sarvamai 0.1.5a5__tar.gz → 0.1.5a6__tar.gz

sarvamai-0.1.5a6/PKG-INFO

@@ -0,0 +1,174 @@
+Metadata-Version: 2.1
+Name: sarvamai
+Version: 0.1.5a6
+Summary: 
+Requires-Python: >=3.8,<4.0
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: MacOS
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Operating System :: OS Independent
+Classifier: Operating System :: POSIX
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Typing :: Typed
+Requires-Dist: httpx (>=0.21.2)
+Requires-Dist: pydantic (>=1.9.2)
+Requires-Dist: pydantic-core (>=2.18.2,<3.0.0)
+Requires-Dist: typing_extensions (>=4.0.0)
+Description-Content-Type: text/markdown
+
+# Sarvam Python Library
+
+[![fern shield](https://img.shields.io/badge/%F0%9F%8C%BF-Built%20with%20Fern-brightgreen)](https://buildwithfern.com?utm_source=github&utm_medium=github&utm_campaign=readme&utm_source=https%3A%2F%2Fgithub.com%2Fsarvamai%2Fsarvam-python-sdk)
+[![pypi](https://img.shields.io/pypi/v/sarvamai)](https://pypi.python.org/pypi/sarvamai)
+
+The Sarvam Python library provides convenient access to the Sarvam API from Python.
+
+## Documentation
+
+API reference documentation is available [here](https://www.sarvam.ai/).
+
+## Installation
+
+```sh
+pip install sarvamai
+```
+
+## Reference
+
+A full reference for this library is available [here](https://github.com/sarvamai/sarvam-python-sdk/blob/HEAD/./reference.md).
+
+## Usage
+
+Instantiate and use the client with the following:
+
+```python
+from sarvamai import SarvamAI
+
+client = SarvamAI(
+    api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+)
+client.text.translate(
+    input="input",
+    source_language_code="auto",
+    target_language_code="bn-IN",
+)
+```
+
+## Async Client
+
+The SDK also exports an `async` client so that you can make non-blocking calls to our API.
+
+```python
+import asyncio
+
+from sarvamai import AsyncSarvamAI
+
+client = AsyncSarvamAI(
+    api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+)
+
+
+async def main() -> None:
+    await client.text.translate(
+        input="input",
+        source_language_code="auto",
+        target_language_code="bn-IN",
+    )
+
+
+asyncio.run(main())
+```
+
+## Exception Handling
+
+When the API returns a non-success status code (4xx or 5xx response), a subclass of the following error
+will be thrown.
+
+```python
+from sarvamai.core.api_error import ApiError
+
+try:
+    client.text.translate(...)
+except ApiError as e:
+    print(e.status_code)
+    print(e.body)
+```
+
+## Advanced
+
+### Retries
+
+The SDK is instrumented with automatic retries with exponential backoff. A request will be retried as long
+as the request is deemed retryable and the number of retry attempts has not grown larger than the configured
+retry limit (default: 2).
+
+A request is deemed retryable when any of the following HTTP status codes is returned:
+
+- [408](https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/408) (Timeout)
+- [429](https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429) (Too Many Requests)
+- [5XX](https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/500) (Internal Server Errors)
+
+Use the `max_retries` request option to configure this behavior.
+
+```python
+client.text.translate(..., request_options={
+    "max_retries": 1
+})
+```
+
+### Timeouts
+
+The SDK defaults to a 60 second timeout. You can configure this with a timeout option at the client or request level.
+
+```python
+
+from sarvamai import SarvamAI
+
+client = SarvamAI(
+    ...,
+    timeout=20.0,
+)
+
+
+# Override timeout for a specific method
+client.text.translate(..., request_options={
+    "timeout_in_seconds": 1
+})
+```
+
+### Custom Client
+
+You can override the `httpx` client to customize it for your use-case. Some common use-cases include support for proxies
+and transports.
+
+```python
+import httpx
+from sarvamai import SarvamAI
+
+client = SarvamAI(
+    ...,
+    httpx_client=httpx.Client(
+        proxies="http://my.test.proxy.example.com",
+        transport=httpx.HTTPTransport(local_address="0.0.0.0"),
+    ),
+)
+```
+
+## Contributing
+
+While we value open-source contributions to this SDK, this library is generated programmatically.
+Additions made directly to this library would have to be moved over to our generation code,
+otherwise they would be overwritten upon the next generated release. Feel free to open a PR as
+a proof of concept, but know that we will not be able to merge it as-is. We suggest opening
+an issue first to discuss with us!
+
+On the other hand, contributions to the README are always very welcome!
+

sarvamai-0.1.5a6/README.md

@@ -0,0 +1,147 @@
+# Sarvam Python Library
+
+[![fern shield](https://img.shields.io/badge/%F0%9F%8C%BF-Built%20with%20Fern-brightgreen)](https://buildwithfern.com?utm_source=github&utm_medium=github&utm_campaign=readme&utm_source=https%3A%2F%2Fgithub.com%2Fsarvamai%2Fsarvam-python-sdk)
+[![pypi](https://img.shields.io/pypi/v/sarvamai)](https://pypi.python.org/pypi/sarvamai)
+
+The Sarvam Python library provides convenient access to the Sarvam API from Python.
+
+## Documentation
+
+API reference documentation is available [here](https://www.sarvam.ai/).
+
+## Installation
+
+```sh
+pip install sarvamai
+```
+
+## Reference
+
+A full reference for this library is available [here](https://github.com/sarvamai/sarvam-python-sdk/blob/HEAD/./reference.md).
+
+## Usage
+
+Instantiate and use the client with the following:
+
+```python
+from sarvamai import SarvamAI
+
+client = SarvamAI(
+    api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+)
+client.text.translate(
+    input="input",
+    source_language_code="auto",
+    target_language_code="bn-IN",
+)
+```
+
+## Async Client
+
+The SDK also exports an `async` client so that you can make non-blocking calls to our API.
+
+```python
+import asyncio
+
+from sarvamai import AsyncSarvamAI
+
+client = AsyncSarvamAI(
+    api_subscription_key="YOUR_API_SUBSCRIPTION_KEY",
+)
+
+
+async def main() -> None:
+    await client.text.translate(
+        input="input",
+        source_language_code="auto",
+        target_language_code="bn-IN",
+    )
+
+
+asyncio.run(main())
+```
+
+## Exception Handling
+
+When the API returns a non-success status code (4xx or 5xx response), a subclass of the following error
+will be thrown.
+
+```python
+from sarvamai.core.api_error import ApiError
+
+try:
+    client.text.translate(...)
+except ApiError as e:
+    print(e.status_code)
+    print(e.body)
+```
+
+## Advanced
+
+### Retries
+
+The SDK is instrumented with automatic retries with exponential backoff. A request will be retried as long
+as the request is deemed retryable and the number of retry attempts has not grown larger than the configured
+retry limit (default: 2).
+
+A request is deemed retryable when any of the following HTTP status codes is returned:
+
+- [408](https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/408) (Timeout)
+- [429](https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429) (Too Many Requests)
+- [5XX](https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/500) (Internal Server Errors)
+
+Use the `max_retries` request option to configure this behavior.
+
+```python
+client.text.translate(..., request_options={
+    "max_retries": 1
+})
+```
+
+### Timeouts
+
+The SDK defaults to a 60 second timeout. You can configure this with a timeout option at the client or request level.
+
+```python
+
+from sarvamai import SarvamAI
+
+client = SarvamAI(
+    ...,
+    timeout=20.0,
+)
+
+
+# Override timeout for a specific method
+client.text.translate(..., request_options={
+    "timeout_in_seconds": 1
+})
+```
+
+### Custom Client
+
+You can override the `httpx` client to customize it for your use-case. Some common use-cases include support for proxies
+and transports.
+
+```python
+import httpx
+from sarvamai import SarvamAI
+
+client = SarvamAI(
+    ...,
+    httpx_client=httpx.Client(
+        proxies="http://my.test.proxy.example.com",
+        transport=httpx.HTTPTransport(local_address="0.0.0.0"),
+    ),
+)
+```
+
+## Contributing
+
+While we value open-source contributions to this SDK, this library is generated programmatically.
+Additions made directly to this library would have to be moved over to our generation code,
+otherwise they would be overwritten upon the next generated release. Feel free to open a PR as
+a proof of concept, but know that we will not be able to merge it as-is. We suggest opening
+an issue first to discuss with us!
+
+On the other hand, contributions to the README are always very welcome!

{sarvamai-0.1.5a5 → sarvamai-0.1.5a6}/pyproject.toml

@@ -3,7 +3,7 @@ name = "sarvamai"
 
 [tool.poetry]
 name = "sarvamai"
-version = "0.1.5a5"
+version = "0.1.5a6"
 description = ""
 readme = "README.md"
 authors = []
@@ -39,15 +39,14 @@ httpx = ">=0.21.2"
 pydantic = ">= 1.9.2"
 pydantic-core = "^2.18.2"
 typing_extensions = ">= 4.0.0"
-websockets = "12.0"
 
-[tool.poetry.group.dev.dependencies]
-mypy = "==1.13.0"
+[tool.poetry.dev-dependencies]
+mypy = "1.0.1"
 pytest = "^7.4.0"
 pytest-asyncio = "^0.23.5"
 python-dateutil = "^2.9.0"
 types-python-dateutil = "^2.9.0.20240316"
-ruff = "==0.11.5"
+ruff = "^0.5.6"
 
 [tool.pytest.ini_options]
 testpaths = [ "tests" ]
@@ -59,26 +58,6 @@ plugins = ["pydantic.mypy"]
 [tool.ruff]
 line-length = 120
 
-[tool.ruff.lint]
-select = [
-    "E",  # pycodestyle errors
-    "F",  # pyflakes
-    "I",  # isort
-]
-ignore = [
-    "E402",  # Module level import not at top of file
-    "E501",  # Line too long
-    "E711",  # Comparison to `None` should be `cond is not None`
-    "E712",  # Avoid equality comparisons to `True`; use `if ...:` checks
-    "E721",  # Use `is` and `is not` for type comparisons, or `isinstance()` for insinstance checks
-    "E722",  # Do not use bare `except`
-    "E731",  # Do not assign a `lambda` expression, use a `def`
-    "F821",  # Undefined name
-    "F841"   # Local variable ... is assigned to but never used
-]
-
-[tool.ruff.lint.isort]
-section-order = ["future", "standard-library", "third-party", "first-party"]
 
 [build-system]
 requires = ["poetry-core"]

{sarvamai-0.1.5a5 → sarvamai-0.1.5a6}/src/sarvamai/__init__.py

@@ -1,11 +1,6 @@
 # This file was auto-generated by Fern from our API Definition.
 
-# isort: skip_file
-
 from .types import (
-    AudioData,
-    AudioDataEncoding,
-    AudioMessage,
     ChatCompletionRequestAssistantMessage,
     ChatCompletionRequestMessage,
     ChatCompletionRequestMessage_Assistant,
@@ -20,12 +15,9 @@ from .types import (
     DiarizedEntry,
     DiarizedTranscript,
     ErrorCode,
-    ErrorData,
     ErrorDetails,
     ErrorMessage,
-    EventsData,
     FinishReason,
-    Format,
     LanguageIdentificationResponse,
     NumeralsFormat,
     ReasoningEffort,
@@ -35,9 +27,6 @@ from .types import (
     SpeechToTextLanguage,
     SpeechToTextModel,
     SpeechToTextResponse,
-    SpeechToTextStreamingResponse,
-    SpeechToTextStreamingResponseData,
-    SpeechToTextStreamingResponseType,
     SpeechToTextTranslateLanguage,
     SpeechToTextTranslateModel,
     SpeechToTextTranslateResponse,
@@ -48,8 +37,6 @@ from .types import (
     TextToSpeechResponse,
     TextToSpeechSpeaker,
     TimestampsModel,
-    TranscriptionData,
-    TranscriptionMetrics,
     TranslateMode,
     TranslateModel,
     TranslateSourceLanguage,
@@ -69,12 +56,10 @@ from .errors import (
     TooManyRequestsError,
     UnprocessableEntityError,
 )
-from . import chat, speech_to_text, speech_to_text_streaming, text, text_to_speech
+from . import chat, speech_to_text, text, text_to_speech
 from .client import AsyncSarvamAI, SarvamAI
 from .environment import SarvamAIEnvironment
 from .requests import (
-    AudioDataParams,
-    AudioMessageParams,
     ChatCompletionRequestAssistantMessageParams,
     ChatCompletionRequestMessageParams,
     ChatCompletionRequestMessage_AssistantParams,
@@ -88,33 +73,21 @@ from .requests import (
     CreateChatCompletionResponseParams,
     DiarizedEntryParams,
     DiarizedTranscriptParams,
-    ErrorDataParams,
     ErrorDetailsParams,
     ErrorMessageParams,
-    EventsDataParams,
     LanguageIdentificationResponseParams,
     SpeechToTextResponseParams,
-    SpeechToTextStreamingResponseDataParams,
-    SpeechToTextStreamingResponseParams,
     SpeechToTextTranslateResponseParams,
     StopConfigurationParams,
     TextToSpeechResponseParams,
     TimestampsModelParams,
-    TranscriptionDataParams,
-    TranscriptionMetricsParams,
     TranslationResponseParams,
     TransliterationResponseParams,
 )
-from .speech_to_text_streaming import SpeechToTextStreamingLanguageCode, SpeechToTextStreamingModel
 from .version import __version__
 
 __all__ = [
     "AsyncSarvamAI",
-    "AudioData",
-    "AudioDataEncoding",
-    "AudioDataParams",
-    "AudioMessage",
-    "AudioMessageParams",
     "BadRequestError",
     "ChatCompletionRequestAssistantMessage",
     "ChatCompletionRequestAssistantMessageParams",
@@ -143,17 +116,12 @@ __all__ = [
     "DiarizedTranscript",
     "DiarizedTranscriptParams",
     "ErrorCode",
-    "ErrorData",
-    "ErrorDataParams",
     "ErrorDetails",
     "ErrorDetailsParams",
     "ErrorMessage",
     "ErrorMessageParams",
-    "EventsData",
-    "EventsDataParams",
     "FinishReason",
     "ForbiddenError",
-    "Format",
     "InternalServerError",
     "LanguageIdentificationResponse",
     "LanguageIdentificationResponseParams",
@@ -169,13 +137,6 @@ __all__ = [
     "SpeechToTextModel",
     "SpeechToTextResponse",
     "SpeechToTextResponseParams",
-    "SpeechToTextStreamingLanguageCode",
-    "SpeechToTextStreamingModel",
-    "SpeechToTextStreamingResponse",
-    "SpeechToTextStreamingResponseData",
-    "SpeechToTextStreamingResponseDataParams",
-    "SpeechToTextStreamingResponseParams",
-    "SpeechToTextStreamingResponseType",
     "SpeechToTextTranslateLanguage",
     "SpeechToTextTranslateModel",
     "SpeechToTextTranslateResponse",
@@ -191,10 +152,6 @@ __all__ = [
     "TimestampsModel",
     "TimestampsModelParams",
     "TooManyRequestsError",
-    "TranscriptionData",
-    "TranscriptionDataParams",
-    "TranscriptionMetrics",
-    "TranscriptionMetricsParams",
     "TranslateMode",
     "TranslateModel",
     "TranslateSourceLanguage",
@@ -211,7 +168,6 @@ __all__ = [
     "__version__",
     "chat",
     "speech_to_text",
-    "speech_to_text_streaming",
     "text",
     "text_to_speech",
 ]

{sarvamai-0.1.5a5 → sarvamai-0.1.5a6}/src/sarvamai/chat/__init__.py

@@ -1,4 +1,2 @@
 # This file was auto-generated by Fern from our API Definition.
 
-# isort: skip_file
-

{sarvamai-0.1.5a5 → sarvamai-0.1.5a6}/src/sarvamai/chat/client.py

@@ -1,14 +1,15 @@
 # This file was auto-generated by Fern from our API Definition.
 
 import typing
-
-from ..core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
-from ..core.request_options import RequestOptions
+from ..core.client_wrapper import SyncClientWrapper
+from .raw_client import RawChatClient
 from ..requests.chat_completion_request_message import ChatCompletionRequestMessageParams
+from ..types.reasoning_effort import ReasoningEffort
 from ..requests.stop_configuration import StopConfigurationParams
+from ..core.request_options import RequestOptions
 from ..types.create_chat_completion_response import CreateChatCompletionResponse
-from ..types.reasoning_effort import ReasoningEffort
-from .raw_client import AsyncRawChatClient, RawChatClient
+from ..core.client_wrapper import AsyncClientWrapper
+from .raw_client import AsyncRawChatClient
 
 # this is used as the default value for optional parameters
 OMIT = typing.cast(typing.Any, ...)
@@ -116,7 +117,7 @@ class ChatClient:
             messages=[{"content": "content", "role": "assistant"}],
         )
         """
-        _response = self._raw_client.completions(
+        response = self._raw_client.completions(
             messages=messages,
             temperature=temperature,
             top_p=top_p,
@@ -131,7 +132,7 @@ class ChatClient:
             wiki_grounding=wiki_grounding,
             request_options=request_options,
         )
-        return _response.data
+        return response.data
 
 
 class AsyncChatClient:
@@ -244,7 +245,7 @@ class AsyncChatClient:
 
         asyncio.run(main())
         """
-        _response = await self._raw_client.completions(
+        response = await self._raw_client.completions(
             messages=messages,
             temperature=temperature,
             top_p=top_p,
@@ -259,4 +260,4 @@ class AsyncChatClient:
             wiki_grounding=wiki_grounding,
             request_options=request_options,
         )
-        return _response.data
+        return response.data