Update app.py

app.py

@@ -1,62 +1,35 @@
 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 pipeline
+from transformers.utils import logging
+from llama_index.embeddings.huggingface import HuggingFaceEmbedding
+import torch
+from llama_index.core import VectorStoreIndex
+from llama_index.core import Document
+from llama_index.core import Settings
+from llama_index.llms.huggingface import (
+    HuggingFaceInferenceAPI,
+    HuggingFaceLLM,
+)
+Settings.llm = HuggingFaceLLM(model_name="facebook/blenderbot-400M-distill",
+                              device_map="cpu",
+                              context_window=128,
+                              tokenizer_name="facebook/blenderbot-400M-distill"
+                             )
+Settings.embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5")
+documents = [Document(text="Indian parliament elections happened in April-May 2024. BJP Party won.")]
+index = VectorStoreIndex.from_documents(
+    documents,
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+query_engine = index.as_query_engine()
+def rag(input_text, file):
+    return query_engine.query(
+        input_text
+    )
+
+iface = gr.Interface(fn=rag, inputs=[gr.Textbox(label="Question", lines=6), gr.File()], 
+                     outputs=[gr.Textbox(label="Result", lines=6)], 
+                     title="Answer my question",
+                     description= "CoolChatBot"
+                    )
+iface.launch()