wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
3,945 Commits 276 Branches 111 Tags
3da711ba8b4aaa1d1ef4f4f6aa45406b18719b5c
Commit Graph

3945 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
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
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
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
Vanessa Pyne
a809b710c5 Merge pull request #1844 from pipecat-ai/vp-docsinreadme 
add docs link at top of readme
 2025-05-22 21:52:18 -05:00
vipyne
f6289e9db2 add docs link at top of readme 2025-05-22 21:51:29 -05:00
Mark Backman
26b4c4df22 Merge pull request #1870 from pipecat-ai/mb/gemini-2.5-flash-update 
Update GeminiMultimodalLiveLLMService to use Gemini 2.5 Flash Native …
 2025-05-22 18:19:55 -04:00
Mark Backman
f3a9844295 Merge pull request #1860 from pipecat-ai/mb/organize-otel-demos 
Reorganize OpenTelemetry demos, add top-level README
 2025-05-22 18:15:20 -04:00
Mark Backman
692821bdae Merge pull request #1873 from pipecat-ai/mb/readme-sarvam 
Add SarvamTTSService to README
 2025-05-22 18:14:40 -04:00
Mark Backman
ee143d5b3a Update GeminiMultimodalLiveLLMService to use Gemini 2.5 Flash Native Audio Dialog model 2025-05-22 18:13:41 -04:00
Mark Backman
7e178a634a Merge pull request #1871 from pipecat-ai/mb/claude-sonnet-4-update 
Update default model for Anthropic to Claude Sonnet 4
 2025-05-22 18:12:47 -04:00
Mark Backman
fe88a3d80b Add SarvamTTSService to README 2025-05-22 18:11:11 -04:00
Mark Backman
a196eac290 Merge pull request #1872 from pipecat-ai/mb/add-sarvam-tts 
Add SarvamTTSService
 2025-05-22 18:02:36 -04:00
Mark Backman
3c819955a2 Add SarvamTTSService 2025-05-22 16:23:08 -04:00
Mark Backman
ca0d7bbbed Update default model for Anthropic to Claude Sonnet 4 2025-05-22 15:13:33 -04:00
Mark Backman
f93bd1e817 Merge pull request #1864 from pipecat-ai/mb/fix-11lab-set-model-voice 
Fix: ElevenLabsTTSService, change voice and model
 2025-05-22 14:36:24 -04:00
Mark Backman
415bc6ca0a Fix: ElevenLabsTTSService, change voice and model 2025-05-22 14:28:50 -04:00
Mark Backman
8543c8d11d Merge pull request #1869 from pipecat-ai/mb/update-readme-nova-sonic 
Add AWS Nova Sonic to README
 2025-05-22 14:07:35 -04:00
Mark Backman
bf5ad64575 Add AWS Nova Sonic to README 2025-05-22 14:03:28 -04:00
Aleix Conchillo Flaqué
0718f79ff2 Merge pull request #1866 from pipecat-ai/aleix/base-observers-are-base-objects 
BaseObserver: inherit from BaseObject so we can have events
 2025-05-21 16:07:38 -07:00
Aleix Conchillo Flaqué
9bbce225ce BaseObserver: inherit from BaseObject so we can have events 2025-05-21 16:04:44 -07:00
Mark Backman
fb35fd6d71 Merge pull request #1859 from pipecat-ai/mb/otel-attribute-naming 
Update OTel attribute names
 2025-05-21 12:10:15 -04:00
Mark Backman
b4fd92aed6 Merge pull request #1862 from marctorsoc/clean-links-in-md-text-filter 
Add link cleaning in MD text filter
 2025-05-21 09:20:27 -04:00
Mark Backman
36931825b3 Merge pull request #1854 from sklinglernv/fix/elevenlab-tts 
fix(elevenlabs tts): message parameter naming
 2025-05-21 09:17:29 -04:00
marc.torsoc
ca35299dcd add link cleaning and a test for it 2025-05-21 12:08:53 +02:00
Severin Klingler
e74b900914 revert most of the changes except keyword naming fix 2025-05-21 09:24:03 +02:00
Mark Backman
25115668a7 Reorganize OpenTelemetry demos, add top-level README 2025-05-20 23:30:46 -04:00
Mark Backman
fb94db3e64 Update to use GenAI naming 2025-05-20 22:56:02 -04:00