Update app.py

app.py

@@ -1,64 +1,42 @@
 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)",
-        ),
-    ],
+from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
+
+# 1. Choose a bilingual or multilingual QA model
+MODEL_NAME = "mrm8488/xlm-roberta-large-finetuned-squadv2"
+
+# 2. Load model + tokenizer
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForQuestionAnswering.from_pretrained(MODEL_NAME)
+
+# 3. Initialize QA pipeline
+qa_pipeline = pipeline("question-answering", model=model, tokenizer=tokenizer)
+
+# 4. Load or define custom knowledge base
+with open("knowledge.txt", "r", encoding="utf-8") as f:
+    knowledge_text = f.read()
+
+# 5. Define function to answer questions
+def answer_question(question):
+    if not question.strip():
+        return "Please ask a valid question."
+    try:
+        result = qa_pipeline(question=question, context=knowledge_text)
+        return result["answer"]
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+# 6. Build Gradio interface
+iface = gr.Interface(
+    fn=answer_question,
+    inputs=gr.Textbox(lines=2, placeholder="Enter your question here..."),
+    outputs="text",
+    title="Budtender LLM (Bilingual QA)",
+    description=(
+        "A bilingual Q&A model trained on Spanish and English data. "
+        "Ask your cannabis-related questions here!"
+    )
 )
 
-
+# 7. Launch app
 if __name__ == "__main__":
-    demo.launch()
+    iface.launch()