Resolving Timeout error

Dockerfile

@@ -1,35 +1,17 @@
-# Use the official Python slim image as the base image
 FROM python:3.12-slim
-
-# Set the working directory in the container
 WORKDIR /app
-
-# Update pip to the latest version
 RUN pip install --upgrade pip
-
-# Install build dependencies for compiling Python packages
 RUN apt-get update && apt-get install -y \
     gcc \
     g++ \
     libffi-dev \
     libssl-dev \
     python3-dev \
+    libespeak1 \
     && rm -rf /var/lib/apt/lists/*
-
-# Copy the requirements.txt file into the container
+RUN mkdir -p /tmp && chmod 777 /tmp
 COPY requirements.txt .
-
-# Verify that requirements.txt exists (for debugging)
-RUN ls -la /app && test -f /app/requirements.txt || (echo "Error: requirements.txt not found in /app" && exit 1)
-
-# Install Python dependencies from requirements.txt
 RUN pip install --no-cache-dir -r requirements.txt
-
-# Copy the application code into the container
 COPY . .
-
-# Expose the port Gradio will run on (default is 7860)
 EXPOSE 7860
-
-# Command to run the Gradio app
 CMD ["python", "app.py"]

agent.py

@@ -26,52 +26,19 @@ class AnalysisDescription(BaseModel):
 MODEL = "mistral-medium-latest"
 
 def play_wav(url: str, save_path: str = "/tmp/audio.wav"):
-    """
-    Plays a WAV file from a URL or local file path.
-    Args:
-        url (str): URL or file path (e.g., file://path/to/file.wav).
-        save_path (str, optional): Path to save downloaded files. Defaults to "/tmp/audio.wav".
-    Returns:
-        str: Status message
-    """
     try:
-        # Handle local file paths
         if url.startswith("file://"):
             file_path = urllib.parse.urlparse(url).path
-            if platform.system() == "Windows":
-                # On Windows, remove leading slash AND decode percent-encoding
-                file_path = urllib.parse.unquote(file_path.lstrip("/"))
-            else:
-                file_path = urllib.parse.unquote(file_path)
-            print(f"Playing local file: {file_path}")
+            file_path = urllib.parse.unquote(file_path.lstrip("/"))
         else:
-            # Download from URL
-            print(f"Attempting to download WAV file from {url}...")
             response = requests.get(url, timeout=10)
             response.raise_for_status()
-            
             with open(save_path, 'wb') as f:
                 f.write(response.content)
-            print(f"WAV file successfully downloaded and saved to {save_path}")
             file_path = save_path
-        
-        print(f"Attempting to play {file_path}...")
-        try:
-            # Jupyter playback
-            display(Audio(filename=file_path))
-        except NameError:
-            # Non-Jupyter playback
-            if platform.system() == "Windows":
-                os.startfile(file_path)
-            elif platform.system() == "Darwin":  # macOS
-                subprocess.run(["open", file_path], check=True)
-            else:  # Linux
-                subprocess.run(["xdg-open", file_path], check=True)
-        
-        return "Audio played successfully"
-    
+        return file_path
     except Exception as e:
-        print(f"Error playing audio: {str(e)}")
+        print(f"Error handling audio: {str(e)}")
         return f"Error: {str(e)}"
 
 # Create DocAgent for OCR PDF processing

app.py

@@ -3,13 +3,35 @@ import asyncio
 import json
 import os
 import base64
-from agent import (create_doc_agent, create_image_agent, create_json_analyzer_agent, 
-                 create_speech_agent, process_document_workflow, process_image_workflow, 
-                 complete_analysis_workflow, tts_with_mcp, simulate_process_climate_document,
-                 simulate_analyze_image, simulate_analyze_json_data, simulate_text_to_speech, play_wav)
+from agent import (
+    create_doc_agent, create_image_agent, create_json_analyzer_agent, 
+    create_speech_agent, process_document_workflow, process_image_workflow, 
+    complete_analysis_workflow, tts_with_mcp, simulate_process_climate_document,
+    simulate_analyze_image, simulate_analyze_json_data, simulate_text_to_speech, play_wav
+)
 from mistralai import Mistral
-from typing import Dict, Any
-# Function to initialize Mistral client and agents
+
+client = None
+agents = None
+
+def initialize_client_and_agents(api_key: str):
+    global client, agents
+    if client is None or agents is None:
+        try:
+            client = Mistral(api_key=api_key)
+            doc_agent = create_doc_agent(client)
+            image_agent = create_image_agent(client)
+            json_analyzer_agent = create_json_analyzer_agent(client)
+            speech_agent = create_speech_agent(client)
+            agents = {
+                "doc_agent_id": doc_agent.id,
+                "image_agent_id": image_agent.id,
+                "json_analyzer_agent_id": json_analyzer_agent.id,
+                "speech_agent_id": speech_agent.id
+            }
+        except Exception as e:
+            return None, f"Error initializing client: {str(e)}"
+    return client, agents
 
 custom_css = """
 body {
@@ -46,23 +68,6 @@ input, textarea, select {
 }
 """
 
-
-def initialize_client_and_agents(api_key: str):
-    try:
-        client = Mistral(api_key=api_key)
-        doc_agent = create_doc_agent(client)
-        image_agent = create_image_agent(client)
-        json_analyzer_agent = create_json_analyzer_agent(client)
-        speech_agent = create_speech_agent(client)
-        return client, {
-            "doc_agent_id": doc_agent.id,
-            "image_agent_id": image_agent.id,
-            "json_analyzer_agent_id": json_analyzer_agent.id,
-            "speech_agent_id": speech_agent.id
-        }
-    except Exception as e:
-        return None, f"Error initializing client: {str(e)}"
-
 # Function to handle document processing workflow
 async def run_document_workflow(api_key: str, file, document_type):
     if not api_key:

requirements.txt

@@ -4,6 +4,4 @@ pydantic
 IPython
 gtts
 gradio
-asyncio
-mcp
 authlib