chore: Python v2 migration

.github/workflows/ci.yaml

@@ -36,7 +36,7 @@ jobs:
     steps:
     - uses: actions/checkout@v4
     - name: Install dependencies
-      run: pip install .[dev]
+      run: pip install pylint
     - name: Lint
       run: make lint
 

.github/workflows/speakeasy_sdk_generation.yml

@@ -24,3 +24,11 @@ jobs:
             github_access_token: ${{ secrets.GITHUB_TOKEN }}
             pypi_token: ${{ secrets.PYPI_TOKEN }}
             speakeasy_api_key: ${{ secrets.SPEAKEASY_API_KEY }}
+  # We don't need this unless we're modifying the generated code
+  patch-custom-code:
+    runs-on: ubuntu-latest
+    needs: [generate]
+    steps:
+    - name: Patch in custom code after regenerating
+      run: make patch-custom-code
+

.gitignore

@@ -1,10 +1,10 @@
+pyrightconfig.json
 venv/
 src/*.egg-info/
 __pycache__/
 .pytest_cache/
 .python-version
 .DS_Store
-
 # human-added igore files
 .ipynb_checkpoints/
 .idea/

.speakeasy/gen.lock

@@ -1,57 +1,76 @@
 lockVersion: 2.0.0
 id: 8b5fa338-9106-4734-abf0-e30d67044a90
 management:
-  docChecksum: 17bd23e4247d7b65a92813afd1252693
+  docChecksum: a6ff17ff485bb4b5884d75af244e18a1
   docVersion: 1.0.44
-  speakeasyVersion: 1.361.1
-  generationVersion: 2.393.4
-  releaseVersion: 0.25.5
-  configChecksum: 6b4c1555edde75f4f1e422e49a07c208
+  speakeasyVersion: 1.346.0
+  generationVersion: 2.379.3
+  releaseVersion: 0.26.0
+  configChecksum: b455a107798458739736480ac5f51e86
   repoURL: https://github.com/Unstructured-IO/unstructured-python-client.git
   repoSubDirectory: .
   installationURL: https://github.com/Unstructured-IO/unstructured-python-client.git
   published: true
 features:
   python:
-    additionalDependencies: 0.1.0
-    constsAndDefaults: 0.1.4
-    core: 4.8.4
-    examples: 2.81.3
-    globalSecurity: 2.83.7
-    globalSecurityCallbacks: 0.1.0
-    globalSecurityFlattening: 0.1.0
-    globalServerURLs: 2.82.2
-    nameOverrides: 2.81.2
-    nullables: 0.1.0
-    openEnums: 0.1.0
-    responseFormat: 0.1.0
-    retries: 2.82.2
-    sdkHooks: 0.1.0
-    serverIDs: 2.81.1
-    unions: 2.82.9
+    additionalDependencies: 1.0.0
+    constsAndDefaults: 1.0.0
+    core: 5.2.4
+    defaultEnabledRetries: 0.2.0
+    envVarSecurityUsage: 0.2.0
+    examples: 3.0.0
+    globalSecurity: 3.0.0
+    globalSecurityCallbacks: 1.0.0
+    globalSecurityFlattening: 1.0.0
+    globalServerURLs: 3.0.0
+    multipartFileContentType: 1.0.0
+    nameOverrides: 3.0.0
+    nullables: 1.0.0
+    openEnums: 1.0.0
+    responseFormat: 1.0.0
+    retries: 3.0.0
+    sdkHooks: 1.0.0
+    serverIDs: 3.0.0
+    unions: 3.0.1
+    uploadStreams: 1.0.0
 generatedFiles:
   - src/unstructured_client/sdkconfiguration.py
   - src/unstructured_client/general.py
   - src/unstructured_client/sdk.py
+  - .vscode/settings.json
   - py.typed
   - pylintrc
+  - pyproject.toml
   - scripts/publish.sh
-  - setup.py
   - src/unstructured_client/__init__.py
+  - src/unstructured_client/basesdk.py
+  - src/unstructured_client/httpclient.py
+  - src/unstructured_client/py.typed
+  - src/unstructured_client/types/__init__.py
+  - src/unstructured_client/types/basemodel.py
   - src/unstructured_client/utils/__init__.py
+  - src/unstructured_client/utils/annotations.py
   - src/unstructured_client/utils/enums.py
+  - src/unstructured_client/utils/eventstreaming.py
+  - src/unstructured_client/utils/forms.py
+  - src/unstructured_client/utils/headers.py
+  - src/unstructured_client/utils/metadata.py
+  - src/unstructured_client/utils/queryparams.py
+  - src/unstructured_client/utils/requestbodies.py
   - src/unstructured_client/utils/retries.py
-  - src/unstructured_client/utils/utils.py
+  - src/unstructured_client/utils/security.py
+  - src/unstructured_client/utils/serializers.py
+  - src/unstructured_client/utils/url.py
+  - src/unstructured_client/utils/values.py
   - src/unstructured_client/models/errors/sdkerror.py
   - src/unstructured_client/models/operations/partition.py
+  - src/unstructured_client/models/operations/__init__.py
   - src/unstructured_client/models/errors/httpvalidationerror.py
   - src/unstructured_client/models/errors/servererror.py
+  - src/unstructured_client/models/errors/__init__.py
   - src/unstructured_client/models/shared/validationerror.py
   - src/unstructured_client/models/shared/partition_parameters.py
   - src/unstructured_client/models/shared/security.py
-  - src/unstructured_client/models/__init__.py
-  - src/unstructured_client/models/errors/__init__.py
-  - src/unstructured_client/models/operations/__init__.py
   - src/unstructured_client/models/shared/__init__.py
   - docs/models/operations/partitionrequest.md
   - docs/models/operations/partitionresponse.md

Makefile

@@ -67,6 +67,10 @@ client-generate-local:
 	speakeasy overlay apply -s ./openapi.json -o ./overlay_client.yaml > ./openapi_client.json
 	speakeasy generate sdk -s ./openapi_client.json -o ./ -l python
 
+.PHONY: patch-custom-code
+patch-custom-code:
+	git apply _custom_code.patch
+
 .PHONY: publish
 publish:
 	./scripts/publish.sh

README.md

@@ -30,9 +30,15 @@ Please refer to the [Unstructured docs](https://docs.unstructured.io/api-referen
 <!-- Start SDK Installation [installation] -->
 ## SDK Installation
 
+PIP
 ```bash
 pip install unstructured-client
 ```
+
+Poetry
+```bash
+poetry add unstructured-client
+```
 <!-- End SDK Installation [installation] -->
 
 ## SDK Example Usage
@@ -131,28 +137,30 @@ Some of the endpoints in this SDK support retries. If you use the SDK without an
 
 To change the default retry strategy for a single API call, simply provide a `RetryConfig` object to the call:
 ```python
-import unstructured_client
-from unstructured_client.models import operations, shared
+from unstructured_client import UnstructuredClient
+from unstructured_client.models import shared
 from unstructured_client.utils import BackoffStrategy, RetryConfig
 
-s = unstructured_client.UnstructuredClient()
+s = UnstructuredClient(
+    api_key_auth="YOUR_API_KEY",
+)
 
 
-res = s.general.partition(request=operations.PartitionRequest(
-    partition_parameters=shared.PartitionParameters(
-        files=shared.Files(
-            content='0x2cC94b2FEF'.encode(),
-            file_name='your_file_here',
-        ),
-        chunking_strategy=shared.ChunkingStrategy.BY_TITLE,
-        split_pdf_page_range=[
+res = s.general.partition(request={
+    "partition_parameters": {
+        "files": {
+            "content": open("<file_path>", "rb"),
+            "file_name": "your_file_here",
+        },
+        "chunking_strategy": shared.ChunkingStrategy.BY_TITLE,
+        "split_pdf_page_range": [
             1,
             10,
         ],
-        strategy=shared.Strategy.HI_RES,
-    ),
-),
-    RetryConfig('backoff', BackoffStrategy(1, 50, 1.1, 100), False))
+        "strategy": shared.Strategy.HI_RES,
+    },
+},
+    RetryConfig("backoff", BackoffStrategy(1, 50, 1.1, 100), False))
 
 if res.elements is not None:
     # handle response
@@ -162,29 +170,30 @@ if res.elements is not None:
 
 If you'd like to override the default retry strategy for all operations that support retries, you can use the `retry_config` optional parameter when initializing the SDK:
 ```python
-import unstructured_client
-from unstructured_client.models import operations, shared
+from unstructured_client import UnstructuredClient
+from unstructured_client.models import shared
 from unstructured_client.utils import BackoffStrategy, RetryConfig
 
-s = unstructured_client.UnstructuredClient(
-    retry_config=RetryConfig('backoff', BackoffStrategy(1, 50, 1.1, 100), False),
+s = UnstructuredClient(
+    retry_config=RetryConfig("backoff", BackoffStrategy(1, 50, 1.1, 100), False),
+    api_key_auth="YOUR_API_KEY",
 )
 
 
-res = s.general.partition(request=operations.PartitionRequest(
-    partition_parameters=shared.PartitionParameters(
-        files=shared.Files(
-            content='0x2cC94b2FEF'.encode(),
-            file_name='your_file_here',
-        ),
-        chunking_strategy=shared.ChunkingStrategy.BY_TITLE,
-        split_pdf_page_range=[
+res = s.general.partition(request={
+    "partition_parameters": {
+        "files": {
+            "content": open("<file_path>", "rb"),
+            "file_name": "your_file_here",
+        },
+        "chunking_strategy": shared.ChunkingStrategy.BY_TITLE,
+        "split_pdf_page_range": [
             1,
             10,
         ],
-        strategy=shared.Strategy.HI_RES,
-    ),
-))
+        "strategy": shared.Strategy.HI_RES,
+    },
+})
 
 if res.elements is not None:
     # handle response
@@ -196,16 +205,81 @@ if res.elements is not None:
 <!-- Start Custom HTTP Client [http-client] -->
 ## Custom HTTP Client
 
-The Python SDK makes API calls using the [requests](https://pypi.org/project/requests/) HTTP library.  In order to provide a convenient way to configure timeouts, cookies, proxies, custom headers, and other low-level configuration, you can initialize the SDK client with a custom `requests.Session` object.
+The Python SDK makes API calls using the [httpx](https://www.python-httpx.org/) HTTP library.  In order to provide a convenient way to configure timeouts, cookies, proxies, custom headers, and other low-level configuration, you can initialize the SDK client with your own HTTP client instance.
+Depending on whether you are using the sync or async version of the SDK, you can pass an instance of `HttpClient` or `AsyncHttpClient` respectively, which are Protocol's ensuring that the client has the necessary methods to make API calls.
+This allows you to wrap the client with your own custom logic, such as adding custom headers, logging, or error handling, or you can just pass an instance of `httpx.Client` or `httpx.AsyncClient` directly.
 
 For example, you could specify a header for every request that this sdk makes as follows:
 ```python
-import unstructured_client
-import requests
+from unstructured_client import UnstructuredClient
+import httpx
+
+http_client = httpx.Client(headers={"x-custom-header": "someValue"})
+s = UnstructuredClient(client=http_client)
+```
 
-http_client = requests.Session()
-http_client.headers.update({'x-custom-header': 'someValue'})
-s = unstructured_client.UnstructuredClient(client=http_client)
+or you could wrap the client with your own custom logic:
+```python
+from unstructured_client import UnstructuredClient
+from unstructured_client.httpclient import AsyncHttpClient
+import httpx
+
+class CustomClient(AsyncHttpClient):
+    client: AsyncHttpClient
+
+    def __init__(self, client: AsyncHttpClient):
+        self.client = client
+
+    async def send(
+        self,
+        request: httpx.Request,
+        *,
+        stream: bool = False,
+        auth: Union[
+            httpx._types.AuthTypes, httpx._client.UseClientDefault, None
+        ] = httpx.USE_CLIENT_DEFAULT,
+        follow_redirects: Union[
+            bool, httpx._client.UseClientDefault
+        ] = httpx.USE_CLIENT_DEFAULT,
+    ) -> httpx.Response:
+        request.headers["Client-Level-Header"] = "added by client"
+
+        return await self.client.send(
+            request, stream=stream, auth=auth, follow_redirects=follow_redirects
+        )
+
+    def build_request(
+        self,
+        method: str,
+        url: httpx._types.URLTypes,
+        *,
+        content: Optional[httpx._types.RequestContent] = None,
+        data: Optional[httpx._types.RequestData] = None,
+        files: Optional[httpx._types.RequestFiles] = None,
+        json: Optional[Any] = None,
+        params: Optional[httpx._types.QueryParamTypes] = None,
+        headers: Optional[httpx._types.HeaderTypes] = None,
+        cookies: Optional[httpx._types.CookieTypes] = None,
+        timeout: Union[
+            httpx._types.TimeoutTypes, httpx._client.UseClientDefault
+        ] = httpx.USE_CLIENT_DEFAULT,
+        extensions: Optional[httpx._types.RequestExtensions] = None,
+    ) -> httpx.Request:
+        return self.client.build_request(
+            method,
+            url,
+            content=content,
+            data=data,
+            files=files,
+            json=json,
+            params=params,
+            headers=headers,
+            cookies=cookies,
+            timeout=timeout,
+            extensions=extensions,
+        )
+
+s = UnstructuredClient(async_client=CustomClient(httpx.AsyncClient()))
 ```
 <!-- End Custom HTTP Client [http-client] -->
 
@@ -216,6 +290,47 @@ s = unstructured_client.UnstructuredClient(client=http_client)
 <!-- No Server Selection -->
 <!-- No Authentication -->
 
+<!-- Start File uploads [file-upload] -->
+## File uploads
+
+Certain SDK methods accept file objects as part of a request body or multi-part request. It is possible and typically recommended to upload files as a stream rather than reading the entire contents into memory. This avoids excessive memory consumption and potentially crashing with out-of-memory errors when working with very large files. The following example demonstrates how to attach a file stream to a request.
+
+> [!TIP]
+>
+> For endpoints that handle file uploads bytes arrays can also be used. However, using streams is recommended for large files.
+>
+
+```python
+from unstructured_client import UnstructuredClient
+from unstructured_client.models import shared
+
+s = UnstructuredClient(
+    api_key_auth="YOUR_API_KEY",
+)
+
+
+res = s.general.partition(request={
+    "partition_parameters": {
+        "files": {
+            "content": open("<file_path>", "rb"),
+            "file_name": "your_file_here",
+        },
+        "chunking_strategy": shared.ChunkingStrategy.BY_TITLE,
+        "split_pdf_page_range": [
+            1,
+            10,
+        ],
+        "strategy": shared.Strategy.HI_RES,
+    },
+})
+
+if res.elements is not None:
+    # handle response
+    pass
+
+```
+<!-- End File uploads [file-upload] -->
+
 <!-- Placeholder for Future Speakeasy SDK Sections -->
 
 ### Maturity