Create Home.py

Home.py

@@ -0,0 +1,130 @@
+import os
+import zipfile
+from pathlib import Path
+import streamlit as st
+from langchain_community.document_loaders import UnstructuredPDFLoader
+from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace
+from langchain.prompts import PromptTemplate
+from langchain_core.output_parsers import PydanticOutputParser
+from pydantic import BaseModel, Field
+
+st.markdown(
+    """
+    <style>
+    .stApp {
+        background-color: midnightblue;
+        color: white;
+    }
+    </style>
+    """,
+    unsafe_allow_html=True
+)
+
+# Setup your HF token and model (replace with your token handling)
+newhf = st.secrets["HF_TOKEN"]
+
+# Create folders if not present
+Path("Extracted_Resumes").mkdir(exist_ok=True)
+Path("Selected_Resumes").mkdir(exist_ok=True)
+
+# Set up the LLaMA model
+llama_model = HuggingFaceEndpoint(
+    repo_id="meta-llama/Llama-3.1-8B-Instruct",
+    provider="nebius",
+    temperature=0.7,
+    api_key=newhf,
+    max_new_tokens=512,
+    task="conversational"
+)
+
+model = ChatHuggingFace(
+    llm=llama_model,
+    repo_id="meta-llama/Llama-3.1-8B-Instruct",
+    provider="nebius",
+    temperature=0.7,
+    api_key=newhf,
+    max_new_tokens=512,
+    task="conversational"
+)
+
+# Pydantic schema for parsing resume content
+class JobDesc(BaseModel):
+    Objective: str = Field(description="Objective")
+    Name: str = Field(description="Name")
+    Age: int = Field(description="Age")
+    Qualification: str = Field(description="Qualification")
+    Skills: list[str] = Field(description="Skills")
+    Experience: float = Field(description="Work Experience")
+
+parser = PydanticOutputParser(pydantic_object=JobDesc)
+
+# Prompt template for extracting fields from resume
+pt = PromptTemplate(template="""
+Extract the following fields from the resume description below and return them as a JSON object.
+
+Resume Text:
+{input}
+
+Return JSON matching this format exactly:
+{instruction}
+""")
+
+# Streamlit app UI
+st.title("📄 Resume Screening Application")
+
+uploaded_zip = st.file_uploader("Upload a ZIP file containing resumes", type="zip")
+
+if uploaded_zip:
+    with zipfile.ZipFile(uploaded_zip, "r") as zip_ref:
+        zip_ref.extractall("Extracted_Resumes")
+    st.success("✅ Resumes extracted successfully!")
+
+    resumes = list(Path("Extracted_Resumes").glob("*.pdf"))
+    valid_resumes = []
+
+    # Check for 2-page resumes
+    for pdf in resumes:
+        try:
+            loader = UnstructuredPDFLoader(str(pdf), mode="paged")
+            pages = loader.load()
+            if len(pages) == 2:
+                valid_resumes.append((pdf.name, pages))
+        except Exception as e:
+            st.warning(f"❌ Could not process {pdf.name}: {e}")
+
+    if valid_resumes:
+        st.subheader("🔎 Select Required Skills")
+
+        # Extract skills from all resumes
+        all_resume_skills = set()
+
+        parsed_resumes = {}
+
+        for filename, pages in valid_resumes:
+            final_data = [page for page in pages]
+            fp = pt.format(input=final_data, instruction=parser.get_format_instructions())
+            result = model.invoke(fp)
+            parsed_resume = parser.parse(result.content)
+            parsed_resumes[filename] = parsed_resume
+            all_resume_skills.update(map(str.lower, parsed_resume.Skills))
+
+        selected_skills = st.multiselect("Choose required skills:", sorted(all_resume_skills))
+
+        # Match resumes based on selected skills
+        for filename, parsed_resume in parsed_resumes.items():
+            resume_skills = parsed_resume.Skills
+            found_skills = [
+                skill for skill in selected_skills
+                if any(skill.lower() in rs.lower() for rs in resume_skills)
+            ]
+
+            if set(found_skills) == set(selected_skills):
+                src_path = Path("Extracted_Resumes") / filename
+                dest_path = Path("Selected_Resumes") / filename
+                with open(src_path, "rb") as src, open(dest_path, "wb") as dst:
+                    dst.write(src.read())
+                st.success(f"✅ {filename} matches and saved to 'Selected_Resumes'")
+            else:
+                st.info(f"ℹ️ {filename} does not match all selected skills.")
+    else:
+        st.warning("⚠️ No 2-page resumes found.")