Upload pitch_deck.py

pitch_deck.py

@@ -0,0 +1,383 @@
+# -*- coding: utf-8 -*-
+"""Pitch_deck
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1ryLKlHjf3azJ4gp_klTOF2zhSOn01cSH
+
+# A full business solution
+
+## Now we will take our project from Day 1 to the next level
+
+### BUSINESS CHALLENGE:
+
+Create a product that builds a Brochure for a company to be used for prospective clients, investors and potential recruits.
+
+We will be provided a company name and their primary website.
+
+See the end of this notebook for examples of real-world business applications.
+
+And remember: I'm always available if you have problems or ideas! Please do reach out.
+"""
+
+# !pip install dotenv
+# !pip install openai
+# !pip install bs4
+# !pip install requests
+# !pip install python-dotenv
+# !pip install IPython
+
+# import the important
+
+import os
+import requests
+import json
+from typing import List
+from dotenv import load_dotenv
+from bs4 import BeautifulSoup
+from IPython.display import Markdown, display, update_display
+from openai import OpenAI
+
+#initilize the openai key
+from google.colab import userdata
+open_ai_key = userdata.get('OPENAI_API_KEY')
+grok_key = userdata.get('XAI_API_KEY')
+openai = OpenAI(api_key = open_ai_key)
+MODEL = 'gpt-4o-mini'
+
+# Initialize and constants
+
+# load_dotenv(override=True)
+# api_key = os.getenv('OPENAI_API_KEY')
+
+# if api_key and api_key.startswith('sk-proj-') and len(api_key)>10:
+#     print("API key looks good so far")
+# else:
+#     print("There might be a problem with your API key? Please visit the troubleshooting notebook!")
+
+# MODEL = 'gpt-4o-mini'
+# openai = OpenAI()
+
+# A class to represent a Webpage
+
+# Some websites need you to use proper headers when fetching them:
+headers = {
+ "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36"
+}
+
+class Website:
+    """
+    A utility class to represent a Website that we have scraped, now with links
+    """
+
+    def __init__(self, url):
+        self.url = url
+        response = requests.get(url, headers=headers)
+        self.body = response.content
+        soup = BeautifulSoup(self.body, 'html.parser')
+        self.title = soup.title.string if soup.title else "No title found"
+        if soup.body:
+            for irrelevant in soup.body(["script", "style", "img", "input"]):
+                irrelevant.decompose()
+            self.text = soup.body.get_text(separator="\n", strip=True)
+        else:
+            self.text = ""
+        links = [link.get('href') for link in soup.find_all('a')]
+        self.links = [link for link in links if link]
+
+    def get_contents(self):
+        return f"Webpage Title:\n{self.title}\nWebpage Contents:\n{self.text}\n\n"
+
+# ted = Website("https://invoice.2go.com")
+# ted.links
+
+link_system_prompted = "You are to choose the links that are relevant in terms of marketing in this website and then \
+                        and then you are to follow through with picking them out. Do not choose privacy link, and anyother irrelevant ones\n"
+link_system_prompted += "Respond in Json"
+link_system_prompted += """Follow this example \
+"links ={type: about us : "https://something/somethinhg"}"""
+
+link_system_prompted
+
+def link_user_prompted(website):
+    User_prompter = f"I would like to know the relevant link in the {website.url} - "
+    User_prompter += "Please decide which of the links is more relevant and also ignore privacy policy and emails"
+    User_prompter +=  "\n" .join(website.links)
+    return User_prompter
+
+link_user_prompted(ted)
+
+def get_stuff(Url):
+    website = Website.url
+    response =openai.chat.completion.create(
+        model = Model,
+        messages=[
+            {"role": "system", "content": link_user_prompted},
+            {"role": "user", "content": link_user_prompted(website)}
+      ],
+        response_format={"type": "json_object"}
+    )
+    result = response.choices[0].message.content
+    return json.loads(result)
+
+# ed = Website("https://squeakycleaningservices.co.uk")
+# ed.links
+
+"""## First step: Have GPT-4o-mini figure out which links are relevant
+
+### Use a call to gpt-4o-mini to read the links on a webpage, and respond in structured JSON.  
+It should decide which links are relevant, and replace relative links such as "/about" with "https://company.com/about".  
+We will use "one shot prompting" in which we provide an example of how it should respond in the prompt.
+
+This is an excellent use case for an LLM, because it requires nuanced understanding. Imagine trying to code this without LLMs by parsing and analyzing the webpage - it would be very hard!
+
+Sidenote: there is a more advanced technique called "Structured Outputs" in which we require the model to respond according to a spec. We cover this technique in Week 8 during our autonomous Agentic AI project.
+"""
+
+link_system_prompt = "You are provided with a list of links found on a webpage. \
+You are able to decide which of the links would be most relevant to include in a brochure about the company, \
+such as links to an About page, or a Company page, or Careers/Jobs pages.\n"
+link_system_prompt += "You should respond in JSON as in this example:"
+link_system_prompt += """
+{
+    "links": [
+        {"type": "about page", "url": "https://full.url/goes/here/about"},
+        {"type": "careers page": "url": "https://another.full.url/careers"}
+    ]
+}
+"""
+
+print(link_system_prompt)
+
+def get_links_user_prompt(website):
+    user_prompt = f"Here is the list of links on the website of {website.url} - "
+    user_prompt += "please decide which of these are relevant web links for a brochure about the company, respond with the full https URL in JSON format. \
+Do not include Terms of Service, Privacy, email links.\n"
+    user_prompt += "Links (some might be relative links):\n"
+    user_prompt += "\n".join(website.links)
+    return user_prompt
+
+print(get_links_user_prompt(ed))
+
+def get_links(url):
+    website = Website(url)
+    response = openai.chat.completions.create(
+        model= MODEL,
+        messages=[
+            {"role": "system", "content": link_system_prompt},
+            {"role": "user", "content": get_links_user_prompt(website)}
+      ],
+        response_format={"type": "json_object"}
+    )
+    result = response.choices[0].message.content
+    return json.loads(result)
+
+# sample
+
+Diamondadverts = Website("https://diamondadverts.com")
+Diamondadverts.links
+
+get_links("https://squeakycleaningservices.co.uk")
+
+
+
+"""## Second step: make the pitch deck!
+
+Assemble all the details into another prompt to GPT4-o
+"""
+
+def get_all_details(url):
+    result = "Landing page:\n"
+    result += Website(url).get_contents()
+    links = get_links(url)
+    print("Found links:", links)
+    for link in links["links"]:
+        result += f"\n\n{link['type']}\n"
+        result += Website(link["url"]).get_contents()
+    return result
+
+print(get_all_details("https://squeakycleaningservices.co.uk"))
+
+# system_prompt = "You are an assistant that analyzes the contents of several relevant pages from a company website \
+# and creates a short pitch deck for the company, so the comapany can use it to apply for mor jobs and clients, investors and recruits. Respond in markdown.\
+# Include details of company culture, customers and careers/jobs if you have the information."
+
+system_prompt = """
+You are a business analyst specializing in creating compelling pitch decks from company website content. Respond in markdown.\
+Your task is to analyze multiple relevant pages from a company's website and synthesize the information into a concise, \
+professional pitch deck that the company can use for business development, investor relations.
+
+Your pitch deck should be formatted in markdown and include the following sections when information is available:
+- Company overview and mission
+- Products/services and value proposition
+- Target market and customer base
+- Company culture and values
+- Growth potential and achievements
+- Contact information
+- End with We are always happy to help you with (list the services again)
+
+Focus on creating a narrative that highlights the company's strengths, unique positioning, and opportunities for partnership,\
+ investment. Ensure the content is professional, engaging, and suitable for multiple audiences including potential clients and investors."""
+
+
+# system_prompt = "You are an assistant that analyzes the contents of several relevant pages from a company website \
+# and creates a short humorous, entertaining, jokey brochure about the company for prospective customers, investors and recruits. Respond in markdown.\
+# Include details of company culture, customers and careers/jobs if you have the information."
+
+def get_pitch_user_prompt(company_name, url):
+    user_prompt = f"You are looking at a company called: {company_name}\n"
+    user_prompt += f"Here are the contents of its landing page and other relevant pages; use this information to build a short pitch deck for the company, of the company in markdown.\n"
+    user_prompt += get_all_details(url)
+    user_prompt = user_prompt[:5_000] # Truncate if more than 5,000 characters
+    return user_prompt
+
+get_pitch_user_prompt("Squeaky cleaning Services", "https://squeakycleaningservices.co.uk")
+
+def pitch_deck(company_name, url):
+    response = openai.chat.completions.create(
+        model=MODEL,
+        messages=[
+            {"role": "system", "content": system_prompt},
+            {"role": "user", "content": get_pitch_user_prompt(company_name, url)}
+          ],
+    )
+    result = response.choices[0].message.content
+    display(Markdown(result))
+
+pitch_deck("Squeaky Cleaning Services", "https://squeakycleaningservices.co.uk")
+
+"""## Finally - a minor improvement
+
+With a small adjustment, we can change this so that the results stream back from OpenAI,
+with the familiar typewriter animation
+"""
+
+def stream_pitchdeck(company_name, url):
+    stream = openai.chat.completions.create(
+        model=MODEL,
+        messages=[
+            {"role": "system", "content": system_prompt},
+            {"role": "user", "content": get_pitch_user_prompt(company_name, url)}
+          ],
+        stream=True
+    )
+
+    response = ""
+    display_handle = display(Markdown(""), display_id=True)
+    for chunk in stream:
+        response += chunk.choices[0].delta.content or ''
+        response = response.replace("```","").replace("markdown", "")
+        update_display(Markdown(response), display_id=display_handle.display_id)
+
+stream_pitchdeck("Squeaky Cleaning Services", "https://squeakycleaningservices.co.uk")
+
+# Try
+
+# stream_pitchdeck("Squeaky Cleaning Services", "https://squeakycleaningservices.co.uk")
+
+# prompt: Generate a gradio code from the funtion
+
+!pip install gradio -q
+import gradio as gr
+
+def get_links_user_prompt(website):
+    user_prompt = f"Here is the list of links on the website of {website.url} - "
+    user_prompt += "please decide which of these are relevant web links for a brochure about the company, respond with the full https URL in JSON format. \
+Do not include Terms of Service, Privacy, email links.\n"
+    user_prompt += "Links (some might be relative links):\n"
+    user_prompt += "\n".join(website.links)
+    return user_prompt
+
+system_prompt = """
+You are a business analyst specializing in creating compelling pitch decks from company website content. Respond in markdown.\
+Your task is to analyze multiple relevant pages from a company's website and synthesize the information into a concise, \
+professional pitch deck that the company can use for business development, investor relations.
+
+Your pitch deck should be formatted in markdown and include the following sections when information is available:
+- Company overview and mission
+- Products/services and value proposition
+- Target market and customer base
+- Company culture and values
+- Growth potential and achievements
+- Contact information
+- End with We are always happy to help you with (list the services again)
+
+Focus on creating a narrative that highlights the company's strengths, unique positioning, and opportunities for partnership,\
+ investment. Ensure the content is professional, engaging, and suitable for multiple audiences including potential clients and investors."""
+
+def get_all_details(url):
+    result = "Landing page:\n"
+    result += Website(url).get_contents()
+    links = get_links(url)
+    print("Found links:", links)
+    for link in links.get("links", []):
+        result += f"\n\n{link.get('type', 'Unknown Type')}\n"
+        # Ensure the URL is valid before attempting to scrape
+        if link.get('url') and (link['url'].startswith('http://') or link['url'].startswith('https://')):
+            try:
+                result += Website(link["url"]).get_contents()
+            except Exception as e:
+                result += f"Could not retrieve content for {link['url']}: {e}\n"
+        else:
+            result += f"Invalid URL found: {link.get('url')}\n"
+    return result
+
+def get_pitch_user_prompt(company_name, url):
+    user_prompt = f"You are looking at a company called: {company_name}\n"
+    user_prompt += f"Here are the contents of its landing page and other relevant pages; use this information to build a short pitch deck for the company, of the company in markdown.\n"
+    try:
+        user_prompt += get_all_details(url)
+    except Exception as e:
+        user_prompt += f"Error getting website details: {e}\n"
+        print(f"Error getting website details for {url}: {e}")
+        # Provide a fallback or stop processing if website cannot be scraped
+        return "Could not retrieve website details to generate pitch deck."
+
+    user_prompt = user_prompt[:5_000] # Truncate if more than 5,000 characters
+    return user_prompt
+
+
+def generate_pitch_deck(company_name, url):
+    if not company_name or not url:
+        return "Please provide both company name and URL."
+
+    user_prompt = get_pitch_user_prompt(company_name, url)
+
+    if user_prompt == "Could not retrieve website details to generate pitch deck.":
+        return user_prompt
+
+    try:
+        response = openai.chat.completions.create(
+            model=MODEL,
+            messages=[
+                {"role": "system", "content": system_prompt},
+                {"role": "user", "content": user_prompt}
+              ],
+            stream=True  # Enable streaming for better UX in Gradio
+        )
+
+        # Stream the response
+        full_response = ""
+        for chunk in response:
+            content = chunk.choices[0].delta.content
+            if content is not None:
+                full_response += content
+                yield full_response # Yield intermediate results for streaming
+
+        return full_response # Return the final result
+    except Exception as e:
+        return f"An error occurred during OpenAI API call: {e}"
+
+iface = gr.Interface(
+    fn=generate_pitch_deck,
+    inputs=[
+        gr.Textbox(label="Company Name"),
+        gr.Textbox(label="Company Website URL")
+    ],
+    outputs=gr.Markdown(label="Generated Pitch Deck"),
+    title="Company Pitch Deck Generator",
+    description="Enter the company name and website URL to generate a pitch deck based on their website content."
+)
+
+iface.launch()