Update app.py

app.py

@@ -26,6 +26,9 @@ import urllib.request
 import sqlite3
 import pandas as pd
 import pandasql as ps
+import pyaudio
+import wave
+
 
 def clean(value):
     val = value.replace("'",'').replace("[",'').replace("]",'')
@@ -249,6 +252,45 @@ def g_sheet_log(myinput, output):
       body=value_range_body
   ).execute()
 
+openai.api_key = st.secrets["OPENAI_KEY"]
+RATE = 44100
+CHANNELS = 1
+FORMAT = pyaudio.paInt16
+CHUNK = 1024
+RECORD_SECONDS = 5
+
+def record_audio():
+    p = pyaudio.PyAudio()
+
+    # Open the microphone stream
+    stream = p.open(format=FORMAT,
+                    channels=CHANNELS,
+                    rate=RATE,
+                    input=True,
+                    frames_per_buffer=CHUNK)
+
+    # Record the audio
+    frames = []
+    for i in range(0, int(RATE / CHUNK * RECORD_SECONDS)):
+        data = stream.read(CHUNK)
+        frames.append(data)
+
+    # Close the microphone stream
+    stream.stop_stream()
+    stream.close()
+    p.terminate()
+
+    # Save the recorded audio to a WAV file
+    wf = wave.open("output.mp3", "wb")
+    wf.setnchannels(CHANNELS)
+    wf.setsampwidth(p.get_sample_size(FORMAT))
+    wf.setframerate(RATE)
+    wf.writeframes(b"".join(frames))
+    wf.close()
+
+    # Return the path to the recorded audio file
+    return "output.mp3"
+
 
 def openai_response(PROMPT):
     response = openai.Image.create(
@@ -446,223 +488,284 @@ elif Usage == 'Random Questions':
     6. Current Affairs and News.
     7. Create or compose tweets or Linkedin posts or email.''')
     
-    # Input_type = st.radio(
-    #     "**Input type:**",
-    #     ('TEXT', 'SPEECH')
-    #     )
-    
-    # if Input_type == 'TEXT':
-    #page_bg_img2 = """
-    #<style>
-    #[data-testid="stAppViewContainer"] {
-    #background-color: #e5e5f7;
-    #opacity: 0.8;
-    #background-size: 20px 20px;
-    #background-image:  repeating-linear-gradient(0deg, #32d947, #32d947 1px, #e5e5f7 1px, #e5e5f7);
-    #}
-    #</style>
-    #"""
-    #st.markdown(page_bg_img, unsafe_allow_html=True)
-    st.write('**You are now in Text input mode**')
-    mytext = st.text_input('**Go on! Ask me anything:**')
-    if st.button("SUBMIT"):
-        question=mytext
-        response = openai.Completion.create(
-          model="text-davinci-003",
-          prompt=f'''Your name is HyperBot and  knowledge cutoff date is 2021-09, and you are not aware of any events after that time. if the  
-                    Answer to following questions is not from your knowledge base or in case of queries like weather 
-                      updates / stock updates / current news or people which requires you to have internet connection  then print i don't have access to internet to answer your question, 
-                      if  question is related to  image or  painting or drawing generation then print ipython type output function gen_draw("detailed prompt of image to be generated")
-                      if the question is related to playing a song or video or music of a singer then print ipython type output  function vid_tube("relevent search query")
-                      if the question is related to operating home appliances then print ipython type output function home_app(" action(ON/Off),appliance(TV,Geaser,Fridge,Lights,fans,AC)") . 
-                      if question is realted to sending mail or sms then print ipython type output function messenger_app(" message of us ,messenger(email,sms)")
-                      \nQuestion-{question}
-                      \nAnswer -''',
-          temperature=0.49,
-          max_tokens=256,
-          top_p=1,
-          frequency_penalty=0,
-          presence_penalty=0
+    Input_type = st.radio(
+        "**Input type:**",
+        ('TEXT', 'SPEECH')
         )
-        string_temp=response.choices[0].text
-
-        if ("gen_draw" in string_temp):
-            try:
-                try:
-                    wget.download(openai_response(prompt))
-                    img2 = Image.open(wget.download(openai_response(prompt)))
-                    img2.show()
-                    rx = 'Image returned'
-                    g_sheet_log(mytext, rx)
-                except:
-                    urllib.request.urlretrieve(openai_response(prompt),"img_ret.png")
-                    img = Image.open("img_ret.png")
-                    img.show()
-                    rx = 'Image returned'
-                    g_sheet_log(mytext, rx)
-            except:
-                # Set up our initial generation parameters.
-                answers = stability_api.generate(
-                prompt = mytext,
-                seed=992446758, # If a seed is provided, the resulting generated image will be deterministic.
-                        # What this means is that as long as all generation parameters remain the same, you can always recall the same image simply by generating it again.
-                        # Note: This isn't quite the case for Clip Guided generations, which we'll tackle in a future example notebook.
-                steps=30, # Amount of inference steps performed on image generation. Defaults to 30.
-                cfg_scale=8.0, # Influences how strongly your generation is guided to match your prompt.
-                    # Setting this value higher increases the strength in which it tries to match your prompt.
-                    # Defaults to 7.0 if not specified.
-                width=512, # Generation width, defaults to 512 if not included.
-                height=512, # Generation height, defaults to 512 if not included.
-                samples=1, # Number of images to generate, defaults to 1 if not included.
-                sampler=generation.SAMPLER_K_DPMPP_2M # Choose which sampler we want to denoise our generation with.
-                                                    # Defaults to k_dpmpp_2m if not specified. Clip Guidance only supports ancestral samplers.
-                                                    # (Available Samplers: ddim, plms, k_euler, k_euler_ancestral, k_heun, k_dpm_2, k_dpm_2_ancestral, k_dpmpp_2s_ancestral, k_lms, k_dpmpp_2m)
+    
+        if Input_type == 'TEXT':
+            st.write('**You are now in Text input mode**')
+            mytext = st.text_input('**Go on! Ask me anything:**')
+            if st.button("SUBMIT"):
+                question=mytext
+                response = openai.Completion.create(
+                  model="text-davinci-003",
+                  prompt=f'''Your name is HyperBot and  knowledge cutoff date is 2021-09, and you are not aware of any events after that time. if the  
+                            Answer to following questions is not from your knowledge base or in case of queries like weather 
+                              updates / stock updates / current news or people which requires you to have internet connection  then print i don't have access to internet to answer your question, 
+                              if  question is related to  image or  painting or drawing generation then print ipython type output function gen_draw("detailed prompt of image to be generated")
+                              if the question is related to playing a song or video or music of a singer then print ipython type output  function vid_tube("relevent search query")
+                              if the question is related to operating home appliances then print ipython type output function home_app(" action(ON/Off),appliance(TV,Geaser,Fridge,Lights,fans,AC)") . 
+                              if question is realted to sending mail or sms then print ipython type output function messenger_app(" message of us ,messenger(email,sms)")
+                              \nQuestion-{question}
+                              \nAnswer -''',
+                  temperature=0.49,
+                  max_tokens=256,
+                  top_p=1,
+                  frequency_penalty=0,
+                  presence_penalty=0
                 )
-
-                # Set up our warning to print to the console if the adult content classifier is tripped.
-                # If adult content classifier is not tripped, save generated images.
-                for resp in answers:
-                    for artifact in resp.artifacts:
-                        if artifact.finish_reason == generation.FILTER:
-                            warnings.warn(
-                                "Your request activated the API's safety filters and could not be processed."
-                                "Please modify the prompt and try again.")
-                        if artifact.type == generation.ARTIFACT_IMAGE:
-                            img = Image.open(io.BytesIO(artifact.binary))
-                            st.image(img)
-                            img.save(str(artifact.seed)+ ".png") # Save our generated images with their seed number as the filename.
+                string_temp=response.choices[0].text
+        
+                if ("gen_draw" in string_temp):
+                    try:
+                        try:
+                            wget.download(openai_response(prompt))
+                            img2 = Image.open(wget.download(openai_response(prompt)))
+                            img2.show()
                             rx = 'Image returned'
                             g_sheet_log(mytext, rx)
-                            
-            # except:        
-            #     st.write('image is being generated please wait...')
-            #     def extract_image_description(input_string):
-            #         return input_string.split('gen_draw("')[1].split('")')[0]
-            #     prompt=extract_image_description(string_temp)
-            #     # model_id = "CompVis/stable-diffusion-v1-4"
-            #     model_id='runwayml/stable-diffusion-v1-5'
-            #     device = "cuda"
-
-
-            #     pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
-            #     pipe = pipe.to(device)
-
-            #     # prompt = "a photo of an astronaut riding a horse on mars"
-            #     image = pipe(prompt).images[0]  
+                        except:
+                            urllib.request.urlretrieve(openai_response(prompt),"img_ret.png")
+                            img = Image.open("img_ret.png")
+                            img.show()
+                            rx = 'Image returned'
+                            g_sheet_log(mytext, rx)
+                    except:
+                        # Set up our initial generation parameters.
+                        answers = stability_api.generate(
+                        prompt = mytext,
+                        seed=992446758, # If a seed is provided, the resulting generated image will be deterministic.
+                                # What this means is that as long as all generation parameters remain the same, you can always recall the same image simply by generating it again.
+                                # Note: This isn't quite the case for Clip Guided generations, which we'll tackle in a future example notebook.
+                        steps=30, # Amount of inference steps performed on image generation. Defaults to 30.
+                        cfg_scale=8.0, # Influences how strongly your generation is guided to match your prompt.
+                            # Setting this value higher increases the strength in which it tries to match your prompt.
+                            # Defaults to 7.0 if not specified.
+                        width=512, # Generation width, defaults to 512 if not included.
+                        height=512, # Generation height, defaults to 512 if not included.
+                        samples=1, # Number of images to generate, defaults to 1 if not included.
+                        sampler=generation.SAMPLER_K_DPMPP_2M # Choose which sampler we want to denoise our generation with.
+                                                            # Defaults to k_dpmpp_2m if not specified. Clip Guidance only supports ancestral samplers.
+                                                            # (Available Samplers: ddim, plms, k_euler, k_euler_ancestral, k_heun, k_dpm_2, k_dpm_2_ancestral, k_dpmpp_2s_ancestral, k_lms, k_dpmpp_2m)
+                        )
+        
+                        # Set up our warning to print to the console if the adult content classifier is tripped.
+                        # If adult content classifier is not tripped, save generated images.
+                        for resp in answers:
+                            for artifact in resp.artifacts:
+                                if artifact.finish_reason == generation.FILTER:
+                                    warnings.warn(
+                                        "Your request activated the API's safety filters and could not be processed."
+                                        "Please modify the prompt and try again.")
+                                if artifact.type == generation.ARTIFACT_IMAGE:
+                                    img = Image.open(io.BytesIO(artifact.binary))
+                                    st.image(img)
+                                    img.save(str(artifact.seed)+ ".png") # Save our generated images with their seed number as the filename.
+                                    rx = 'Image returned'
+                                    g_sheet_log(mytext, rx)
+                                    
+                    # except:        
+                    #     st.write('image is being generated please wait...')
+                    #     def extract_image_description(input_string):
+                    #         return input_string.split('gen_draw("')[1].split('")')[0]
+                    #     prompt=extract_image_description(string_temp)
+                    #     # model_id = "CompVis/stable-diffusion-v1-4"
+                    #     model_id='runwayml/stable-diffusion-v1-5'
+                    #     device = "cuda"
+        
+        
+                    #     pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+                    #     pipe = pipe.to(device)
+        
+                    #     # prompt = "a photo of an astronaut riding a horse on mars"
+                    #     image = pipe(prompt).images[0]  
+                        
+                    #     image.save("astronaut_rides_horse.png")
+                    #     st.image(image)
+                    #     # image
+        
+                elif ("vid_tube" in string_temp):
+                    s = Search(mytext)
+                    search_res = s.results
+                    first_vid = search_res[0]
+                    print(first_vid)
+                    string = str(first_vid)
+                    video_id = string[string.index('=') + 1:-1]
+                    # print(video_id)
+                    YoutubeURL = "https://www.youtube.com/watch?v="
+                    OurURL = YoutubeURL + video_id
+                    st.write(OurURL)
+                    st_player(OurURL)
+                    ry = 'Youtube link and video returned'
+                    g_sheet_log(mytext, ry)
+        
+                elif ("don't" in string_temp or "internet" in string_temp):
+                    st.write('searching internet ')
+                    search_internet(question)
+                    rz = 'Internet result returned'
+                    g_sheet_log(mytext, string_temp)
+        
+                else:
+                    st.write(string_temp)
+                    g_sheet_log(mytext, string_temp)
+
+        elif Input_type == 'SPEECH':
+            try:
+                st.text("Record your audio, **max length - 5 seconds**")
+                if st.button("Record"):
+                    st.write("Recording...")
+                    audio_file = record_audio()
+                    st.write("Recording complete.")
+                    file = open(audio_file, "rb")
                 
-            #     image.save("astronaut_rides_horse.png")
-            #     st.image(image)
-            #     # image
-
-        elif ("vid_tube" in string_temp):
-            s = Search(mytext)
-            search_res = s.results
-            first_vid = search_res[0]
-            print(first_vid)
-            string = str(first_vid)
-            video_id = string[string.index('=') + 1:-1]
-            # print(video_id)
-            YoutubeURL = "https://www.youtube.com/watch?v="
-            OurURL = YoutubeURL + video_id
-            st.write(OurURL)
-            st_player(OurURL)
-            ry = 'Youtube link and video returned'
-            g_sheet_log(mytext, ry)
-
-        elif ("don't" in string_temp or "internet" in string_temp):
-            st.write('searching internet ')
-            search_internet(question)
-            rz = 'Internet result returned'
-            g_sheet_log(mytext, string_temp)
-
-        else:
-            st.write(string_temp)
-            g_sheet_log(mytext, string_temp)
-else:
-    pass
-    # elif Input_type == 'SPEECH':
-    #     stt_button = Button(label="Speak", width=100)
-    #     stt_button.js_on_event("button_click", CustomJS(code="""
-    #         var recognition = new webkitSpeechRecognition();
-    #         recognition.continuous = true;
-    #         recognition.interimResults = true;
-    #         recognition.onresult = function (e) {
-    #             var value = "";
-    #             for (var i = e.resultIndex; i < e.results.length; ++i) {
-    #                 if (e.results[i].isFinal) {
-    #                     value += e.results[i][0].transcript;
-    #                 }
-    #             }
-    #             if ( value != "") {
-    #                 document.dispatchEvent(new CustomEvent("GET_TEXT", {detail: value}));
-    #             }
-    #         }
-    #         recognition.start();
-    #         """))
+                    # Play the recorded audio
+                    st.audio(audio_file)
+                
+                    transcription = openai.Audio.transcribe("whisper-1", file)
+                    result = transcription["text"]
+                    st.write(f"Fetched from audio - {result}")
+                    question = result
+                    response = openai.Completion.create(
+                    model="text-davinci-003",
+                    prompt=f'''Your knowledge cutoff is 2021-09, and it is not aware of any events after that time. if the  
+                              Answer to following questions is not  from your knowledge base or in case of queries like weather 
+                                updates / stock updates / current news Etc which requires you to have internet connection  then print i don't have access to internet to answer your question, 
+                                if  question is related to  image or  painting or drawing generation then print ipython type output   function gen_draw("detailed prompt of image to be generated")
+                                if the question is related to playing a song or video or music of a singer then print ipython type output  function vid_tube("relevent search query")
+                                \nQuestion-{question}
+                                \nAnswer -''',
+                    temperature=0.49,
+                    max_tokens=256,
+                    top_p=1,
+                    frequency_penalty=0,
+                    presence_penalty=0
+                    )
+                    string_temp=response.choices[0].text
         
-    #     result = streamlit_bokeh_events(
-    #     stt_button,
-    #     events="GET_TEXT",
-    #     key="listen",
-    #     refresh_on_update=False,
-    #     override_height=75,
-    #     debounce_time=0)
-    
-    #     if result:
-    #         if "GET_TEXT" in result:
-    #             st.write(result.get("GET_TEXT"))
-    #             question = result.get("GET_TEXT")
-    #             response = openai.Completion.create(
-    #             model="text-davinci-003",
-    #             prompt=f'''Your knowledge cutoff is 2021-09, and it is not aware of any events after that time. if the  
-    #                       Answer to following questions is not  from your knowledge base or in case of queries like weather 
-    #                         updates / stock updates / current news Etc which requires you to have internet connection  then print i don't have access to internet to answer your question, 
-    #                         if  question is related to  image or  painting or drawing generation then print ipython type output   function gen_draw("detailed prompt of image to be generated")
-    #                         if the question is related to playing a song or video or music of a singer then print ipython type output  function vid_tube("relevent search query")
-    #                         \nQuestion-{question}
-    #                         \nAnswer -''',
-    #             temperature=0.49,
-    #             max_tokens=256,
-    #             top_p=1,
-    #             frequency_penalty=0,
-    #             presence_penalty=0
-    #             )
-    #             string_temp=response.choices[0].text
-    
-    #             if ("gen_draw" in string_temp):
-    #                 st.write('*image is being generated please wait..* ')
-    #                 def extract_image_description(input_string):
-    #                     return input_string.split('gen_draw("')[1].split('")')[0]
-    #                 prompt=extract_image_description(string_temp)
-    #                 # model_id = "CompVis/stable-diffusion-v1-4"
-    #                 model_id='runwayml/stable-diffusion-v1-5'
-    #                 device = "cuda"
-    
-    #                 pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
-    #                 pipe = pipe.to(device)
-    
-    #                 # prompt = "a photo of an astronaut riding a horse on mars"
-    #                 image = pipe(prompt).images[0]  
-                      
-    #                 image.save("astronaut_rides_horse.png")
-    #                 st.image(image)
-    #                 # image 
+                    if ("gen_draw" in string_temp):
+                        st.write('*image is being generated please wait..* ')
+                        def extract_image_description(input_string):
+                            return input_string.split('gen_draw("')[1].split('")')[0]
+                        prompt=extract_image_description(string_temp)
+                        # model_id = "CompVis/stable-diffusion-v1-4"
+                        model_id='runwayml/stable-diffusion-v1-5'
+                        device = "cuda"
+        
+                        pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+                        pipe = pipe.to(device)
+        
+                        # prompt = "a photo of an astronaut riding a horse on mars"
+                        image = pipe(prompt).images[0]  
+                          
+                        image.save("astronaut_rides_horse.png")
+                        st.image(image)
+                        # image 
+                    
+                    elif ("vid_tube" in string_temp):
+                        s = Search(question)
+                        search_res = s.results
+                        first_vid = search_res[0]
+                        print(first_vid)
+                        string = str(first_vid)
+                        video_id = string[string.index('=') + 1:-1]
+                        # print(video_id)
+                        YoutubeURL = "https://www.youtube.com/watch?v="
+                        OurURL = YoutubeURL + video_id
+                        st.write(OurURL)
+                        st_player(OurURL)
+        
+                    elif ("don't" in string_temp or "internet" in string_temp  ):
+                        st.write('*searching internet*')
+                        search_internet(question)
+                    else:
+                        st.write(string_temp)
+                    
+            except:
+                stt_button = Button(label="Speak", width=100)
+                stt_button.js_on_event("button_click", CustomJS(code="""
+                    var recognition = new webkitSpeechRecognition();
+                    recognition.continuous = true;
+                    recognition.interimResults = true;
+                    recognition.onresult = function (e) {
+                        var value = "";
+                        for (var i = e.resultIndex; i < e.results.length; ++i) {
+                            if (e.results[i].isFinal) {
+                                value += e.results[i][0].transcript;
+                            }
+                        }
+                        if ( value != "") {
+                            document.dispatchEvent(new CustomEvent("GET_TEXT", {detail: value}));
+                        }
+                    }
+                    recognition.start();
+                    """))
                 
-    #             elif ("vid_tube" in string_temp):
-    #                 s = Search(question)
-    #                 search_res = s.results
-    #                 first_vid = search_res[0]
-    #                 print(first_vid)
-    #                 string = str(first_vid)
-    #                 video_id = string[string.index('=') + 1:-1]
-    #                 # print(video_id)
-    #                 YoutubeURL = "https://www.youtube.com/watch?v="
-    #                 OurURL = YoutubeURL + video_id
-    #                 st.write(OurURL)
-    #                 st_player(OurURL)
-    
-    #             elif ("don't" in string_temp or "internet" in string_temp  ):
-    #                 st.write('*searching internet*')
-    #                 search_internet(question)
-    #             else:
-    #                 st.write(string_temp)
+                result = streamlit_bokeh_events(
+                stt_button,
+                events="GET_TEXT",
+                key="listen",
+                refresh_on_update=False,
+                override_height=75,
+                debounce_time=0)
+            
+                if result:
+                    if "GET_TEXT" in result:
+                        st.write(result.get("GET_TEXT"))
+                        question = result.get("GET_TEXT")
+                        response = openai.Completion.create(
+                        model="text-davinci-003",
+                        prompt=f'''Your knowledge cutoff is 2021-09, and it is not aware of any events after that time. if the  
+                                  Answer to following questions is not  from your knowledge base or in case of queries like weather 
+                                    updates / stock updates / current news Etc which requires you to have internet connection  then print i don't have access to internet to answer your question, 
+                                    if  question is related to  image or  painting or drawing generation then print ipython type output   function gen_draw("detailed prompt of image to be generated")
+                                    if the question is related to playing a song or video or music of a singer then print ipython type output  function vid_tube("relevent search query")
+                                    \nQuestion-{question}
+                                    \nAnswer -''',
+                        temperature=0.49,
+                        max_tokens=256,
+                        top_p=1,
+                        frequency_penalty=0,
+                        presence_penalty=0
+                        )
+                        string_temp=response.choices[0].text
+            
+                        if ("gen_draw" in string_temp):
+                            st.write('*image is being generated please wait..* ')
+                            def extract_image_description(input_string):
+                                return input_string.split('gen_draw("')[1].split('")')[0]
+                            prompt=extract_image_description(string_temp)
+                            # model_id = "CompVis/stable-diffusion-v1-4"
+                            model_id='runwayml/stable-diffusion-v1-5'
+                            device = "cuda"
+            
+                            pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+                            pipe = pipe.to(device)
+            
+                            # prompt = "a photo of an astronaut riding a horse on mars"
+                            image = pipe(prompt).images[0]  
+                              
+                            image.save("astronaut_rides_horse.png")
+                            st.image(image)
+                            # image 
+                        
+                        elif ("vid_tube" in string_temp):
+                            s = Search(question)
+                            search_res = s.results
+                            first_vid = search_res[0]
+                            print(first_vid)
+                            string = str(first_vid)
+                            video_id = string[string.index('=') + 1:-1]
+                            # print(video_id)
+                            YoutubeURL = "https://www.youtube.com/watch?v="
+                            OurURL = YoutubeURL + video_id
+                            st.write(OurURL)
+                            st_player(OurURL)
+            
+                        elif ("don't" in string_temp or "internet" in string_temp  ):
+                            st.write('*searching internet*')
+                            search_internet(question)
+                        else:
+                            st.write(string_temp)
+else:
+    pass