feat(client): add support for streaming raw responses

README.md

@@ -414,7 +414,7 @@ if response.my_field is None:
 
 ### Accessing raw response data (e.g. headers)
 
-The "raw" Response object can be accessed by prefixing `.with_raw_response.` to any HTTP method call.
+The "raw" Response object can be accessed by prefixing `.with_raw_response.` to any HTTP method call, e.g.,
 
 ```py
 from openai import OpenAI
@@ -433,7 +433,40 @@ completion = response.parse()  # get the object that `chat.completions.create()`
 print(completion)
 ```
 
-These methods return an [`APIResponse`](https://github.com/openai/openai-python/tree/main/src/openai/_response.py) object.
+These methods return an [`LegacyAPIResponse`](https://github.com/openai/openai-python/tree/main/src/openai/_legacy_response.py) object. This is a legacy class as we're changing it slightly in the next major version.
+
+For the sync client this will mostly be the same with the exception
+of `content` & `text` will be methods instead of properties. In the
+async client, all methods will be async.
+
+A migration script will be provided & the migration in general should
+be smooth.
+
+#### `.with_streaming_response`
+
+The above interface eagerly reads the full response body when you make the request, which may not always be what you want.
+
+To stream the response body, use `.with_streaming_response` instead, which requires a context manager and only reads the response body once you call `.read()`, `.text()`, `.json()`, `.iter_bytes()`, `.iter_text()`, `.iter_lines()` or `.parse()`. In the async client, these are async methods.
+
+As such, `.with_streaming_response` methods return a different [`APIResponse`](https://github.com/openai/openai-python/tree/main/src/openai/_response.py) object, and the async client returns an [`AsyncAPIResponse`](https://github.com/openai/openai-python/tree/main/src/openai/_response.py) object.
+
+```python
+with client.chat.completions.with_streaming_response.create(
+    messages=[
+        {
+            "role": "user",
+            "content": "Say this is a test",
+        }
+    ],
+    model="gpt-3.5-turbo",
+) as response:
+    print(response.headers.get("X-My-Header"))
+
+    for line in response.iter_lines():
+        print(line)
+```
+
+The context manager is required so that the response will reliably be closed.
 
 ### Configuring the HTTP client
 

examples/audio.py

@@ -12,14 +12,18 @@
 
 def main() -> None:
     # Create text-to-speech audio file
-    response = openai.audio.speech.create(
-        model="tts-1", voice="alloy", input="the quick brown fox jumped over the lazy dogs"
-    )
-
-    response.stream_to_file(speech_file_path)
+    with openai.audio.speech.with_streaming_response.create(
+        model="tts-1",
+        voice="alloy",
+        input="the quick brown fox jumped over the lazy dogs",
+    ) as response:
+        response.stream_to_file(speech_file_path)
 
     # Create transcription from audio file
-    transcription = openai.audio.transcriptions.create(model="whisper-1", file=speech_file_path)
+    transcription = openai.audio.transcriptions.create(
+        model="whisper-1",
+        file=speech_file_path,
+    )
     print(transcription.text)
 
     # Create translation from audio file

src/openai/__init__.py

@@ -10,6 +10,7 @@
 from ._utils import file_from_path
 from ._client import Client, OpenAI, Stream, Timeout, Transport, AsyncClient, AsyncOpenAI, AsyncStream, RequestOptions
 from ._version import __title__, __version__
+from ._response import APIResponse as APIResponse, AsyncAPIResponse as AsyncAPIResponse
 from ._exceptions import (
     APIError,
     OpenAIError,