Update brain_strom_with_influencer_input.py

brain_strom_with_influencer_input.py

@@ -1,281 +1,280 @@
-import os
-
-import gradio as gr
-import torch
-import re
-# from transformers import AutoTokenizer, AutoModelForCausalLM
-from keybert import KeyBERT
-from sentence_transformers import SentenceTransformer
-from datasets import load_dataset,Dataset
-from shared_resources import shared_resources
-from phi.agent import Agent
-from phi.tools.duckduckgo import DuckDuckGo
-from phi.agent import Agent, RunResponse
-from phi.model.huggingface import HuggingFaceChat
-
-
-
-class ResponseGenerator:
-    def __init__(self):
-
-        self.ST = shared_resources.sentence_transformer
-        self.data = shared_resources.data
-        self.original_query = ""
-    
-        # Define the search function
-    def search(self, query: str, usernames=None, k: int = 3):
-        """Function to get recommended videos based on user input"""
-        self.embedded_query = self.ST.encode(query)  # Embed the user input
-        self.all_retrievals=[]
-        if usernames:
-          dataset=self.data.to_pandas()
-          for username in usernames:
-            username = [username]
-            filtered_df = dataset[dataset['username'].isin(username)]
-            self.temp_data = Dataset.from_pandas(filtered_df)
-            self.temp_data=self.temp_data.add_faiss_index("embeddings")
-            self.scores, self.retrieved_examples = self.temp_data.get_nearest_examples("embeddings", self.embedded_query, k=k)  # Search for top k results
-            self.all_retrievals.append(str(self.retrieved_examples['Caption'][0]))
-            self.temp_data=None
-          print('All retrievals are:',self.all_retrievals)
-          return self.all_retrievals
-
-        self.scores, self.retrieved_examples = self.data.get_nearest_examples("embeddings", self.embedded_query, k=k)  # Search for top k results
-        return self.scores, self.retrieved_examples
-
-
-    def generate_response(self, query, username=None, additional_focus=None):
-        # print('The usernames are:',username)
-        """
-        Generates text using the Llama 3.1 model.
-        """
-        self.original_query = query  # Save the original query for future focus
-        
-        # If we are going deeper, add the additional focus to the prompt
-        if additional_focus:
-            # prompt = f"Explain the Given topic:\n{self.original_query}. Also focus on: {additional_focus}\n1."
-            prompt = f"""
-        I want to create a detailed storyline for a video primarily focusing on the sentence: **{additional_focus}**, keeping it under 500 words. Please provide the storyline in 6 concise paragraphs that must incorporate the following key features everytime:  
-
-        1. **Story:** How to introduce the scene and set the tone. What is happening in the scence? Describe key visuals and actions.  
-        2. **Narration or Voiceover:** Suggestions for narration or voiceover that complements the visuals.  
-        3. **Text in the Video:** Propose important text overlays for key moments.  
-        4. **Transitions:** Smooth transitions between scenes to maintain flow.  
-        5. **Emotional Tone:** The mood and energy of the scenes (e.g., excitement, calm, tension, joy).  
-        6. **Key Visuals & Sounds:** Important props, locations, sound effects, or background music to enhance the video.  
-
-        The storyline should flow naturally, without repeating the same information or listing individual features. Ensure the output is engaging and cohesive.
-
-        Also, suggest **5 relevant hashtags** for the video that reflect its content and themes commonly used on social media for similar videos.
-
-
-        """
-
-        else:
-            # prompt = f"Explain the Given topic:\n{query}\n1."
-            prompt = f"""
-        I want to create a detailed storyline for a video in any domain, keeping it under 500 words. Please provide the storyline in 6 concise paragraphs that must incorporate the following key features everytime:  
-
-        1. **Story:** How to introduce the scene and set the tone. What is happening in the scene? Describe key visuals and actions.  
-        2. **Narration or Voiceover:** Suggestions for narration or voiceover that complements the visuals.  
-        3. **Text in the Video:** Propose important text overlays for key moments.  
-        4. **Transitions:** Smooth transitions between scenes to maintain flow.  
-        5. **Emotional Tone:** The mood and energy of the scenes (e.g., excitement, calm, tension, joy).  
-        6. **Key Visuals & Sounds:** Important props, locations, sound effects, or background music to enhance the video.  
-
-        The storyline should flow naturally, without repeating the same information or listing individual features. Ensure the output is engaging and cohesive.
-
-        Also, suggest **5 relevant hashtags** for the video that reflect its content and themes commonly used on social media for similar videos.
-
-        """
-
-        
-        # prefix = f"The question is:{self.original_query}"
-        # print('The data is:',self.data)
-        if username:
-            retrieved_list = self.search(query,username,1)
-            retrieved_context = "\n".join(retrieved_list)
-            prompt = prompt + f"\n Here is the random video story from the dataset for you. You can use it just for analysing purpose, not for similar generation. This is the story:\n{retrieved_context}"
-            prompt = prompt + f"\nNow finally i am providing you a question to create a detailed story line for a video. The question is: **{self.original_query}**"
-        
-        else:
-            prompt = prompt + f"\nNow finally i am providing you a question to create a detailed story line for a video. The question is: **{self.original_query}**"
-        agent = Agent(
-            model=HuggingFaceChat(
-                id="meta-llama/Meta-Llama-3-8B-Instruct",
-                max_tokens=4096,
-            ),
-            # tools=[DuckDuckGo()],
-            markdown=True
-        )
-
-        # Get the response in a variable
-        run: RunResponse = agent.run(prompt)
-        return run.content
-
-
-
-    def extract_topics(self, story):
-        """
-        Extracts 5 key sentences from the generated text using KeyBERT.
-        """
-
-        prompt = f'''I want to brainstorm ways to diversify or improve a storyline in exactly 5 sentences. No more than 5 nor less than 5.  
-The goal is to generate creative and actionable ideas that are not on the storyline on how the storyline can be expanded or modified for better engagement. 
-For example: If the storyline is about creating a promotional video for a restaurant, the new suggestions might include:  
-- I want to showcase the chef preparing a signature dish.  
-- I want to add a sequence of customers sharing their experiences at the restaurant.  
-- I want to highlight the farm-to-table sourcing of ingredients with a short segment showing local farms.  
-- I want to include a time-lapse of the restaurant transforming from day to night, capturing its unique ambiance.  
-- I want to feature a quick interview with the owner sharing the story behind the restaurant. 
-
-Now, I will provide you with the storyline. The storyline is:\n{story}
-Please remember, don't give any introduction or explanations. Just generate 5 sentences directly, focusing on creative suggestions for diversifying or modifying the storyline.  '''
-
-
-        agent = Agent(
-            model=HuggingFaceChat(
-                id="meta-llama/Meta-Llama-3-8B-Instruct",
-                max_tokens=4096,
-            ),
-            # tools=[DuckDuckGo()],
-            markdown=True
-        )
-
-        # Get the response in a variable
-        run: RunResponse = agent.run(prompt)
-        generated_text=run.content
-        # Split the text into sentences and strip each one
-        sentences = [sentence.strip() for sentence in re.split(r'[.?]', generated_text) if sentence.strip()]
-        print('The sentences are:',sentences)
-
-        return sentences[-4:]
-
-
-    def on_select_topic(self, selected_topic, history_stack, current_state):
-        """
-        Generates new points for the selected topic and updates history.
-        """
-        # Save current state in history
-        history_stack.append(current_state)
-
-        # Generate new outputs with the selected topic as additional focus
-        new_response = self.generate_response(self.original_query, additional_focus=selected_topic)
-        new_topics = self.extract_topics(new_response)
-
-        # Prepare new state
-        new_state = {
-            "response": new_response,
-            "topics": new_topics,
-            "key_topics": new_topics
-        }
-
-        return new_state, history_stack, gr.update(value=new_response), gr.update(choices=new_topics)
-
-    def on_back(self, history_stack):
-        """
-        Restores the previous state for all outputs.
-        """
-        if history_stack:
-            # Pop the last state from history
-            previous_state = history_stack.pop()
-
-            return history_stack, gr.update(value=previous_state["response"]), \
-                gr.update(choices=previous_state["key_topics"])
-
-        # If no history, clear outputs
-        return history_stack, gr.update(value=""), gr.update(choices=[])
-
-class ResponseGeneratorApp:
-    def __init__(self):
-        self.point_generator = ResponseGenerator()
-
-    def build_ui(self):
-        with gr.Blocks() as demo:
-            gr.Markdown(
-                """
-                #Brainstorming App
-                Enter a query to generate a detailed response and start brainstroming for further exploration.
-                """
-            )
-
-            query_input = gr.Textbox(
-                label="Enter your query",
-                placeholder="Type a query, e.g., 'I want to create a promotional video of Begnas Lake.'",
-                lines=2,
-            )
-
-            usernames = [
-        "_travelwithsapana", "givina_9", "rajen.rb", "wh0z.khu5h1", "palam061", 
-        "prettiest_sky", "explorepokhara", "ggkaam610", "anjana_dhl1"
-            ]
-
-            # username_inputs =gr.Radio(label="Select Username of whose you want similar story::", choices=usernames, type="value")
-
-            username_inputs = gr.CheckboxGroup(choices=usernames,label="Choose one or more username of whose you want similar story::",type="value")
-        
-    
-
-            generate_btn = gr.Button(value="Generate")
-
-            # Output box for the generated text
-            response_output = gr.Textbox(
-                label="Generated Response",
-                lines=10,
-                interactive=False
-            )
-
-            # Dynamic radio buttons area for the extracted topics
-            topics_radio = gr.Radio(
-                label="Brain Stroming Areas....",
-                choices=[],
-                type="value",
-                interactive=True
-            )
-
-            back_btn = gr.Button(value="Back")
-
-            # State for managing current topics and history
-            current_state = gr.State({})  # Store response, topics, and key_topics
-            history_stack = gr.State([])  # Stack of previous states
-
-            # Link the generate button to the processing function
-            generate_btn.click(
-                fn=lambda query,usernames: self.generate_handler(query,usernames),
-                inputs=[query_input,username_inputs], 
-                outputs=[current_state, response_output, topics_radio],
-            )
-
-            # Handle selection of a topic (generate new stage)
-            topics_radio.change(
-                fn=self.point_generator.on_select_topic,
-                inputs=[topics_radio, history_stack, current_state],
-                outputs=[current_state, history_stack, response_output, topics_radio]
-            )
-
-            # Handle back button
-            back_btn.click(
-                fn=self.point_generator.on_back,
-                inputs=[history_stack],
-                outputs=[history_stack, response_output, topics_radio]
-            )
-
-        return demo
-
-    def generate_handler(self, query,usernames):
-        """
-        Handles the generation of the response and topics.
-        """
-        response = self.point_generator.generate_response(query,usernames)
-        topics = self.point_generator.extract_topics(response)
-
-        # Prepare the current state
-        current_state = {
-            "response": response,
-            "topics": topics,
-            "key_topics": topics
-        }
-
-        return current_state, gr.update(value=response), gr.update(choices=topics)
-
-
+import os
+
+import gradio as gr
+import torch
+import re
+# from transformers import AutoTokenizer, AutoModelForCausalLM
+from sentence_transformers import SentenceTransformer
+from datasets import load_dataset,Dataset
+from shared_resources import shared_resources
+from phi.agent import Agent
+from phi.tools.duckduckgo import DuckDuckGo
+from phi.agent import Agent, RunResponse
+from phi.model.huggingface import HuggingFaceChat
+
+
+
+class ResponseGenerator:
+    def __init__(self):
+
+        self.ST = shared_resources.sentence_transformer
+        self.data = shared_resources.data
+        self.original_query = ""
+    
+        # Define the search function
+    def search(self, query: str, usernames=None, k: int = 3):
+        """Function to get recommended videos based on user input"""
+        self.embedded_query = self.ST.encode(query)  # Embed the user input
+        self.all_retrievals=[]
+        if usernames:
+          dataset=self.data.to_pandas()
+          for username in usernames:
+            username = [username]
+            filtered_df = dataset[dataset['username'].isin(username)]
+            self.temp_data = Dataset.from_pandas(filtered_df)
+            self.temp_data=self.temp_data.add_faiss_index("embeddings")
+            self.scores, self.retrieved_examples = self.temp_data.get_nearest_examples("embeddings", self.embedded_query, k=k)  # Search for top k results
+            self.all_retrievals.append(str(self.retrieved_examples['Caption'][0]))
+            self.temp_data=None
+          print('All retrievals are:',self.all_retrievals)
+          return self.all_retrievals
+
+        self.scores, self.retrieved_examples = self.data.get_nearest_examples("embeddings", self.embedded_query, k=k)  # Search for top k results
+        return self.scores, self.retrieved_examples
+
+
+    def generate_response(self, query, username=None, additional_focus=None):
+        # print('The usernames are:',username)
+        """
+        Generates text using the Llama 3.1 model.
+        """
+        self.original_query = query  # Save the original query for future focus
+        
+        # If we are going deeper, add the additional focus to the prompt
+        if additional_focus:
+            # prompt = f"Explain the Given topic:\n{self.original_query}. Also focus on: {additional_focus}\n1."
+            prompt = f"""
+        I want to create a detailed storyline for a video primarily focusing on the sentence: **{additional_focus}**, keeping it under 500 words. Please provide the storyline in 6 concise paragraphs that must incorporate the following key features everytime:  
+
+        1. **Story:** How to introduce the scene and set the tone. What is happening in the scence? Describe key visuals and actions.  
+        2. **Narration or Voiceover:** Suggestions for narration or voiceover that complements the visuals.  
+        3. **Text in the Video:** Propose important text overlays for key moments.  
+        4. **Transitions:** Smooth transitions between scenes to maintain flow.  
+        5. **Emotional Tone:** The mood and energy of the scenes (e.g., excitement, calm, tension, joy).  
+        6. **Key Visuals & Sounds:** Important props, locations, sound effects, or background music to enhance the video.  
+
+        The storyline should flow naturally, without repeating the same information or listing individual features. Ensure the output is engaging and cohesive.
+
+        Also, suggest **5 relevant hashtags** for the video that reflect its content and themes commonly used on social media for similar videos.
+
+
+        """
+
+        else:
+            # prompt = f"Explain the Given topic:\n{query}\n1."
+            prompt = f"""
+        I want to create a detailed storyline for a video in any domain, keeping it under 500 words. Please provide the storyline in 6 concise paragraphs that must incorporate the following key features everytime:  
+
+        1. **Story:** How to introduce the scene and set the tone. What is happening in the scene? Describe key visuals and actions.  
+        2. **Narration or Voiceover:** Suggestions for narration or voiceover that complements the visuals.  
+        3. **Text in the Video:** Propose important text overlays for key moments.  
+        4. **Transitions:** Smooth transitions between scenes to maintain flow.  
+        5. **Emotional Tone:** The mood and energy of the scenes (e.g., excitement, calm, tension, joy).  
+        6. **Key Visuals & Sounds:** Important props, locations, sound effects, or background music to enhance the video.  
+
+        The storyline should flow naturally, without repeating the same information or listing individual features. Ensure the output is engaging and cohesive.
+
+        Also, suggest **5 relevant hashtags** for the video that reflect its content and themes commonly used on social media for similar videos.
+
+        """
+
+        
+        # prefix = f"The question is:{self.original_query}"
+        # print('The data is:',self.data)
+        if username:
+            retrieved_list = self.search(query,username,1)
+            retrieved_context = "\n".join(retrieved_list)
+            prompt = prompt + f"\n Here is the random video story from the dataset for you. You can use it just for analysing purpose, not for similar generation. This is the story:\n{retrieved_context}"
+            prompt = prompt + f"\nNow finally i am providing you a question to create a detailed story line for a video. The question is: **{self.original_query}**"
+        
+        else:
+            prompt = prompt + f"\nNow finally i am providing you a question to create a detailed story line for a video. The question is: **{self.original_query}**"
+        agent = Agent(
+            model=HuggingFaceChat(
+                id="meta-llama/Meta-Llama-3-8B-Instruct",
+                max_tokens=4096,
+            ),
+            # tools=[DuckDuckGo()],
+            markdown=True
+        )
+
+        # Get the response in a variable
+        run: RunResponse = agent.run(prompt)
+        return run.content
+
+
+
+    def extract_topics(self, story):
+        """
+        Extracts 5 key sentences from the generated text using KeyBERT.
+        """
+
+        prompt = f'''I want to brainstorm ways to diversify or improve a storyline in exactly 5 sentences. No more than 5 nor less than 5.  
+The goal is to generate creative and actionable ideas that are not on the storyline on how the storyline can be expanded or modified for better engagement. 
+For example: If the storyline is about creating a promotional video for a restaurant, the new suggestions might include:  
+- I want to showcase the chef preparing a signature dish.  
+- I want to add a sequence of customers sharing their experiences at the restaurant.  
+- I want to highlight the farm-to-table sourcing of ingredients with a short segment showing local farms.  
+- I want to include a time-lapse of the restaurant transforming from day to night, capturing its unique ambiance.  
+- I want to feature a quick interview with the owner sharing the story behind the restaurant. 
+
+Now, I will provide you with the storyline. The storyline is:\n{story}
+Please remember, don't give any introduction or explanations. Just generate 5 sentences directly, focusing on creative suggestions for diversifying or modifying the storyline.  '''
+
+
+        agent = Agent(
+            model=HuggingFaceChat(
+                id="meta-llama/Meta-Llama-3-8B-Instruct",
+                max_tokens=4096,
+            ),
+            # tools=[DuckDuckGo()],
+            markdown=True
+        )
+
+        # Get the response in a variable
+        run: RunResponse = agent.run(prompt)
+        generated_text=run.content
+        # Split the text into sentences and strip each one
+        sentences = [sentence.strip() for sentence in re.split(r'[.?]', generated_text) if sentence.strip()]
+        print('The sentences are:',sentences)
+
+        return sentences[-4:]
+
+
+    def on_select_topic(self, selected_topic, history_stack, current_state):
+        """
+        Generates new points for the selected topic and updates history.
+        """
+        # Save current state in history
+        history_stack.append(current_state)
+
+        # Generate new outputs with the selected topic as additional focus
+        new_response = self.generate_response(self.original_query, additional_focus=selected_topic)
+        new_topics = self.extract_topics(new_response)
+
+        # Prepare new state
+        new_state = {
+            "response": new_response,
+            "topics": new_topics,
+            "key_topics": new_topics
+        }
+
+        return new_state, history_stack, gr.update(value=new_response), gr.update(choices=new_topics)
+
+    def on_back(self, history_stack):
+        """
+        Restores the previous state for all outputs.
+        """
+        if history_stack:
+            # Pop the last state from history
+            previous_state = history_stack.pop()
+
+            return history_stack, gr.update(value=previous_state["response"]), \
+                gr.update(choices=previous_state["key_topics"])
+
+        # If no history, clear outputs
+        return history_stack, gr.update(value=""), gr.update(choices=[])
+
+class ResponseGeneratorApp:
+    def __init__(self):
+        self.point_generator = ResponseGenerator()
+
+    def build_ui(self):
+        with gr.Blocks() as demo:
+            gr.Markdown(
+                """
+                #Brainstorming App
+                Enter a query to generate a detailed response and start brainstroming for further exploration.
+                """
+            )
+
+            query_input = gr.Textbox(
+                label="Enter your query",
+                placeholder="Type a query, e.g., 'I want to create a promotional video of Begnas Lake.'",
+                lines=2,
+            )
+
+            usernames = [
+        "_travelwithsapana", "givina_9", "rajen.rb", "wh0z.khu5h1", "palam061", 
+        "prettiest_sky", "explorepokhara", "ggkaam610", "anjana_dhl1"
+            ]
+
+            # username_inputs =gr.Radio(label="Select Username of whose you want similar story::", choices=usernames, type="value")
+
+            username_inputs = gr.CheckboxGroup(choices=usernames,label="Choose one or more username of whose you want similar story::",type="value")
+        
+    
+
+            generate_btn = gr.Button(value="Generate")
+
+            # Output box for the generated text
+            response_output = gr.Textbox(
+                label="Generated Response",
+                lines=10,
+                interactive=False
+            )
+
+            # Dynamic radio buttons area for the extracted topics
+            topics_radio = gr.Radio(
+                label="Brain Stroming Areas....",
+                choices=[],
+                type="value",
+                interactive=True
+            )
+
+            back_btn = gr.Button(value="Back")
+
+            # State for managing current topics and history
+            current_state = gr.State({})  # Store response, topics, and key_topics
+            history_stack = gr.State([])  # Stack of previous states
+
+            # Link the generate button to the processing function
+            generate_btn.click(
+                fn=lambda query,usernames: self.generate_handler(query,usernames),
+                inputs=[query_input,username_inputs], 
+                outputs=[current_state, response_output, topics_radio],
+            )
+
+            # Handle selection of a topic (generate new stage)
+            topics_radio.change(
+                fn=self.point_generator.on_select_topic,
+                inputs=[topics_radio, history_stack, current_state],
+                outputs=[current_state, history_stack, response_output, topics_radio]
+            )
+
+            # Handle back button
+            back_btn.click(
+                fn=self.point_generator.on_back,
+                inputs=[history_stack],
+                outputs=[history_stack, response_output, topics_radio]
+            )
+
+        return demo
+
+    def generate_handler(self, query,usernames):
+        """
+        Handles the generation of the response and topics.
+        """
+        response = self.point_generator.generate_response(query,usernames)
+        topics = self.point_generator.extract_topics(response)
+
+        # Prepare the current state
+        current_state = {
+            "response": response,
+            "topics": topics,
+            "key_topics": topics
+        }
+
+        return current_state, gr.update(value=response), gr.update(choices=topics)
+
+