FastAPIExperience2 / services /resume_service.py
utkarsh134's picture
Upload 4 files
bd093cc verified
Raw History Blame Contribute Delete
5.23 kB
import json
from typing import Dict
from datetime import datetime
from core.doc_processor import (
extract_text_from_bytes,
extract_text_from_docx,
parse_pdf_date
)
from core.text_processor import chunk_text
from core.vector_store import create_or_load_vectorstore, similarity_search
from services.llm_service import get_llm, get_unified_resume_prompt
from services.db_service import store_candidate_data
async def analyze_resume_document(
file_bytes: bytes, job_role: str, file_extension: str
) -> Dict:
if file_extension.lower() == ".pdf":
resume_text, mod_date = extract_text_from_bytes(file_bytes)
file_modified_date = parse_pdf_date(mod_date) if mod_date else datetime.now()
elif file_extension.lower() == ".docx":
resume_text, mod_date = extract_text_from_docx(file_bytes)
file_modified_date = mod_date if mod_date else datetime.now()
else:
raise ValueError(f"Unsupported file format: {file_extension}")
if resume_text.startswith("Error"):
raise ValueError(resume_text)
chunks = chunk_text(resume_text)
vector_store = create_or_load_vectorstore(chunks)
analysis_result = analyze_resume_with_llm(vector_store, resume_text, job_role, file_modified_date)
try:
db_record = await store_candidate_data(analysis_result)
analysis_result["id"] = db_record.get("id")
analysis_result["stored_in_db"] = True
except Exception as e:
print(f"Error storing candidate data: {str(e)}")
analysis_result["stored_in_db"] = False
analysis_result["db_error"] = str(e)
return analysis_result
def analyze_resume_with_llm(vectorstore, resume_text: str, job_role: str, file_modified_date: datetime) -> Dict:
try:
retrieved_docs = similarity_search(vectorstore, job_role)
relevant_content = "\n".join([doc.page_content for doc in retrieved_docs])
unified_prompt = get_unified_resume_prompt()
llm = get_llm()
chain = unified_prompt | llm
response = chain.invoke(
{
"resume_text": resume_text,
"relevant_content": relevant_content,
"job_role": job_role,
}
)
response_text = response.content.strip()
if response_text.startswith("`"):
response_text = response_text.strip("`")
if response_text.startswith("json"):
response_text = response_text[4:]
parsed_response = json.loads(response_text.strip())
default_response = {
"candidate_name": "",
"gender": None,
"date_of_birth": None,
"email": None,
"mobile_number": None,
"address": None,
"pan_number": None,
"aadhar_number": None,
"passport_number": None,
"highest_education": None,
"university_name": None,
"designation": None,
"skills": "",
"skill_score": [],
"total_experience": None,
"region": None,
"relevant_experience": None,
"experience_summary": "No relevant experience analysis available",
"hr_questions": []
}
result = {**default_response, **parsed_response}
result["file_modified_date"] = file_modified_date
return result
except json.JSONDecodeError as e:
print(f"JSON Parse Error: {str(e)}")
return {
"candidate_name": "",
"gender": None,
"date_of_birth": None,
"email": None,
"mobile_number": None,
"address": None,
"pan_number": None,
"aadhar_number": None,
"passport_number": None,
"highest_education": None,
"university_name": None,
"designation": None,
"skills": "",
"skill_score": [],
"total_experience": None,
"region": None,
"relevant_experience": None,
"experience_summary": "Could not parse resume details from response",
"hr_questions": [],
"file_modified_date": file_modified_date
}
except Exception as e:
print(f"Unexpected Error: {str(e)}")
return {
"candidate_name": "",
"gender": None,
"date_of_birth": None,
"email": None,
"mobile_number": None,
"address": None,
"pan_number": None,
"aadhar_number": None,
"passport_number": None,
"highest_education": None,
"university_name": None,
"designation": None,
"skills": "",
"skill_score": [],
"total_experience": None,
"region": None,
"relevant_experience": None,
"experience_summary": f"Error analyzing resume: {str(e)}",
"hr_questions": [],
"file_modified_date": file_modified_date
}