You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 

152 lines
4.3 KiB

{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"source": [
"# Getting MOM from call transcripts"
],
"metadata": {
"id": "99Z21wE7xpKS"
}
},
{
"cell_type": "markdown",
"source": [
"Import necessary libraries"
],
"metadata": {
"id": "YZMeexE8M_Pp"
}
},
{
"cell_type": "code",
"source": [
"# imports\n",
"\n",
"import os\n",
"import requests\n",
"\n",
"from bs4 import BeautifulSoup\n",
"from IPython.display import Markdown, display\n",
"from openai import OpenAI\n"
],
"metadata": {
"id": "u5DCVg0Mxj5T"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "i0V11JQ2az-C"
},
"outputs": [],
"source": [
"# Load environment variables in a file called .env\n",
"\n",
"#The below code can be uncommented in using .env file\n",
"\n",
"#from dotenv import load_dotenv\n",
"#load_dotenv(override=True)\n",
"#api_key = os.getenv('OPENAI_API_KEY')\n",
"\n",
"#I am using google colab to import api_key\n",
"from google.colab import userdata\n",
"api_key=userdata.get('gemini_api')\n",
"\n",
"# Check the key\n",
"if not api_key:\n",
" print(\"No API key was found - please head over to the troubleshooting notebook in this folder to identify & fix!\")\n",
"elif not api_key.startswith(\"sk-proj-\"):\n",
" print(\"An API key was found, but it doesn't start sk-proj-; please check you're using the right key - see troubleshooting notebook\")\n",
"elif api_key.strip() != api_key:\n",
" print(\"An API key was found, but it looks like it might have space or tab characters at the start or end - please remove them - see troubleshooting notebook\")\n",
"else:\n",
" print(\"API key found and looks good so far!\")"
]
},
{
"cell_type": "code",
"source": [
"# A class to represet Transcript\n",
"from pathlib import Path\n",
"class Transcript:\n",
" def __init__(self, file_path):\n",
" self.file_path=file_path\n",
" self.content=Path(file_path).read_text(encoding='utf-8')\n"
],
"metadata": {
"id": "j6UTsnTEyWZ-"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Source of the text file -\"https://raw.githubusercontent.com/GeminiLn/EarningsCall_Dataset/refs/heads/master/3M%20Company_20170425/Text.txt\"\n",
"path = '/content/Text.txt' # Specify the path of file you want to use - format should be .txt\n",
"t=Transcript(path)\n"
],
"metadata": {
"id": "hquePU_mzZ7s"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"\n",
"system_prompt = \"You are expert at taking Meeting Notes & given the below transcript , create an MOM (Minutes of meeting)\""
],
"metadata": {
"id": "ex5DB7M8L7KT"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"from google import genai\n",
"from google.genai import types\n",
"\n",
"client = genai.Client(api_key=api_key)\n",
"\n",
"response = client.models.generate_content(\n",
" model=\"gemini-2.0-flash\",\n",
" config=types.GenerateContentConfig(\n",
" system_instruction=system_prompt,\n",
" max_output_tokens=500,\n",
" temperature=0.1\n",
" ),\n",
" contents=t.content,\n",
")\n",
"\n",
"print(response.text)"
],
"metadata": {
"id": "wcpJ34qfMKmV"
},
"execution_count": null,
"outputs": []
}
]
}