From Snippets to Reports: Building a Multi‑Round Research Agent with Gemini and DuckDuckGo

import os
import json
import time
import requests
from typing import List, Dict, Any
from dataclasses import dataclass
import google.generativeai as genai
from urllib.parse import quote_plus
import re

@dataclass
class ResearchConfig:
   gemini_api_key: str
   max_sources: int = 10
   max_content_length: int = 5000
   search_delay: float = 1.0


class DeepResearchSystem:
   def __init__(self, config: ResearchConfig):
       self.config = config
       genai.configure(api_key=config.gemini_api_key)
       self.model = genai.GenerativeModel('gemini-1.5-flash')


   def search_web(self, query: str, num_results: int = 5) -> List[Dict[str, str]]:
       """Search web using DuckDuckGo Instant Answer API"""
       try:
           encoded_query = quote_plus(query)
           url = f"https://api.duckduckgo.com/?q={encoded_query}&format=json&no_redirect=1"


           response = requests.get(url, timeout=10)
           data = response.json()


           results = []


           if 'RelatedTopics' in data:
               for topic in data['RelatedTopics'][:num_results]:
                   if isinstance(topic, dict) and 'Text' in topic:
                       results.append({
                           'title': topic.get('Text', '')[:100] + '...',
                           'url': topic.get('FirstURL', ''),
                           'snippet': topic.get('Text', '')
                       })


           if not results:
               results = [{
                   'title': f"Research on: {query}",
                   'url': f"https://search.example.com/q={encoded_query}",
                   'snippet': f"General information and research about {query}"
               }]


           return results


       except Exception as e:
           print(f"Search error: {e}")
           return [{'title': f"Research: {query}", 'url': '', 'snippet': f"Topic: {query}"}]


   def extract_key_points(self, content: str) -> List[str]:
       """Extract key points using Gemini"""
       prompt = f"""
       Extract 5-7 key points from this content. Be concise and factual:


       {content[:2000]}


       Return as numbered list:
       """


       try:
           response = self.model.generate_content(prompt)
           return [line.strip() for line in response.text.split('\n') if line.strip()]
       except:
           return ["Key information extracted from source"]


   def analyze_sources(self, sources: List[Dict[str, str]], query: str) -> Dict[str, Any]:
       """Analyze sources for relevance and extract insights"""
       analysis = {
           'total_sources': len(sources),
           'key_themes': [],
           'insights': [],
           'confidence_score': 0.7
       }


       all_content = " ".join([s.get('snippet', '') for s in sources])


       if len(all_content) > 100:
           prompt = f"""
           Analyze this research content for the query: "{query}"


           Content: {all_content[:1500]}


           Provide:
           1. 3-4 key themes (one line each)
           2. 3-4 main insights (one line each)
           3. Overall confidence (0.1-1.0)


           Format as JSON with keys: themes, insights, confidence
           """


           try:
               response = self.model.generate_content(prompt)
               text = response.text
               if 'themes' in text.lower():
                   analysis['key_themes'] = ["Theme extracted from analysis"]
                   analysis['insights'] = ["Insight derived from sources"]
           except:
               pass


       return analysis


   def generate_comprehensive_report(self, query: str, sources: List[Dict[str, str]],
                                   analysis: Dict[str, Any]) -> str:
       """Generate final research report"""


       sources_text = "\n".join([f"- {s['title']}: {s['snippet'][:200]}"
                                for s in sources[:5]])


       prompt = f"""
       Create a comprehensive research report on: "{query}"


       Based on these sources:
       {sources_text}


       Analysis summary:
       - Total sources: {analysis['total_sources']}
       - Confidence: {analysis['confidence_score']}


       Structure the report with:
       1. Executive Summary (2-3 sentences)
       2. Key Findings (3-5 bullet points)
       3. Detailed Analysis (2-3 paragraphs)
       4. Conclusions & Implications (1-2 paragraphs)
       5. Research Limitations


       Be factual, well-structured, and insightful.
       """


       try:
           response = self.model.generate_content(prompt)
           return response.text
       except Exception as e:
           return f"""
# Research Report: {query}


## Executive Summary
Research conducted on "{query}" using {analysis['total_sources']} sources.


## Key Findings
- Multiple perspectives analyzed
- Comprehensive information gathered
- Research completed successfully


## Analysis
The research process involved systematic collection and analysis of information related to {query}. Various sources were consulted to provide a balanced perspective.


## Conclusions
The research provides a foundation for understanding {query} based on available information.


## Research Limitations
Limited by API constraints and source availability.
           """


   def conduct_research(self, query: str, depth: str = "standard") -> Dict[str, Any]:
       """Main research orchestration method"""
       print(f" Starting research on: {query}")


       search_rounds = {"basic": 1, "standard": 2, "deep": 3}.get(depth, 2)
       sources_per_round = {"basic": 3, "standard": 5, "deep": 7}.get(depth, 5)


       all_sources = []


       search_queries = [query]


       if depth in ["standard", "deep"]:
           try:
               related_prompt = f"Generate 2 related search queries for: {query}. One line each."
               response = self.model.generate_content(related_prompt)
               additional_queries = [q.strip() for q in response.text.split('\n') if q.strip()][:2]
               search_queries.extend(additional_queries)
           except:
               pass


       for i, search_query in enumerate(search_queries[:search_rounds]):
           print(f" Search round {i+1}: {search_query}")
           sources = self.search_web(search_query, sources_per_round)
           all_sources.extend(sources)
           time.sleep(self.config.search_delay)


       unique_sources = []
       seen_urls = set()
       for source in all_sources:
           if source['url'] not in seen_urls:
               unique_sources.append(source)
               seen_urls.add(source['url'])


       print(f" Analyzing {len(unique_sources)} unique sources...")


       analysis = self.analyze_sources(unique_sources[:self.config.max_sources], query)


       print(" Generating comprehensive report...")


       report = self.generate_comprehensive_report(query, unique_sources, analysis)


       return {
           'query': query,
           'sources_found': len(unique_sources),
           'analysis': analysis,
           'report': report,
           'sources': unique_sources[:10]
       }

def setup_research_system(api_key: str) -> DeepResearchSystem:
   """Quick setup for Google Colab"""
   config = ResearchConfig(
       gemini_api_key=api_key,
       max_sources=15,
       max_content_length=6000,
       search_delay=0.5
   )
   return DeepResearchSystem(config)

if __name__ == "__main__":
   API_KEY = "Use Your Own API Key Here"


   researcher = setup_research_system(API_KEY)


   query = "Deep Research Agent Architecture"
   results = researcher.conduct_research(query, depth="standard")


   print("="*50)
   print("RESEARCH RESULTS")
   print("="*50)
   print(f"Query: {results['query']}")
   print(f"Sources found: {results['sources_found']}")
   print(f"Confidence: {results['analysis']['confidence_score']}")
   print("\n" + "="*50)
   print("COMPREHENSIVE REPORT")
   print("="*50)
   print(results['report'])


   print("\n" + "="*50)
   print("SOURCES CONSULTED")
   print("="*50)
   for i, source in enumerate(results['sources'][:5], 1):
       print(f"{i}. {source['title']}")
       print(f"   URL: {source['url']}")
       print(f"   Preview: {source['snippet'][:150]}...")
       print()