Spaces:
Sleeping
Sleeping
File size: 3,657 Bytes
df69a6f e4184fb df69a6f |
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 |
# data_service.py
from typing import Dict, List, Any
from data_structures import WEB_DATA_REPORTS
from gpt_analyzer import GPTAnalyzer
class DataAssessmentService:
def __init__(self, api_key: str):
self.analyzer = GPTAnalyzer(api_key)
self.web_data = WEB_DATA_REPORTS
def check_data_availability(self, analysis_result: dict) -> dict:
availability = {
"available_in_webdata": [],
"needs_datalake": [],
"not_available": [],
"access_instructions": []
}
for required in analysis_result.get("required_reports", []):
category = required["category"]
report_type = required["report_type"]
if category in self.web_data:
matching_reports = []
for report_name, report_details in self.web_data[category].items():
required_fields = set(required.get("fields_needed", []))
available_fields = set(report_details["fields"].keys())
if required_fields.issubset(available_fields):
matching_reports.append({
"report_name": report_name,
"description": report_details["description"],
"access_path": f"/web-data/{category.lower()}/{report_name}",
"filters": report_details["filters"]
})
if matching_reports:
availability["available_in_webdata"].extend(matching_reports)
availability["access_instructions"].append(
f"Access {category} data through Web Data portal using filters: "
f"{', '.join(matching_reports[0]['filters'])}"
)
else:
availability["needs_datalake"].append({
"category": category,
"report_type": report_type,
"reason": "Required fields not available in Web Data"
})
else:
availability["not_available"].append({
"category": category,
"report_type": report_type,
"reason": "Category not found in Web Data"
})
return availability
def assess_request(self, request_text: str) -> Dict[str, Any]:
# 1. Analyze the request
analysis = self.analyzer.analyze_request(request_text, list(self.web_data.keys()))
if "error" in analysis:
return {"status": "error", "message": analysis["error"]}
# 2. Check data availability
availability = self.check_data_availability(analysis)
# 3. Generate response
response = {
"status": "success",
"request_analysis": {
"interpretation": analysis["interpretation"],
"confidence": analysis["confidence_score"]
},
"data_availability": {
"available_reports": availability["available_in_webdata"],
"access_instructions": availability["access_instructions"]
}
}
if availability["needs_datalake"]:
response["data_lake_requirements"] = {
"reports_needed": availability["needs_datalake"],
"estimated_processing_time": "2-3 business days",
"requires_it_support": True
}
if availability["not_available"]:
response["unavailable_data"] = availability["not_available"]
return response |