Upload 6 files

app/.env

@@ -0,0 +1 @@
+GROQ_API_KEY=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

app/chains.py

@@ -0,0 +1,60 @@
+import os
+from langchain_groq import ChatGroq
+from langchain_core.prompts import PromptTemplate
+from langchain_core.output_parsers import JsonOutputParser
+from langchain_core.exceptions import OutputParserException
+from dotenv import load_dotenv
+
+load_dotenv()
+
+class Chain:
+    def __init__(self):
+        self.llm = ChatGroq(temperature=0, groq_api_key=os.getenv("GROQ_API_KEY"), model_name="llama-3.1-70b-versatile")
+
+    def extract_jobs(self, cleaned_text):
+        prompt_extract = PromptTemplate.from_template(
+            """
+            ### SCRAPED TEXT FROM WEBSITE:
+            {page_data}
+            ### INSTRUCTION:
+            The scraped text is from the career's page of a website.
+            Your job is to extract the job postings and return them in JSON format containing the following keys: `role`, `experience`, `skills` and `description`.
+            Only return the valid JSON.
+            ### VALID JSON (NO PREAMBLE):
+            """
+        )
+        chain_extract = prompt_extract | self.llm
+        res = chain_extract.invoke(input={"page_data": cleaned_text})
+        try:
+            json_parser = JsonOutputParser()
+            res = json_parser.parse(res.content)
+        except OutputParserException:
+            raise OutputParserException("Context too big. Unable to parse jobs.")
+        return res if isinstance(res, list) else [res]
+
+    def write_mail(self, job, links):
+        prompt_email = PromptTemplate.from_template(
+            """
+            ### JOB DESCRIPTION:
+            {job_description}
+
+            ### INSTRUCTION:
+            You are Mohan, a business development executive at AtliQ. AtliQ is an AI & Software Consulting company dedicated to facilitating
+            the seamless integration of business processes through automated tools. 
+            Over our experience, we have empowered numerous enterprises with tailored solutions, fostering scalability, 
+            process optimization, cost reduction, and heightened overall efficiency. 
+            Your job is to write a cold email to the client regarding the job mentioned above describing the capability of AtliQ 
+            in fulfilling their needs.
+            Also add the most relevant ones from the following links to showcase Atliq's portfolio: {link_list}
+            Remember you are Mohan, BDE at AtliQ. 
+            Do not provide a preamble.
+            ### EMAIL (NO PREAMBLE):
+
+            """
+        )
+        chain_email = prompt_email | self.llm
+        res = chain_email.invoke({"job_description": str(job), "link_list": links})
+        return res.content
+
+if __name__ == "__main__":
+    print(os.getenv("GROQ_API_KEY"))

app/main.py

@@ -0,0 +1,35 @@
+import streamlit as st
+from langchain_community.document_loaders import WebBaseLoader
+
+from chains import Chain
+from portfolio import Portfolio
+from utils import clean_text
+
+
+def create_streamlit_app(llm, portfolio, clean_text):
+    st.title("📧 Cold Mail Generator")
+    url_input = st.text_input("Enter a URL:", value="https://jobs.nike.com/job/R-33460")
+    submit_button = st.button("Submit")
+
+    if submit_button:
+        try:
+            loader = WebBaseLoader([url_input])
+            data = clean_text(loader.load().pop().page_content)
+            portfolio.load_portfolio()
+            jobs = llm.extract_jobs(data)
+            for job in jobs:
+                skills = job.get('skills', [])
+                links = portfolio.query_links(skills)
+                email = llm.write_mail(job, links)
+                st.code(email, language='markdown')
+        except Exception as e:
+            st.error(f"An Error Occurred: {e}")
+
+
+if __name__ == "__main__":
+    chain = Chain()
+    portfolio = Portfolio()
+    st.set_page_config(layout="wide", page_title="Cold Email Generator", page_icon="📧")
+    create_streamlit_app(chain, portfolio, clean_text)
+
+

app/portfolio.py

@@ -0,0 +1,21 @@
+import pandas as pd
+import chromadb
+import uuid
+
+
+class Portfolio:
+    def __init__(self, file_path="app/resource/my_portfolio.csv"):
+        self.file_path = file_path
+        self.data = pd.read_csv(file_path)
+        self.chroma_client = chromadb.PersistentClient('vectorstore')
+        self.collection = self.chroma_client.get_or_create_collection(name="portfolio")
+
+    def load_portfolio(self):
+        if not self.collection.count():
+            for _, row in self.data.iterrows():
+                self.collection.add(documents=row["Techstack"],
+                                    metadatas={"links": row["Links"]},
+                                    ids=[str(uuid.uuid4())])
+
+    def query_links(self, skills):
+        return self.collection.query(query_texts=skills, n_results=2).get('metadatas', [])

app/resource/my_portfolio.csv

@@ -0,0 +1,21 @@
+"Techstack","Links"
+"React, Node.js, MongoDB","https://example.com/react-portfolio"
+"Angular,.NET, SQL Server","https://example.com/angular-portfolio"
+"Vue.js, Ruby on Rails, PostgreSQL","https://example.com/vue-portfolio"
+"Python, Django, MySQL","https://example.com/python-portfolio"
+"Java, Spring Boot, Oracle","https://example.com/java-portfolio"
+"Flutter, Firebase, GraphQL","https://example.com/flutter-portfolio"
+"WordPress, PHP, MySQL","https://example.com/wordpress-portfolio"
+"Magento, PHP, MySQL","https://example.com/magento-portfolio"
+"React Native, Node.js, MongoDB","https://example.com/react-native-portfolio"
+"iOS, Swift, Core Data","https://example.com/ios-portfolio"
+"Android, Java, Room Persistence","https://example.com/android-portfolio"
+"Kotlin, Android, Firebase","https://example.com/kotlin-android-portfolio"
+"Android TV, Kotlin, Android NDK","https://example.com/android-tv-portfolio"
+"iOS, Swift, ARKit","https://example.com/ios-ar-portfolio"
+"Cross-platform, Xamarin, Azure","https://example.com/xamarin-portfolio"
+"Backend, Kotlin, Spring Boot","https://example.com/kotlin-backend-portfolio"
+"Frontend, TypeScript, Angular","https://example.com/typescript-frontend-portfolio"
+"Full-stack, JavaScript, Express.js","https://example.com/full-stack-js-portfolio"
+"Machine Learning, Python, TensorFlow","https://example.com/ml-python-portfolio"
+"DevOps, Jenkins, Docker","https://example.com/devops-portfolio"

app/utils.py

@@ -0,0 +1,16 @@
+import re
+
+def clean_text(text):
+    # Remove HTML tags
+    text = re.sub(r'<[^>]*?>', '', text)
+    # Remove URLs
+    text = re.sub(r'http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+', '', text)
+    # Remove special characters
+    text = re.sub(r'[^a-zA-Z0-9 ]', '', text)
+    # Replace multiple spaces with a single space
+    text = re.sub(r'\s{2,}', ' ', text)
+    # Trim leading and trailing whitespace
+    text = text.strip()
+    # Remove extra whitespace
+    text = ' '.join(text.split())
+    return text