Upload 4 files

firm-capsule-436804-b5-5f553d9f1043.json

@@ -0,0 +1,13 @@
+{
+  "type": "service_account",
+  "project_id": "firm-capsule-436804-b5",
+  "private_key_id": "5f553d9f10439131e44a6fd903ad024e9872344c",
+  "private_key": "-----BEGIN PRIVATE KEY-----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\nRvlqI5p9EOBJSqwEksd+jxY=\n-----END PRIVATE KEY-----\n",
+  "client_email": "[email protected]",
+  "client_id": "105433240521758892195",
+  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+  "token_uri": "https://oauth2.googleapis.com/token",
+  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
+  "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/genai-328%40firm-capsule-436804-b5.iam.gserviceaccount.com",
+  "universe_domain": "googleapis.com"
+}

resume_generation_gemini_pro.py

@@ -0,0 +1,188 @@
+# -*- coding: utf-8 -*-
+"""Resume_generation_Gemini_pro.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/16z793IRwVmvKYCaOLGZFDYj-XOj8zEJL
+"""
+
+# from google.colab import drive,userdata
+
+# drive.mount('/content/drive')
+
+# !pip install streamlit -qq
+
+# !pip install PyPDF2 -qq
+
+# !pip install langchain_community -qq
+
+# !pip install langchain_google_genai -qq
+
+# !pip install python-docx -qq
+
+# !pip install docx2txt -qq
+
+# !pip install faiss-gpu -qq
+
+# !pip install google-generativeai -qq
+
+# !pip install --upgrade google-generativeai -qq
+
+import docx2txt
+import PyPDF2
+def extract_text(file_path):
+    if file_path.endswith(".docx"):
+        # Extract text from DOCX file
+        return docx2txt.process(file_path)
+
+    elif file_path.endswith(".pdf"):
+        # Extract text from PDF file
+        text = ""
+        with open(file_path, 'rb') as file:
+            reader = PyPDF2.PdfReader(file)
+            for page_num in range(len(reader.pages)):
+                text += reader.pages[page_num].extract_text()
+        return text
+
+    else:
+        raise ValueError("Unsupported file type")
+
+# from google.colab import auth
+# auth.authenticate_user()
+
+import os
+os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "firm-capsule-436804-b5-5f553d9f1043.json"
+
+# !pip install python-docx
+
+import os
+import streamlit as st
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores.faiss import FAISS
+# from google.colab import drive
+from docx import Document
+import google.generativeai as genai
+from datetime import datetime
+
+api_key_google = 'AIzaSyC8rXXpyVnAnnMG1rxPOF0JpWWPnCH1h_Y'
+genai.configure(api_key=api_key_google)
+
+# Mount Google Drive
+# drive.mount('/content/drive')
+
+model = genai.GenerativeModel('gemini-pro')
+
+def save_resume_to_docx(tailored_resume, file_path):
+    doc = Document()
+    doc.add_heading('Tailored Resume', level=1)
+    doc.add_paragraph(tailored_resume)
+    doc.save(file_path)
+
+# Function to read text from a .docx file
+def read_docx(file_path):
+    doc = Document(file_path)
+    return "\n".join([para.text for para in doc.paragraphs])
+
+def generate_resume_text(resume_text):
+    prompt = f"""
+Given the following resume content:
+
+[Resume Start]
+{resume_text}
+[Resume End]
+
+Format this resume content with appropriate section titles. Only use the information provided and avoid placeholders like "[Your Name]". Ensure it retains the structure and details exactly as shown.
+"""
+    try:
+        response = model.generate_content(prompt)
+        print(response)
+        # Accessing the generated text content
+        return response.candidates[0].content.parts[0].text
+    except Exception as e:
+        print("Error in generating resume text:", e)
+        return None
+
+def tailor_resume(resume_text, job_description):
+    # Use the generate_resume_text function to get the formatted resume content
+    formatted_resume = generate_resume_text(resume_text)
+    print("formatted resume:",formatted_resume)
+    if formatted_resume:
+        prompt = f"""
+Below is the candidate's original formatted resume content:
+
+[Resume Start]
+{formatted_resume}
+[Resume End]
+
+Using the candidate's resume above and the job description below, create a tailored resume.
+
+[Job Description Start]
+{job_description}
+[Job Description End]
+
+Please generate a resume that:
+1. Uses real data from the candidate's resume, including name, and education.
+2. Avoids placeholders like "[Your Name]" and includes actual details.
+3. In the experience section, emphasizes professional experiences and skills that are directly relevant to the job description.
+4. Keeps only a maximum of the top three accomplishments/ responsibilities for each job position held so as to make the candidate standout in the new job role
+5. Removes special characters from the section titles
+6. Only includes publications if the job description is research based
+7. Summarizes the skills and technical skills section into a brief profile
+8. Does not include courses, certification, references, skills and a technical skills sections
+"""
+        try:
+            response = model.generate_content(prompt)
+            return response.candidates[0].content.parts[0].text
+        except Exception as e:
+            print("Error in tailoring resume:", e)
+            return None
+    else:
+        return "Failed to generate resume text."
+
+#Entry function for the model
+def generate_gemini(current_resume,job_description):
+    st.header('Resume Tailoring')
+
+    # Load the resume and job description from Google Drive
+    resume_text = extract_text(current_resume)
+    job_description = extract_text(job_description)
+
+    # Tailor resume based on job description
+    tailored_resume = tailor_resume(resume_text, job_description)
+    st.write("**Tailored Resume:**")
+    st.write(tailored_resume)
+    print(tailored_resume)
+
+        # Save the tailored resume to a .docx file
+    if tailored_resume:
+        file_path = f"Tailored_Resume_{datetime.now().strftime('%Y%m%d_%H%M%S')}.docx"
+        save_resume_to_docx(tailored_resume, file_path)
+        st.success(f"Download tailored resume")
+        # st.success(f"Tailored resume saved to {file_path}")        
+
+    return tailored_resume, file_path
+
+# Main function for Streamlit app
+# def Gemini_pro_main(current_resume,job_description):
+#     st.header('Resume Tailoring')
+
+#     # Load the resume and job description from Google Drive
+#     resume_text = extract_text(current_resume)
+#     job_description = extract_text(job_description)
+
+#     # Tailor resume based on job description
+#     tailored_resume = tailor_resume(resume_text, job_description)
+#     st.write("**Tailored Resume:**")
+#     st.write(tailored_resume)
+#     print(tailored_resume)
+
+#         # Save the tailored resume to a .docx file
+#     if tailored_resume:
+#         file_path = f"Tailored_Resume_{datetime.now().strftime('%Y%m%d_%H%M%S')}.docx"
+#         save_resume_to_docx(tailored_resume, file_path)
+#         st.success(f"Tailored resume saved to {file_path}")
+
+# if __name__ == '__main__':
+#     main()
+

similarity_score_refined.py

@@ -0,0 +1,145 @@
+# -*- coding: utf-8 -*-
+"""Similarity_score_refined (2).ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1c8mlCBnLbduLsI8rUGFEOYDuyBqdz2JJ
+"""
+
+# !pip install sentence_transformers
+# !pip install openai==0.28
+# !pip install docx2txt PyPDF2 transformers
+
+# from google.colab import drive,userdata
+# drive.mount("/content/drive")
+# print("Google Drive mounted.")
+
+import re
+from sklearn.feature_extraction.text import TfidfVectorizer
+from nltk.corpus import stopwords
+from nltk.stem import WordNetLemmatizer
+
+# Ensure you have downloaded stopwords and wordnet
+import nltk
+nltk.download('stopwords')
+nltk.download('wordnet')
+
+def extract_text(file_path):
+    import docx2txt
+    import PyPDF2
+    if file_path.endswith(".docx"):
+        # Extract text from DOCX file
+        return docx2txt.process(file_path)
+
+    elif file_path.endswith(".pdf"):
+        # Extract text from PDF file
+        text = ""
+        with open(file_path, 'rb') as file:
+            reader = PyPDF2.PdfReader(file)
+            for page_num in range(len(reader.pages)):
+                text += reader.pages[page_num].extract_text()
+        return text
+
+    else:
+        raise ValueError("Unsupported file type")
+
+def preprocess(text):
+    # Lowercase the text
+    text = text.lower()
+
+    # Remove special characters and numbers
+    text = re.sub(r'[^a-z\s]', '', text)
+
+    # Tokenize the text by splitting on whitespace
+    words = text.split()
+
+    # Remove stop words
+    stop_words = set(stopwords.words('english'))
+    words = [word for word in words if word not in stop_words]
+
+    # Lemmatize the words (to get root form)
+    lemmatizer = WordNetLemmatizer()
+    words = [lemmatizer.lemmatize(word) for word in words]
+
+    # Join words back into a single string
+    return ' '.join(words)
+
+def calculate_tfidf(doc):
+    vectorizer = TfidfVectorizer()
+    tfidf_matrix = vectorizer.fit_transform([doc])  # Only fit on the individual document
+    feature_names = vectorizer.get_feature_names_out()
+    dense_tfidf_matrix = tfidf_matrix.todense()
+
+    # Extract important terms from the document with a threshold
+    important_terms = [feature_names[i] for i in range(len(feature_names)) if dense_tfidf_matrix[0, i] > 0.2]
+
+    return ' '.join(important_terms)
+
+def call_chatgpt_api(prompt, api_key,model="gpt-3.5-turbo"):
+    import openai
+    openai.api_key = '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'
+    response = openai.ChatCompletion.create(
+        model="gpt-3.5-turbo",
+        messages=[
+            {"role": "system", "content": "You are a helpful assistant."},
+            {"role": "user", "content": prompt}
+        ],
+        max_tokens=500,
+        temperature= 0,
+        top_p=1,
+        frequency_penalty= 0,
+        presence_penalty= 0
+    )
+    return response['choices'][0]['message']['content'].strip()
+
+def calculate_similarity(resume, job_desc, model_name="sentence-transformers/all-MiniLM-L6-v2"):
+    from sentence_transformers import SentenceTransformer, util
+    model = SentenceTransformer(model_name)
+
+    # Convert texts to embeddings
+    embeddings1 = model.encode(resume, convert_to_tensor=True)
+    embeddings2 = model.encode(job_desc, convert_to_tensor=True)
+
+    # Calculate cosine similarity
+    similarity_score = util.pytorch_cos_sim(embeddings1, embeddings2)
+    return similarity_score.item()  # return as a scalar
+
+def similarity_main(resume_path,job_description_path):
+
+    # Extract text from files (replace with actual file paths)
+    Resume_text = extract_text(resume_path)
+    job_des = extract_text(job_description_path)
+    api_key='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'
+
+
+    prompt=f"Extract the skills or competencies section from the resume. Avoid using name of the candidate:\n\n{Resume_text}"
+    resume_skills = call_chatgpt_api(prompt,api_key)
+    experience_prompt = f"Extract the experience of the candidate from the resume. Avoid using name of the candidate:\n\n{Resume_text}"
+    resume_experience = call_chatgpt_api(experience_prompt,api_key)
+
+    # Extract sections from job description (JD)
+    jd_skills_prompt = f"Extract the skills section from the job description:\n\n{job_des}"
+    jd_skills = call_chatgpt_api(jd_skills_prompt,api_key)
+
+    jd_experience_prompt = f"Extract the experience section from the job description:\n\n{job_des}"
+    jd_experience = call_chatgpt_api(jd_experience_prompt,api_key)
+
+    resume_skills_clean = preprocess(resume_skills)
+    jd_skills_clean = preprocess(jd_skills)
+
+    resume_experience_clean = preprocess(resume_experience)
+    jd_experience_clean = preprocess(jd_experience)
+
+    filtered_resume = calculate_tfidf(resume_skills_clean)
+    filtered_jd = calculate_tfidf(jd_skills_clean)
+    similarity_skills=calculate_similarity(filtered_resume,filtered_jd)
+
+    filtered_resume_ex = calculate_tfidf(resume_experience_clean)
+    filtered_jd_ex = calculate_tfidf(jd_experience_clean)
+    similarity_ex=calculate_similarity(filtered_resume_ex,filtered_jd_ex)
+
+    Average_Score=(similarity_skills+similarity_ex)/2
+    percentage= f"{Average_Score * 100:.2f}%"
+    return percentage
+