducto/resources/split.py">run_job</a>(\*\*<a href="src/reducto/types/split_run_job_params.py">params</a>) -> <a href="./src/reducto/types/shared/async_split_response.py">AsyncSplitResponse</a></code>
 
 # Edit
 
 Types:
 
 ```python
-from reducto.types import BoundingBox, EditOptions, EditResponse, EditWidget, EditRunJobResponse
+from reducto.types import BoundingBox, EditOptions, EditWidget
 ```
 
 Methods:
 
-- <code title="post /edit">client.edit.<a href="./src/reducto/resources/edit.py">run</a>(\*\*<a href="src/reducto/types/edit_run_params.py">params</a>) -> <a href="./src/reducto/types/edit_response.py">EditResponse</a></code>
-- <code title="post /edit_async">client.edit.<a href="./src/reducto/resources/edit.py">run_job</a>(\*\*<a href="src/reducto/types/edit_run_job_params.py">params</a>) -> <a href="./src/reducto/types/edit_run_job_response.py">EditRunJobResponse</a></code>
+- <code title="post /edit">client.edit.<a href="./src/reducto/resources/edit.py">run</a>(\*\*<a href="src/reducto/types/edit_run_params.py">params</a>) -> <a href="./src/reducto/types/shared/edit_response.py">EditResponse</a></code>
+- <code title="post /edit_async">client.edit.<a href="./src/reducto/resources/edit.py">run_job</a>(\*\*<a href="src/reducto/types/edit_run_job_params.py">params</a>) -> <a href="./src/reducto/types/shared/async_edit_response.py">AsyncEditResponse</a></code>
 
 # Pipeline
 
 Types:
 
 ```python
-from reducto.types import PipelineResponse, PipelineSettings, PipelineRunJobResponse
+from reducto.types import PipelineSettings
 ```
 
 Methods:
 
-- <code title="post /pipeline">client.pipeline.<a href="./src/reducto/resources/pipeline.py">run</a>(\*\*<a href="src/reducto/types/pipeline_run_params.py">params</a>) -> <a href="./src/reducto/types/pipeline_response.py">PipelineResponse</a></code>
-- <code title="post /pipeline_async">client.pipeline.<a href="./src/reducto/resources/pipeline.py">run_job</a>(\*\*<a href="src/reducto/types/pipeline_run_job_params.py">params</a>) -> <a href="./src/reducto/types/pipeline_run_job_response.py">PipelineRunJobResponse</a></code>
+- <code title="post /pipeline">client.pipeline.<a href="./src/reducto/resources/pipeline.py">run</a>(\*\*<a href="src/reducto/types/pipeline_run_params.py">params</a>) -> <a href="./src/reducto/types/shared/pipeline_response.py">PipelineResponse</a></code>
+- <code title="post /pipeline_async">client.pipeline.<a href="./src/reducto/resources/pipeline.py">run_job</a>(\*\*<a href="src/reducto/types/pipeline_run_job_params.py">params</a>) -> <a href="./src/reducto/types/shared/async_pipeline_response.py">AsyncPipelineResponse</a></code>
 
 # Classify
 
-Types:
-
-```python
-from reducto.types import ClassifyResponse, PageRange
-```
-
 Methods:
 
-- <code title="post /classify">client.classify.<a href="./src/reducto/resources/classify.py">run</a>(\*\*<a href="src/reducto/types/classify_run_params.py">params</a>) -> <a href="./src/reducto/types/classify_response.py">ClassifyResponse</a></code>
+- <code title="post /classify">client.classify.<a href="./src/reducto/resources/classify.py">run</a>(\*\*<a href="src/reducto/types/classify_run_params.py">params</a>) -> <a href="./src/reducto/types/shared/classify_response.py">ClassifyResponse</a></code>
 
 # Webhook
 
@@ -138,7 +154,7 @@ Methods:
 Types:
 
 ```python
-from reducto.types import ExtractResponse, JobGetResponse, JobGetAllResponse
+from reducto.types import JobGetResponse, JobGetAllResponse
 ```
 
 Methods:

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "reductoai"
-version = "0.20.0"
+version = "0.21.0"
 description = "The official Python library for the reducto API"
 dynamic = ["readme"]
 license = "Apache-2.0"
@@ -168,7 +168,7 @@ show_error_codes = true
 #
 # We also exclude our `tests` as mypy doesn't always infer
 # types correctly and Pyright will still catch any type errors.
-exclude = ['src/reducto/_files.py', '_dev/.*.py', 'tests/.*']
+exclude = ["src/reducto/_files.py", "_dev/.*.py", "tests/.*"]
 
 strict_equality = true
 implicit_reexport = true

scripts/bootstrap

@@ -4,7 +4,7 @@ set -e
 
 cd "$(dirname "$0")/.."
 
-if [ -f "Brewfile" ] && [ "$(uname -s)" = "Darwin" ] && [ "$SKIP_BREW" != "1" ] && [ -t 0 ]; then
+if [ -f "Brewfile" ] && [ "$(uname -s)" = "Darwin" ] && [ "${SKIP_BREW:-}" != "1" ] && [ -t 0 ]; then
   brew bundle check >/dev/null 2>&1 || {
     echo -n "==> Install Homebrew dependencies? (y/N): "
     read -r response

src/reducto/_base_client.py

@@ -558,6 +558,10 @@ def _build_request(
                 files = cast(HttpxRequestFiles, ForceMultipartDict())
 
         prepared_url = self._prepare_url(options.url)
+        # preserve hard-coded query params from the url
+        if params and prepared_url.query:
+            params = {**dict(prepared_url.params.items()), **params}
+            prepared_url = prepared_url.copy_with(raw_path=prepared_url.raw_path.split(b"?", 1)[0])
         if "_" in prepared_url.host:
             # work around https://github.com/encode/httpx/discussions/2880
             kwargs["extensions"] = {"sni_hostname": prepared_url.host.replace("_", "-")}

src/reducto/_client.py

@@ -11,13 +11,15 @@
 from . import _exceptions
 from ._qs import Querystring
 from .types import client_upload_params
+from ._files import deepcopy_with_paths
 from ._types import (
     Body,
     Omit,
     Query,
     Headers,
     Timeout,
     NotGiven,
+    FileTypes,
     Transport,
     ProxiesTypes,
     RequestOptions,
@@ -26,6 +28,8 @@
 )
 from ._utils import (
     is_given,
+    is_mapping_t,
+    extract_files,
     maybe_transform,
     get_async_library,
     async_maybe_transform,
@@ -147,6 +151,15 @@ def __init__(
             except KeyError as exc:
                 raise ValueError(f"Unknown environment: {environment}") from exc
 
+        custom_headers_env = os.environ.get("REDUCTO_CUSTOM_HEADERS")
+        if custom_headers_env is not None:
+            parsed: dict[str, str] = {}
+            for line in custom_headers_env.split("\n"):
+                colon = line.find(":")
+                if colon >= 0:
+                    parsed[line[:colon].strip()] = line[colon + 1 :].strip()
+            default_headers = {**parsed, **(default_headers if is_mapping_t(default_headers) else {})}
+
         super().__init__(
             version=__version__,
             base_url=base_url,
@@ -315,7 +328,7 @@ def upload(
         self,
         *,
         extension: Optional[str] | Omit = omit,
-        file: Optional[str] | Omit = omit,
+        file: Optional[FileTypes] | 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,
@@ -335,9 +348,17 @@ def upload(
 
           timeout: Override the client-level default timeout for this request, in seconds
         """
+        body = deepcopy_with_paths({"file": file}, [["file"]])
+        files = extract_files(cast(Mapping[str, object], body), paths=[["file"]])
+        if files:
+            # It should be noted that the actual Content-Type header that will be
+            # sent to the server will contain a `boundary` parameter, e.g.
+            # multipart/form-data; boundary=---abc--
+            extra_headers = {"Content-Type": "multipart/form-data", **(extra_headers or {})}
         return self.post(
             "/upload",
-            body=maybe_transform({"file": file}, client_upload_params.ClientUploadParams),
+            body=maybe_transform(body, client_upload_params.ClientUploadParams),
+            files=files,
             options=make_request_options(
                 extra_headers=extra_headers,
                 extra_query=extra_query,
@@ -450,6 +471,15 @@ def __init__(
             except KeyError as exc:
                 raise ValueError(f"Unknown environment: {environment}") from exc
 
+        custom_headers_env = os.environ.get("REDUCTO_CUSTOM_HEADERS")
+        if custom_headers_env is not None:
+            parsed: dict[str, str] = {}
+            for line in custom_headers_env.split("\n"):
+                colon = line.find(":")
+                if colon >= 0:
+                    parsed[line[:colon].strip()] = line[colon + 1 :].strip()
+            default_headers = {**parsed, **(default_headers if is_mapping_t(default_headers) else {})}
+
         super().__init__(
             version=__version__,
             base_url=base_url,
@@ -618,7 +648,7 @@ async def upload(
         self,
         *,
         extension: Optional[str] | Omit = omit,
-        file: Optional[str] | Omit = omit,
+        file: Optional[FileTypes] | 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,
@@ -638,9 +668,17 @@ async def upload(
 
           timeout: Override the client-level default timeout for this request, in seconds
         """
+        body = deepcopy_with_paths({"file": file}, [["file"]])
+        files = extract_files(cast(Mapping[str, object], body), paths=[["file"]])
+        if files:
+            # It should be noted that the actual Content-Type header that will be
+            # sent to the server will contain a `boundary` parameter, e.g.
+            # multipart/form-data; boundary=---abc--
+            extra_headers = {"Content-Type": "multipart/form-data", **(extra_headers or {})}
         return await self.post(
             "/upload",
-            body=await async_maybe_transform({"file": file}, client_upload_params.ClientUploadParams),
+            body=await async_maybe_transform(body, client_upload_params.ClientUploadParams),
+            files=files,
             options=make_request_options(
                 extra_headers=extra_headers,
                 extra_query=extra_query,