Upload app.py

app.py

@@ -1,87 +1,64 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-import urllib.request
-import xml.etree.ElementTree as ET
 
-# HuggingFace Inference Client
-#client = InferenceClient("meta-llama/Llama-3.3-70B-Instruct")
+"""
+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")
 
 
-
-# Funktion, um relevante Studien von arXiv zu suchen
-def fetch_arxiv_summary(query, sort_by="relevance", sort_order="descending", max_results=20):
-    url = (f'http://export.arxiv.org/api/query?search_query=all:{urllib.parse.quote(query)}'
-           f'&start=0&max_results={max_results}&sortBy={sort_by}&sortOrder={sort_order}')
-    try:
-        data = urllib.request.urlopen(url)
-        xml_data = data.read().decode("utf-8")
-        root = ET.fromstring(xml_data)
-        summaries = []
-        for entry in root.findall(".//{http://www.w3.org/2005/Atom}entry"):
-            title = entry.find("{http://www.w3.org/2005/Atom}title")
-            link_element = entry.find("{http://www.w3.org/2005/Atom}link[@rel='alternate']")
-            summary = entry.find("{http://www.w3.org/2005/Atom}summary")
-            link = link_element.attrib.get("href") if link_element is not None else "Kein Link verfügbar"
-            if summary is not None and title is not None:
-                summaries.append(f"Titel: {title.text.strip()}\nLink: {link}\nZusammenfassung: {summary.text.strip()}")
-        return summaries if summaries else ["Keine relevanten Studien gefunden."]
-    except Exception as e:
-        return [f"Fehler beim Abrufen der Studie: {str(e)}"]
-
-# Chatbot-Logik mit arXiv-Integration
 def respond(
     message,
     history: list[tuple[str, str]],
     system_message,
-    sort_by,
-    sort_order,
-    max_results,
-    query
+    max_tokens,
+    temperature,
+    top_p,
 ):
-    # Query generieren und Studien abrufen
-    study_summaries = fetch_arxiv_summary(query, sort_by, sort_order, max_results)
-    study_info = "\n".join(study_summaries)
+    messages = [{"role": "system", "content": system_message}]
 
-    # Nachrichten vorbereiten
-    messages = [{"role": "system", "content": f"{system_message} You are a highly capable assistant specializing in parsing and summarizing study abstracts. Your task is to analyze the provided study data, extract relevant information, and offer concise summaries. Always include the study's title and a direct link, ensuring clarity and accessibility.\n"}]
     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": f"{message}\nUse this Kontext:\n{study_info}"})
+    messages.append({"role": "user", "content": message})
 
-    # Antwort vom Modell generieren
     response = ""
+
     for message in client.chat_completion(
         messages,
-        stream=True
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
     ):
         token = message.choices[0].delta.content
+
         response += token
         yield response
 
-# Gradio-Interface mit zusätzlichen Eingaben
 
-with gr.Blocks() as demo:
-    gr.Markdown("""Helloooooo
-                This chatbot uses AI to answer your questions and retrieve relevant studies from the arXiv database.
-Enter your specific query in the field below, and the bot will provide you with studies including the title, link, and summary.
-    """)
-    
-  
-    chat_interface = gr.ChatInterface(
-        additional_inputs=[
-            gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-            gr.Dropdown(label="Sortby", choices=["relevance", "lastUpdatedDate", "submittedDate"], value="relevance"),
-            gr.Dropdown(label="Sort", choices=["ascending", "descending"], value="descending"),
-            gr.Slider(label="MaxEntries", minimum=1, maximum=50, value=20, step=1),
-            gr.Textbox(value="", label="Query", placeholder="Enter your specific search term.")
+"""
+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()
+    demo.launch()