Update app.py

app.py

@@ -1,70 +1,40 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    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,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = 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
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    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)",
-        ),
-    ],
+import faiss
+import pickle
+import numpy as np
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
+
+# ---- Load FAISS index and metadata ----
+index = faiss.read_index("faiss_index/index.faiss")
+with open("faiss_index/metadata.pkl", "rb") as f:
+    passages = pickle.load(f)
+
+# ---- Load FLAN-T5 model ----
+model_name = "google/flan-t5-large"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+
+# Optionally use HF pipeline for simplicity
+generator = pipeline("text2text-generation", model=model, tokenizer=tokenizer)
+
+def get_relevant_chunks(query, k=3):
+    # In practice you’d embed the query; here we mock similarity search
+    # For demo, return first few passages
+    _, I = index.search(np.random.random((1, index.d)), k)  # replace with real embedding lookup
+    return " ".join([passages[i] for i in I[0]])
+
+def rag_answer(query):
+    context = get_relevant_chunks(query)
+    prompt = f"Question: {query}\nContext: {context}\nAnswer:"
+    result = generator(prompt, max_new_tokens=150, do_sample=False)
+    return result[0]['generated_text']
+
+iface = gr.Interface(
+    fn=rag_answer,
+    inputs=gr.Textbox(label="Ask about Śrīla Prabhupāda"),
+    outputs=gr.Textbox(label="Answer"),
+    title="Śrīla Prabhupāda RAG Assistant",
+    description="Retrieval-Augmented Generation model using FLAN-T5-Large to answer spiritual and biographical questions."
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
-if __name__ == "__main__":
-    demo.launch()
+iface.launch()