Update app.py

app.py

@@ -1,8 +1,7 @@
 import os
 from collections.abc import Iterator
 from threading import Thread
-import networkx as nx
-import matplotlib.pyplot as plt
+
 import gradio as gr
 import spaces
 import torch
@@ -28,29 +27,8 @@ model = AutoModelForCausalLM.from_pretrained(
 model.config.sliding_window = 4096
 model.eval()
 
-def generate_knowledge_graph():
-    # Create a simple knowledge graph
-    G = nx.Graph()
-    G.add_node("AI", title="Artificial Intelligence")
-    G.add_node("ML", title="Machine Learning")
-    G.add_node("DL", title="Deep Learning")
-    G.add_edge("AI", "ML")
-    G.add_edge("ML", "DL")
-
-    # Draw the graph using matplotlib
-    plt.figure(figsize=(8, 6))
-    pos = nx.spring_layout(G)
-    nx.draw(G, pos, with_labels=True, node_size=3000, node_color="lightblue", font_size=10, font_weight="bold")
-    plt.title("Knowledge Graph")
-
-    # Save the graph as a PDF
-    pdf_path = "knowledge_graph.pdf"
-    plt.savefig(pdf_path, format="pdf")
-    plt.close()
-
-    return pdf_path
 
-@spaces.GPU(duration=120)
+@spaces.GPU()
 def generate(
     message: str,
     chat_history: list[dict],
@@ -63,17 +41,15 @@ def generate(
     conversation = chat_history.copy()
     conversation.append({"role": "user", "content": message})
 
-    # Tokenize the input
     input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt=True, return_tensors="pt")
     if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
         input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
         gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
     input_ids = input_ids.to(model.device)
 
-    # Set up the streamer
     streamer = TextIteratorStreamer(tokenizer, timeout=20.0, skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
-        input_ids=input_ids,
+        {"input_ids": input_ids},
         streamer=streamer,
         max_new_tokens=max_new_tokens,
         do_sample=True,
@@ -83,22 +59,14 @@ def generate(
         num_beams=1,
         repetition_penalty=repetition_penalty,
     )
-
-    # Start the generation in a separate thread
     t = Thread(target=model.generate, kwargs=generate_kwargs)
     t.start()
 
-    # Stream the output
     outputs = []
     for text in streamer:
         outputs.append(text)
         yield "".join(outputs)
 
-    # Ensure the thread is joined after completion
-    t.join()
-
-# Generate the knowledge graph PDF file
-pdf_path = generate_knowledge_graph()
 
 demo = gr.ChatInterface(
     fn=generate,
@@ -138,15 +106,13 @@ demo = gr.ChatInterface(
             step=0.05,
             value=1.2,
         ),
-        gr.File(label="Download Knowledge Graph (PDF)", value=pdf_path, visible=True),
     ],
     stop_btn=None,
     examples=[
         ["Write a Python function to reverses a string if it's length is a multiple of 4. def reverse_string(str1): if len(str1) % 4 == 0: return ''.join(reversed(str1)) return str1 print(reverse_string('abcd')) print(reverse_string('python')) "],
         ["Rectangle $ABCD$ is the base of pyramid $PABCD$. If $AB = 10$, $BC = 5$, $\overline{PA}\perp \text{plane } ABCD$, and $PA = 8$, then what is the volume of $PABCD$?"],
         ["Difference between List comprehension and Lambda in Python lst  =  [x ** 2  for x in range (1, 11)   if  x % 2 == 1] print(lst)"],
-        ["How many hours does it take a man to eat a Helicopter?"],
-        ["Write a 100-word article on 'Benefits of Open-Source in AI research'"],
+        ["How Many R's in the Word 'STRAWBERRY' ?"],
     ],
     cache_examples=False,
     type="messages",
@@ -155,5 +121,6 @@ demo = gr.ChatInterface(
     fill_height=True,
 )
 
+
 if __name__ == "__main__":
-    demo.queue(max_size=20).launch(share=True)  # Set share=True for a public link
+    demo.queue(max_size=20).launch()