add code

app.py

@@ -4,36 +4,15 @@ import json
 import os
 from dataclasses import dataclass
 from typing import Any
+
 import gradio as gr
+from dotenv import load_dotenv
 from httpx import AsyncClient
-from groq import Groq
-import numpy as np
-from gradio_webrtc import WebRTC, AdditionalOutputs, ReplyOnPause, audio_to_bytes
-
 from pydantic_ai import Agent, ModelRetry, RunContext
-from pydantic_ai.messages import ModelStructuredResponse, ToolReturn, ModelTextResponse
-
-from dotenv import load_dotenv
+from pydantic_ai.messages import ModelStructuredResponse, ModelTextResponse, ToolReturn
 
 load_dotenv()
 
-import logging
-
-# Configure the root logger to WARNING to suppress debug messages from other libraries
-logging.basicConfig(level=logging.WARNING)
-
-# Create a console handler
-console_handler = logging.StreamHandler()
-console_handler.setLevel(logging.DEBUG)
-
-# Create a formatter
-formatter = logging.Formatter("%(name)s - %(levelname)s - %(message)s")
-console_handler.setFormatter(formatter)
-
-# Configure the logger for your specific library
-logger = logging.getLogger("gradio_webrtc")
-logger.setLevel(logging.DEBUG)
-logger.addHandler(console_handler)
 
 @dataclass
 class Deps:
@@ -43,8 +22,8 @@ class Deps:
 
 
 weather_agent = Agent(
-    'openai:gpt-4o',
-    system_prompt='You are an expert packer. A user will ask you for help packing for a trip given a destination. Use your weather tools to provide a concise and effective packing list. Also ask follow up questions if neccessary.',
+    "openai:gpt-4o",
+    system_prompt="You are an expert packer. A user will ask you for help packing for a trip given a destination. Use your weather tools to provide a concise and effective packing list. Also ask follow up questions if neccessary.",
     deps_type=Deps,
     retries=2,
 )
@@ -62,20 +41,20 @@ async def get_lat_lng(
     """
     if ctx.deps.geo_api_key is None:
         # if no API key is provided, return a dummy response (London)
-        return {'lat': 51.1, 'lng': -0.1}
+        return {"lat": 51.1, "lng": -0.1}
 
     params = {
-        'q': location_description,
-        'api_key': ctx.deps.geo_api_key,
+        "q": location_description,
+        "api_key": ctx.deps.geo_api_key,
     }
-    r = await ctx.deps.client.get('https://geocode.maps.co/search', params=params)
+    r = await ctx.deps.client.get("https://geocode.maps.co/search", params=params)
     r.raise_for_status()
     data = r.json()
 
     if data:
-        return {'lat': data[0]['lat'], 'lng': data[0]['lon']}
+        return {"lat": data[0]["lat"], "lng": data[0]["lon"]}
     else:
-        raise ModelRetry('Could not find the location')
+        raise ModelRetry("Could not find the location")
 
 
 @weather_agent.tool
@@ -89,107 +68,115 @@ async def get_weather(ctx: RunContext[Deps], lat: float, lng: float) -> dict[str
     """
     if ctx.deps.weather_api_key is None:
         # if no API key is provided, return a dummy response
-        return {'temperature': '21 °C', 'description': 'Sunny'}
+        return {"temperature": "21 °C", "description": "Sunny"}
 
     params = {
-        'apikey': ctx.deps.weather_api_key,
-        'location': f'{lat},{lng}',
-        'units': 'metric',
+        "apikey": ctx.deps.weather_api_key,
+        "location": f"{lat},{lng}",
+        "units": "metric",
     }
     r = await ctx.deps.client.get(
-        'https://api.tomorrow.io/v4/weather/realtime', params=params
+        "https://api.tomorrow.io/v4/weather/realtime", params=params
     )
     r.raise_for_status()
     data = r.json()
 
-    values = data['data']['values']
+    values = data["data"]["values"]
     # https://docs.tomorrow.io/reference/data-layers-weather-codes
     code_lookup = {
-        1000: 'Clear, Sunny',
-        1100: 'Mostly Clear',
-        1101: 'Partly Cloudy',
-        1102: 'Mostly Cloudy',
-        1001: 'Cloudy',
-        2000: 'Fog',
-        2100: 'Light Fog',
-        4000: 'Drizzle',
-        4001: 'Rain',
-        4200: 'Light Rain',
-        4201: 'Heavy Rain',
-        5000: 'Snow',
-        5001: 'Flurries',
-        5100: 'Light Snow',
-        5101: 'Heavy Snow',
-        6000: 'Freezing Drizzle',
-        6001: 'Freezing Rain',
-        6200: 'Light Freezing Rain',
-        6201: 'Heavy Freezing Rain',
-        7000: 'Ice Pellets',
-        7101: 'Heavy Ice Pellets',
-        7102: 'Light Ice Pellets',
-        8000: 'Thunderstorm',
+        1000: "Clear, Sunny",
+        1100: "Mostly Clear",
+        1101: "Partly Cloudy",
+        1102: "Mostly Cloudy",
+        1001: "Cloudy",
+        2000: "Fog",
+        2100: "Light Fog",
+        4000: "Drizzle",
+        4001: "Rain",
+        4200: "Light Rain",
+        4201: "Heavy Rain",
+        5000: "Snow",
+        5001: "Flurries",
+        5100: "Light Snow",
+        5101: "Heavy Snow",
+        6000: "Freezing Drizzle",
+        6001: "Freezing Rain",
+        6200: "Light Freezing Rain",
+        6201: "Heavy Freezing Rain",
+        7000: "Ice Pellets",
+        7101: "Heavy Ice Pellets",
+        7102: "Light Ice Pellets",
+        8000: "Thunderstorm",
     }
     return {
-        'temperature': f'{values["temperatureApparent"]:0.0f}°C',
-        'description': code_lookup.get(values['weatherCode'], 'Unknown'),
+        "temperature": f'{values["temperatureApparent"]:0.0f}°C',
+        "description": code_lookup.get(values["weatherCode"], "Unknown"),
     }
 
 
-TOOL_TO_DISPLAY_NAME = {
-    'get_lat_lng': 'Geocoding API',
-    "get_weather": "Weather API"
-}
-
-
-groq_client = Groq()
+TOOL_TO_DISPLAY_NAME = {"get_lat_lng": "Geocoding API", "get_weather": "Weather API"}
 
 client = AsyncClient()
-weather_api_key = os.getenv('WEATHER_API_KEY')
+weather_api_key = os.getenv("WEATHER_API_KEY")
 # create a free API key at https://geocode.maps.co/
-geo_api_key = os.getenv('GEO_API_KEY')
-deps = Deps(
-    client=client, weather_api_key=weather_api_key, geo_api_key=geo_api_key
-)
-
-
-async def stream_from_agent(audio: tuple[int, np.ndarray], chatbot: list[dict], past_messages: list):
+geo_api_key = os.getenv("GEO_API_KEY")
+deps = Deps(client=client, weather_api_key=weather_api_key, geo_api_key=geo_api_key)
 
-    prompt = groq_client.audio.transcriptions.create(
-      file=("audio-file.mp3", audio_to_bytes(audio)),
-        model="whisper-large-v3-turbo",
-        response_format="verbose_json",
-    ).text
 
-    chatbot.append({'role': 'user', 'content': prompt})
-    yield AdditionalOutputs(chatbot, gr.skip())
-    async with weather_agent.run_stream(prompt, deps=deps, message_history=past_messages) as result:
+async def stream_from_agent(prompt: str, chatbot: list[dict], past_messages: list):
+    chatbot.append({"role": "user", "content": prompt})
+    yield gr.Textbox(interactive=False, value=""), chatbot, gr.skip()
+    async with weather_agent.run_stream(
+        prompt, deps=deps, message_history=past_messages
+    ) as result:
         for message in result.new_messages():
             past_messages.append(message)
             if isinstance(message, ModelStructuredResponse):
                 for call in message.calls:
-                    gr_message = {"role": "assistant",
-                                  "content": "",
-                                  "metadata": {"title": f"### 🛠️ Using {TOOL_TO_DISPLAY_NAME[call.tool_name]}",
-                                                          "id": call.tool_id}
+                    gr_message = {
+                        "role": "assistant",
+                        "content": "",
+                        "metadata": {
+                            "title": f"### 🛠️ Using {TOOL_TO_DISPLAY_NAME[call.tool_name]}",
+                            "id": call.tool_id,
+                        },
                     }
                     chatbot.append(gr_message)
             if isinstance(message, ToolReturn):
                 for gr_message in chatbot:
-                    if gr_message.get('metadata', {}).get('id', "") == message.tool_id:
-                        gr_message['content'] = f"Output: {json.dumps(message.content)}"
-            yield AdditionalOutputs(chatbot, gr.skip())
-        chatbot.append({'role': 'assistant', 'content': ""})
+                    if gr_message.get("metadata", {}).get("id", "") == message.tool_id:
+                        gr_message["content"] = f"Output: {json.dumps(message.content)}"
+            yield gr.skip(), chatbot, gr.skip()
+        chatbot.append({"role": "assistant", "content": ""})
         async for message in result.stream_text():
             chatbot[-1]["content"] = message
-            yield AdditionalOutputs(chatbot, gr.skip())
+            yield gr.skip(), chatbot, gr.skip()
         data = await result.get_data()
         past_messages.append(ModelTextResponse(content=data))
-        yield AdditionalOutputs(gr.skip(), past_messages)
+        yield gr.Textbox(interactive=True), gr.skip(), past_messages
+
+
+async def handle_retry(chatbot, past_messages: list, retry_data: gr.RetryData):
+    new_history = chatbot[: retry_data.index]
+    previous_prompt = chatbot[retry_data.index]["content"]
+    past_messages = past_messages[: retry_data.index]
+    async for update in stream_from_agent(previous_prompt, new_history, past_messages):
+        yield update
+
+
+def undo(chatbot, past_messages: list, undo_data: gr.UndoData):
+    new_history = chatbot[: undo_data.index]
+    past_messages = past_messages[: undo_data.index]
+    return chatbot[undo_data.index]["content"], new_history, past_messages
+
+
+def select_data(message: gr.SelectData) -> str:
+    return message.value["text"]
 
 
 with gr.Blocks() as demo:
     gr.HTML(
-    """
+        """
 <div style="display: flex; justify-content: center; align-items: center; gap: 2rem; padding: 1rem; width: 100%">
     <img src="https://ai.pydantic.dev/img/logo-white.svg" style="max-width: 200px; height: auto">
     <div>
@@ -203,19 +190,34 @@ with gr.Blocks() as demo:
     </div>
 </div>
 """
-        )
+    )
     past_messages = gr.State([])
-    chatbot = gr.Chatbot(label="Packing Assistant", type="messages",
-                         avatar_images=(None, "https://ai.pydantic.dev/img/logo-white.svg"))
-    audio= WebRTC(label="Talk with the Agent",
-                  modality="audio",
-                  mode="send")
-    audio.stream(ReplyOnPause(stream_from_agent), inputs=[audio, chatbot, past_messages],
-                 outputs=[audio])
-    audio.on_additional_outputs(lambda c,s: (c, s), outputs=[chatbot, past_messages],
-                                queue=False, show_progress="hidden")
-
+    chatbot = gr.Chatbot(
+        label="Packing Assistant",
+        type="messages",
+        avatar_images=(None, "https://ai.pydantic.dev/img/logo-white.svg"),
+        examples=[
+            {"text": "I am going to Paris for the holidays, what should I pack?"},
+            {"text": "I am going to Tokyo this week."},
+        ],
+    )
+    with gr.Row():
+        prompt = gr.Textbox(
+            lines=1,
+            show_label=False,
+            placeholder="I am planning a trip to Miami, what should I pack?",
+        )
+    generation = prompt.submit(
+        stream_from_agent,
+        inputs=[prompt, chatbot, past_messages],
+        outputs=[prompt, chatbot, past_messages],
+    )
+    chatbot.example_select(select_data, None, [prompt])
+    chatbot.retry(
+        handle_retry, [chatbot, past_messages], [prompt, chatbot, past_messages]
+    )
+    chatbot.undo(undo, [chatbot, past_messages], [prompt, chatbot, past_messages])
 
 
-if __name__ == '__main__':
-    demo.launch()
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -2,10 +2,6 @@
 #    uv pip compile requirements.in -o requirements.txt
 aiofiles==23.2.1
     # via gradio
-aioice==0.9.0
-    # via aiortc
-aiortc==1.9.0
-    # via gradio-webrtc
 annotated-types==0.7.0
     # via pydantic
 anyio==4.6.2.post1
@@ -15,10 +11,6 @@ anyio==4.6.2.post1
     #   httpx
     #   openai
     #   starlette
-audioread==3.0.1
-    # via librosa
-av==12.3.0
-    # via aiortc
 cachetools==5.5.0
     # via google-auth
 certifi==2024.8.30
@@ -26,12 +18,6 @@ certifi==2024.8.30
     #   httpcore
     #   httpx
     #   requests
-cffi==1.17.1
-    # via
-    #   aiortc
-    #   cryptography
-    #   pylibsrtp
-    #   soundfile
 charset-normalizer==3.4.0
     # via requests
 click==8.1.7
@@ -40,50 +26,32 @@ click==8.1.7
     #   uvicorn
 colorama==0.4.6
     # via griffe
-coloredlogs==15.0.1
-    # via onnxruntime
-cryptography==44.0.0
-    # via
-    #   aiortc
-    #   pyopenssl
-decorator==5.1.1
-    # via librosa
 distro==1.9.0
     # via
     #   groq
     #   openai
-dnspython==2.7.0
-    # via aioice
 eval-type-backport==0.2.0
     # via pydantic-ai-slim
-fastapi==0.115.5
+fastapi==0.115.6
     # via gradio
 ffmpy==0.4.0
     # via gradio
 filelock==3.16.1
     # via huggingface-hub
-flatbuffers==24.3.25
-    # via onnxruntime
 fsspec==2024.10.0
     # via
     #   gradio-client
     #   huggingface-hub
 google-auth==2.36.0
     # via pydantic-ai-slim
-google-crc32c==1.6.0
-    # via aiortc
 gradio==5.7.1
-    # via gradio-webrtc
+    # via -r requirements.in
 gradio-client==1.5.0
     # via gradio
-gradio-webrtc==0.0.16rc1
-    # via -r requirements.in
 griffe==1.5.1
     # via pydantic-ai-slim
 groq==0.13.0
-    # via
-    #   -r requirements.in
-    #   pydantic-ai-slim
+    # via pydantic-ai-slim
 h11==0.14.0
     # via
     #   httpcore
@@ -102,27 +70,15 @@ huggingface-hub==0.26.3
     # via
     #   gradio
     #   gradio-client
-humanfriendly==10.0
-    # via coloredlogs
 idna==3.10
     # via
     #   anyio
     #   httpx
     #   requests
-ifaddr==0.2.0
-    # via aioice
 jinja2==3.1.4
     # via gradio
 jiter==0.8.0
     # via openai
-joblib==1.4.2
-    # via
-    #   librosa
-    #   scikit-learn
-lazy-loader==0.4
-    # via librosa
-librosa==0.10.2.post1
-    # via gradio-webrtc
 llvmlite==0.43.0
     # via numba
 logfire-api==2.6.0
@@ -135,28 +91,17 @@ markupsafe==2.1.5
     #   jinja2
 mdurl==0.1.2
     # via markdown-it-py
-mpmath==1.3.0
-    # via sympy
-msgpack==1.1.0
-    # via librosa
 numba==0.60.0
-    # via
-    #   -r requirements.in
-    #   librosa
+    # via -r requirements.in
 numpy==2.0.2
     # via
     #   gradio
-    #   librosa
     #   numba
-    #   onnxruntime
     #   pandas
-    #   scikit-learn
-    #   scipy
-    #   soxr
-onnxruntime==1.20.1
-    # via gradio-webrtc
-openai==1.56.1
-    # via pydantic-ai-slim
+openai==1.56.2
+    # via
+    #   -r requirements.in
+    #   pydantic-ai-slim
 orjson==3.10.12
     # via gradio
 packaging==24.2
@@ -164,27 +109,16 @@ packaging==24.2
     #   gradio
     #   gradio-client
     #   huggingface-hub
-    #   lazy-loader
-    #   onnxruntime
-    #   pooch
 pandas==2.2.3
     # via gradio
 pillow==11.0.0
     # via gradio
-platformdirs==4.3.6
-    # via pooch
-pooch==1.8.2
-    # via librosa
-protobuf==5.29.0
-    # via onnxruntime
 pyasn1==0.6.1
     # via
     #   pyasn1-modules
     #   rsa
 pyasn1-modules==0.4.1
     # via google-auth
-pycparser==2.22
-    # via cffi
 pydantic==2.10.3
     # via
     #   fastapi
@@ -192,22 +126,16 @@ pydantic==2.10.3
     #   groq
     #   openai
     #   pydantic-ai-slim
-pydantic-ai==0.0.8
+pydantic-ai==0.0.9
     # via -r requirements.in
-pydantic-ai-slim==0.0.8
+pydantic-ai-slim==0.0.9
     # via pydantic-ai
 pydantic-core==2.27.1
     # via pydantic
 pydub==0.25.1
     # via gradio
-pyee==12.1.1
-    # via aiortc
 pygments==2.18.0
     # via rich
-pylibsrtp==0.10.0
-    # via aiortc
-pyopenssl==24.3.0
-    # via aiortc
 python-dateutil==2.9.0.post0
     # via pandas
 python-dotenv==1.0.1
@@ -223,7 +151,6 @@ pyyaml==6.0.2
 requests==2.32.3
     # via
     #   huggingface-hub
-    #   pooch
     #   pydantic-ai-slim
 rich==13.9.4
     # via typer
@@ -233,12 +160,6 @@ ruff==0.8.1
     # via gradio
 safehttpx==0.1.6
     # via gradio
-scikit-learn==1.5.2
-    # via librosa
-scipy==1.14.1
-    # via
-    #   librosa
-    #   scikit-learn
 semantic-version==2.10.0
     # via gradio
 shellingham==1.5.4
@@ -250,18 +171,10 @@ sniffio==1.3.1
     #   anyio
     #   groq
     #   openai
-soundfile==0.12.1
-    # via librosa
-soxr==0.5.0.post1
-    # via librosa
 starlette==0.41.3
     # via
     #   fastapi
     #   gradio
-sympy==1.13.3
-    # via onnxruntime
-threadpoolctl==3.5.0
-    # via scikit-learn
 tomlkit==0.12.0
     # via gradio
 tqdm==4.67.1
@@ -277,11 +190,9 @@ typing-extensions==4.12.2
     #   gradio-client
     #   groq
     #   huggingface-hub
-    #   librosa
     #   openai
     #   pydantic
     #   pydantic-core
-    #   pyee
     #   typer
 tzdata==2024.2
     # via pandas