Category: computing

Message-Chaining Protocol (MCP) Implementation:

    clsMCPMessage.py
    clsMCPBroker.py

YouTube Transcript Extraction:

    clsYouTubeVideoProcessor.py

Language Detection:

    clsLanguageDetector.py

Translation Services & Agents:

    clsTranslationAgent.py
    clsTranslationService.py

Documentation Agent:

    clsDocumentationAgent.py
    
Research Agent:

    clsDocumentationAgent.py

def extract_youtube_id(youtube_url):
    """Extract YouTube video ID from URL"""
    youtube_id_match = re.search(r'(?:v=|\/)([0-9A-Za-z_-]{11}).*', youtube_url)
    if youtube_id_match:
        return youtube_id_match.group(1)
    return None

def get_youtube_transcript(youtube_url):
    """Get transcript from YouTube video"""
    video_id = extract_youtube_id(youtube_url)
    if not video_id:
        return {"error": "Invalid YouTube URL or ID"}
    
    try:
        transcript_list = YouTubeTranscriptApi.list_transcripts(video_id)
        
        # First try to get manual transcripts
        try:
            transcript = transcript_list.find_manually_created_transcript(["en"])
            transcript_data = transcript.fetch()
            print(f"Debug - Manual transcript format: {type(transcript_data)}")
            if transcript_data and len(transcript_data) > 0:
                print(f"Debug - First item type: {type(transcript_data[0])}")
                print(f"Debug - First item sample: {transcript_data[0]}")
            return {"text": transcript_data, "language": "en", "auto_generated": False}
        except Exception as e:
            print(f"Debug - No manual transcript: {str(e)}")
            # If no manual English transcript, try any available transcript
            try:
                available_transcripts = list(transcript_list)
                if available_transcripts:
                    transcript = available_transcripts[0]
                    print(f"Debug - Using transcript in language: {transcript.language_code}")
                    transcript_data = transcript.fetch()
                    print(f"Debug - Auto transcript format: {type(transcript_data)}")
                    if transcript_data and len(transcript_data) > 0:
                        print(f"Debug - First item type: {type(transcript_data[0])}")
                        print(f"Debug - First item sample: {transcript_data[0]}")
                    return {
                        "text": transcript_data, 
                        "language": transcript.language_code, 
                        "auto_generated": transcript.is_generated
                    }
                else:
                    return {"error": "No transcripts available for this video"}
            except Exception as e:
                return {"error": f"Error getting transcript: {str(e)}"}
    except Exception as e:
        return {"error": f"Error getting transcript list: {str(e)}"}

# ----------------------------------------------------------------------------------
# YouTube Video Processor
# ----------------------------------------------------------------------------------

class clsYouTubeVideoProcessor:
    """Process YouTube videos using the agent system"""
    
    def __init__(self, documentation_agent, translation_agent, research_agent):
        self.documentation_agent = documentation_agent
        self.translation_agent = translation_agent
        self.research_agent = research_agent
    
    def process_youtube_video(self, youtube_url):
        """Process a YouTube video"""
        print(f"Processing YouTube video: {youtube_url}")
        
        # Extract transcript
        transcript_result = get_youtube_transcript(youtube_url)
        
        if "error" in transcript_result:
            return {"error": transcript_result["error"]}
        
        # Start a new conversation
        conversation_id = self.documentation_agent.start_processing()
        
        # Process transcript segments
        transcript_data = transcript_result["text"]
        transcript_language = transcript_result["language"]
        
        print(f"Debug - Type of transcript_data: {type(transcript_data)}")
        
        # For each segment, detect language and translate if needed
        processed_segments = []
        
        try:
            # Make sure transcript_data is a list of dictionaries with text and start fields
            if isinstance(transcript_data, list):
                for idx, segment in enumerate(transcript_data):
                    print(f"Debug - Processing segment {idx}, type: {type(segment)}")
                    
                    # Extract text properly based on the type
                    if isinstance(segment, dict) and "text" in segment:
                        text = segment["text"]
                        start = segment.get("start", 0)
                    else:
                        # Try to access attributes for non-dict types
                        try:
                            text = segment.text
                            start = getattr(segment, "start", 0)
                        except AttributeError:
                            # If all else fails, convert to string
                            text = str(segment)
                            start = idx * 5  # Arbitrary timestamp
                    
                    print(f"Debug - Extracted text: {text[:30]}...")
                    
                    # Create a standardized segment
                    std_segment = {
                        "text": text,
                        "start": start
                    }
                    
                    # Process through translation agent
                    translation_result = self.translation_agent.process_text(text, conversation_id)
                    
                    # Update segment with translation information
                    segment_with_translation = {
                        **std_segment,
                        "translation_info": translation_result
                    }
                    
                    # Use translated text for documentation
                    if "final_text" in translation_result and translation_result["final_text"] != text:
                        std_segment["processed_text"] = translation_result["final_text"]
                    else:
                        std_segment["processed_text"] = text
                    
                    processed_segments.append(segment_with_translation)
            else:
                # If transcript_data is not a list, treat it as a single text block
                print(f"Debug - Transcript is not a list, treating as single text")
                text = str(transcript_data)
                std_segment = {
                    "text": text,
                    "start": 0
                }
                
                translation_result = self.translation_agent.process_text(text, conversation_id)
                segment_with_translation = {
                    **std_segment,
                    "translation_info": translation_result
                }
                
                if "final_text" in translation_result and translation_result["final_text"] != text:
                    std_segment["processed_text"] = translation_result["final_text"]
                else:
                    std_segment["processed_text"] = text
                
                processed_segments.append(segment_with_translation)
                
        except Exception as e:
            print(f"Debug - Error processing transcript: {str(e)}")
            return {"error": f"Error processing transcript: {str(e)}"}
        
        # Process the transcript with the documentation agent
        documentation_result = self.documentation_agent.process_transcript(
            processed_segments,
            conversation_id
        )
        
        return {
            "youtube_url": youtube_url,
            "transcript_language": transcript_language,
            "processed_segments": processed_segments,
            "documentation": documentation_result,
            "conversation_id": conversation_id
        }

def extract_youtube_id(youtube_url):
    ...

def get_youtube_transcript(youtube_url):
    ...

class clsYouTubeVideoProcessor:
    ...

def process_youtube_video(self, youtube_url):
    ...

class clsDocumentationAgent:
    """Documentation Agent built with LangChain"""
    
    def __init__(self, agent_id: str, broker: clsMCPBroker):
        self.agent_id = agent_id
        self.broker = broker
        self.broker.register_agent(agent_id)
        
        # Initialize LangChain components
        self.llm = ChatOpenAI(
            model="gpt-4-0125-preview",
            temperature=0.1,
            api_key=OPENAI_API_KEY
        )
        
        # Create tools
        self.tools = [
            clsSendMessageTool(sender_id=self.agent_id, broker=self.broker)
        ]
        
        # Set up LLM with tools
        self.llm_with_tools = self.llm.bind(
            tools=[tool.tool_config for tool in self.tools]
        )
        
        # Setup memory
        self.memory = ConversationBufferMemory(
            memory_key="chat_history",
            return_messages=True
        )
        
        # Create prompt
        self.prompt = ChatPromptTemplate.from_messages([
            ("system", """You are a Documentation Agent for YouTube video transcripts. Your responsibilities include:
                1. Process YouTube video transcripts
                2. Identify key points, topics, and main ideas
                3. Organize content into a coherent and structured format
                4. Create concise summaries
                5. Request research information when necessary
                
                When you need additional context or research, send a request to the Research Agent.
                Always maintain a professional tone and ensure your documentation is clear and organized.
            """),
            MessagesPlaceholder(variable_name="chat_history"),
            ("human", "{input}"),
            MessagesPlaceholder(variable_name="agent_scratchpad"),
        ])
        
        # Create agent
        self.agent = (
            {
                "input": lambda x: x["input"],
                "chat_history": lambda x: self.memory.load_memory_variables({})["chat_history"],
                "agent_scratchpad": lambda x: format_to_openai_tool_messages(x["intermediate_steps"]),
            }
            | self.prompt
            | self.llm_with_tools
            | OpenAIToolsAgentOutputParser()
        )
        
        # Create agent executor
        self.agent_executor = AgentExecutor(
            agent=self.agent,
            tools=self.tools,
            verbose=True,
            memory=self.memory
        )
        
        # Video data
        self.current_conversation_id = None
        self.video_notes = {}
        self.key_points = []
        self.transcript_segments = []
        
    def start_processing(self) -> str:
        """Start processing a new video"""
        self.current_conversation_id = str(uuid.uuid4())
        self.video_notes = {}
        self.key_points = []
        self.transcript_segments = []
        
        return self.current_conversation_id
    
    def process_transcript(self, transcript_segments, conversation_id=None):
        """Process a YouTube transcript"""
        if not conversation_id:
            conversation_id = self.start_processing()
        self.current_conversation_id = conversation_id
        
        # Store transcript segments
        self.transcript_segments = transcript_segments
        
        # Process segments
        processed_segments = []
        for segment in transcript_segments:
            processed_result = self.process_segment(segment)
            processed_segments.append(processed_result)
        
        # Generate summary
        summary = self.generate_summary()
        
        return {
            "processed_segments": processed_segments,
            "summary": summary,
            "conversation_id": conversation_id
        }
    
    def process_segment(self, segment):
        """Process individual transcript segment"""
        text = segment.get("text", "")
        start = segment.get("start", 0)
        
        # Use LangChain agent to process the segment
        result = self.agent_executor.invoke({
            "input": f"Process this video transcript segment at timestamp {start}s: {text}. If research is needed, send a request to the research_agent."
        })
        
        # Update video notes
        timestamp = start
        self.video_notes[timestamp] = {
            "text": text,
            "analysis": result["output"]
        }
        
        return {
            "timestamp": timestamp,
            "text": text,
            "analysis": result["output"]
        }
    
    def handle_mcp_message(self, message: clsMCPMessage) -> Optional[clsMCPMessage]:
        """Handle an incoming MCP message"""
        if message.message_type == "research_response":
            # Process research information received from Research Agent
            research_info = message.content.get("text", "")
            
            result = self.agent_executor.invoke({
                "input": f"Incorporate this research information into video analysis: {research_info}"
            })
            
            # Send acknowledgment back to Research Agent
            response = clsMCPMessage(
                sender=self.agent_id,
                receiver=message.sender,
                message_type="acknowledgment",
                content={"text": "Research information incorporated into video analysis."},
                reply_to=message.id,
                conversation_id=message.conversation_id
            )
            
            self.broker.publish(response)
            return response
        
        elif message.message_type == "translation_response":
            # Process translation response from Translation Agent
            translation_result = message.content
            
            # Process the translated text
            if "final_text" in translation_result:
                text = translation_result["final_text"]
                original_text = translation_result.get("original_text", "")
                language_info = translation_result.get("language", {})
                
                result = self.agent_executor.invoke({
                    "input": f"Process this translated text: {text}\nOriginal language: {language_info.get('language', 'unknown')}\nOriginal text: {original_text}"
                })
                
                # Update notes with translation information
                for timestamp, note in self.video_notes.items():
                    if note["text"] == original_text:
                        note["translated_text"] = text
                        note["language"] = language_info
                        break
            
            return None
        
        return None
    
    def run(self):
        """Run the agent to listen for MCP messages"""
        print(f"Documentation Agent {self.agent_id} is running...")
        while True:
            message = self.broker.get_message(self.agent_id, timeout=1)
            if message:
                self.handle_mcp_message(message)
            time.sleep(0.1)
    
    def generate_summary(self) -> str:
        """Generate a summary of the video"""
        if not self.video_notes:
            return "No video data available to summarize."
        
        all_notes = "\n".join([f"{ts}: {note['text']}" for ts, note in self.video_notes.items()])
        
        result = self.agent_executor.invoke({
            "input": f"Generate a concise summary of this YouTube video, including key points and topics:\n{all_notes}"
        })
        
        return result["output"]