Spaces:
Running
Running
File size: 2,590 Bytes
82a1a91 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 |
import gradio as gr
# 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,
)
#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()
|