Merge pull request #697 from srbmisc/week3_day5_srb

Week 3 Day 5 meeting minutes generator using gradio.

week3/community-contributions/day5_srb_meeting_minutes_generator.ipynb

@@ -0,0 +1,167 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "7ce4a475",
+   "metadata": {},
+   "source": [
+    "Week 3, day 5, meeting minutes generator. Code for Google Collab."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2abc87f0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install -q --upgrade torch==2.5.1+cu124 torchvision==0.20.1+cu124 torchaudio==2.5.1+cu124 --index-url https://download.pytorch.org/whl/cu124\n",
+    "!pip install -q requests bitsandbytes==0.46.0 transformers==4.48.3 accelerate==1.3.0 openai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "83fa62ec",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# imports\n",
+    "\n",
+    "import os\n",
+    "import requests\n",
+    "from IPython.display import Markdown, display\n",
+    "from openai import OpenAI\n",
+    "from huggingface_hub import login\n",
+    "from google.colab import userdata\n",
+    "from transformers import AutoTokenizer, AutoModelForCausalLM, TextStreamer, BitsAndBytesConfig\n",
+    "import torch\n",
+    "import gradio as gr"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e5ee86f8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Sign in to HuggingFace Hub\n",
+    "\n",
+    "hf_token = userdata.get('HF_TOKEN')\n",
+    "login(hf_token, add_to_git_credential=True)\n",
+    "\n",
+    "# Sign in to OpenAI using Secrets in Colab\n",
+    "\n",
+    "openai_api_key = userdata.get('OPENAI_API_KEY')\n",
+    "openai = OpenAI(api_key=openai_api_key)\n",
+    "\n",
+    "\n",
+    "AUDIO_MODEL = \"whisper-1\"\n",
+    "LLAMA = \"meta-llama/Meta-Llama-3.1-8B-Instruct\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f0dd5a0d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def generate_meeting_minutes(file_data):\n",
+    "  print(\"calling openai to generate transcript\")\n",
+    "  transcription = openai.audio.transcriptions.create(model=AUDIO_MODEL, file=file_data, response_format=\"text\")\n",
+    "  print(\"transcript generated\")\n",
+    "  print(transcription)\n",
+    "  system_message = \"You are an assistant that produces minutes of meetings from transcripts, with summary, key discussion points, takeaways and action items with owners, in markdown.\"\n",
+    "  user_prompt = f\"Below is an extract transcript of a Denver council meeting. Please write minutes in markdown, including a summary with attendees, location and date; discussion points; takeaways; and action items with owners.\\n{transcription}\"\n",
+    "\n",
+    "  messages = [\n",
+    "    {\"role\": \"system\", \"content\": system_message},\n",
+    "    {\"role\": \"user\", \"content\": user_prompt}\n",
+    "  ]\n",
+    "  quant_config = BitsAndBytesConfig(\n",
+    "    load_in_4bit=True,\n",
+    "    bnb_4bit_use_double_quant=True,\n",
+    "    bnb_4bit_compute_dtype=torch.bfloat16,\n",
+    "    bnb_4bit_quant_type=\"nf4\"\n",
+    "  )\n",
+    "  print(\"calling tokenizer\")\n",
+    "  tokenizer = AutoTokenizer.from_pretrained(LLAMA)\n",
+    "  tokenizer.pad_token = tokenizer.eos_token\n",
+    "  inputs = tokenizer.apply_chat_template(messages, return_tensors=\"pt\").to(\"cuda\")\n",
+    "  streamer = TextStreamer(tokenizer)\n",
+    "  print(\"calling model\")\n",
+    "  model = AutoModelForCausalLM.from_pretrained(LLAMA, device_map=\"auto\", quantization_config=quant_config)\n",
+    "  outputs = model.generate(inputs, max_new_tokens=2000, streamer=streamer)\n",
+    "  return tokenizer.decode(outputs[0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a938b681",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def process_binary_file(file_data):\n",
+    "    \"\"\"\n",
+    "    This function receives the uploaded file content as a bytes object.\n",
+    "    You can then process the binary data as needed.\n",
+    "    \"\"\"\n",
+    "    if file_data:\n",
+    "        # Example: Get the size of the binary data\n",
+    "        print(f\"processing file\")\n",
+    "        with open(file_data.name, \"rb\") as f:\n",
+    "          return generate_meeting_minutes(f)\n",
+    "\n",
+    "    return \"No file uploaded or file is empty.\"\n",
+    "\n",
+    "with gr.Blocks() as demo:\n",
+    "    gr.Markdown(\"Upload a file and its binary content will be processed.\")\n",
+    "\n",
+    "    # Use gr.File with type=\"binary\"\n",
+    "    file_input = gr.File(type=\"filepath\", file_count=\"single\", file_types=[\".mp3\"], label=\"Upload a meeting file\")\n",
+    "\n",
+    "    # Or use gr.UploadButton with type=\"binary\"\n",
+    "    # upload_button = gr.UploadButton(\"Click to Upload Binary File\", type=\"binary\")\n",
+    "\n",
+    "    output_text = gr.Textbox(label=\"Processing Result\")\n",
+    "\n",
+    "    # Link the file_input to the processing function\n",
+    "    file_input.upload(process_binary_file, inputs=file_input, outputs=output_text)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6baed239",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "demo.launch(debug=True)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.11"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}