Update app.py

app.py

@@ -5,11 +5,10 @@ import feedparser
 from dotenv import load_dotenv
 from duckduckgo_search import DDGS
 
-# Load API key from .env
 load_dotenv()
 OPENROUTER_API_KEY = os.getenv("OPENROUTER_API_KEY")
 
-# --- LLM Function ---
+# --- Call OpenRouter LLM ---
 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 = {
@@ -29,13 +28,12 @@ def call_llm(messages, model="deepseek/deepseek-chat-v3-0324:free", max_tokens=2
     except Exception as e:
         raise RuntimeError(f"Failed to connect or parse response: {e}")
     if response.status_code != 200:
-        error = result.get("error", {}).get("message", response.text)
-        raise RuntimeError(f"OpenRouter API Error: {error}")
+        raise RuntimeError(result.get("error", {}).get("message", "LLM API error"))
     if "choices" not in result:
         raise RuntimeError(f"Invalid response: {result}")
     return result["choices"][0]["message"]["content"]
 
-# --- Source Fetching Functions ---
+# --- Search Utilities ---
 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}"
@@ -50,12 +48,11 @@ 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)
-    papers = response.json().get("data", [])
     return [{
         "title": p.get("title", ""),
         "summary": p.get("abstract", "No abstract").strip(),
         "url": p.get("url", "")
-    } for p in papers]
+    } for p in response.json().get("data", [])]
 
 def search_duckduckgo(query, max_results=3):
     with DDGS() as ddgs:
@@ -65,76 +62,96 @@ def search_duckduckgo(query, max_results=3):
             "url": r["href"]
         } for r in ddgs.text(query, max_results=max_results)]
 
-def get_image_url(query):
+def get_image_urls(query, max_images=3):
     with DDGS() as ddgs:
-        for r in ddgs.images(query, max_results=1):
-            return r["image"]
-    return None
+        return [img["image"] for img in ddgs.images(query, max_results=max_images)]
 
-# --- Autonomous Agent ---
+# --- Autonomous Research Agent ---
 def autonomous_research_agent(topic):
     arxiv = get_arxiv_papers(topic)
     scholar = get_semantic_scholar_papers(topic)
     web = search_duckduckgo(topic)
-    image = get_image_url(topic)
+    images = get_image_urls(topic)
 
-    prompt = f"# Research Topic: {topic}\n\n"
+    image_md = ""
+    if images:
+        for img in images:
+            image_md += f"![Image]({img}) "
+        image_md += "\n\n"
 
-    if image:
-        prompt += f"![Relevant Image]({image})\n\n"
-
-    prompt += "## ArXiv:\n"
+    arxiv_md = ""
     for p in arxiv:
-        prompt += f"- [{p['title']}]({p['url']})\n> {p['summary'][:300]}...\n\n"
+        arxiv_md += f"- [{p['title']}]({p['url']})\n> {p['summary'][:300]}...\n\n"
 
-    prompt += "## Semantic Scholar:\n"
+    scholar_md = ""
     for p in scholar:
-        prompt += f"- [{p['title']}]({p['url']})\n> {p['summary'][:300]}...\n\n"
+        scholar_md += f"- [{p['title']}]({p['url']})\n> {p['summary'][:300]}...\n\n"
 
-    prompt += "## Web Insights:\n"
+    web_md = ""
     for w in web:
-        prompt += f"- [{w['title']}]({w['url']})\n> {w['snippet']}\n\n"
+        web_md += f"- [{w['title']}]({w['url']})\n> {w['snippet']}\n\n"
+
+    prompt = f"""
+# Research Topic: {topic}
+
+{image_md}
+
+## ArXiv:
+{arxiv_md}
+
+## Semantic Scholar:
+{scholar_md}
 
-    prompt += (
-        "Now, based on the above sources:\n"
-        "1. Identify overlapping research themes\n"
-        "2. Highlight a gap or opportunity\n"
-        "3. Propose a novel research direction\n"
-        "4. Write a full academic-style narrative in markdown (no section labels)\n"
-    )
+## Web Insights:
+{web_md}
 
-    return call_llm([{"role": "user", "content": prompt}], max_tokens=3000)
+Now synthesize this information into:
+1. A research gap
+2. A novel research direction
+3. A full markdown-formatted research article (continuous, no section labels, academic tone)
+"""
+    response = call_llm([{"role": "user", "content": prompt}], max_tokens=3000)
 
-# --- Streamlit App ---
-st.set_page_config("Autonomous Research Agent", layout="wide")
+    # Append Sources
+    response += "\n\n---\n### Sources Cited\n"
+    if arxiv_md:
+        response += "**ArXiv:**\n" + arxiv_md
+    if scholar_md:
+        response += "**Semantic Scholar:**\n" + scholar_md
+    if web_md:
+        response += "**Web:**\n" + web_md
+
+    return response
+
+# --- Streamlit UI ---
+st.set_page_config("Autonomous Research Assistant", 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"):
+if st.button("Run Research Agent"):
     with st.spinner("Gathering sources & thinking..."):
         try:
-            response = autonomous_research_agent(topic)
+            result = autonomous_research_agent(topic)
             st.session_state.chat_history.append({"role": "user", "content": topic})
-            st.session_state.chat_history.append({"role": "assistant", "content": response})
-            st.markdown(response)
+            st.session_state.chat_history.append({"role": "assistant", "content": result})
+            st.markdown(result)
         except Exception as e:
             st.error(f"Failed: {e}")
 
-# --- Follow-up Chat ---
+# --- Follow-up Q&A ---
 st.divider()
-st.subheader("💬 Follow-up Questions")
-followup = st.text_input("Ask something about the research:")
+st.subheader("💬 Follow-up Q&A")
+followup = st.text_input("Ask a follow-up question:")
 if st.button("Ask"):
     if followup:
-        chat = st.session_state.chat_history + [{"role": "user", "content": followup}]
-        with st.spinner("Answering..."):
-            try:
-                answer = 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": answer})
-                st.markdown(answer)
-            except Exception as e:
-                st.error(f"Follow-up error: {e}")
+        try:
+            chat = st.session_state.chat_history + [{"role": "user", "content": followup}]
+            answer = 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": answer})
+            st.markdown(answer)
+        except Exception as e:
+            st.error(f"Follow-up error: {e}")