app.py

import gradio as gr
from openai import OpenAI
from smolagents import DuckDuckGoSearchTool
import re
import time
import datetime

current_date = datetime.datetime.now().strftime("%d:%m:%Y")
refresh_time = datetime.datetime.now().strftime("%H:%M")

web_search = DuckDuckGoSearchTool()

SYSTEM_PROMPT = '''
You are a methodical web search agent designed to solve complex tasks through iterative, step-by-step web searches. Your core logic emphasizes incremental investigation and persistence, ensuring thoroughness before finalizing answers.

**Core Principles:**
1. **Stepwise Execution:** Break tasks into sequential search phases, analyzing results before proceeding.
2. **Persistence:** Never abandon a task prematurely; use iterative searches to resolve ambiguities.
3. **Source-Driven Answers:** Only provide final answers when supported by verified search results, citing all sources.

**Workflow:**
1. **Clarify:** Ask targeted questions if the task is ambiguous (e.g., "Do you need AI news from specific regions?").
2. **Search:** Use `<search>` blocks for queries, prioritizing high-yield terms. Wait for results before proceeding.
3. **Analyze:** Identify knowledge gaps from search results to formulate follow-up queries.
4. **Repeat:** Iterate searches until all aspects of the task are addressed (e.g., initial broad search → targeted follow-ups).
5. **Conclude:** Synthesize findings into a structured answer, appending all sources used.

**Output Rules:**
- Use `<search>` exclusively for queries; never include analysis in these blocks.
- Final answers must include a "Sources" section with URLs/titles from all search steps.
- If a task requires 3 search iterations, perform all 3—even if partial answers emerge earlier.

**How to use search:**
<search>
query 1
query 2
etc...
</search>

**Example:**
Task: "Explain quantum computing breakthroughs in 2023."
1. Search: ["2023 quantum computing breakthroughs", "latest quantum supremacy milestones"]
2. Analyze results → identify key researchers/institutions.
3. Follow-up search: ["John Doe quantum research 2023", "IBM quantum roadmap 2023"]
4. Compile findings with sources.

**Constraints:**
- Never speculate; only use verified search data.
- If results are contradictory, search for consensus sources.
- For numerical data, cross-validate with ≥2 reputable sources.

**Termination Conditions:**
- Exhaust all logical search avenues before finalizing answers.
- If stuck, search for alternative phrasings (e.g., "quantum computing" → "quantum information science").
'''

def process_searches(response):
    formatted_response = response.replace("<thinking>", "\n💭 THINKING PROCESS:\n").replace("</thinking>", "\n")
    searches = re.findall(r'<search>(.*?)</search>', formatted_response, re.DOTALL)
    if searches:
        queries = [q.strip() for q in searches[0].split('\n') if q.strip()]
        return queries
    return None

def search_with_retry(query, max_retries=3, delay=2):
    for attempt in range(max_retries):
        try:
            return web_search(query)
        except Exception as e:
            if attempt < max_retries - 1:
                time.sleep(delay)
                continue
            raise
    return None

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    model_name,
    max_tokens,
    temperature,
    top_p,
    openrouter_key,
):
    client = OpenAI(
        base_url="https://openrouter.ai/api/v1",
        api_key=openrouter_key,
    )
    
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})
    
    full_response = ""
    search_cycle = True
    
    try:
        while search_cycle:
            search_cycle = False
            
            try:
                completion = client.chat.completions.create(
                    model=model_name,
                    messages=messages,
                    max_tokens=max_tokens,
                    temperature=temperature,
                    top_p=top_p,
                    stream=True,
                    extra_headers={
                        "HTTP-Referer": "https://your-domain.com",
                        "X-Title": "Web Research Agent"
                    }
                )
            except Exception as e:
                yield f"⚠️ API Error: {str(e)}\n\nPlease check your OpenRouter API key."
                return

            response = ""
            for chunk in completion:
                token = chunk.choices[0].delta.content or ""
                response += token
                full_response += token
                yield full_response

            queries = process_searches(response)
            
            if queries:
                search_cycle = True
                messages.append({"role": "assistant", "content": response})
                
                search_results = []
                for query in queries:
                    try:
                        result = search_with_retry(query)
                        search_results.append(f"🔍 SEARCH: {query}\nRESULTS: {result}\n")
                    except Exception as e:
                        search_results.append(f"⚠️ Search Error: {str(e)}\nQuery: {query}")
                        time.sleep(2)
                
                messages.append({
                    "role": "user",
                    "content": f"SEARCH RESULTS:\n{chr(10).join(search_results)}\nAnalyze these results..."
                })
                full_response += "\n🔍 Analyzing search results...\n"
                yield full_response

    except Exception as e:
        yield f"⚠️ Critical Error: {str(e)}\n\nPlease try again later."

demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value=SYSTEM_PROMPT, label="System Prompt", lines=8),
        gr.Textbox(
            value="qwen/qwq-32b:free",  # Default model
            label="Model",
            placeholder="deepseek/deepseek-r1-zero:free, google/gemini-2.0-pro-exp-02-05:free...",
            info="OpenRouter model ID"
        ),
        gr.Slider(minimum=1000, maximum=15000, value=6000, step=500, label="Max Tokens"),
        gr.Slider(minimum=0.1, maximum=1.0, value=0.5, step=0.1, label="Temperature"),
        gr.Slider(minimum=0.1, maximum=1.0, value=0.85, step=0.05, label="Top-p"),
        gr.Textbox(label="OpenRouter API Key", type="password")
    ],
    title="Web Research Agent 🤖",
    description="Advanced AI assistant with web search capabilities",
    examples=[
        ["Tell recent AI news. 2025"],
        ["Tell about recent new ML discoveries with VERY simple words. 2025"],
        ["Write a report on the impact of AI on our daily lives."]
    ],
    cache_examples=False
)

if __name__ == "__main__":
    demo.launch()