Update app.py

app.py

@@ -1,163 +1,117 @@
 import os
-import arxiv
-import requests
 import streamlit as st
-from dotenv import load_dotenv
+import requests
+import feedparser
 from duckduckgo_search import DDGS
-import subprocess
-import re
+from dotenv import load_dotenv
 
-# Load environment
 load_dotenv()
-API_KEY = os.getenv("OPENROUTER_API_KEY")
-
-# ========== UTILITY FUNCTIONS ==========
-def sanitize_filename(title):
-    return re.sub(r'[^\w\s-]', '', title).replace(" ", "_")[:50]
-
-def escape_latex(text):
-    replacements = {
-        '&': r'\&', '%': r'\%', '$': r'\$', '#': r'\#',
-        '_': r'\_', '{': r'\{', '}': r'\}', '~': r'\textasciitilde{}',
-        '^': r'\^{}', '\\': r'\textbackslash{}',
+OPENROUTER_API_KEY = os.getenv("OPENROUTER_API_KEY")  # secure access
+
+# --- LLM Wrapper ---
+def call_llm(messages, model="deepseek/deepseek-chat-v3-0324:free", max_tokens=2048, temperature=0.7):
+    url = "https://openrouter.ai/api/v1/chat/completions"
+    headers = {
+        "Authorization": f"Bearer {OPENROUTER_API_KEY}",
+        "Content-Type": "application/json",
+        "X-Title": "Autonomous Research Agent"
     }
-    for original, replacement in replacements.items():
-        text = text.replace(original, replacement)
-    return text
-
-# ========== LLM INTERACTION ==========
-def call_llm(prompt):
-    try:
-        url = "https://openrouter.ai/api/v1/chat/completions"
-        headers = {
-            "Authorization": f"Bearer {API_KEY}",
-            "Content-Type": "application/json"
-        }
-        data = {
-            "model": "google/gemma-3-1b-it:free",
-            "messages": [{"role": "user", "content": prompt}]
-        }
-        response = requests.post(url, headers=headers, json=data)
-        response.raise_for_status()
-        return response.json()['choices'][0]['message']['content']
-    except Exception as e:
-        return f"❌ LLM Error: {str(e)}"
-
-# ========== FETCH RESEARCH ==========
-def fetch_arxiv_papers(topic):
-    results = arxiv.Search(query=topic, max_results=5, sort_by=arxiv.SortCriterion.SubmittedDate)
-    return [{
-        "title": result.title,
-        "summary": result.summary,
-        "url": result.pdf_url
-    } for result in results.results()]
-
-def fetch_image_url(query):
-    try:
-        with DDGS() as ddgs:
-            results = list(ddgs.images(query, max_results=1))
-            if results:
-                return results[0]['image']
-    except:
-        pass
-    return None
-
-# ========== PDF EXPORT ==========
-def create_latex(title, content, image_url):
-    title_safe = sanitize_filename(title)
-    content = escape_latex(content)
-    tex = f"""
-\\documentclass[12pt]{{article}}
-\\usepackage[margin=1in]{{geometry}}
-\\usepackage{{graphicx}}
-\\usepackage{{hyperref}}
-\\title{{\\textbf{{{escape_latex(title)}}}}}
-\\date{{\\today}}
-\\begin{{document}}
-\\maketitle
-"""
-
-    if image_url:
-        img_data = requests.get(image_url).content
-        with open("image.jpg", "wb") as img:
-            img.write(img_data)
-        tex += """
-\\begin{figure}[h]
-    \\centering
-    \\includegraphics[width=0.7\\textwidth]{image.jpg}
-    \\caption{Auto-fetched Diagram}
-\\end{figure}
-"""
-
-    tex += f"{content}\n\\end{{document}}"
-
-    tex_file = f"{title_safe}.tex"
-    with open(tex_file, "w", encoding="utf-8") as f:
-        f.write(tex)
-
-    subprocess.run(["pdflatex", tex_file], stdout=subprocess.DEVNULL)
-    return f"{title_safe}.pdf"
-
-# ========== STREAMLIT UI ==========
-st.set_page_config("AI Research Assistant", layout="wide")
-st.title("🧪 AI-Powered Research Assistant")
-
-topic = st.text_input("🔍 Enter your research topic:")
-
-if topic:
-    with st.spinner("🔎 Fetching relevant arXiv papers..."):
-        papers = fetch_arxiv_papers(topic)
-        summaries = "\n\n".join([f"Title: {p['title']}\nSummary: {p['summary']}" for p in papers])
-
-    st.subheader("📄 Recent arXiv Papers")
-    for p in papers:
-        st.markdown(f"**{p['title']}**\n[🔗 PDF Link]({p['url']})\n> {p['summary'][:300]}...")
-
-    with st.spinner("🧠 Analyzing gaps and proposing ideas..."):
-        gaps = call_llm(f"You're a top AI researcher. Read the summaries and find research gaps:\n\n{summaries}")
-        idea = call_llm(f"Based on the gaps below, propose a novel research idea:\n\n{gaps}")
-        paper_prompt = f"""
-You're an expert AI researcher and LaTeX academic writer.
-
-Write a **complete research paper** in well-formatted plain text (NOT just sections or instructions) titled: **"{topic}"**, based on this novel idea:
-
-"{idea}"
-
-Follow this structure **strictly** (include headings for each):
-1. Abstract
-2. Introduction
-3. Related Work
-4. Methodology
-5. Experiments
-6. Results & Discussion
-7. Conclusion
-8. References
-
-⚠️ Do NOT ask the user to provide content. Write the full content yourself.
-
-Limit the total length to approximately 2000-2500 words to avoid truncation.
-Write in an academic tone and avoid repetition.
-Include citations in the format [Author, Year] without needing actual sources.
-Make sure it's export-ready.
-"""
-
-    paper = call_llm(paper_prompt)
-
-
-    st.subheader("💡 Novel Research Idea")
-    st.markdown(idea)
-
-    st.subheader("📃 Full Generated Paper")
-    st.text_area("Academic Paper", paper, height=600)
-
-    with st.spinner("🖼️ Fetching diagram..."):
-        image_url = fetch_image_url(topic)
-        if image_url:
-            st.image(image_url, caption="Auto-fetched relevant diagram")
-
-    if st.button("📥 Export to PDF"):
-        with st.spinner("📄 Generating PDF..."):
-            pdf_file = create_latex(topic, paper, image_url)
-            with open(pdf_file, "rb") as f:
-                st.download_button("Download Paper as PDF", f, file_name=pdf_file)
-
+    data = {
+        "model": model,
+        "messages": messages,
+        "max_tokens": max_tokens,
+        "temperature": temperature
+    }
+    response = requests.post(url, headers=headers, json=data)
+    result = response.json()
+    if "choices" not in result:
+        raise RuntimeError(f"LLM returned invalid response: {result}")
+    return result["choices"][0]["message"]["content"]
+
+# --- Research Source Functions ---
+def get_arxiv_papers(query, max_results=3):
+    from urllib.parse import quote_plus
+    url = f"http://export.arxiv.org/api/query?search_query=all:{quote_plus(query)}&start=0&max_results={max_results}"
+    feed = feedparser.parse(url)
+    papers = []
+    for entry in feed.entries:
+        pdf = next((link.href for link in entry.links if link.type == "application/pdf"), "")
+        papers.append({"title": entry.title, "summary": entry.summary[:300], "url": pdf})
+    return papers
+
+def get_semantic_scholar_papers(query, max_results=3):
+    url = "https://api.semanticscholar.org/graph/v1/paper/search"
+    params = {"query": query, "limit": max_results, "fields": "title,abstract,url"}
+    response = requests.get(url, params=params)
+    results = response.json().get("data", [])
+    return [{"title": p["title"], "summary": p.get("abstract", "N/A")[:300], "url": p.get("url", "")} for p in results]
+
+def search_duckduckgo_snippets(query, max_results=3):
+    with DDGS() as ddgs:
+        return [
+            {"title": r["title"], "snippet": r["body"], "url": r["href"]}
+            for r in ddgs.text(query, max_results=max_results)
+        ]
+
+def get_image_urls(query, max_images=1):
+    with DDGS() as ddgs:
+        return [img["image"] for img in ddgs.images(query, max_results=max_images)]
+
+# --- Research Agent ---
+def autonomous_research_agent(topic):
+    arxiv = get_arxiv_papers(topic)
+    scholar = get_semantic_scholar_papers(topic)
+    web = search_duckduckgo_snippets(topic)
+    images = get_image_urls(topic)
+
+    prompt = f"Topic: {topic}\n\n"
+
+    if images:
+        prompt += f"![Related Image]({images[0]})\n\n"
+
+    prompt += "## ArXiv:\n" + "\n".join(f"- [{p['title']}]({p['url']})\n> {p['summary']}..." for p in arxiv) + "\n\n"
+    prompt += "## Semantic Scholar:\n" + "\n".join(f"- [{p['title']}]({p['url']})\n> {p['summary']}..." for p in scholar) + "\n\n"
+    prompt += "## Web:\n" + "\n".join(f"- [{w['title']}]({w['url']})\n> {w['snippet']}" for w in web) + "\n\n"
+    
+    prompt += (
+        "Now synthesize all this into:\n"
+        "1. Research gap\n"
+        "2. Proposed research direction\n"
+        "3. A full academic narrative (markdown format, formal tone)"
+    )
+
+    return call_llm([{"role": "user", "content": prompt}], max_tokens=3000)
+
+# --- Streamlit UI ---
+st.set_page_config("Autonomous Research Agent", layout="wide")
+st.title("🤖 Autonomous AI Research Assistant")
+
+if "chat_history" not in st.session_state:
+    st.session_state.chat_history = []
+
+topic = st.text_input("Enter a research topic:")
+if st.button("Run Agent"):
+    with st.spinner("Researching..."):
+        try:
+            output = autonomous_research_agent(topic)
+            st.session_state.chat_history.append({"role": "user", "content": topic})
+            st.session_state.chat_history.append({"role": "assistant", "content": output})
+            st.markdown(output)
+        except Exception as e:
+            st.error(f"Error: {e}")
+
+# --- Follow-up Chat ---
+st.divider()
+st.subheader("💬 Ask Follow-up Questions")
+followup = st.text_input("Ask something based on the previous research:")
+if st.button("Send"):
+    if followup:
+        chat = st.session_state.chat_history + [{"role": "user", "content": followup}]
+        with st.spinner("Thinking..."):
+            try:
+                response = call_llm(chat, max_tokens=1500)
+                st.session_state.chat_history.append({"role": "user", "content": followup})
+                st.session_state.chat_history.append({"role": "assistant", "content": response})
+                st.markdown(response)
+            except Exception as e:
+                st.error(f"Follow-up failed: {e}")