237 lines
8.3 KiB
Python
237 lines
8.3 KiB
Python
"""
|
|
Report generator module for the intelligent research system.
|
|
|
|
This module provides functionality to generate reports from search results
|
|
by scraping documents, storing them in a database, and synthesizing them
|
|
into a comprehensive report.
|
|
"""
|
|
|
|
import os
|
|
import asyncio
|
|
import logging
|
|
from typing import Dict, List, Any, Optional, Tuple, Union
|
|
|
|
from report.database.db_manager import get_db_manager, initialize_database
|
|
from report.document_scraper import get_document_scraper
|
|
from report.document_processor import get_document_processor
|
|
|
|
# Configure logging
|
|
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
|
|
logger = logging.getLogger(__name__)
|
|
|
|
class ReportGenerator:
|
|
"""
|
|
Report generator for the intelligent research system.
|
|
|
|
This class provides methods to generate reports from search results
|
|
by scraping documents, storing them in a database, and synthesizing them
|
|
into a comprehensive report.
|
|
"""
|
|
|
|
def __init__(self):
|
|
"""Initialize the report generator."""
|
|
self.db_manager = get_db_manager()
|
|
self.document_scraper = get_document_scraper()
|
|
self.document_processor = get_document_processor()
|
|
|
|
async def initialize(self):
|
|
"""Initialize the report generator by setting up the database."""
|
|
await initialize_database()
|
|
logger.info("Report generator initialized")
|
|
|
|
async def process_search_results(self, search_results: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
|
|
"""
|
|
Process search results by scraping the URLs and storing them in the database.
|
|
|
|
Args:
|
|
search_results: List of search results, each containing at least a 'url' field
|
|
|
|
Returns:
|
|
List of processed documents
|
|
"""
|
|
# Extract URLs from search results
|
|
urls = [result.get('url') for result in search_results if result.get('url')]
|
|
|
|
# Extract relevance scores if available
|
|
relevance_scores = {}
|
|
for result in search_results:
|
|
if result.get('url') and result.get('score') is not None:
|
|
relevance_scores[result.get('url')] = result.get('score')
|
|
|
|
# Scrape URLs and store in database
|
|
documents = await self.document_scraper.scrape_urls(urls)
|
|
|
|
# Log results
|
|
logger.info(f"Processed {len(documents)} documents out of {len(urls)} URLs")
|
|
|
|
return documents, relevance_scores
|
|
|
|
async def get_document_by_url(self, url: str) -> Optional[Dict[str, Any]]:
|
|
"""
|
|
Get a document by its URL.
|
|
|
|
Args:
|
|
url: URL of the document
|
|
|
|
Returns:
|
|
Document as a dictionary, or None if not found
|
|
"""
|
|
return await self.db_manager.get_document_by_url(url)
|
|
|
|
async def search_documents(self, query: str, limit: int = 10) -> List[Dict[str, Any]]:
|
|
"""
|
|
Search for documents in the database.
|
|
|
|
Args:
|
|
query: Search query
|
|
limit: Maximum number of results to return
|
|
|
|
Returns:
|
|
List of matching documents
|
|
"""
|
|
return await self.db_manager.search_documents(query, limit)
|
|
|
|
async def prepare_documents_for_report(self,
|
|
search_results: List[Dict[str, Any]],
|
|
token_budget: Optional[int] = None,
|
|
chunk_size: int = 1000,
|
|
overlap_size: int = 100) -> List[Dict[str, Any]]:
|
|
"""
|
|
Prepare documents for report generation by processing search results,
|
|
prioritizing documents, and chunking them to fit within token budget.
|
|
|
|
Args:
|
|
search_results: List of search results
|
|
token_budget: Maximum number of tokens to use
|
|
chunk_size: Maximum number of tokens per chunk
|
|
overlap_size: Number of tokens to overlap between chunks
|
|
|
|
Returns:
|
|
List of selected document chunks
|
|
"""
|
|
# Process search results to get documents and relevance scores
|
|
documents, relevance_scores = await self.process_search_results(search_results)
|
|
|
|
# Prioritize and chunk documents
|
|
selected_chunks = self.document_processor.process_documents_for_report(
|
|
documents,
|
|
relevance_scores,
|
|
token_budget,
|
|
chunk_size,
|
|
overlap_size
|
|
)
|
|
|
|
return selected_chunks
|
|
|
|
async def generate_report(self,
|
|
search_results: List[Dict[str, Any]],
|
|
query: str,
|
|
token_budget: Optional[int] = None,
|
|
chunk_size: int = 1000,
|
|
overlap_size: int = 100) -> str:
|
|
"""
|
|
Generate a report from search results.
|
|
|
|
Args:
|
|
search_results: List of search results
|
|
query: Original search query
|
|
token_budget: Maximum number of tokens to use
|
|
chunk_size: Maximum number of tokens per chunk
|
|
overlap_size: Number of tokens to overlap between chunks
|
|
|
|
Returns:
|
|
Generated report as a string
|
|
"""
|
|
# Prepare documents for report
|
|
selected_chunks = await self.prepare_documents_for_report(
|
|
search_results,
|
|
token_budget,
|
|
chunk_size,
|
|
overlap_size
|
|
)
|
|
|
|
# TODO: Implement report synthesis using LLM
|
|
# For now, just return a placeholder report
|
|
report = f"# Report for: {query}\n\n"
|
|
report += f"Based on {len(selected_chunks)} document chunks\n\n"
|
|
|
|
# Add document summaries
|
|
for i, chunk in enumerate(selected_chunks[:5]): # Show first 5 chunks
|
|
report += f"## Document {i+1}: {chunk.get('title', 'Untitled')}\n"
|
|
report += f"Source: {chunk.get('url', 'Unknown')}\n"
|
|
report += f"Chunk type: {chunk.get('chunk_type', 'Unknown')}\n"
|
|
report += f"Priority score: {chunk.get('priority_score', 0.0):.2f}\n\n"
|
|
|
|
# Add a snippet of the content
|
|
content = chunk.get('content', '')
|
|
snippet = content[:200] + "..." if len(content) > 200 else content
|
|
report += f"{snippet}\n\n"
|
|
|
|
return report
|
|
|
|
|
|
# Create a singleton instance for global use
|
|
report_generator = ReportGenerator()
|
|
|
|
async def initialize_report_generator():
|
|
"""Initialize the report generator."""
|
|
await report_generator.initialize()
|
|
|
|
def get_report_generator() -> ReportGenerator:
|
|
"""
|
|
Get the global report generator instance.
|
|
|
|
Returns:
|
|
ReportGenerator instance
|
|
"""
|
|
return report_generator
|
|
|
|
async def test_report_generator():
|
|
"""Test the report generator with sample search results."""
|
|
# Initialize the report generator
|
|
await initialize_report_generator()
|
|
|
|
# Sample search results
|
|
search_results = [
|
|
{
|
|
'title': 'Example Document 1',
|
|
'url': 'https://example.com/doc1',
|
|
'snippet': 'This is an example document.',
|
|
'score': 0.95
|
|
},
|
|
{
|
|
'title': 'Example Document 2',
|
|
'url': 'https://example.com/doc2',
|
|
'snippet': 'This is another example document.',
|
|
'score': 0.85
|
|
},
|
|
{
|
|
'title': 'Python Documentation',
|
|
'url': 'https://docs.python.org/3/',
|
|
'snippet': 'Official Python documentation.',
|
|
'score': 0.75
|
|
}
|
|
]
|
|
|
|
# Process search results
|
|
documents, relevance_scores = await report_generator.process_search_results(search_results)
|
|
|
|
# Print documents
|
|
print(f"Processed {len(documents)} documents")
|
|
for doc in documents:
|
|
print(f"Document: {doc.get('title')} ({doc.get('url')})")
|
|
print(f"Token count: {doc.get('token_count')}")
|
|
print(f"Content snippet: {doc.get('content')[:100]}...")
|
|
print()
|
|
|
|
# Generate report
|
|
report = await report_generator.generate_report(search_results, "Python programming")
|
|
|
|
# Print report
|
|
print("Generated Report:")
|
|
print(report)
|
|
|
|
# Run test if this module is executed directly
|
|
if __name__ == "__main__":
|
|
asyncio.run(test_report_generator())
|