Update examples/foundational/26f-gemini-multimodal-live-files-api.py

examples/foundational/26f-gemini-multimodal-live-files-api.py

@@ -18,17 +18,47 @@ from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.gemini_multimodal_live.gemini import (
-    GeminiMultimodalLiveLLMService,
     GeminiMultimodalLiveContext,
+    GeminiMultimodalLiveLLMService,
 )
-from pipecat.transports.base_transport import TransportParams
+from pipecat.transports.base_transport import BaseTransport, TransportParams
-from pipecat.transports.network.small_webrtc import SmallWebRTCTransport
+from pipecat.transports.services.daily import DailyParams
-from pipecat.transports.network.webrtc_connection import SmallWebRTCConnection
 
 load_dotenv(override=True)
 
 
+# We store functions so objects (e.g. SileroVADAnalyzer) don't get
+# instantiated. The function will be called when the desired transport gets
+# selected.
+transport_params = {
+    "daily": lambda: DailyParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        video_in_enabled=False,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        video_in_enabled=False,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
+    ),
+    "webrtc": lambda: TransportParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        video_in_enabled=False,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
+    ),
+}
+
+
+sample_file_path = ""
+
+
 async def create_sample_file():
+    if sample_file_path:
+        return sample_file_path
+    else:
         """Create a sample text file for testing the File API."""
         content = """# Sample Document for Gemini File API Test
 
@@ -52,33 +82,23 @@ The AI should be able to reference and discuss the contents of this file.
     """
 
         # Create a temporary file
-    with tempfile.NamedTemporaryFile(mode='w', suffix='.txt', delete=False) as f:
+        with tempfile.NamedTemporaryFile(mode="w", suffix=".txt", delete=False) as f:
             f.write(content)
             return f.name
 
 
-async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespace):
+async def run_example(transport: BaseTransport, _: argparse.Namespace, handle_sigint: bool):
     logger.info(f"Starting File API bot")
 
     # Create a sample file to upload
     sample_file_path = await create_sample_file()
     logger.info(f"Created sample file: {sample_file_path}")
 
-    # Initialize the SmallWebRTCTransport with the connection
-    transport = SmallWebRTCTransport(
-        webrtc_connection=webrtc_connection,
-        params=TransportParams(
-            audio_in_enabled=True,
-            audio_out_enabled=True,
-            video_in_enabled=False,
-            vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)),
-        ),
-    )
-
     system_instruction = """
     You are a helpful AI assistant with access to a document that has been uploaded for analysis.
     
-    The document contains test information including a secret phrase. You should be able to:
+    The document contains test information.
+    You should be able to:
     - Reference and discuss the contents of the uploaded document
     - Answer questions about what's in the document
     - Use the information from the document in our conversation
@@ -100,8 +120,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespac
     file_info = None
     try:
         file_info = await llm.file_api.upload_file(
-            sample_file_path, 
+            sample_file_path, display_name="Sample Test Document"
-            display_name="Sample Test Document"
         )
         logger.info(f"File uploaded successfully: {file_info['file']['name']}")
 
@@ -117,16 +136,13 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespac
                     "content": [
                         {
                             "type": "text",
-                            "text": "Greet the user and let them know you have access to a document they can ask you about. Mention that you can discuss its contents."
+                            "text": "Greet the user and let them know you have access to a document they can ask you about. Mention that you can discuss its contents.",
                         },
                         {
                             "type": "file_data",
-                            "file_data": {
+                            "file_data": {"mime_type": mime_type, "file_uri": file_uri},
-                                "mime_type": mime_type,
+                        },
-                                "file_uri": file_uri
+                    ],
-                            }
-                        }
-                    ]
                 }
             ]
         )
@@ -140,7 +156,7 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespac
             [
                 {
                     "role": "user",
-                    "content": "Greet the user and explain that there was an issue with file upload, but you're ready to help with other tasks."
+                    "content": "Greet the user and explain that there was an issue with file upload, but you're ready to help with other tasks.",
                 }
             ]
         )
@@ -149,13 +165,15 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespac
     context_aggregator = llm.create_context_aggregator(context)
 
     # Build the pipeline
-    pipeline = Pipeline([
+    pipeline = Pipeline(
+        [
             transport.input(),
             context_aggregator.user(),
             llm,
             transport.output(),
             context_aggregator.assistant(),
-    ])
+        ]
+    )
 
     # Configure the pipeline task
     task = PipelineTask(
@@ -205,6 +223,20 @@ async def run_bot(webrtc_connection: SmallWebRTCConnection, _: argparse.Namespac
 
 
 if __name__ == "__main__":
-    from run import main
+    from pipecat.examples.run import main
 
-    main() 
+    upload_example_file = input("""
+
+        Please pass in a TEXT filepath to test upload.
+        NOTE: Files are stored on Google's servers for 48 hours.
+
+        Press Enter to use a default test file.
+
+        text filepath : """)
+    if upload_example_file:
+        print(f"Uploading file: {upload_example_file}")
+        sample_file_path = upload_example_file.strip()
+    else:
+        print(f"Using default file")
+
+    main(run_example, transport_params=transport_params)