From 4fd8df208f63733a2733759c3ecb4c172c7402d1 Mon Sep 17 00:00:00 2001
From: getchannel <78183014+getchannel@users.noreply.github.com>
Date: Fri, 30 May 2025 18:07:09 -0400
Subject: [PATCH] Add groundingMetadata events.py

---
 .../services/gemini_multimodal_live/events.py | 68 +++++++++++++++++--
 1 file changed, 64 insertions(+), 4 deletions(-)

diff --git a/src/pipecat/services/gemini_multimodal_live/events.py b/src/pipecat/services/gemini_multimodal_live/events.py
index b70e2bf3e..6df94148b 100644
--- a/src/pipecat/services/gemini_multimodal_live/events.py
+++ b/src/pipecat/services/gemini_multimodal_live/events.py
@@ -12,6 +12,7 @@ import json
 from enum import Enum
 from typing import List, Literal, Optional
 
+from loguru import logger
 from PIL import Image
 from pydantic import BaseModel, Field
 
@@ -247,6 +248,49 @@ class Config(BaseModel):
     setup: Setup
 
 
+#
+# Grounding metadata models
+#
+
+
+class SearchEntryPoint(BaseModel):
+    """Represents the search entry point with rendered content for search suggestions."""
+    renderedContent: Optional[str] = None
+
+
+class WebSource(BaseModel):
+    """Represents a web source from grounding chunks."""
+    uri: Optional[str] = None
+    title: Optional[str] = None
+
+
+class GroundingChunk(BaseModel):
+    """Represents a grounding chunk containing web source information."""
+    web: Optional[WebSource] = None
+
+
+class GroundingSegment(BaseModel):
+    """Represents a segment of text that is grounded."""
+    startIndex: Optional[int] = None
+    endIndex: Optional[int] = None
+    text: Optional[str] = None
+
+
+class GroundingSupport(BaseModel):
+    """Represents support information for grounded text segments."""
+    segment: Optional[GroundingSegment] = None
+    groundingChunkIndices: Optional[List[int]] = None
+    confidenceScores: Optional[List[float]] = None
+
+
+class GroundingMetadata(BaseModel):
+    """Represents grounding metadata from Google Search."""
+    searchEntryPoint: Optional[SearchEntryPoint] = None
+    groundingChunks: Optional[List[GroundingChunk]] = None
+    groundingSupports: Optional[List[GroundingSupport]] = None
+    webSearchQueries: Optional[List[str]] = None
+
+
 #
 # Server events
 #
@@ -338,6 +382,7 @@ class ServerContent(BaseModel):
     turnComplete: Optional[bool] = None
     inputTranscription: Optional[BidiGenerateContentTranscription] = None
     outputTranscription: Optional[BidiGenerateContentTranscription] = None
+    groundingMetadata: Optional[GroundingMetadata] = None
 
 
 class FunctionCall(BaseModel):
@@ -430,7 +475,7 @@ class ServerEvent(BaseModel):
     usageMetadata: Optional[UsageMetadata] = None
 
 
-def parse_server_event(str):
+def parse_server_event(message_str):
     """Parse a server event from JSON string.
 
     Args:
@@ -439,11 +484,26 @@ def parse_server_event(str):
     Returns:
         ServerEvent instance if parsing succeeds, None otherwise.
     """
+    from loguru import logger  # Import logger locally to avoid scoping issues
+    
     try:
-        evt = json.loads(str)
-        return ServerEvent.model_validate(evt)
+        evt_dict = json.loads(message_str)
+        
+        # Only log grounding metadata detection if truly needed for debugging
+        # In production, this could be removed entirely or moved to TRACE level
+        if 'serverContent' in evt_dict:
+            server_content = evt_dict['serverContent']
+            if 'groundingMetadata' in server_content:
+                # Consider removing this log entirely for production
+                pass
+
+        evt = ServerEvent.model_validate(evt_dict)
+        return evt
     except Exception as e:
-        print(f"Error parsing server event: {e}")
+        logger.error(f"Error parsing server event: {e}")
+        # Truncate raw message to avoid logging potentially sensitive or overly long data
+        truncated_message = message_str[:200] + "..." if len(message_str) > 200 else message_str
+        logger.error(f"Raw message (truncated): {truncated_message}")
         return None