Spaces:
Runtime error
Runtime error
Upload 14 files
Browse files- Dockerfile +26 -0
- api/__init__.py +0 -0
- api/models.py +22 -0
- api/routes.py +31 -0
- config/__init__.py +0 -0
- config/settings.py +24 -0
- core/__init__.py +0 -0
- core/doc_processor.py +77 -0
- core/text_processor.py +13 -0
- core/vector_store.py +32 -0
- main.py +25 -0
- services/__init__.py +0 -0
- services/llm_service.py +74 -0
- services/resume_service.py +127 -0
Dockerfile
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Use Python 3.10 as base image
|
| 2 |
+
FROM python:3.11-slim
|
| 3 |
+
|
| 4 |
+
# Set working directory
|
| 5 |
+
WORKDIR /app
|
| 6 |
+
|
| 7 |
+
# Install system dependencies
|
| 8 |
+
RUN apt-get update && apt-get install -y \
|
| 9 |
+
build-essential \
|
| 10 |
+
python3-dev \
|
| 11 |
+
&& rm -rf /var/lib/apt/lists/*
|
| 12 |
+
|
| 13 |
+
# Copy requirements file
|
| 14 |
+
COPY requirements.txt .
|
| 15 |
+
|
| 16 |
+
# Install Python dependencies
|
| 17 |
+
RUN pip install --no-cache-dir -r requirements.txt
|
| 18 |
+
|
| 19 |
+
# Copy the application code
|
| 20 |
+
COPY . .
|
| 21 |
+
|
| 22 |
+
# Expose the port the app runs on
|
| 23 |
+
EXPOSE 8000
|
| 24 |
+
|
| 25 |
+
# Command to run the application
|
| 26 |
+
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]
|
api/__init__.py
ADDED
|
File without changes
|
api/models.py
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from pydantic import BaseModel
|
| 2 |
+
from typing import List, Optional
|
| 3 |
+
from datetime import datetime
|
| 4 |
+
|
| 5 |
+
class ResumeAnalysisResponse(BaseModel):
|
| 6 |
+
candidate_name: str = ""
|
| 7 |
+
gender: Optional[str] = None
|
| 8 |
+
date_of_birth: Optional[str] = None
|
| 9 |
+
email: Optional[str] = None
|
| 10 |
+
mobile_number: Optional[str] = None
|
| 11 |
+
address: Optional[str] = None
|
| 12 |
+
pan_number: Optional[str] = None
|
| 13 |
+
aadhar_number: Optional[str] = None
|
| 14 |
+
passport_number: Optional[str] = None
|
| 15 |
+
highest_education: Optional[str] = None
|
| 16 |
+
designation: Optional[str] = None
|
| 17 |
+
skills: Optional[str] = ""
|
| 18 |
+
total_experience: Optional[str] = None
|
| 19 |
+
region: Optional[str] = None
|
| 20 |
+
relevant_experience: Optional[str] = None
|
| 21 |
+
experience_summary: Optional[str] = None
|
| 22 |
+
file_modified_date: Optional[datetime] = None
|
api/routes.py
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from fastapi import APIRouter, File, UploadFile, Form, HTTPException
|
| 2 |
+
import os
|
| 3 |
+
|
| 4 |
+
from api.models import ResumeAnalysisResponse
|
| 5 |
+
from services.resume_service import analyze_resume_document
|
| 6 |
+
|
| 7 |
+
router = APIRouter()
|
| 8 |
+
|
| 9 |
+
@router.post("/analyze-resume", response_model=ResumeAnalysisResponse)
|
| 10 |
+
async def analyze_resume(
|
| 11 |
+
resume_file: UploadFile = File(...),
|
| 12 |
+
job_role: str = Form(...)
|
| 13 |
+
):
|
| 14 |
+
_, file_extension = os.path.splitext(resume_file.filename)
|
| 15 |
+
file_extension = file_extension.lower()
|
| 16 |
+
|
| 17 |
+
allowed_extensions = ['.pdf', '.docx']
|
| 18 |
+
if file_extension not in allowed_extensions:
|
| 19 |
+
raise HTTPException(
|
| 20 |
+
status_code=400,
|
| 21 |
+
detail=f"Only PDF and DOCX files are supported. Got: {file_extension}"
|
| 22 |
+
)
|
| 23 |
+
|
| 24 |
+
try:
|
| 25 |
+
file_bytes = await resume_file.read()
|
| 26 |
+
|
| 27 |
+
result = analyze_resume_document(file_bytes, job_role, file_extension)
|
| 28 |
+
return result
|
| 29 |
+
|
| 30 |
+
except Exception as e:
|
| 31 |
+
raise HTTPException(status_code=500, detail=f"Error processing resume: {str(e)}")
|
config/__init__.py
ADDED
|
File without changes
|
config/settings.py
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import os
|
| 2 |
+
from dotenv import load_dotenv
|
| 3 |
+
|
| 4 |
+
DEFAULT_CHUNK_SIZE = 1000
|
| 5 |
+
DEFAULT_CHUNK_OVERLAP = 200
|
| 6 |
+
DEFAULT_LLM_MODEL = "gemini-2.0-flash"
|
| 7 |
+
DEFAULT_EMBEDDING_MODEL = "models/embedding-001"
|
| 8 |
+
DEFAULT_TEMPERATURE = 0
|
| 9 |
+
|
| 10 |
+
def init_settings():
|
| 11 |
+
load_dotenv()
|
| 12 |
+
|
| 13 |
+
if not os.getenv("GOOGLE_API_KEY"):
|
| 14 |
+
raise ValueError("GOOGLE_API_KEY environment variable is not set")
|
| 15 |
+
|
| 16 |
+
def get_settings():
|
| 17 |
+
return {
|
| 18 |
+
"chunk_size": int(os.getenv("CHUNK_SIZE", DEFAULT_CHUNK_SIZE)),
|
| 19 |
+
"chunk_overlap": int(os.getenv("CHUNK_OVERLAP", DEFAULT_CHUNK_OVERLAP)),
|
| 20 |
+
"llm_model": os.getenv("LLM_MODEL", DEFAULT_LLM_MODEL),
|
| 21 |
+
"embedding_model": os.getenv("EMBEDDING_MODEL", DEFAULT_EMBEDDING_MODEL),
|
| 22 |
+
"temperature": float(os.getenv("TEMPERATURE", DEFAULT_TEMPERATURE)),
|
| 23 |
+
"google_api_key": os.getenv("GOOGLE_API_KEY")
|
| 24 |
+
}
|
core/__init__.py
ADDED
|
File without changes
|
core/doc_processor.py
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import pymupdf
|
| 2 |
+
from io import BytesIO
|
| 3 |
+
import docx2txt
|
| 4 |
+
from datetime import datetime
|
| 5 |
+
import zipfile
|
| 6 |
+
from xml.etree import ElementTree as ET
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
def extract_text_from_bytes(pdf_bytes):
|
| 10 |
+
try:
|
| 11 |
+
memory_stream = BytesIO(pdf_bytes)
|
| 12 |
+
doc = pymupdf.open(stream=memory_stream, filetype="pdf")
|
| 13 |
+
|
| 14 |
+
# Extract text
|
| 15 |
+
text = ""
|
| 16 |
+
for page in doc:
|
| 17 |
+
text += page.get_text()
|
| 18 |
+
|
| 19 |
+
# Get modification date
|
| 20 |
+
metadata = doc.metadata
|
| 21 |
+
mod_date = metadata.get("modDate", None)
|
| 22 |
+
|
| 23 |
+
doc.close()
|
| 24 |
+
return text, mod_date
|
| 25 |
+
except Exception as e:
|
| 26 |
+
return f"Error reading PDF: {str(e)}", None
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
def get_docx_last_modified(docx_stream):
|
| 30 |
+
|
| 31 |
+
try:
|
| 32 |
+
docx_stream.seek(0) # Reset stream position to start
|
| 33 |
+
with zipfile.ZipFile(docx_stream, 'r') as docx:
|
| 34 |
+
if 'docProps/core.xml' in docx.namelist():
|
| 35 |
+
with docx.open('docProps/core.xml') as f:
|
| 36 |
+
core_xml = f.read()
|
| 37 |
+
|
| 38 |
+
root = ET.fromstring(core_xml)
|
| 39 |
+
|
| 40 |
+
namespaces = {
|
| 41 |
+
'cp': 'http://schemas.openxmlformats.org/package/2006/metadata/core-properties',
|
| 42 |
+
'dcterms': 'http://purl.org/dc/terms/'
|
| 43 |
+
}
|
| 44 |
+
|
| 45 |
+
modified_element = root.find('.//dcterms:modified', namespaces)
|
| 46 |
+
|
| 47 |
+
if modified_element is not None:
|
| 48 |
+
modified_date_str = modified_element.text
|
| 49 |
+
return datetime.fromisoformat(modified_date_str.replace('Z', '+00:00'))
|
| 50 |
+
except Exception as e:
|
| 51 |
+
print(f"Error extracting DOCX metadata: {e}")
|
| 52 |
+
return None
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
def extract_text_from_docx(docx_bytes):
|
| 56 |
+
try:
|
| 57 |
+
docx_stream = BytesIO(docx_bytes)
|
| 58 |
+
text = docx2txt.process(docx_stream)
|
| 59 |
+
|
| 60 |
+
metadata_stream = BytesIO(docx_bytes)
|
| 61 |
+
mod_date = get_docx_last_modified(metadata_stream)
|
| 62 |
+
|
| 63 |
+
return text, mod_date
|
| 64 |
+
except Exception as e:
|
| 65 |
+
return f"Error reading DOCX: {str(e)}", None
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
def parse_pdf_date(pdf_date: str) -> datetime:
|
| 69 |
+
|
| 70 |
+
if not pdf_date or not pdf_date.startswith("D:"):
|
| 71 |
+
return datetime.now()
|
| 72 |
+
|
| 73 |
+
try:
|
| 74 |
+
date_str = pdf_date[2:14]
|
| 75 |
+
return datetime.strptime(date_str, "%Y%m%d%H%M")
|
| 76 |
+
except Exception:
|
| 77 |
+
return datetime.now()
|
core/text_processor.py
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
| 2 |
+
|
| 3 |
+
|
| 4 |
+
def chunk_text(text, chunk_size=1000, chunk_overlap=200):
|
| 5 |
+
text_splitter = RecursiveCharacterTextSplitter(
|
| 6 |
+
chunk_size=chunk_size,
|
| 7 |
+
chunk_overlap=chunk_overlap,
|
| 8 |
+
length_function=len,
|
| 9 |
+
is_separator_regex=False,
|
| 10 |
+
)
|
| 11 |
+
|
| 12 |
+
chunks = text_splitter.split_text(text)
|
| 13 |
+
return chunks
|
core/vector_store.py
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import os
|
| 2 |
+
from langchain_google_genai import GoogleGenerativeAIEmbeddings
|
| 3 |
+
from langchain_community.vectorstores import FAISS
|
| 4 |
+
from langchain_core.documents import Document
|
| 5 |
+
|
| 6 |
+
def create_or_load_vectorstore(text_chunks):
|
| 7 |
+
embeddings = GoogleGenerativeAIEmbeddings(
|
| 8 |
+
model="models/embedding-001", google_api_key=os.getenv("GOOGLE_API_KEY")
|
| 9 |
+
)
|
| 10 |
+
|
| 11 |
+
documents = [
|
| 12 |
+
Document(page_content=chunk, metadata={"source": "resume"})
|
| 13 |
+
for chunk in text_chunks
|
| 14 |
+
]
|
| 15 |
+
|
| 16 |
+
vectorstore = FAISS.from_documents(
|
| 17 |
+
documents=documents,
|
| 18 |
+
embedding=embeddings
|
| 19 |
+
)
|
| 20 |
+
|
| 21 |
+
return vectorstore
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
def similarity_search(vectorstore, query, k=5):
|
| 25 |
+
try:
|
| 26 |
+
documents = vectorstore.similarity_search(query, k=k)
|
| 27 |
+
return documents
|
| 28 |
+
except Exception as e:
|
| 29 |
+
print(f"Error in similarity search: {str(e)}")
|
| 30 |
+
return []
|
| 31 |
+
|
| 32 |
+
|
main.py
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from fastapi import FastAPI
|
| 2 |
+
from fastapi.middleware.cors import CORSMiddleware
|
| 3 |
+
|
| 4 |
+
|
| 5 |
+
from api.routes import router as api_router
|
| 6 |
+
from config.settings import init_settings
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
app = FastAPI(
|
| 10 |
+
title="Relevant Experience Analyzer",
|
| 11 |
+
description="API for extracting job-relevant experience from resumes using semantic search",
|
| 12 |
+
version="1.0.0"
|
| 13 |
+
)
|
| 14 |
+
|
| 15 |
+
app.add_middleware(
|
| 16 |
+
CORSMiddleware,
|
| 17 |
+
allow_origins=["*"],
|
| 18 |
+
allow_credentials=True,
|
| 19 |
+
allow_methods=["*"],
|
| 20 |
+
allow_headers=["*"],
|
| 21 |
+
)
|
| 22 |
+
|
| 23 |
+
init_settings()
|
| 24 |
+
|
| 25 |
+
app.include_router(api_router)
|
services/__init__.py
ADDED
|
File without changes
|
services/llm_service.py
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from langchain_google_genai import ChatGoogleGenerativeAI
|
| 2 |
+
from langchain.prompts import PromptTemplate
|
| 3 |
+
from config.settings import get_settings
|
| 4 |
+
|
| 5 |
+
|
| 6 |
+
def get_llm():
|
| 7 |
+
settings = get_settings()
|
| 8 |
+
return ChatGoogleGenerativeAI(
|
| 9 |
+
model=settings["llm_model"],
|
| 10 |
+
temperature=settings["temperature"],
|
| 11 |
+
google_api_key=settings["google_api_key"],
|
| 12 |
+
)
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
def get_unified_resume_prompt():
|
| 16 |
+
return PromptTemplate(
|
| 17 |
+
input_variables=["resume_text", "relevant_content", "job_role"],
|
| 18 |
+
template='''You are a professional resume analyzer with expertise in technical recruiting.
|
| 19 |
+
|
| 20 |
+
Your task is to extract both basic information and relevant work experience from the resume.
|
| 21 |
+
|
| 22 |
+
RESUME CONTENT:
|
| 23 |
+
{resume_text}
|
| 24 |
+
|
| 25 |
+
MOST RELEVANT SECTIONS (semantically similar to job requirements):
|
| 26 |
+
{relevant_content}
|
| 27 |
+
|
| 28 |
+
TARGET JOB ROLE: {job_role}
|
| 29 |
+
|
| 30 |
+
TASK INSTRUCTIONS:
|
| 31 |
+
Basic Information:
|
| 32 |
+
1. Extract all personally identifiable information that is explicitly stated in the text
|
| 33 |
+
2. For fields where information is not found, use null
|
| 34 |
+
3. Do not invent or infer information not present in the text
|
| 35 |
+
4. For education, only return the highest level completed (postgraduate > undergraduate > 12th > 10th)
|
| 36 |
+
5. For role, use the most recent/current position mentioned
|
| 37 |
+
6. Return complete values - do not truncate or summarize unnecessarily
|
| 38 |
+
7. Maintain exact formatting/capitalization as shown in the resume
|
| 39 |
+
8. Extract all contact information including email and phone number (just the primary number)
|
| 40 |
+
9. Look for any government ID numbers (PAN, Aadhar, Passport) that might be present
|
| 41 |
+
|
| 42 |
+
Experience Analysis:
|
| 43 |
+
1. Create a single concise paragraph summarizing ALL relevant professional experience that directly relates to the job role
|
| 44 |
+
2. Focus only on experiences that explicitly demonstrate use of the exact technologies/tools required
|
| 45 |
+
3. If NO relevant experience is found, return null for relevant_experience
|
| 46 |
+
4. Provide a brief summary analyzing how well the candidate's experience matches the job role
|
| 47 |
+
|
| 48 |
+
FORMAT YOUR RESPONSE AS A VALID JSON OBJECT WITH THIS EXACT STRUCTURE:
|
| 49 |
+
{{
|
| 50 |
+
"candidate_name": "full name of the candidate",
|
| 51 |
+
"gender": "gender if mentioned",
|
| 52 |
+
"date_of_birth": "DOB in YYYY/MM/DD format if mentioned",
|
| 53 |
+
"email": "email address if mentioned",
|
| 54 |
+
"mobile_number": "primary phone number if mentioned",
|
| 55 |
+
"address": "complete physical address if mentioned",
|
| 56 |
+
"pan_number": "PAN number if mentioned",
|
| 57 |
+
"aadhar_number": "Aadhar number if mentioned",
|
| 58 |
+
"passport_number": "Passport number if mentioned",
|
| 59 |
+
"highest_education": "most advanced completed education level, interpret from the data and return only 4 of these options : 10th, 12th, UG, PG",
|
| 60 |
+
"designation": "current or most recent role/position",
|
| 61 |
+
"skills": "comma-separated list of technical and professional skills",
|
| 62 |
+
"total_experience": "total work experience in terms of years i.e., if experience is 6 months return "0.5", divide the number of months found by 12 and return the number as a string",
|
| 63 |
+
"region": "geographical region/city of work",
|
| 64 |
+
"relevant_experience": "single paragraph summarizing all experience relevant to the job role",
|
| 65 |
+
"experience_summary": "brief analysis of how well the experience matches the job role"
|
| 66 |
+
}}
|
| 67 |
+
|
| 68 |
+
IMPORTANT:
|
| 69 |
+
- DO NOT INVENT OR ADD INFORMATION that is not in the resume
|
| 70 |
+
- BE EXTREMELY STRICT about experience relevance
|
| 71 |
+
- Response must be a valid JSON object
|
| 72 |
+
- For sensitive information like Aadhar/PAN, return only if explicitly mentioned in resume
|
| 73 |
+
- Skills should be returned as a comma-separated string (e.g. "Java, Spring Boot, Docker, AWS, PostgreSQL")'''
|
| 74 |
+
)
|
services/resume_service.py
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import json
|
| 2 |
+
from typing import Dict
|
| 3 |
+
from datetime import datetime
|
| 4 |
+
|
| 5 |
+
from core.doc_processor import (
|
| 6 |
+
extract_text_from_bytes,
|
| 7 |
+
extract_text_from_docx,
|
| 8 |
+
parse_pdf_date
|
| 9 |
+
)
|
| 10 |
+
from core.text_processor import chunk_text
|
| 11 |
+
from core.vector_store import create_or_load_vectorstore, similarity_search
|
| 12 |
+
from services.llm_service import get_llm, get_unified_resume_prompt
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
def analyze_resume_document(
|
| 16 |
+
file_bytes: bytes, job_role: str, file_extension: str
|
| 17 |
+
) -> Dict:
|
| 18 |
+
if file_extension.lower() == ".pdf":
|
| 19 |
+
resume_text, mod_date = extract_text_from_bytes(file_bytes)
|
| 20 |
+
file_modified_date = parse_pdf_date(mod_date) if mod_date else datetime.now()
|
| 21 |
+
elif file_extension.lower() == ".docx":
|
| 22 |
+
resume_text, mod_date = extract_text_from_docx(file_bytes)
|
| 23 |
+
file_modified_date = mod_date if mod_date else datetime.now()
|
| 24 |
+
else:
|
| 25 |
+
raise ValueError(f"Unsupported file format: {file_extension}")
|
| 26 |
+
|
| 27 |
+
if resume_text.startswith("Error"):
|
| 28 |
+
raise ValueError(resume_text)
|
| 29 |
+
|
| 30 |
+
chunks = chunk_text(resume_text)
|
| 31 |
+
vector_store = create_or_load_vectorstore(chunks)
|
| 32 |
+
return analyze_resume_with_llm(vector_store, resume_text, job_role, file_modified_date)
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
def analyze_resume_with_llm(vectorstore, resume_text: str, job_role: str, file_modified_date: datetime) -> Dict:
|
| 36 |
+
try:
|
| 37 |
+
retrieved_docs = similarity_search(vectorstore, job_role)
|
| 38 |
+
relevant_content = "\n".join([doc.page_content for doc in retrieved_docs])
|
| 39 |
+
|
| 40 |
+
unified_prompt = get_unified_resume_prompt()
|
| 41 |
+
llm = get_llm()
|
| 42 |
+
chain = unified_prompt | llm
|
| 43 |
+
|
| 44 |
+
response = chain.invoke(
|
| 45 |
+
{
|
| 46 |
+
"resume_text": resume_text,
|
| 47 |
+
"relevant_content": relevant_content,
|
| 48 |
+
"job_role": job_role,
|
| 49 |
+
}
|
| 50 |
+
)
|
| 51 |
+
|
| 52 |
+
response_text = response.content.strip()
|
| 53 |
+
if response_text.startswith("`"):
|
| 54 |
+
response_text = response_text.strip("`")
|
| 55 |
+
if response_text.startswith("json"):
|
| 56 |
+
response_text = response_text[4:]
|
| 57 |
+
|
| 58 |
+
parsed_response = json.loads(response_text.strip())
|
| 59 |
+
|
| 60 |
+
default_response = {
|
| 61 |
+
"candidate_name": "",
|
| 62 |
+
"gender": None,
|
| 63 |
+
"date_of_birth": None,
|
| 64 |
+
"email": None,
|
| 65 |
+
"mobile_number": None,
|
| 66 |
+
"address": None,
|
| 67 |
+
"pan_number": None,
|
| 68 |
+
"aadhar_number": None,
|
| 69 |
+
"passport_number": None,
|
| 70 |
+
"highest_education": None,
|
| 71 |
+
"designation": None,
|
| 72 |
+
"skills": "",
|
| 73 |
+
"total_experience": None,
|
| 74 |
+
"region": None,
|
| 75 |
+
"relevant_experience": None,
|
| 76 |
+
"experience_summary": "No relevant experience analysis available",
|
| 77 |
+
"file_modified_date": file_modified_date
|
| 78 |
+
}
|
| 79 |
+
|
| 80 |
+
result = {**default_response, **parsed_response}
|
| 81 |
+
|
| 82 |
+
result["file_modified_date"] = file_modified_date
|
| 83 |
+
|
| 84 |
+
return result
|
| 85 |
+
|
| 86 |
+
except json.JSONDecodeError as e:
|
| 87 |
+
print(f"JSON Parse Error: {str(e)}")
|
| 88 |
+
return {
|
| 89 |
+
"candidate_name": "",
|
| 90 |
+
"gender": None,
|
| 91 |
+
"date_of_birth": None,
|
| 92 |
+
"email": None,
|
| 93 |
+
"mobile_number": None,
|
| 94 |
+
"address": None,
|
| 95 |
+
"pan_number": None,
|
| 96 |
+
"aadhar_number": None,
|
| 97 |
+
"passport_number": None,
|
| 98 |
+
"highest_education": None,
|
| 99 |
+
"designation": None,
|
| 100 |
+
"skills": "",
|
| 101 |
+
"total_experience": None,
|
| 102 |
+
"region": None,
|
| 103 |
+
"relevant_experience": None,
|
| 104 |
+
"experience_summary": "Could not parse resume details from response",
|
| 105 |
+
"file_modified_date": file_modified_date
|
| 106 |
+
}
|
| 107 |
+
except Exception as e:
|
| 108 |
+
print(f"Unexpected Error: {str(e)}")
|
| 109 |
+
return {
|
| 110 |
+
"candidate_name": "",
|
| 111 |
+
"gender": None,
|
| 112 |
+
"date_of_birth": None,
|
| 113 |
+
"email": None,
|
| 114 |
+
"mobile_number": None,
|
| 115 |
+
"address": None,
|
| 116 |
+
"pan_number": None,
|
| 117 |
+
"aadhar_number": None,
|
| 118 |
+
"passport_number": None,
|
| 119 |
+
"highest_education": None,
|
| 120 |
+
"designation": None,
|
| 121 |
+
"skills": "",
|
| 122 |
+
"total_experience": None,
|
| 123 |
+
"region": None,
|
| 124 |
+
"relevant_experience": None,
|
| 125 |
+
"experience_summary": f"Error analyzing resume: {str(e)}",
|
| 126 |
+
"file_modified_date": file_modified_date
|
| 127 |
+
}
|