utkarsh134 commited on
Commit
c43d2fc
·
verified ·
1 Parent(s): 84779a6

Update services/resume_service.py

Browse files
Files changed (1) hide show
  1. services/resume_service.py +146 -126
services/resume_service.py CHANGED
@@ -1,127 +1,147 @@
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
  }
 
1
+ import json
2
+ from typing import Dict, Tuple, Any
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
+ from services.db_service import store_candidate_data
14
+ from config.settings import get_settings
15
+
16
+
17
+ async def analyze_resume_document(
18
+ file_bytes: bytes, job_role: str, file_extension: str
19
+ ) -> Dict:
20
+ if file_extension.lower() == ".pdf":
21
+ resume_text, mod_date = extract_text_from_bytes(file_bytes)
22
+ file_modified_date = parse_pdf_date(mod_date) if mod_date else datetime.now()
23
+ elif file_extension.lower() == ".docx":
24
+ resume_text, mod_date = extract_text_from_docx(file_bytes)
25
+ file_modified_date = mod_date if mod_date else datetime.now()
26
+ else:
27
+ raise ValueError(f"Unsupported file format: {file_extension}")
28
+
29
+ if resume_text.startswith("Error"):
30
+ raise ValueError(resume_text)
31
+
32
+ chunks = chunk_text(resume_text)
33
+ vector_store = create_or_load_vectorstore(chunks)
34
+
35
+ # Analyze resume
36
+ analysis_result = analyze_resume_with_llm(vector_store, resume_text, job_role, file_modified_date)
37
+
38
+ # Store in database if enabled
39
+ settings = get_settings()
40
+ if settings.get("store_analysis_result", True):
41
+ try:
42
+ db_record = await store_candidate_data(analysis_result)
43
+ # Add database ID to result
44
+ analysis_result["id"] = db_record.get("id")
45
+ analysis_result["stored_in_db"] = True
46
+ except Exception as e:
47
+ # Log error but continue with analysis
48
+ print(f"Error storing candidate data: {str(e)}")
49
+ analysis_result["stored_in_db"] = False
50
+ analysis_result["db_error"] = str(e)
51
+
52
+ return analysis_result
53
+
54
+
55
+ def analyze_resume_with_llm(vectorstore, resume_text: str, job_role: str, file_modified_date: datetime) -> Dict:
56
+ try:
57
+ retrieved_docs = similarity_search(vectorstore, job_role)
58
+ relevant_content = "\n".join([doc.page_content for doc in retrieved_docs])
59
+
60
+ unified_prompt = get_unified_resume_prompt()
61
+ llm = get_llm()
62
+ chain = unified_prompt | llm
63
+
64
+ response = chain.invoke(
65
+ {
66
+ "resume_text": resume_text,
67
+ "relevant_content": relevant_content,
68
+ "job_role": job_role,
69
+ }
70
+ )
71
+
72
+ response_text = response.content.strip()
73
+ if response_text.startswith("`"):
74
+ response_text = response_text.strip("`")
75
+ if response_text.startswith("json"):
76
+ response_text = response_text[4:]
77
+
78
+ parsed_response = json.loads(response_text.strip())
79
+
80
+ default_response = {
81
+ "candidate_name": "",
82
+ "gender": None,
83
+ "date_of_birth": None,
84
+ "email": None,
85
+ "mobile_number": None,
86
+ "address": None,
87
+ "pan_number": None,
88
+ "aadhar_number": None,
89
+ "passport_number": None,
90
+ "highest_education": None,
91
+ "designation": None,
92
+ "skills": "",
93
+ "total_experience": None,
94
+ "region": None,
95
+ "relevant_experience": None,
96
+ "experience_summary": "No relevant experience analysis available",
97
+ "file_modified_date": file_modified_date
98
+ }
99
+
100
+ result = {**default_response, **parsed_response}
101
+
102
+ result["file_modified_date"] = file_modified_date
103
+
104
+ return result
105
+
106
+ except json.JSONDecodeError as e:
107
+ print(f"JSON Parse Error: {str(e)}")
108
+ return {
109
+ "candidate_name": "",
110
+ "gender": None,
111
+ "date_of_birth": None,
112
+ "email": None,
113
+ "mobile_number": None,
114
+ "address": None,
115
+ "pan_number": None,
116
+ "aadhar_number": None,
117
+ "passport_number": None,
118
+ "highest_education": None,
119
+ "designation": None,
120
+ "skills": "",
121
+ "total_experience": None,
122
+ "region": None,
123
+ "relevant_experience": None,
124
+ "experience_summary": "Could not parse resume details from response",
125
+ "file_modified_date": file_modified_date
126
+ }
127
+ except Exception as e:
128
+ print(f"Unexpected Error: {str(e)}")
129
+ return {
130
+ "candidate_name": "",
131
+ "gender": None,
132
+ "date_of_birth": None,
133
+ "email": None,
134
+ "mobile_number": None,
135
+ "address": None,
136
+ "pan_number": None,
137
+ "aadhar_number": None,
138
+ "passport_number": None,
139
+ "highest_education": None,
140
+ "designation": None,
141
+ "skills": "",
142
+ "total_experience": None,
143
+ "region": None,
144
+ "relevant_experience": None,
145
+ "experience_summary": f"Error analyzing resume: {str(e)}",
146
+ "file_modified_date": file_modified_date
147
  }