release: 0.14.0 (#159)

Co-authored-by: stainless-app[bot] <142633134+stainless-app[bot]@users.noreply.github.com>

.release-please-manifest.json

@@ -1,3 +1,3 @@
 {
-  ".": "0.13.1"
+  ".": "0.14.0"
 }

.stats.yml

@@ -1,2 +1,2 @@
 configured_endpoints: 7
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/groqcloud%2Fgroqcloud-a711d22c2283945608fc5ab6a399805da8961d6b9e0e068637d389ed611230c0.yml
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/groqcloud%2Fgroqcloud-33be0d612b9f1153b86f53e95bf7c571af2f1e466bda2330b632e6c05832e2a6.yml

CHANGELOG.md

@@ -1,5 +1,35 @@
 # Changelog
 
+## 0.14.0 (2025-01-09)
+
+Full Changelog: [v0.13.1...v0.14.0](https://github.com/groq/groq-python/compare/v0.13.1...v0.14.0)
+
+### Features
+
+* **api:** api update ([#163](https://github.com/groq/groq-python/issues/163)) ([43a7a5b](https://github.com/groq/groq-python/commit/43a7a5b048b22f4a5edba53ec31b2b8967681708))
+* **api:** api update ([#167](https://github.com/groq/groq-python/issues/167)) ([5016206](https://github.com/groq/groq-python/commit/5016206e461c384806ac3c68b8dfab3d342ba93c))
+* **api:** api update ([#170](https://github.com/groq/groq-python/issues/170)) ([2b35e95](https://github.com/groq/groq-python/commit/2b35e952e12020116adc45e40007c3fd61db1bb7))
+
+
+### Bug Fixes
+
+* **client:** only call .close() when needed ([#169](https://github.com/groq/groq-python/issues/169)) ([6a0ec57](https://github.com/groq/groq-python/commit/6a0ec576de707ed90a4a536ff206e9ee07fc5a3a))
+
+
+### Chores
+
+* add missing isclass check ([#166](https://github.com/groq/groq-python/issues/166)) ([9cb1e72](https://github.com/groq/groq-python/commit/9cb1e727377c93c92d1bbd49f1c5b8613730c3a6))
+* **internal:** bump httpx dependency ([#168](https://github.com/groq/groq-python/issues/168)) ([c260ae9](https://github.com/groq/groq-python/commit/c260ae969caa5f4e7b48dd558802b933da98bed6))
+* **internal:** codegen related update ([#158](https://github.com/groq/groq-python/issues/158)) ([85b5765](https://github.com/groq/groq-python/commit/85b5765b2b6cfa9560c763600699fd05f7b2a632))
+* **internal:** codegen related update ([#160](https://github.com/groq/groq-python/issues/160)) ([8b87c4d](https://github.com/groq/groq-python/commit/8b87c4d657e0a9d2296323eff6d298ec98b34b3e))
+* **internal:** codegen related update ([#164](https://github.com/groq/groq-python/issues/164)) ([d7b6be5](https://github.com/groq/groq-python/commit/d7b6be5f4bba87002409330644045ba630856880))
+* **internal:** fix some typos ([#162](https://github.com/groq/groq-python/issues/162)) ([32482ae](https://github.com/groq/groq-python/commit/32482ae691f24fdbd5c80282c597a299a48a247d))
+
+
+### Documentation
+
+* **readme:** example snippet for client context manager ([#161](https://github.com/groq/groq-python/issues/161)) ([b7bfd15](https://github.com/groq/groq-python/commit/b7bfd15768d60beb2059ab3d326bae1b19c6bf17))
+
 ## 0.13.1 (2024-12-14)
 
 Full Changelog: [v0.13.0...v0.13.1](https://github.com/groq/groq-python/compare/v0.13.0...v0.13.1)

LICENSE

@@ -186,7 +186,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright 2024 Groq
+   Copyright 2025 Groq
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

README.md

@@ -363,6 +363,16 @@ client.with_options(http_client=DefaultHttpxClient(...))
 
 By default the library closes underlying HTTP connections whenever the client is [garbage collected](https://docs.python.org/3/reference/datamodel.html#object.__del__). You can manually close the client using the `.close()` method if desired, or with a context manager that closes when exiting.
 
+```py
+from groq import Groq
+
+with Groq() as client:
+  # make requests here
+  ...
+
+# HTTP client is now closed
+```
+
 ## Versioning
 
 This package generally follows [SemVer](https://semver.org/spec/v2.0.0.html) conventions, though certain backwards-incompatible changes may be released as minor versions:

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "groq"
-version = "0.13.1"
+version = "0.14.0"
 description = "The official Python library for the groq API"
 dynamic = ["readme"]
 license = "Apache-2.0"
@@ -54,7 +54,7 @@ dev-dependencies = [
     "dirty-equals>=0.6.0",
     "importlib-metadata>=6.7.0",
     "rich>=13.7.1",
-    "nest_asyncio==1.6.0"
+    "nest_asyncio==1.6.0",
 ]
 
 [tool.rye.scripts]

requirements-dev.lock

@@ -35,7 +35,7 @@ h11==0.14.0
     # via httpcore
 httpcore==1.0.2
     # via httpx
-httpx==0.25.2
+httpx==0.28.1
     # via groq
     # via respx
 idna==3.4
@@ -76,7 +76,7 @@ python-dateutil==2.8.2
     # via time-machine
 pytz==2023.3.post1
     # via dirty-equals
-respx==0.20.2
+respx==0.22.0
 rich==13.7.1
 ruff==0.6.9
 setuptools==68.2.2
@@ -86,7 +86,6 @@ six==1.16.0
 sniffio==1.3.0
     # via anyio
     # via groq
-    # via httpx
 time-machine==2.9.0
 tomli==2.0.2
     # via mypy

requirements.lock

@@ -25,7 +25,7 @@ h11==0.14.0
     # via httpcore
 httpcore==1.0.2
     # via httpx
-httpx==0.25.2
+httpx==0.28.1
     # via groq
 idna==3.4
     # via anyio
@@ -37,7 +37,6 @@ pydantic-core==2.27.1
 sniffio==1.3.0
     # via anyio
     # via groq
-    # via httpx
 typing-extensions==4.12.2
     # via anyio
     # via groq

src/groq/_base_client.py

@@ -767,6 +767,9 @@ def __init__(self, **kwargs: Any) -> None:
 
 class SyncHttpxClientWrapper(DefaultHttpxClient):
     def __del__(self) -> None:
+        if self.is_closed:
+            return
+
         try:
             self.close()
         except Exception:
@@ -1334,6 +1337,9 @@ def __init__(self, **kwargs: Any) -> None:
 
 class AsyncHttpxClientWrapper(DefaultAsyncHttpxClient):
     def __del__(self) -> None:
+        if self.is_closed:
+            return
+
         try:
             # TODO(someday): support non asyncio runtimes here
             asyncio.get_running_loop().create_task(self.aclose())

src/groq/_models.py

@@ -488,7 +488,11 @@ def construct_type(*, value: object, type_: object) -> object:
         _, items_type = get_args(type_)  # Dict[_, items_type]
         return {key: construct_type(value=item, type_=items_type) for key, item in value.items()}
 
-    if not is_literal_type(type_) and (issubclass(origin, BaseModel) or issubclass(origin, GenericModel)):
+    if (
+        not is_literal_type(type_)
+        and inspect.isclass(origin)
+        and (issubclass(origin, BaseModel) or issubclass(origin, GenericModel))
+    ):
         if is_list(value):
             return [cast(Any, type_).construct(**entry) if is_mapping(entry) else entry for entry in value]
 

src/groq/_version.py

@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
 __title__ = "groq"
-__version__ = "0.13.1"  # x-release-please-version
+__version__ = "0.14.0"  # x-release-please-version

src/groq/resources/audio/transcriptions.py

@@ -186,8 +186,7 @@ def create(
               improve accuracy and latency.
 
           prompt: An optional text to guide the model's style or continue a previous audio
-              segment. The [prompt](/docs/guides/speech-to-text/prompting) should match the
-              audio language.
+              segment. The [prompt](/docs/speech-text) should match the audio language.
 
           response_format: The format of the transcript output, in one of these options: `json`, `text`, or
               `verbose_json`.
@@ -396,8 +395,7 @@ async def create(
               improve accuracy and latency.
 
           prompt: An optional text to guide the model's style or continue a previous audio
-              segment. The [prompt](/docs/guides/speech-to-text/prompting) should match the
-              audio language.
+              segment. The [prompt](/docs/speech-text) should match the audio language.
 
           response_format: The format of the transcript output, in one of these options: `json`, `text`, or
               `verbose_json`.

src/groq/resources/chat/completions.py

@@ -69,6 +69,7 @@ def create(
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "on_demand", "flex"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
@@ -103,6 +104,7 @@ def create(
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "on_demand", "flex"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         stream: Literal[True],
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
@@ -137,6 +139,7 @@ def create(
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "on_demand", "flex"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         stream: bool,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
@@ -170,6 +173,7 @@ def create(
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "on_demand", "flex"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
@@ -247,6 +251,12 @@ def create(
               the same result. Determinism is not guaranteed, and you should refer to the
               `system_fingerprint` response parameter to monitor changes in the backend.
 
+          service_tier: The service tier to use for the request. Defaults to `on_demand`.
+
+              - `auto` will automatically select the highest tier available within the rate
+                limits of your organization.
+              - `flex` uses the flex tier, which will succeed or fail quickly.
+
           stop: Up to 4 sequences where the API will stop generating further tokens. The
               returned text will not contain the stop sequence.
 
@@ -312,6 +322,7 @@ def create(
                     "presence_penalty": presence_penalty,
                     "response_format": response_format,
                     "seed": seed,
+                    "service_tier": service_tier,
                     "stop": stop,
                     "stream": stream,
                     "temperature": temperature,
@@ -369,6 +380,7 @@ async def create(
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "on_demand", "flex"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
@@ -403,6 +415,7 @@ async def create(
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "on_demand", "flex"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         stream: Literal[True],
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
@@ -437,6 +450,7 @@ async def create(
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "on_demand", "flex"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         stream: bool,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
@@ -470,6 +484,7 @@ async def create(
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
         seed: Optional[int] | NotGiven = NOT_GIVEN,
+        service_tier: Optional[Literal["auto", "on_demand", "flex"]] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
         stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
@@ -547,6 +562,12 @@ async def create(
               the same result. Determinism is not guaranteed, and you should refer to the
               `system_fingerprint` response parameter to monitor changes in the backend.
 
+          service_tier: The service tier to use for the request. Defaults to `on_demand`.
+
+              - `auto` will automatically select the highest tier available within the rate
+                limits of your organization.
+              - `flex` uses the flex tier, which will succeed or fail quickly.
+
           stop: Up to 4 sequences where the API will stop generating further tokens. The
               returned text will not contain the stop sequence.
 
@@ -612,6 +633,7 @@ async def create(
                     "presence_penalty": presence_penalty,
                     "response_format": response_format,
                     "seed": seed,
+                    "service_tier": service_tier,
                     "stop": stop,
                     "stream": stream,
                     "temperature": temperature,

src/groq/types/audio/transcription_create_params.py

@@ -136,8 +136,7 @@ class TranscriptionCreateParams(TypedDict, total=False):
     """An optional text to guide the model's style or continue a previous audio
     segment.
 
-    The [prompt](/docs/guides/speech-to-text/prompting) should match the audio
-    language.
+    The [prompt](/docs/speech-text) should match the audio language.
     """
 
     response_format: Literal["json", "text", "verbose_json"]

src/groq/types/chat/completion_create_params.py

@@ -106,6 +106,14 @@ class CompletionCreateParams(TypedDict, total=False):
     `system_fingerprint` response parameter to monitor changes in the backend.
     """
 
+    service_tier: Optional[Literal["auto", "on_demand", "flex"]]
+    """The service tier to use for the request. Defaults to `on_demand`.
+
+    - `auto` will automatically select the highest tier available within the rate
+      limits of your organization.
+    - `flex` uses the flex tier, which will succeed or fail quickly.
+    """
+
     stop: Union[Optional[str], List[str], None]
     """Up to 4 sequences where the API will stop generating further tokens.
 

tests/api_resources/chat/test_completions.py

@@ -58,6 +58,7 @@ def test_method_create_with_all_params(self, client: Groq) -> None:
             presence_penalty=-2,
             response_format={"type": "text"},
             seed=0,
+            service_tier="auto",
             stop="\n",
             stream=False,
             temperature=1,
@@ -159,6 +160,7 @@ async def test_method_create_with_all_params(self, async_client: AsyncGroq) -> N
             presence_penalty=-2,
             response_format={"type": "text"},
             seed=0,
+            service_tier="auto",
             stop="\n",
             stream=False,
             temperature=1,

tests/test_client.py

@@ -342,11 +342,11 @@ def test_default_query_option(self) -> None:
             FinalRequestOptions(
                 method="get",
                 url="/foo",
-                params={"foo": "baz", "query_param": "overriden"},
+                params={"foo": "baz", "query_param": "overridden"},
             )
         )
         url = httpx.URL(request.url)
-        assert dict(url.params) == {"foo": "baz", "query_param": "overriden"}
+        assert dict(url.params) == {"foo": "baz", "query_param": "overridden"}
 
     def test_request_extra_json(self) -> None:
         request = self.client._build_request(
@@ -1158,11 +1158,11 @@ def test_default_query_option(self) -> None:
             FinalRequestOptions(
                 method="get",
                 url="/foo",
-                params={"foo": "baz", "query_param": "overriden"},
+                params={"foo": "baz", "query_param": "overridden"},
             )
         )
         url = httpx.URL(request.url)
-        assert dict(url.params) == {"foo": "baz", "query_param": "overriden"}
+        assert dict(url.params) == {"foo": "baz", "query_param": "overridden"}
 
     def test_request_extra_json(self) -> None:
         request = self.client._build_request(