Spaces:
Runtime error
Runtime error
File size: 2,574 Bytes
a5778f2 | 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 | import os
from pathlib import Path
from typing import Dict, List, Optional
class KnowledgeBaseManager:
def __init__(self, knowledge_base_path: str = "knowledge_base"):
self.kb_path = Path(knowledge_base_path)
self.documents = {}
self.kb_path.mkdir(exist_ok=True)
def scan_documents(self) -> Dict:
documents = {}
categories = {
'faqs': 'Frequently Asked Questions',
'policies': 'Company Policies',
'product_manuals': 'Product Manuals',
# 'development' intentionally omitted
}
for category, desc in categories.items():
cat_path = self.kb_path / category
if cat_path.exists():
docs = []
for f in cat_path.glob('*.md'):
docs.append(self._analyze_document(f, category))
documents[category] = {'description': desc, 'documents': docs}
self.documents = documents
return documents
def _analyze_document(self, file_path: Path, category: str) -> Dict:
with open(file_path, 'r', encoding='utf-8') as f:
content = f.read()
title = next((line.strip('# ').strip() for line in content.split('\n') if line.startswith('# ')), file_path.stem)
return {
'filename': file_path.name,
'title': title,
'category': category,
'path': str(file_path.relative_to(self.kb_path)),
'size': file_path.stat().st_size,
'word_count': len(content.split()),
'char_count': len(content)
}
def load_document_content(self, document_path: str) -> Optional[str]:
full = self.kb_path / document_path
if full.exists():
with open(full, 'r', encoding='utf-8') as f:
return f.read()
return None
def search_documents(self, query: str, category: Optional[str] = None) -> List[Dict]:
results = []
ql = query.lower()
for cat, info in self.documents.items():
if category and cat != category:
continue
for doc in info['documents']:
content = self.load_document_content(doc['path'])
if not content:
continue
if ql in content.lower() or ql in doc['title'].lower():
score = content.lower().count(ql)
results.append({**doc, 'relevance_score': score})
results.sort(key=lambda x: x['relevance_score'], reverse=True)
return results
|