Update app.py

app.py

@@ -1,56 +1,52 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-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
+# 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,
+)
 
-"""
-https://docs.llamaindex.ai/en/stable/examples/customization/llms/SimpleIndexDemo-Huggingface_stablelm/
-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)",
-        ),
-    ],
+#system_sr = "Zoveš se U-Chat AI asistent i pomažeš korisniku usluga kompanije United Group. Korisnik postavlja pitanje ili problem, upareno sa dodatnima saznanjima. Na osnovu toga napiši korisniku kratak i ljubazan odgovor koji kompletira njegov zahtev ili mu daje odgovor na pitanje. "
+# " Ako ne znaš odgovor, reci da ne znaš, ne izmišljaj ga."
+#system_sr += "Usluge kompanije United Group uključuju i kablovsku mrežu za digitalnu televiziju, pristup internetu, uređaj EON SMART BOX za TV sadržaj, kao i fiksnu telefoniju."
+
+system_propmpt = "You are a friendly Chatbot."
+
+# "facebook/blenderbot-400M-distill",  facebook/blenderbot-400M-distill , BAAI/bge-small-en-v1.5
+Settings.llm = HuggingFaceLLM(model_name="stabilityai/stablelm-zephyr-3b",
+                              device_map="auto",
+                              system_prompt = system_propmpt,
+                              context_window=4096,
+                              max_new_tokens=256,
+#                              stopping_ids=[50278, 50279, 50277, 1, 0],
+                              generate_kwargs={"temperature": 0.5, "do_sample": False},
+#                              tokenizer_kwargs={"max_length": 4096},
+                              tokenizer_name="stabilityai/stablelm-zephyr-3b", 
+                             )
+
+Settings.embed_model = HuggingFaceEmbedding(model_name="sentence-transformers/all-MiniLM-L6-v2")
+documents = [Document(text="Indian parliament elections happened in April-May 2024. BJP Party won."),
+             Document(text="Indian parliament elections happened in April-May 2021. XYZ Party won."),
+             Document(text="Indian parliament elections happened in 2020. ABC Party won."),
+            ]
+index = VectorStoreIndex.from_documents(
+    documents,
 )
+
+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()