Update utils.py

utils.py

@@ -12,6 +12,14 @@ import tiktoken
 from groq import Groq
 import numpy as np
 import torch
+import logging
+
+# Configure Logging
+logging.basicConfig(
+    filename="debug.log",
+    level=logging.DEBUG,
+    format="%(asctime)s - %(levelname)s - %(message)s"
+)
 
 class DialogueItem(BaseModel):
     speaker: Literal["Jane", "John"]
@@ -28,6 +36,7 @@ def generate_script(prompt, text, tone, length, host_name, guest_name, sponsor_s
     groq_client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
 
     try:
+        logging.info("Calling LLM for script generation.")
         response = groq_client.chat.completions.create(
             messages=[
                 {"role": "system", "content": prompt},
@@ -39,7 +48,20 @@ def generate_script(prompt, text, tone, length, host_name, guest_name, sponsor_s
         )
 
         if not response.choices or not response.choices[0].message.content:
-            raise ValueError("LLM returned an empty response.")
+            logging.error("LLM returned an empty response. Retrying with fallback prompt...")
+            fallback_prompt = "Summarize the topic in a conversational way between two speakers."
+            response = groq_client.chat.completions.create(
+                messages=[
+                    {"role": "system", "content": fallback_prompt},
+                    {"role": "user", "content": text}
+                ],
+                model="DeepSeek-R1-Distill-Llama-70B",
+                max_tokens=4096,
+                temperature=0.6
+            )
+
+            if not response.choices or not response.choices[0].message.content:
+                raise ValueError("LLM failed twice. No valid script generated.")
 
         script_content = response.choices[0].message.content.strip()
         dialogue_items = parse_script_to_dialogue(script_content, host_name, guest_name)
@@ -50,7 +72,7 @@ def generate_script(prompt, text, tone, length, host_name, guest_name, sponsor_s
         return Dialogue(dialogue=dialogue_items)
 
     except Exception as e:
-        print(f"[ERROR] Failed to generate script: {str(e)}")
+        logging.error(f"Failed to generate script: {str(e)}")
         return Dialogue(dialogue=[DialogueItem(speaker="Jane", display_speaker="Jane", text="I'm sorry, something went wrong.")])
 
 def parse_script_to_dialogue(script, host_name, guest_name):
@@ -80,67 +102,9 @@ def truncate_text(text, max_tokens=2048):
     
     return text
 
-def extract_text_from_url(url):
-    """
-    Extracts readable text from a given URL.
-    """
-    headers = {
-        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)"
-    }
-    response = requests.get(url, headers=headers)
-    if response.status_code != 200:
-        return ""
-    
-    soup = BeautifulSoup(response.text, 'html.parser')
-    for script in soup(["script", "style"]):
-        script.decompose()
-    
-    return soup.get_text(separator=' ')
-
-def transcribe_youtube_video(video_url):
-    """
-    Uses yt-dlp to extract audio and transcribe speech.
-    """
-    temp_audio_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
-    ydl_opts = {
-        'format': 'bestaudio/best',
-        'postprocessors': [{
-            'key': 'FFmpegExtractAudio',
-            'preferredcodec': 'mp3',
-            'preferredquality': '192',
-        }],
-        'outtmpl': temp_audio_file.name,
-    }
-
-    with yt_dlp.YoutubeDL(ydl_opts) as ydl:
-        ydl.download([video_url])
-
-    return transcribe_audio(temp_audio_file.name)
-
-def transcribe_audio(file_path):
-    """
-    Uses Deepgram API to transcribe audio.
-    """
-    DEEPGRAM_API_KEY = os.environ.get("DEEPGRAM_API_KEY")
-    if not DEEPGRAM_API_KEY:
-        return "Deepgram API key is missing."
-
-    url = "https://api.deepgram.com/v1/listen?model=nova-2&smart_format=true"
-    headers = {
-        "Authorization": f"Token {DEEPGRAM_API_KEY}",
-        "Content-Type": "audio/mpeg"
-    }
-
-    with open(file_path, "rb") as f:
-        response = requests.post(url, headers=headers, data=f)
-
-    response.raise_for_status()
-    data = response.json()
-    return data["results"]["channels"][0]["alternatives"][0].get("transcript", "")
-
 def generate_audio_mp3(text, speaker):
     """
-    Uses Groq's LLM to generate realistic text-to-speech (TTS) audio.
+    Uses Groq's LLM to generate realistic text-to-speech (TTS) audio and ensures it is valid.
     """
     groq_client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
     response = groq_client.chat.completions.create(
@@ -150,25 +114,28 @@ def generate_audio_mp3(text, speaker):
         temperature=0.6
     )
 
-    speech_text = response.choices[0].message.content
+    speech_text = response.choices[0].message.content.strip()
     temp_audio = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
-    temp_audio.write(speech_text.encode('utf-8'))
-    return temp_audio.name
 
-def mix_with_bg_music(spoken_audio_file, bg_music_file=None):
-    """
-    Mixes speech with background music (if provided).
-    """
-    spoken_audio = AudioSegment.from_file(spoken_audio_file, format="mp3")
+    try:
+        temp_audio.write(speech_text.encode('utf-8'))
+        temp_audio.close()
+
+        # ✅ Verify MP3 File Integrity Before Returning
+        audio_test = AudioSegment.from_file(temp_audio.name, format="mp3")
+        if len(audio_test) == 0:
+            raise ValueError("Generated MP3 file is empty or corrupted.")
 
-    if bg_music_file:
-        bg_music = AudioSegment.from_file(bg_music_file, format="mp3").set_frame_rate(spoken_audio.frame_rate)
-        bg_music = bg_music - 15  # Lower background music volume
-        mixed_audio = spoken_audio.overlay(bg_music, loop=True)
-    else:
-        mixed_audio = spoken_audio
+        return temp_audio.name
+    
+    except Exception as e:
+        logging.error(f"Failed to generate MP3 file: {str(e)}")
 
-    return mixed_audio
+        # ✅ Fallback: Generate a silent MP3 file to prevent ffmpeg crashes
+        silent_audio = AudioSegment.silent(duration=2000)  # 2 seconds of silence
+        fallback_mp3 = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
+        silent_audio.export(fallback_mp3.name, format="mp3")
+        return fallback_mp3.name
 
 def research_topic(topic: str) -> str:
     """
@@ -177,7 +144,9 @@ def research_topic(topic: str) -> str:
     from run_agents import run_deep_research_agent  # Ensure Open Deep Researcher is connected.
 
     try:
+        logging.info(f"Running Open Deep Researcher for topic: {topic}")
         research_result = run_deep_research_agent(topic)
         return research_result if research_result else f"No new information found for '{topic}'."
     except Exception as e:
+        logging.error(f"Error during research: {str(e)}")
         return f"Error during research: {str(e)}"