together 2.0.0a8__tar.gz → 2.0.0a9__tar.gz

together-2.0.0a9/.release-please-manifest.json

@@ -0,0 +1,3 @@
+{
+  ".": "2.0.0-alpha.9"
+}

{together-2.0.0a8 → together-2.0.0a9}/CHANGELOG.md

@@ -1,5 +1,28 @@
 # Changelog
 
+## 2.0.0-alpha.9 (2025-12-03)
+
+Full Changelog: [v2.0.0-alpha.8...v2.0.0-alpha.9](https://github.com/togethercomputer/together-py/compare/v2.0.0-alpha.8...v2.0.0-alpha.9)
+
+### Features
+
+* **api:** api update ([fa5e6f3](https://github.com/togethercomputer/together-py/commit/fa5e6f3eb27475ac2e377bbea9150d45bf4e141e))
+* **api:** api update ([236996f](https://github.com/togethercomputer/together-py/commit/236996f0eba5c0a33d2da59b438a830684e89192))
+
+
+### Bug Fixes
+
+* ensure streams are always closed ([db990c7](https://github.com/togethercomputer/together-py/commit/db990c744ebfffcfe48f52dc44b1ca7b47f1f79a))
+
+
+### Chores
+
+* bump required `uv` version ([1dfec56](https://github.com/togethercomputer/together-py/commit/1dfec5659c5a8e6c8abc7a1035d602a3e47ff67a))
+* **deps:** mypy 1.18.1 has a regression, pin to 1.17 ([2235b95](https://github.com/togethercomputer/together-py/commit/2235b95d3e8dc11c9edc308e2b4b69b1463d21cb))
+* **docs:** use environment variables for authentication in code snippets ([051c1b4](https://github.com/togethercomputer/together-py/commit/051c1b489cb80ded1ad60f6b8722512dd2efae3f))
+* fix internal type issues ([4a2b0f1](https://github.com/togethercomputer/together-py/commit/4a2b0f1cfebc013102e21d54318269a0fe037b7a))
+* update lockfile ([e93c953](https://github.com/togethercomputer/together-py/commit/e93c95338756fb37f279aec946d0c5f74cf22877))
+
 ## 2.0.0-alpha.8 (2025-11-26)
 
 Full Changelog: [v2.0.0-alpha.7...v2.0.0-alpha.8](https://github.com/togethercomputer/together-py/compare/v2.0.0-alpha.7...v2.0.0-alpha.8)

{together-2.0.0a8 → together-2.0.0a9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: together
-Version: 2.0.0a8
+Version: 2.0.0a9
 Summary: The official Python library for the together API
 Project-URL: Homepage, https://github.com/togethercomputer/together-py
 Project-URL: Repository, https://github.com/togethercomputer/together-py
@@ -144,6 +144,7 @@ pip install 'together[aiohttp] @ git+ssh://git@github.com/togethercomputer/toget
 Then you can enable it by instantiating the client with `http_client=DefaultAioHttpClient()`:
 
 ```python
+import os
 import asyncio
 from together import DefaultAioHttpClient
 from together import AsyncTogether
@@ -151,7 +152,7 @@ from together import AsyncTogether
 
 async def main() -> None:
     async with AsyncTogether(
-        api_key="My API Key",
+        api_key=os.environ.get("TOGETHER_API_KEY"),  # This is the default and can be omitted
         http_client=DefaultAioHttpClient(),
     ) as client:
         chat_completion = await client.chat.completions.create(

{together-2.0.0a8 → together-2.0.0a9}/README.md

@@ -98,6 +98,7 @@ pip install 'together[aiohttp] @ git+ssh://git@github.com/togethercomputer/toget
 Then you can enable it by instantiating the client with `http_client=DefaultAioHttpClient()`:
 
 ```python
+import os
 import asyncio
 from together import DefaultAioHttpClient
 from together import AsyncTogether
@@ -105,7 +106,7 @@ from together import AsyncTogether
 
 async def main() -> None:
     async with AsyncTogether(
-        api_key="My API Key",
+        api_key=os.environ.get("TOGETHER_API_KEY"),  # This is the default and can be omitted
         http_client=DefaultAioHttpClient(),
     ) as client:
         chat_completion = await client.chat.completions.create(

{together-2.0.0a8 → together-2.0.0a9}/pyproject.toml

@@ -1,19 +1,20 @@
 [project]
 name = "together"
-version = "2.0.0-alpha.8"
+version = "2.0.0-alpha.9"
 description = "The official Python library for the together API"
 dynamic = ["readme"]
 license = "Apache-2.0"
 authors = [
 { name = "Together", email = "dev-feedback@TogetherAI.com" },
 ]
+
 dependencies = [
-    "httpx>=0.23.0, <1",
-    "pydantic>=1.9.0, <3",
-    "typing-extensions>=4.10, <5",
-    "anyio>=3.5.0, <5",
-    "distro>=1.7.0, <2",
-    "sniffio",
+  "httpx>=0.23.0, <1",
+  "pydantic>=1.9.0, <3",
+  "typing-extensions>=4.10, <5",
+  "anyio>=3.5.0, <5",
+  "distro>=1.7.0, <2",
+  "sniffio",
     "click>=8.1.7",
     "rich>=13.7.1",
     "tabulate>=0.9.0",
@@ -23,6 +24,7 @@ dependencies = [
     "types-tqdm>=4.67.0.20250516",
     "filelock>=3.13.1",
 ]
+
 requires-python = ">= 3.9"
 classifiers = [
   "Typing :: Typed",
@@ -55,7 +57,7 @@ together = "together.lib.cli.cli:main"
 
 [tool.uv]
 managed = true
-required-version = ">=0.5.0"
+required-version = ">=0.9"
 conflicts = [
     [
       { group = "pydantic-v1" },
@@ -67,7 +69,7 @@ conflicts = [
 # version pins are in uv.lock
 dev = [
     "pyright==1.1.399",
-    "mypy",
+    "mypy==1.17",
     "respx",
     "pytest",
     "pytest-asyncio",

{together-2.0.0a8 → together-2.0.0a9}/requirements-dev.lock

@@ -8,7 +8,7 @@ aiosignal==1.4.0
     # via aiohttp
 annotated-types==0.7.0
     # via pydantic
-anyio==4.11.0
+anyio==4.12.0
     # via
     #   httpx
     #   together
@@ -76,7 +76,7 @@ multidict==6.7.0
     # via
     #   aiohttp
     #   yarl
-mypy==1.18.2
+mypy==1.17.0
 mypy-extensions==1.1.0
     # via mypy
 nodeenv==1.9.1
@@ -95,7 +95,7 @@ propcache==0.4.1
     # via
     #   aiohttp
     #   yarl
-pydantic==2.12.4
+pydantic==2.12.5
     # via together
 pydantic-core==2.41.5
     # via pydantic
@@ -123,13 +123,11 @@ python-dateutil==2.9.0.post0 ; python_full_version < '3.10'
 respx==0.22.0
 rich==14.2.0
     # via together
-ruff==0.14.6
+ruff==0.14.7
 six==1.17.0 ; python_full_version < '3.10'
     # via python-dateutil
 sniffio==1.3.1
-    # via
-    #   anyio
-    #   together
+    # via together
 tabulate==0.9.0
     # via together
 time-machine==2.19.0 ; python_full_version < '3.10'

{together-2.0.0a8 → together-2.0.0a9}/src/together/_streaming.py

@@ -55,30 +55,31 @@ class Stream(Generic[_T]):
         process_data = self._client._process_response_data
         iterator = self._iter_events()
 
-        for sse in iterator:
-            if sse.data.startswith("[DONE]"):
-                break
-
-            if sse.event is None:
-                data = sse.json()
-                if is_mapping(data) and data.get("error"):
-                    message = None
-                    error = data.get("error")
-                    if is_mapping(error):
-                        message = error.get("message")
-                    if not message or not isinstance(message, str):
-                        message = "An error occurred during streaming"
-
-                    raise APIError(
-                        message=message,
-                        request=self.response.request,
-                        body=data["error"],
-                    )
-
-                yield process_data(data=data, cast_to=cast_to, response=response)
-
-        # As we might not fully consume the response stream, we need to close it explicitly
-        response.close()
+        try:
+            for sse in iterator:
+                if sse.data.startswith("[DONE]"):
+                    break
+
+                if sse.event is None:
+                    data = sse.json()
+                    if is_mapping(data) and data.get("error"):
+                        message = None
+                        error = data.get("error")
+                        if is_mapping(error):
+                            message = error.get("message")
+                        if not message or not isinstance(message, str):
+                            message = "An error occurred during streaming"
+
+                        raise APIError(
+                            message=message,
+                            request=self.response.request,
+                            body=data["error"],
+                        )
+
+                    yield process_data(data=data, cast_to=cast_to, response=response)
+        finally:
+            # Ensure the response is closed even if the consumer doesn't read all data
+            response.close()
 
     def __enter__(self) -> Self:
         return self
@@ -137,30 +138,31 @@ class AsyncStream(Generic[_T]):
         process_data = self._client._process_response_data
         iterator = self._iter_events()
 
-        async for sse in iterator:
-            if sse.data.startswith("[DONE]"):
-                break
-
-            if sse.event is None:
-                data = sse.json()
-                if is_mapping(data) and data.get("error"):
-                    message = None
-                    error = data.get("error")
-                    if is_mapping(error):
-                        message = error.get("message")
-                    if not message or not isinstance(message, str):
-                        message = "An error occurred during streaming"
-
-                    raise APIError(
-                        message=message,
-                        request=self.response.request,
-                        body=data["error"],
-                    )
-
-                yield process_data(data=data, cast_to=cast_to, response=response)
-
-        # As we might not fully consume the response stream, we need to close it explicitly
-        await response.aclose()
+        try:
+            async for sse in iterator:
+                if sse.data.startswith("[DONE]"):
+                    break
+
+                if sse.event is None:
+                    data = sse.json()
+                    if is_mapping(data) and data.get("error"):
+                        message = None
+                        error = data.get("error")
+                        if is_mapping(error):
+                            message = error.get("message")
+                        if not message or not isinstance(message, str):
+                            message = "An error occurred during streaming"
+
+                        raise APIError(
+                            message=message,
+                            request=self.response.request,
+                            body=data["error"],
+                        )
+
+                    yield process_data(data=data, cast_to=cast_to, response=response)
+        finally:
+            # Ensure the response is closed even if the consumer doesn't read all data
+            await response.aclose()
 
     async def __aenter__(self) -> Self:
         return self

{together-2.0.0a8 → together-2.0.0a9}/src/together/_utils/_utils.py

@@ -373,7 +373,7 @@ def get_required_header(headers: HeadersLike, header: str) -> str:
     lower_header = header.lower()
     if is_mapping_t(headers):
         # mypy doesn't understand the type narrowing here
-        for k, v in headers.items():  # type: ignore[misc, has-type]
+        for k, v in headers.items():  # type: ignore[misc, has-type, attr-defined]
             if k.lower() == lower_header and isinstance(v, str):  # type: ignore[has-type]
                 return v  # type: ignore[has-type]
 

{together-2.0.0a8 → together-2.0.0a9}/src/together/_version.py

@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
 __title__ = "together"
-__version__ = "2.0.0-alpha.8"  # x-release-please-version
+__version__ = "2.0.0-alpha.9"  # x-release-please-version

{together-2.0.0a8 → together-2.0.0a9}/src/together/resources/audio/transcriptions.py

@@ -50,6 +50,8 @@ class TranscriptionsResource(SyncAPIResource):
         file: FileTypes,
         diarize: bool | Omit = omit,
         language: str | Omit = omit,
+        max_speakers: int | Omit = omit,
+        min_speakers: int | Omit = omit,
         model: Literal["openai/whisper-large-v3"] | Omit = omit,
         prompt: str | Omit = omit,
         response_format: Literal["json", "verbose_json"] | Omit = omit,
@@ -82,6 +84,12 @@ class TranscriptionsResource(SyncAPIResource):
           language: Optional ISO 639-1 language code. If `auto` is provided, language is
               auto-detected.
 
+          max_speakers: Maximum number of speakers expected in the audio. Used to improve diarization
+              accuracy when the approximate number of speakers is known.
+
+          min_speakers: Minimum number of speakers expected in the audio. Used to improve diarization
+              accuracy when the approximate number of speakers is known.
+
           model: Model to use for transcription
 
           prompt: Optional text to bias decoding.
@@ -107,6 +115,8 @@ class TranscriptionsResource(SyncAPIResource):
                 "file": file,
                 "diarize": diarize,
                 "language": language,
+                "max_speakers": max_speakers,
+                "min_speakers": min_speakers,
                 "model": model,
                 "prompt": prompt,
                 "response_format": response_format,
@@ -161,6 +171,8 @@ class AsyncTranscriptionsResource(AsyncAPIResource):
         file: FileTypes,
         diarize: bool | Omit = omit,
         language: str | Omit = omit,
+        max_speakers: int | Omit = omit,
+        min_speakers: int | Omit = omit,
         model: Literal["openai/whisper-large-v3"] | Omit = omit,
         prompt: str | Omit = omit,
         response_format: Literal["json", "verbose_json"] | Omit = omit,
@@ -193,6 +205,12 @@ class AsyncTranscriptionsResource(AsyncAPIResource):
           language: Optional ISO 639-1 language code. If `auto` is provided, language is
               auto-detected.
 
+          max_speakers: Maximum number of speakers expected in the audio. Used to improve diarization
+              accuracy when the approximate number of speakers is known.
+
+          min_speakers: Minimum number of speakers expected in the audio. Used to improve diarization
+              accuracy when the approximate number of speakers is known.
+
           model: Model to use for transcription
 
           prompt: Optional text to bias decoding.
@@ -218,6 +236,8 @@ class AsyncTranscriptionsResource(AsyncAPIResource):
                 "file": file,
                 "diarize": diarize,
                 "language": language,
+                "max_speakers": max_speakers,
+                "min_speakers": min_speakers,
                 "model": model,
                 "prompt": prompt,
                 "response_format": response_format,

{together-2.0.0a8 → together-2.0.0a9}/src/together/resources/images.py

@@ -8,7 +8,7 @@ from typing_extensions import Literal
 import httpx
 
 from ..types import image_generate_params
-from .._types import Body, Omit, Query, Headers, NotGiven, omit, not_given
+from .._types import Body, Omit, Query, Headers, NotGiven, SequenceNotStr, omit, not_given
 from .._utils import maybe_transform, async_maybe_transform
 from .._compat import cached_property
 from .._resource import SyncAPIResource, AsyncAPIResource
@@ -64,6 +64,7 @@ class ImagesResource(SyncAPIResource):
         n: int | Omit = omit,
         negative_prompt: str | Omit = omit,
         output_format: Literal["jpeg", "png"] | Omit = omit,
+        reference_images: SequenceNotStr[str] | Omit = omit,
         response_format: Literal["base64", "url"] | Omit = omit,
         seed: int | Omit = omit,
         steps: int | Omit = omit,
@@ -105,6 +106,10 @@ class ImagesResource(SyncAPIResource):
           output_format: The format of the image response. Can be either be `jpeg` or `png`. Defaults to
               `jpeg`.
 
+          reference_images: An array of image URLs that guide the overall appearance and style of the
+              generated image. These reference images influence the visual characteristics
+              consistently across the generation.
+
           response_format: Format of the image response. Can be either a base64 string or a URL.
 
           seed: Seed used for generation. Can be used to reproduce image generations.
@@ -135,6 +140,7 @@ class ImagesResource(SyncAPIResource):
                     "n": n,
                     "negative_prompt": negative_prompt,
                     "output_format": output_format,
+                    "reference_images": reference_images,
                     "response_format": response_format,
                     "seed": seed,
                     "steps": steps,
@@ -189,6 +195,7 @@ class AsyncImagesResource(AsyncAPIResource):
         n: int | Omit = omit,
         negative_prompt: str | Omit = omit,
         output_format: Literal["jpeg", "png"] | Omit = omit,
+        reference_images: SequenceNotStr[str] | Omit = omit,
         response_format: Literal["base64", "url"] | Omit = omit,
         seed: int | Omit = omit,
         steps: int | Omit = omit,
@@ -230,6 +237,10 @@ class AsyncImagesResource(AsyncAPIResource):
           output_format: The format of the image response. Can be either be `jpeg` or `png`. Defaults to
               `jpeg`.
 
+          reference_images: An array of image URLs that guide the overall appearance and style of the
+              generated image. These reference images influence the visual characteristics
+              consistently across the generation.
+
           response_format: Format of the image response. Can be either a base64 string or a URL.
 
           seed: Seed used for generation. Can be used to reproduce image generations.
@@ -260,6 +271,7 @@ class AsyncImagesResource(AsyncAPIResource):
                     "n": n,
                     "negative_prompt": negative_prompt,
                     "output_format": output_format,
+                    "reference_images": reference_images,
                     "response_format": response_format,
                     "seed": seed,
                     "steps": steps,

{together-2.0.0a8 → together-2.0.0a9}/src/together/types/audio/transcription_create_params.py

@@ -34,6 +34,20 @@ class TranscriptionCreateParams(TypedDict, total=False):
     If `auto` is provided, language is auto-detected.
     """
 
+    max_speakers: int
+    """Maximum number of speakers expected in the audio.
+
+    Used to improve diarization accuracy when the approximate number of speakers is
+    known.
+    """
+
+    min_speakers: int
+    """Minimum number of speakers expected in the audio.
+
+    Used to improve diarization accuracy when the approximate number of speakers is
+    known.
+    """
+
     model: Literal["openai/whisper-large-v3"]
     """Model to use for transcription"""
 

{together-2.0.0a8 → together-2.0.0a9}/src/together/types/image_generate_params.py

@@ -5,6 +5,8 @@ from __future__ import annotations
 from typing import Union, Iterable
 from typing_extensions import Literal, Required, TypedDict
 
+from .._types import SequenceNotStr
+
 __all__ = ["ImageGenerateParams", "ImageLora"]
 
 
@@ -61,6 +63,13 @@ class ImageGenerateParams(TypedDict, total=False):
     Can be either be `jpeg` or `png`. Defaults to `jpeg`.
     """
 
+    reference_images: SequenceNotStr[str]
+    """
+    An array of image URLs that guide the overall appearance and style of the
+    generated image. These reference images influence the visual characteristics
+    consistently across the generation.
+    """
+
     response_format: Literal["base64", "url"]
     """Format of the image response. Can be either a base64 string or a URL."""
 

{together-2.0.0a8 → together-2.0.0a9}/tests/api_resources/audio/test_transcriptions.py

@@ -30,6 +30,8 @@ class TestTranscriptions:
             file=b"raw file contents",
             diarize=True,
             language="en",
+            max_speakers=0,
+            min_speakers=0,
             model="openai/whisper-large-v3",
             prompt="prompt",
             response_format="json",
@@ -81,6 +83,8 @@ class TestAsyncTranscriptions:
             file=b"raw file contents",
             diarize=True,
             language="en",
+            max_speakers=0,
+            min_speakers=0,
             model="openai/whisper-large-v3",
             prompt="prompt",
             response_format="json",

{together-2.0.0a8 → together-2.0.0a9}/tests/api_resources/test_images.py

@@ -43,6 +43,7 @@ class TestImages:
             n=0,
             negative_prompt="negative_prompt",
             output_format="jpeg",
+            reference_images=["string"],
             response_format="base64",
             seed=0,
             steps=0,
@@ -108,6 +109,7 @@ class TestAsyncImages:
             n=0,
             negative_prompt="negative_prompt",
             output_format="jpeg",
+            reference_images=["string"],
             response_format="base64",
             seed=0,
             steps=0,