Upload folder using huggingface_hub

.gitignore

@@ -1,2 +1,3 @@
 .env
-__pycache__
+__pycache__
+test*.ipynb

backend.py

@@ -1,20 +1,40 @@
 import os
+import time
 from typing import List
 
 from dotenv import load_dotenv
 import openai
 import gradio as gr
+import numpy as np
 
+load_dotenv()
 
-if load_dotenv():
-    openai.api_key = os.getenv("OPENAI_API_KEY")
-else:
-    openai.api_key = os.environ["OPENAI_API_KEY"]
+openai.api_key = os.getenv("OPENAI_API_KEY")
+# else:
+#     openai.api_key = os.environ["OPENAI_API_KEY"]
 
 
 message_history = []
 cost = 0
 
+def transcribe(audio, state=""):
+    time.sleep(2)
+
+    transcript = openai.Audio.transcribe(
+        model="whisper-1", file=open(audio, "rb"), response_format="verbose_json"
+    )
+
+    text = transcript["text"]
+    cost += np.ceil(transcript["duration"])
+    
+    return text 
+
+    # for char in text:
+    #     state += char
+
+    # yield state
+
+
 
 def add_text(
     user_input: str, history: List, system_role: str = "You are a great assistant"

gen_app.py

@@ -0,0 +1,60 @@
+import os
+from dotenv import load_dotenv
+from typing import Literal, List
+import requests
+
+import openai
+from PIL import Image as img
+from PIL.Image import Image
+
+import gradio as gr
+
+load_dotenv()
+
+openai.api_key = os.getenv("OPENAI_API_KEY")
+
+
+def get_images(
+    prompt: str,
+    num_images=1,
+    img_size: Literal["256x256", "512x512", "1024x1024"] = "256x256",
+) -> List[Image]:
+    response = openai.Image.create(
+        prompt=prompt,
+        n=num_images,
+        size=img_size,
+    )
+
+    urls = [res["url"] for res in response["data"]]
+
+    images = [img.open(requests.get(url, stream=True).raw) for url in urls]
+
+    return images
+
+
+with gr.Blocks() as demo:
+    with gr.Column(variant="panel"):
+        with gr.Row(variant="compact"):
+            text = gr.Textbox(
+                label="Enter your prompt",
+                show_label=False,
+                max_lines=1,
+                placeholder="Enter your prompt",
+                container=False,
+            )
+            btn = gr.Button("Generate image")
+
+        gallery = gr.Gallery(
+            label="Generated images",
+            show_label=False,
+            elem_id="gallery",
+            columns=2,
+            rows=2,
+            object_fit="contain",
+            height="auto",
+        )
+
+    btn.click(fn=get_images, inputs=text, outputs=gallery)
+
+if __name__ == "__main__":
+    demo.launch()

notebook.ipynb

@@ -11,36 +11,101 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from dotenv import load_dotenv\n",
+    "\n",
+    "import openai\n",
+    "\n",
+    "if load_dotenv():\n",
+    "    openai.api_key = os.getenv('OPENAI_API_KEY')\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"audio/use.mp3\", \"rb\") as file:\n",
+    "    transcript = openai.Audio.transcribe(\n",
+    "        model=\"whisper-1\", file=file, response_format=\"verbose_json\"\n",
+    "    )\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# transcript"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "True"
+       "'Hello.'"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "import os\n",
-    "from dotenv import load_dotenv\n",
-    "\n",
-    "import openai\n",
-    "\n",
-    "if load_dotenv():\n",
-    "    openai.api_key = os.getenv('OPENAI_API_KEY')\n"
+    "transcript['text']"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 13,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "9.0"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import numpy as np\n",
+    "np.ceil(transcript['duration'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.054"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "cost = np.ceil(transcript['duration']) * 0.006\n",
+    "cost"
+   ]
   },
   {
    "cell_type": "code",

requirements.txt

@@ -1,3 +1,4 @@
 gradio==3.35.2
+numpy==1.25.0
 openai==0.27.8
 python-dotenv==1.0.0

test.py

@@ -1,32 +1,36 @@
 import gradio as gr
+import openai
 
+from dotenv import load_dotenv
+import os
 
-def sentence_builder(quantity, animal, countries, place, activity_list, morning):
-    return f"""The {quantity} {animal}s from {" and ".join(countries)} went to the {place} where they {" and ".join(activity_list)} until the {"morning" if morning else "night"}"""
-
-
-demo = gr.Interface(
-    sentence_builder,
-    [
-        gr.Slider(2, 20, value=4, label="Count", info="Choose between 2 and 20"),
-        gr.Dropdown(
-            ["cat", "dog", "bird"], label="Animal", info="Will add more animals later!"
-        ),
-        gr.CheckboxGroup(["USA", "Japan", "Pakistan"], label="Countries", info="Where are they from?"),
-        gr.Radio(["park", "zoo", "road"], label="Location", info="Where did they go?"),
-        gr.Dropdown(
-            ["ran", "swam", "ate", "slept"], value=["swam", "slept"], multiselect=True, label="Activity", info="Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed auctor, nisl eget ultricies aliquam, nunc nisl aliquet nunc, eget aliquam nisl nunc vel nisl."
-        ),
-        gr.Checkbox(label="Morning", info="Did they do it in the morning?"),
-    ],
-    "text",
-    examples=[
-        [2, "cat", ["Japan", "Pakistan"], "park", ["ate", "swam"], True],
-        [4, "dog", ["Japan"], "zoo", ["ate", "swam"], False],
-        [10, "bird", ["USA", "Pakistan"], "road", ["ran"], False],
-        [8, "cat", ["Pakistan"], "zoo", ["ate"], True],
-    ]
+load_dotenv()
+
+openai.api_key = os.getenv("OPENAI_API_KEY")
+
+messages = [{"role": "system", "content": "You are a teacher"}]
+
+
+def transcribe(audio):
+    global messages
+    file = open(audio, "rb")
+    transcription = openai.Audio.transcribe("whisper-1", file)
+    print(transcription)
+    messages.append({"role": "user", "content": transcription["text"]})
+    response = openai.ChatCompletion.create(model="gpt-3.5-turbo", messages=messages)
+
+    AImessage = response["choices"][0]["message"]["content"]
+    
+    messages.append({"role": "assistant", "content": AImessage})
+    chat = ""
+    for message in messages:
+        if message["role"] != "system":
+            chat += message["role"] + ":" + message["content"] + "\n\n"
+    return chat
+
+
+ui = gr.Interface(
+    fn=transcribe, inputs=gr.Audio(type="filepath"), outputs="text"
 )
 
-if __name__ == "__main__":
-    demo.launch()
+ui.launch()

work-app.py

@@ -1,27 +1,21 @@
 import gradio as gr
-from backend import generate_response, add_text, calc_cost
-
-
-# @click.command()
-# @click.option(
-#     "-s",
-#     "--system_role",
-#     default="You are good assistant",
-#     type=str,
-#     help="Which role do you want the chatbot to take in replying your messages",
-# )
-# def app():
+from backend import generate_response, add_text, calc_cost, transcribe
+
+
 with gr.Blocks() as demo:
     chatbot = gr.Chatbot()
 
     with gr.Row():
+        # with gr.Column(scale=0.05):
+            # audio = gr.Audio(type="filepath")
+
         with gr.Column(scale=0.9):
             message = gr.Textbox(
-                show_label=False,
+                label="\n",
                 placeholder="Please enter a message and press Enter",
             )
 
-        with gr.Column(scale=0.1):
+        with gr.Column(scale=0.05):
             cost_view = gr.Number(label="Usage in $", value=0)
 
     clear = gr.ClearButton([chatbot, message, cost_view])
@@ -32,6 +26,8 @@ with gr.Blocks() as demo:
         info="Which openai chat model to use",
     )
 
+    # audio.upload(transcribe, inputs=[audio], outputs=[message])
+
     response = (
         message.submit(add_text, [message, chatbot], [message, chatbot], queue=False)
         .then(generate_response, [chatbot, models], chatbot)