Update

app.py

@@ -1,46 +1,44 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
 import os
 from dotenv import load_dotenv
 
 load_dotenv()
 
-client = InferenceClient(
-    model="VentureCircle/LaunchPad",
-    token=os.getenv("huggingface_token")
+# Load model from Hugging Face Hub
+model_id = "VentureCircle/LaunchPad"
+token = os.getenv("huggingface_token")
+
+generator = pipeline(
+    "text-generation",
+    model=model_id,
+    tokenizer=model_id,
+    token=token
 )
 
-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,
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    # Combine chat history and message into a single prompt
+    chat_prompt = system_message + "\n\n"
+    for user, assistant in history:
+        if user:
+            chat_prompt += f"User: {user}\n"
+        if assistant:
+            chat_prompt += f"LaunchPad: {assistant}\n"
+    chat_prompt += f"User: {message}\nLaunchPad:"
+
+    output = generator(
+        chat_prompt,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-        response += token
-        yield response
+        do_sample=True
+    )
+
+    # Extract response only (after "LaunchPad:")
+    response_text = output[0]["generated_text"].split("LaunchPad:")[-1].strip()
+    return response_text
 
+# System message configuration
 system_message = gr.State(
     "I am Bilguun, a third year software engineering student at McGill University and the founder of VentureCircle. "
     "VentureCircle is based in Montreal. "
@@ -49,6 +47,7 @@ system_message = gr.State(
     "LaunchPad is a friendly AI assistant designed to provide useful and supportive guidance for starting and growing a startup."
 )
 
+# Gradio interface
 demo = gr.ChatInterface(
     fn=respond,
     additional_inputs=[