Update app.py

app.py

@@ -1,64 +1,57 @@
-import gradio as gr
+# Import the required libraries
+import streamlit as st
+from phi.assistant import Assistant
+from phi.tools.arxiv_toolkit import ArxivToolkit
 from huggingface_hub import InferenceClient
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    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})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+# Initialize the Hugging Face Inference Client
+client = InferenceClient(model="HuggingFaceH4/zephyr-7b-beta")
+
+# Set up the Streamlit app
+st.set_page_config(page_title="Chat with Research Papers", layout="wide")
+st.title("Chat with Research Papers 🔎🤖")
+st.caption("This app allows you to chat with arXiv research papers using the Zephyr model hosted on Hugging Face.")
+
+# Sidebar Configuration
+st.sidebar.header("Settings")
+temperature = st.sidebar.slider("Temperature", 0.0, 1.0, 0.7, 0.1)
+top_p = st.sidebar.slider("Top-p", 0.0, 1.0, 0.95, 0.05)
+max_tokens = st.sidebar.slider("Max Tokens", 100, 1024, 512, 50)
+
+# Initialize Assistant with Arxiv Toolkit
+assistant = Assistant(llm=client, tools=[ArxivToolkit()])
+
+# Get the search query from the user
+query = st.text_input("Enter your research query or topic:")
+
+if st.button("Search") and query:
+    with st.spinner("Searching arXiv and generating a response..."):
+        # Prepare messages for the chat
+        messages = [
+            {"role": "system", "content": "You are a helpful assistant for arXiv research."},
+            {"role": "user", "content": query}
+        ]
+
+        # Generate response using Zephyr
+        response = ""
+        for message in client.chat_completion(messages, max_tokens=max_tokens, stream=True, temperature=temperature, top_p=top_p):
+            token = message.choices[0].delta.content
+            response += token
+
+        # Search arXiv and parse results
+        arxiv_results = assistant.run(f"Search arxiv for '{query}'", stream=False)
+
+    # Display the response
+    st.subheader("Model Response")
+    st.write(response)
+
+    # Display arXiv results
+    st.subheader("ArXiv Search Results")
+    if arxiv_results:
+        for paper in arxiv_results:
+            with st.expander(paper['title']):
+                st.write(f"**Authors:** {', '.join(paper['authors'])}")
+                st.write(f"**Abstract:** {paper['summary']}")
+                st.write(f"[Read More]({paper['link']})")
+    else:
+        st.write("No results found.")