changes to q&a and mindmap varaibles

app.py

@@ -42,42 +42,8 @@ takeaways = []
 folder_name = "./tests"
 input_accepted = False
 is_completed_analysis = False
-
-def get_initial_message():
-    messages=[
-            {"role": "system", "content": "You are a helpful AI Tutor. Who anwers brief questions about AI."},
-            {"role": "user", "content": "I want to learn AI"},
-            {"role": "assistant", "content": "Thats awesome, what do you want to know aboout AI"}
-        ]
-    return messages
-
-nodes = []
-edges = []
-
-nodes.append( Node(id="Spiderman", 
-                   label="Peter Parker", 
-                   size=25, 
-                   shape="circularImage",
-                   image="http://marvel-force-chart.surge.sh/marvel_force_chart_img/top_spiderman.png") 
-            ) # includes **kwargs
-nodes.append( Node(id="Captain_Marvel", 
-                   size=25,
-                   shape="circularImage",
-                   image="http://marvel-force-chart.surge.sh/marvel_force_chart_img/top_captainmarvel.png") 
-            )
-edges.append( Edge(source="Captain_Marvel", 
-                   label="friend_of", 
-                   target="Spiderman", 
-                   ) 
-            ) 
-
-config = Config(width=750,
-                height=950,
-                directed=True, 
-                physics=True, 
-                hierarchical=False,
-                )
-
+if not os.path.exists(folder_name):
+    os.mkdir(folder_name)
 
 user_secret = os.getenv("OPENAI_API_KEY")
 
@@ -151,10 +117,6 @@ with st.sidebar:
         else:
             st.error("Please type in your youtube link or upload the PDF")  
             st.experimental_rerun()
-           
-        # Save the transcript information
-        with open(f"{folder_name}/data_transcription.json", "w") as f:
-            json.dump(data_transcription, f, indent=4)
             
         # Generate embeddings
         if not os.path.exists(f"{folder_name}/word_embeddings.csv"):
@@ -227,11 +189,11 @@ tab1, tab2, tab3, tab4, tab5, tab6 = st.tabs(["Introduction", "Summary", "Transc
 
 # =========== INTRODUCTION ===========
 with tab1:
-    st.subheader("Introduction")
     st.markdown("## How do I use this?")
     st.markdown("Do one of the following")
     st.markdown('* Type in your youtube URL that you want worked on')
     st.markdown('* Place the PDF file that you want worked on')
+    st.markdown('* Place the audio file that you want worked on')
     st.markdown("**Once the file / url has finished saving, a 'Start Analysis' button will appear. Click on this button to begin the note generation**")
     st.warning("NOTE: This is just a demo product in alpha testing. Any and all bugs will soon be fixed")
     st.warning("After the note taking is done, you will see multiple tabs for more information")
@@ -278,88 +240,89 @@ with tab5:
         st.warning("Please wait for the analysis to finish")
 
 # =========== QUERY BOT ===========
-with tab6:  
-    if 'generated' not in st.session_state:
-        st.session_state['generated'] = []
-
-    if 'past' not in st.session_state:
-        st.session_state['past'] = []
-
-    def get_text():
-        st.header("Ask me something about the video:")
-        input_text = st.text_input("You: ", key="prompt")
-        return input_text
-
-
-    def get_embedding_text(prompt):
-        response = openai.Embedding.create(
-            input= prompt.strip(),
-            model="text-embedding-ada-002"
-        )
-        q_embedding = response['data'][0]['embedding']
-        print("the folder name at got here 1.5 is ", folder_name)
-        df = pd.read_csv(f'{folder_name}/word_embeddings.csv', index_col=0)
-        df['embedding'] = df['embedding'].apply(eval).apply(np.array)
-
-        df['distances'] = distances_from_embeddings(q_embedding, df['embedding'].values, distance_metric='cosine')
-        returns = []
-        
-        # Sort by distance with 2 hints
-        for i, row in df.sort_values('distances', ascending=True).head(4).iterrows():
-            # Else add it to the text that is being returned
-            returns.append(row["text"])
-
-        # Return the context
-        return "\n\n###\n\n".join(returns)
-
-    def generate_response(prompt):
-        one_shot_prompt = '''
-            I am YoutubeGPT, a highly intelligent question answering bot.
-            If you ask me a question that is rooted in truth, I will give you the answer.
-            Q: What is human life expectancy in the United States?
-            A: Human life expectancy in the United States is 78 years.
-            Q: '''+prompt+'''
-            A: 
-        '''
-        completions = openai.Completion.create(
-            engine = "text-davinci-003",
-            prompt = one_shot_prompt,
-            max_tokens = 1024,
-            n = 1,
-            stop=["Q:"],
-            temperature=0.5,
-        )
-        message = completions.choices[0].text
-        return message
-    
+with tab6:
     if is_completed_analysis:
-        user_input = get_text()
-        print("user input is ", user_input)
-        print("the folder name at got here 0.5 is ", folder_name)
-    else:
-        user_input = None
-    
-    if 'messages' not in st.session_state:
-        st.session_state['messages'] = get_initial_message()
-    
-    if user_input:
-        print("got here 1")
-        print("the folder name at got here 1.5 is ", folder_name)
-        text_embedding = get_embedding_text(user_input)
-        print("the folder name at got here 1.5 is ", folder_name)
-        print("got here 2")
-        title = data_transcription['title']
-        string_title = "\n\n###\n\n".join(title)
-        user_input_embedding = 'Using this context: "'+string_title+'. '+text_embedding+'", answer the following question. \n'+user_input
-        print("got here 3")
-        output = generate_response(user_input_embedding)
-        st.session_state.past.append(user_input)
-        st.session_state.generated.append(output)
+        if 'generated' not in st.session_state:
+            st.session_state['generated'] = []
+
+        if 'past' not in st.session_state:
+            st.session_state['past'] = []
+
+        def get_text():
+            st.header("Ask me something about the video:")
+            input_text = st.text_input("You: ", key="prompt")
+            return input_text
+
+
+        def get_embedding_text(prompt):
+            response = openai.Embedding.create(
+                input= prompt.strip(),
+                model="text-embedding-ada-002"
+            )
+            q_embedding = response['data'][0]['embedding']
+            print("the folder name at got here 1.5 is ", folder_name)
+            # df = pd.read_csv(f'{folder_name}/word_embeddings.csv', index_col=0)
+            data['embedding'] = data['embedding'].apply(eval).apply(np.array)
+
+            data['distances'] = distances_from_embeddings(q_embedding, data['embedding'].values, distance_metric='cosine')
+            returns = []
+            
+            # Sort by distance with 2 hints
+            for i, row in data.sort_values('distances', ascending=True).head(4).iterrows():
+                # Else add it to the text that is being returned
+                returns.append(row["text"])
+
+            # Return the context
+            return "\n\n###\n\n".join(returns)
+
+        def generate_response(prompt):
+            one_shot_prompt = '''
+                I am YoutubeGPT, a highly intelligent question answering bot.
+                If you ask me a question that is rooted in truth, I will give you the answer.
+                Q: What is human life expectancy in the United States?
+                A: Human life expectancy in the United States is 78 years.
+                Q: '''+prompt+'''
+                A: 
+            '''
+            completions = openai.Completion.create(
+                engine = "text-davinci-003",
+                prompt = one_shot_prompt,
+                max_tokens = 1024,
+                n = 1,
+                stop=["Q:"],
+                temperature=0.5,
+            )
+            message = completions.choices[0].text
+            return message
+        
+        if is_completed_analysis:
+            user_input = get_text()
+            print("user input is ", user_input)
+            print("the folder name at got here 0.5 is ", folder_name)
+        else:
+            user_input = None
         
-    if st.session_state['generated']:
-        for i in range(len(st.session_state['generated'])-1, -1, -1):
-            message(st.session_state["generated"][i], key=str(i))
-            message(st.session_state['past'][i], is_user=True, key=str(i) + '_user')
+        if 'messages' not in st.session_state:
+            st.session_state['messages'] = get_initial_message()
+        
+        if user_input:
+            print("got here 1")
+            print("the folder name at got here 1.5 is ", folder_name)
+            text_embedding = get_embedding_text(user_input)
+            print("the folder name at got here 1.5 is ", folder_name)
+            print("got here 2")
+            title = data_transcription['title']
+            string_title = "\n\n###\n\n".join(title)
+            user_input_embedding = 'Using this context: "'+string_title+'. '+text_embedding+'", answer the following question. \n'+user_input
+            print("got here 3")
+            output = generate_response(user_input_embedding)
+            st.session_state.past.append(user_input)
+            st.session_state.generated.append(output)
+            
+        if st.session_state['generated']:
+            for i in range(len(st.session_state['generated'])-1, -1, -1):
+                message(st.session_state["generated"][i], key=str(i))
+                message(st.session_state['past'][i], is_user=True, key=str(i) + '_user')
 
 
 # st.header("What else")