Upload app.py

app.py

@@ -1,64 +1,88 @@
-import gradio as gr
-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()
+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")
+
+# Funktion, um die Eingabe zu bereinigen und einen prägnanten Query zu erstellen
+def generate_query(input_text):
+    stopwords = ["welche", "gibt", "es", "zum", "thema", "studien", "über", "zu", "dem"]
+    words = input_text.lower().split()
+    query = " ".join([word for word in words if word not in stopwords])
+    return query.strip()
+
+# 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"):
+            summary = entry.find("{http://www.w3.org/2005/Atom}summary")
+            if summary is not None:
+                summaries.append(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,
+    max_tokens,
+    temperature,
+    top_p,
+    sort_by,
+    sort_order,
+    max_results,
+):
+    # Query generieren und Studien abrufen
+    query = generate_query(message)
+    study_summaries = fetch_arxiv_summary(query, sort_by, sort_order, max_results)
+    study_info = "\n".join(study_summaries)
+
+    # Nachrichten vorbereiten
+    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": f"{message}\nStudien-Info:\n{study_info}"})
+
+    # Antwort vom Modell generieren
+    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
+
+# Gradio-Interface mit zusätzlichen Eingaben
+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)"),
+        gr.Dropdown(label="Sortieren nach", choices=["relevance", "lastUpdatedDate", "submittedDate"], value="relevance"),
+        gr.Dropdown(label="Sortierreihenfolge", choices=["ascending", "descending"], value="descending"),
+        gr.Slider(label="Maximale Ergebnisse", minimum=1, maximum=50, value=20, step=1),
+    ],
+)
+
+if __name__ == "__main__":
+    demo.launch()