Spaces:
Runtime error
Runtime error
Update services/resume_service.py
Browse files- 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 |
-
|
| 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 |
}
|
|
|
|
| 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 |
}
|