AssemblyAI added EU streaming endpoint option #4571
Conversation
|
|
📝 WalkthroughWalkthroughAdds an Changes
Sequence Diagram(s)sequenceDiagram
participant Client
participant STT
participant SpeechStream
participant AssemblyAI_WS
Client->>STT: request stream(start, optional endpoint_url)
STT->>SpeechStream: create stream(..., endpoint_url)
SpeechStream->>AssemblyAI_WS: open WebSocket at endpoint_url
SpeechStream->>AssemblyAI_WS: send audio frames
AssemblyAI_WS-->>SpeechStream: deliver transcription events
SpeechStream-->>STT: forward transcriptions
STT-->>Client: emit transcription results
Estimated code review effort🎯 2 (Simple) | ⏱️ ~8 minutes Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches
📜 Recent review detailsConfiguration used: Organization UI Review profile: CHILL Plan: Pro 📒 Files selected for processing (1)
🧰 Additional context used📓 Path-based instructions (1)**/*.py📄 CodeRabbit inference engine (AGENTS.md)
Files:
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (2)
🔇 Additional comments (2)
✏️ Tip: You can disable this entire section by setting Comment |
longcw
left a comment
longcw
left a comment
There was a problem hiding this comment.
looks good to me! something nit
livekit-plugins/livekit-plugins-assemblyai/livekit/plugins/assemblyai/stt.py
Outdated
Show resolved
Hide resolved
| conn_options: APIConnectOptions, | ||
| api_key: str, | ||
| http_session: aiohttp.ClientSession, | ||
| endpoint_url: str, |
There was a problem hiding this comment.
can you move this to the conn_options?
There was a problem hiding this comment.
i'm not quite sure what you mean.
The conn_options is a shared object not in the AssemblyAI module. So i can't just add an other property here: https://github.com/livekit/agents/blob/main/livekit-agents/livekit/agents/types.py#L54
Could you suggest how/what to change?
Thank you!
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Fix all issues with AI agents
In
`@livekit-plugins/livekit-plugins-assemblyai/livekit/plugins/assemblyai/stt.py`:
- Around line 80-86: The docstring for the parameter endpoint_url is incomplete;
update the parameter description (in the function/method docstring that includes
endpoint_url) to explicitly state the default endpoint, e.g. "Defaults to the US
endpoint (wss://streaming.assemblyai.com/v3/ws)." Ensure the sentence replaces
the dangling "Defaults to US" phrase and clearly names the default URL.
- Around line 359-365: The URL building currently concatenates
self._endpoint_url and a new query string which breaks if self._endpoint_url
already contains query params; instead parse self._endpoint_url (using
urllib.parse.urlparse), merge its existing query params (urllib.parse.parse_qs)
with the filtered_config dict (ensuring boolean -> "true"/"false" conversion
already in filtered_config), flatten/encode the combined params with
urllib.parse.urlencode(doseq=True), reconstruct the full URL with
urllib.parse.urlunparse, and then call await self._session.ws_connect(url,
headers=headers); update the logic around filtered_config, self._endpoint_url,
urlencode, and the ws_connect call to use the merged-safe URL.
📜 Review details
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
livekit-plugins/livekit-plugins-assemblyai/livekit/plugins/assemblyai/stt.py
🧰 Additional context used
📓 Path-based instructions (1)
**/*.py
📄 CodeRabbit inference engine (AGENTS.md)
**/*.py: Format code with ruff
Run ruff linter and auto-fix issues
Run mypy type checker in strict mode
Maintain line length of 100 characters maximum
Ensure Python 3.9+ compatibility
Use Google-style docstrings
Files:
livekit-plugins/livekit-plugins-assemblyai/livekit/plugins/assemblyai/stt.py
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (3)
- GitHub Check: type-check (3.9)
- GitHub Check: unit-tests
- GitHub Check: type-check (3.13)
🔇 Additional comments (2)
livekit-plugins/livekit-plugins-assemblyai/livekit/plugins/assemblyai/stt.py (2)
95-156: Endpoint URL is correctly threaded into new streams.This cleanly ensures all streams use the configured endpoint.
200-208: SpeechStream stores endpoint URL cleanly.No concerns with the propagation pattern here.
✏️ Tip: You can disable this entire section by setting review_details to false in your review settings.
livekit-plugins/livekit-plugins-assemblyai/livekit/plugins/assemblyai/stt.py
Show resolved
Hide resolved
| filtered_config = { | ||
| k: ("true" if v else "false") if isinstance(v, bool) else v | ||
| for k, v in live_config.items() | ||
| if v is not None | ||
| } | ||
| url = f"{ws_url}?{urlencode(filtered_config)}" | ||
| url = f"{self._endpoint_url}?{urlencode(filtered_config)}" | ||
| ws = await self._session.ws_connect(url, headers=headers) |
There was a problem hiding this comment.
Build the WS URL safely if endpoint_url already has query params.
f"{self._endpoint_url}?..." will produce an invalid URL if the caller includes existing query parameters (double ?). Safer to merge queries.
🛠️ Proposed fix
-from urllib.parse import urlencode
+from urllib.parse import parse_qsl, urlencode, urlsplit, urlunsplit
@@
- url = f"{self._endpoint_url}?{urlencode(filtered_config)}"
+ split = urlsplit(self._endpoint_url)
+ query = dict(parse_qsl(split.query))
+ query.update(filtered_config)
+ url = urlunsplit((split.scheme, split.netloc, split.path, urlencode(query), split.fragment))📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| filtered_config = { | |
| k: ("true" if v else "false") if isinstance(v, bool) else v | |
| for k, v in live_config.items() | |
| if v is not None | |
| } | |
| url = f"{ws_url}?{urlencode(filtered_config)}" | |
| url = f"{self._endpoint_url}?{urlencode(filtered_config)}" | |
| ws = await self._session.ws_connect(url, headers=headers) | |
| filtered_config = { | |
| k: ("true" if v else "false") if isinstance(v, bool) else v | |
| for k, v in live_config.items() | |
| if v is not None | |
| } | |
| split = urlsplit(self._endpoint_url) | |
| query = dict(parse_qsl(split.query)) | |
| query.update(filtered_config) | |
| url = urlunsplit((split.scheme, split.netloc, split.path, urlencode(query), split.fragment)) | |
| ws = await self._session.ws_connect(url, headers=headers) |
🤖 Prompt for AI Agents
In `@livekit-plugins/livekit-plugins-assemblyai/livekit/plugins/assemblyai/stt.py`
around lines 359 - 365, The URL building currently concatenates
self._endpoint_url and a new query string which breaks if self._endpoint_url
already contains query params; instead parse self._endpoint_url (using
urllib.parse.urlparse), merge its existing query params (urllib.parse.parse_qs)
with the filtered_config dict (ensuring boolean -> "true"/"false" conversion
already in filtered_config), flatten/encode the combined params with
urllib.parse.urlencode(doseq=True), reconstruct the full URL with
urllib.parse.urlunparse, and then call await self._session.ws_connect(url,
headers=headers); update the logic around filtered_config, self._endpoint_url,
urlencode, and the ws_connect call to use the merged-safe URL.
| keyterms_prompt: NotGivenOr[list[str]] = NOT_GIVEN, | ||
| http_session: aiohttp.ClientSession | None = None, | ||
| buffer_size_seconds: float = 0.05, | ||
| endpoint_url: str = "wss://streaming.assemblyai.com/v3/ws", |
There was a problem hiding this comment.
do you want this to be a base_url instead? do you expect the /v3/ws parameter to be modifiable.
4 participants
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.