release: 0.51.0

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "0.50.0"
+  ".": "0.51.0"
 }

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 55
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/mixedbread%2Fmixedbread-ebd391dad1252eb00dd69ac50455b93bcdcd2cf0177d678e160e47f1d017287f.yml
-openapi_spec_hash: 3bfd5f9eb34711238caef851aa81f5c0
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/mixedbread/mixedbread-fe78c77edfd65d345d21ca8f29af4cbe6c977cb999e514f8073b9f3d9b721312.yml
+openapi_spec_hash: 6e8c61ec14c016c1c74881de9e17d53d
 config_hash: 594a43c9cb8089f079bb9c5442646791

CHANGELOG.md

@@ -1,5 +1,28 @@
 # Changelog
 
+## 0.51.0 (2026-05-12)
+
+Full Changelog: [v0.50.0...v0.51.0](https://github.com/mixedbread-ai/mixedbread-python/compare/v0.50.0...v0.51.0)
+
+### Features
+
+* **api:** api update ([6fe066e](https://github.com/mixedbread-ai/mixedbread-python/commit/6fe066e17443211a47a21f677344bf8c349e6fde))
+* **api:** api update ([eac4b8f](https://github.com/mixedbread-ai/mixedbread-python/commit/eac4b8f34275c9377765cfe62f677d5ca36cf061))
+* **api:** api update ([66aa7dc](https://github.com/mixedbread-ai/mixedbread-python/commit/66aa7dc394357766b869a3d067e4c130cdf482e8))
+* **internal/types:** support eagerly validating pydantic iterators ([3e9c5ac](https://github.com/mixedbread-ai/mixedbread-python/commit/3e9c5ac9ab56db4eddf8a6a2f219a8789c9c45ac))
+* support setting headers via env ([38de0ee](https://github.com/mixedbread-ai/mixedbread-python/commit/38de0ee2781d9e27d6aecafe89f5a5b5baaed75c))
+
+
+### Bug Fixes
+
+* **client:** add missing f-string prefix in file type error message ([fe74792](https://github.com/mixedbread-ai/mixedbread-python/commit/fe74792cd81bb58bd62e58c086d6d1ee6c233c25))
+* use correct field name format for multipart file arrays ([361fcd6](https://github.com/mixedbread-ai/mixedbread-python/commit/361fcd66f8422020375b076d4c70a83c2b82241d))
+
+
+### Chores
+
+* **internal:** reformat pyproject.toml ([8802c53](https://github.com/mixedbread-ai/mixedbread-python/commit/8802c53023895e9248f03b92477c9a17013ec7b7))
+
 ## 0.50.0 (2026-04-23)
 
 Full Changelog: [v0.49.0...v0.50.0](https://github.com/mixedbread-ai/mixedbread-python/compare/v0.49.0...v0.50.0)

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "mixedbread"
-version = "0.50.0"
+version = "0.51.0"
 description = "The official Python library for the Mixedbread 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/mixedbread/_files.py', '_dev/.*.py', 'tests/.*']
+exclude = ["src/mixedbread/_files.py", "_dev/.*.py", "tests/.*"]
 
 strict_equality = true
 implicit_reexport = true

src/mixedbread/_client.py

@@ -27,6 +27,7 @@
 )
 from ._utils import (
     is_given,
+    is_mapping_t,
     maybe_transform,
     get_async_library,
     async_maybe_transform,
@@ -150,6 +151,15 @@ def __init__(
             except KeyError as exc:
                 raise ValueError(f"Unknown environment: {environment}") from exc
 
+        custom_headers_env = os.environ.get("MIXEDBREAD_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,
@@ -547,6 +557,15 @@ def __init__(
             except KeyError as exc:
                 raise ValueError(f"Unknown environment: {environment}") from exc
 
+        custom_headers_env = os.environ.get("MIXEDBREAD_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,

src/mixedbread/_files.py

@@ -99,7 +99,7 @@ async def async_to_httpx_files(files: RequestFiles | None) -> HttpxRequestFiles
     elif is_sequence_t(files):
         files = [(key, await _async_transform_file(file)) for key, file in files]
     else:
-        raise TypeError("Unexpected file type input {type(files)}, expected mapping or sequence")
+        raise TypeError(f"Unexpected file type input {type(files)}, expected mapping or sequence")
 
     return files
 

src/mixedbread/_models.py

@@ -25,7 +25,9 @@
     ClassVar,
     Protocol,
     Required,
+    Annotated,
     ParamSpec,
+    TypeAlias,
     TypedDict,
     TypeGuard,
     final,
@@ -79,7 +81,15 @@
 from ._constants import RAW_RESPONSE_HEADER
 
 if TYPE_CHECKING:
+    from pydantic import GetCoreSchemaHandler, ValidatorFunctionWrapHandler
+    from pydantic_core import CoreSchema, core_schema
     from pydantic_core.core_schema import ModelField, ModelSchema, LiteralSchema, ModelFieldsSchema
+else:
+    try:
+        from pydantic_core import CoreSchema, core_schema
+    except ImportError:
+        CoreSchema = None
+        core_schema = None
 
 __all__ = ["BaseModel", "GenericModel"]
 
@@ -396,6 +406,76 @@ def model_dump_json(
             )
 
 
+class _EagerIterable(list[_T], Generic[_T]):
+    """
+    Accepts any Iterable[T] input (including generators), consumes it
+    eagerly, and validates all items upfront.
+
+    Validation preserves the original container type where possible
+    (e.g. a set[T] stays a set[T]).  Serialization (model_dump / JSON)
+    always emits a list — round-tripping through model_dump() will not
+    restore the original container type.
+    """
+
+    @classmethod
+    def __get_pydantic_core_schema__(
+        cls,
+        source_type: Any,
+        handler: GetCoreSchemaHandler,
+    ) -> CoreSchema:
+        (item_type,) = get_args(source_type) or (Any,)
+        item_schema: CoreSchema = handler.generate_schema(item_type)
+        list_of_items_schema: CoreSchema = core_schema.list_schema(item_schema)
+
+        return core_schema.no_info_wrap_validator_function(
+            cls._validate,
+            list_of_items_schema,
+            serialization=core_schema.plain_serializer_function_ser_schema(
+                cls._serialize,
+                info_arg=False,
+            ),
+        )
+
+    @staticmethod
+    def _validate(v: Iterable[_T], handler: "ValidatorFunctionWrapHandler") -> Any:
+        original_type: type[Any] = type(v)
+
+        # Normalize to list so list_schema can validate each item
+        if isinstance(v, list):
+            items: list[_T] = v
+        else:
+            try:
+                items = list(v)
+            except TypeError as e:
+                raise TypeError("Value is not iterable") from e
+
+        # Validate items against the inner schema
+        validated: list[_T] = handler(items)
+
+        # Reconstruct original container type
+        if original_type is list:
+            return validated
+        # str(list) produces the list's repr, not a string built from items,
+        # so skip reconstruction for str and its subclasses.
+        if issubclass(original_type, str):
+            return validated
+        try:
+            return original_type(validated)
+        except (TypeError, ValueError):
+            # If the type cannot be reconstructed, just return the validated list
+            return validated
+
+    @staticmethod
+    def _serialize(v: Iterable[_T]) -> list[_T]:
+        """Always serialize as a list so Pydantic's JSON encoder is happy."""
+        if isinstance(v, list):
+            return v
+        return list(v)
+
+
+EagerIterable: TypeAlias = Annotated[Iterable[_T], _EagerIterable]
+
+
 def _construct_field(value: object, field: FieldInfo, key: str) -> object:
     if value is None:
         return field_get_default(field)

src/mixedbread/_qs.py

@@ -2,17 +2,13 @@
 
 from typing import Any, List, Tuple, Union, Mapping, TypeVar
 from urllib.parse import parse_qs, urlencode
-from typing_extensions import Literal, get_args
+from typing_extensions import get_args
 
-from ._types import NotGiven, not_given
+from ._types import NotGiven, ArrayFormat, NestedFormat, not_given
 from ._utils import flatten
 
 _T = TypeVar("_T")
 
-
-ArrayFormat = Literal["comma", "repeat", "indices", "brackets"]
-NestedFormat = Literal["dots", "brackets"]
-
 PrimitiveData = Union[str, int, float, bool, None]
 # this should be Data = Union[PrimitiveData, "List[Data]", "Tuple[Data]", "Mapping[str, Data]"]
 # https://github.com/microsoft/pyright/issues/3555

src/mixedbread/_types.py

@@ -47,6 +47,9 @@
 ModelT = TypeVar("ModelT", bound=pydantic.BaseModel)
 _T = TypeVar("_T")
 
+ArrayFormat = Literal["comma", "repeat", "indices", "brackets"]
+NestedFormat = Literal["dots", "brackets"]
+
 
 # Approximates httpx internal ProxiesTypes and RequestFiles types
 # while adding support for `PathLike` instances

src/mixedbread/_utils/_utils.py

@@ -17,11 +17,11 @@
 )
 from pathlib import Path
 from datetime import date, datetime
-from typing_extensions import TypeGuard
+from typing_extensions import TypeGuard, get_args
 
 import sniffio
 
-from .._types import Omit, NotGiven, FileTypes, HeadersLike
+from .._types import Omit, NotGiven, FileTypes, ArrayFormat, HeadersLike
 
 _T = TypeVar("_T")
 _TupleT = TypeVar("_TupleT", bound=Tuple[object, ...])
@@ -40,25 +40,45 @@ def extract_files(
     query: Mapping[str, object],
     *,
     paths: Sequence[Sequence[str]],
+    array_format: ArrayFormat = "brackets",
 ) -> list[tuple[str, FileTypes]]:
     """Recursively extract files from the given dictionary based on specified paths.
 
     A path may look like this ['foo', 'files', '<array>', 'data'].
 
+    ``array_format`` controls how ``<array>`` segments contribute to the emitted
+    field name. Supported values: ``"brackets"`` (``foo[]``), ``"repeat"`` and
+    ``"comma"`` (``foo``), ``"indices"`` (``foo[0]``, ``foo[1]``).
+
     Note: this mutates the given dictionary.
     """
     files: list[tuple[str, FileTypes]] = []
     for path in paths:
-        files.extend(_extract_items(query, path, index=0, flattened_key=None))
+        files.extend(_extract_items(query, path, index=0, flattened_key=None, array_format=array_format))
     return files
 
 
+def _array_suffix(array_format: ArrayFormat, array_index: int) -> str:
+    if array_format == "brackets":
+        return "[]"
+    if array_format == "indices":
+        return f"[{array_index}]"
+    if array_format == "repeat" or array_format == "comma":
+        # Both repeat the bare field name for each file part; there is no
+        # meaningful way to comma-join binary parts.
+        return ""
+    raise NotImplementedError(
+        f"Unknown array_format value: {array_format}, choose from {', '.join(get_args(ArrayFormat))}"
+    )
+
+
 def _extract_items(
     obj: object,
     path: Sequence[str],
     *,
     index: int,
     flattened_key: str | None,
+    array_format: ArrayFormat,
 ) -> list[tuple[str, FileTypes]]:
     try:
         key = path[index]
@@ -75,9 +95,11 @@ def _extract_items(
 
         if is_list(obj):
             files: list[tuple[str, FileTypes]] = []
-            for entry in obj:
-                assert_is_file_content(entry, key=flattened_key + "[]" if flattened_key else "")
-                files.append((flattened_key + "[]", cast(FileTypes, entry)))
+            for array_index, entry in enumerate(obj):
+                suffix = _array_suffix(array_format, array_index)
+                emitted_key = (flattened_key + suffix) if flattened_key else suffix
+                assert_is_file_content(entry, key=emitted_key)
+                files.append((emitted_key, cast(FileTypes, entry)))
             return files
 
         assert_is_file_content(obj, key=flattened_key)
@@ -106,6 +128,7 @@ def _extract_items(
             path,
             index=index,
             flattened_key=flattened_key,
+            array_format=array_format,
         )
     elif is_list(obj):
         if key != "<array>":
@@ -117,9 +140,12 @@ def _extract_items(
                     item,
                     path,
                     index=index,
-                    flattened_key=flattened_key + "[]" if flattened_key is not None else "[]",
+                    flattened_key=(
+                        (flattened_key if flattened_key is not None else "") + _array_suffix(array_format, array_index)
+                    ),
+                    array_format=array_format,
                 )
-                for item in obj
+                for array_index, item in enumerate(obj)
             ]
         )
 

src/mixedbread/_version.py

@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
 __title__ = "mixedbread"
-__version__ = "0.50.0"  # x-release-please-version
+__version__ = "0.51.0"  # x-release-please-version