File size: 5,225 Bytes
bd093cc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a88785b
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
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
        }