Update app.py

app.py

@@ -1,64 +1,39 @@
 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 langchain.vectorstores import FAISS
+from langchain.embeddings import HuggingFaceEmbeddings
+from groq import Groq
+
+# Load FAISS index
+vector_store = FAISS.load_local("faiss_index", HuggingFaceEmbeddings())
+
+# Inisialisasi API Groq
+client = Groq(api_key="YOUR_GROQ_API_KEY")
+
+def retrieve_and_generate(query):
+    # Retrieve top 3 documents
+    docs = vector_store.similarity_search(query, k=3)
+    context = "\n\n".join([doc.page_content for doc in docs])
+
+    # Generate response with LLM
+    response = client.chat.completions.create(
+        model="mixtral-8x7b-32768",
+        messages=[
+            {"role": "system", "content": "Anda adalah asisten AI yang menjawab pertanyaan tentang RoboHome berdasarkan dokumen ini."},
+            {"role": "user", "content": f"{context}\n\nPertanyaan: {query}"}
+        ],
+        temperature=0.7,
+        max_tokens=200
+    )
+
+    return response.choices[0].message.content
+
+# UI dengan Gradio
+iface = gr.Interface(
+    fn=retrieve_and_generate,
+    inputs=gr.Textbox(label="Ajukan pertanyaan tentang RoboHome"),
+    outputs=gr.Textbox(label="Jawaban"),
+    title="RoboHome RAG Chatbot",
+    description="Chatbot ini menjawab pertanyaan berdasarkan dokumentasi RoboHome.",
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+iface.launch()