Commit Graph

4620 Commits

Author SHA1 Message Date
Filipi Fuchter
3039a1444e Refactoring the TavusVideoService to match the same the behavior of the bot started speaking and bot stopped speaking. 2025-05-27 10:26:41 -03:00
Mark Backman
aa7d15beb3 fix: move LLM call outside tracing try block to prevent double execution 2025-05-26 22:06:31 -04:00
Filipi Fuchter
2b3d2cb342 Fixing the issue when using the TavusVideoService with some TTS services. 2025-05-26 22:55:20 -03:00
Filipi Fuchter
5a58357429 Fixing the issue when using the TavusTransport with some TTS services. 2025-05-26 18:34:52 -03:00
Mark Backman
366add2536 Merge pull request #1878 from pipecat-ai/mb/add-plivo-serializer
Add PlivoFrameSerializer
2025-05-26 11:07:13 -04:00
Mark Backman
e13c9fd42e Add PlivoFrameSerializer 2025-05-26 11:00:01 -04:00
Mark Backman
2a6c01f634 Merge pull request #1885 from pipecat-ai/mb/update-langfuse-example 2025-05-26 10:14:02 -04:00
Mark Backman
bf29722e78 Merge pull request #1884 from pipecat-ai/mb/readme-otel-twilio-telnyx 2025-05-26 10:13:23 -04:00
Mark Backman
db227ad15f Merge pull request #1897 from pipecat-ai/mb/fix-websocket-client-example
Fix mismatched html tag in websocket client example
2025-05-26 09:26:53 -04:00
Mark Backman
514716042b Fix mismatched html tag in websocket client example 2025-05-26 08:25:03 -04:00
Aleix Conchillo Flaqué
7a767e680c more avoiding mutable default constructor values 2025-05-25 21:00:35 -07:00
Martin Schweiger
320b52eb1e Merge branch 'm-ods/assemblyai-universal-streaming' of https://github.com/m-ods/pipecat into m-ods/assemblyai-universal-streaming 2025-05-26 09:13:08 +08:00
Martin Schweiger
428cee75c5 Add User-Agent header to AssemblyAI websocket connection 2025-05-26 09:10:55 +08:00
Martin Schweiger
5479a55b2c Add websockets dependency to assemblyai extra 2025-05-26 09:08:56 +08:00
Mark Backman
d1f2a5d04f Merge pull request #1868 from aristid/google-streaming-tts
Add Google streaming TTS as a base TTS service
2025-05-24 12:42:47 -04:00
aristid
09ba319f3e Merge branch 'main' into google-streaming-tts 2025-05-24 17:16:22 +02:00
ezun-kim
3da711ba8b Fix SSE server connection handling for MCP client
### Summary
This PR improves the MCP (Model Context Protocol) client's SSE (Server-Sent Events) server connection handling by replacing the generic string parameter with a proper `SseServerParameters` class.

### Changes
- **Breaking Change**: Changed `server_params` type from `Union[StdioServerParameters, str]` to `Union[StdioServerParameters, SseServerParameters]`
- Added import for `SseServerParameters` from `mcp.client.session_group`
- Updated SSE client connection to use structured parameters instead of a simple URL string
- Fixed error message to correctly reflect the expected parameter types
- Improved logging by changing info-level log to debug-level for consistency

### Details

#### Before
The SSE client connection only accepted a URL string:
```python
async with self._client(self._server_params) as (read, write):
```

#### After
Now properly unpacks SSE server parameters:
```python
async with self._client(
    url=self._server_params.url,
    headers=self._server_params.headers,
    timeout=self._server_params.timeout,
    sse_read_timeout=self._server_params.sse_read_timeout
) as (read, write):
```

### Benefits
- **Type Safety**: Stronger type checking with dedicated `SseServerParameters` class
- **Extended Configuration**: Support for custom headers (authentication), timeouts, and SSE-specific settings
- **Better Error Messages**: Clear type error messages when incorrect parameters are provided
- **Improved Debugging**: Debug logging of SSE server parameters for troubleshooting

### Migration Guide
Users need to update their SSE server initialization:
```python
# Before
client = MCPClient("https://example.com/sse")

# After
from mcp.client.session_group import SseServerParameters
client = MCPClient(SseServerParameters(
    url="https://example.com/sse",
    headers={"Authorization": "Bearer token"},
    timeout=30,
    sse_read_timeout=60
))
```

### Testing
- [ ] Tested with StdioServerParameters (unchanged behavior)
- [ ] Tested with SseServerParameters with various configurations
- [ ] Verified error handling for invalid parameter types

---

This is a necessary change to support production-ready SSE connections with proper authentication and timeout handling.
2025-05-24 22:35:57 +09:00
Mark Backman
6f524fb816 Add LLM response to OTel tracing 2025-05-24 09:15:39 -04:00
unknown
d3e2a9e5c0 Change default voice and fix formatting 2025-05-24 15:14:39 +02:00
Mark Backman
b4cd7d7941 Langfuse OTel env.example improvements 2025-05-24 08:17:10 -04:00
Mark Backman
cd03b91115 Update README: Add OTel, Add serializers 2025-05-24 07:23:59 -04:00
Aleix Conchillo Flaqué
f86d002ceb Merge pull request #1881 from pipecat-ai/aleix/daily-input-audio-and-video-task-fix
daily input audio and video task fix
2025-05-23 19:39:25 -07:00
Aleix Conchillo Flaqué
940926b5ec TavusVideoService: no need to enable audio/video outputs 2025-05-23 19:29:34 -07:00
Aleix Conchillo Flaqué
85c096df0b DailyTransport: create audio/video input tasks when input flag is enabled 2025-05-23 19:28:18 -07:00
Filipi da Silva Fuchter
76d93522ac Merge pull request #1820 from pipecat-ai/tavus_video_service
Tavus improvements
2025-05-23 23:11:00 -03:00
Filipi Fuchter
31492831cc Updating the changelog and readme to reflect the Tavus changes. 2025-05-23 23:04:04 -03:00
Filipi Fuchter
8221dd594e Creating a Tavus example using the DailyTransport. 2025-05-23 23:03:40 -03:00
Filipi Fuchter
6346ca1a84 Creating a Tavus example using the SmallWebRTCTransport. 2025-05-23 23:03:24 -03:00
Filipi Fuchter
4a3404883f Creating a Tavus example using the new TavusTransport. 2025-05-23 23:03:16 -03:00
Filipi Fuchter
1ebca35313 Queuing the app messages if the SmallWebrtcTransport is not connected yet. 2025-05-23 23:03:04 -03:00
Filipi Fuchter
e0d1381f87 Refactoring the TavusVideoService to allow to work with any transport. 2025-05-23 23:02:49 -03:00
Filipi Fuchter
86e6841569 Creating TavusTransport and TavusTransportClient. 2025-05-23 23:02:37 -03:00
Aleix Conchillo Flaqué
28b7a92a00 Merge pull request #1880 from pipecat-ai/aleix/daily-resize-event-loop-fix
BaseOutputTransport: don't block event loop during image resize
2025-05-23 18:32:00 -07:00
Aleix Conchillo Flaqué
4db5b18694 BaseOutputTransport: don't block event loop during image resize 2025-05-23 18:30:28 -07:00
Aleix Conchillo Flaqué
a628e921c0 Merge pull request #1879 from pipecat-ai/aleix/daily-fix-video-task
DailyTransport: fix video task variable
2025-05-23 17:56:08 -07:00
Aleix Conchillo Flaqué
6ca6ff37c9 DailyTransport: fix video task variable 2025-05-23 17:54:25 -07:00
Aleix Conchillo Flaqué
456db3710a Merge pull request #1828 from pipecat-ai/aleix/daily-use-audio-renderers
DailyTransport: replace virtual speaker and microphones
2025-05-23 13:31:51 -07:00
Aleix Conchillo Flaqué
50f024c6f9 LiveKitTransport: use UserAudioRawFrame instead of InputAudioRawFrame 2025-05-23 11:27:53 -07:00
Aleix Conchillo Flaqué
a4de75a8c0 Merge pull request #1867 from pipecat-ai/aleix/user-bot-latency-log-observer
observers: added UserBotLatencyLogObserver
2025-05-23 09:23:03 -07:00
Aleix Conchillo Flaqué
88e8fcdaca observers: added UserBotLatencyLogObserver 2025-05-23 09:17:53 -07:00
unknown
bfe9952c9a Remove sleep(0), add doc string etc. 2025-05-23 12:11:08 +02:00
Martin Schweiger
7f568e3e7e Merge branch 'main' into m-ods/assemblyai-universal-streaming 2025-05-23 17:39:00 +08:00
Martin Schweiger
9b8800ac1d update stt.py 2025-05-23 17:32:31 +08:00
Martin Schweiger
fd53712567 add models for new streaming service 2025-05-23 17:32:12 +08:00
Aleix Conchillo Flaqué
7f74c2465c SileroVADAnalyzer: improve non-matching sample rate log 2025-05-23 01:47:09 -07:00
Aleix Conchillo Flaqué
30d67a78eb examples(chatbot-audio-recording): use same sample rate to avoid downsampling 2025-05-23 01:47:09 -07:00
Aleix Conchillo Flaqué
c3cfd1f0ce DailyTransport: process audio, video and event callbacks in separate tasks 2025-05-23 01:47:09 -07:00
Aleix Conchillo Flaqué
69ac70eed8 DailyTransport: replace virtual microphone with custom microphone track 2025-05-23 01:47:09 -07:00
Aleix Conchillo Flaqué
fcf49e79cc DailyTransport: use participant audio renderers instead of virtual speaker 2025-05-23 01:47:09 -07:00
Aleix Conchillo Flaqué
8d4894846d pyproject: update to daily-python 0.19.0 2025-05-23 01:47:09 -07:00