Spaces:
Sleeping
Sleeping
File size: 3,893 Bytes
b4e5268 8f64959 55a8b20 dd507bb 1282351 b4e5268 9774287 cff9147 cb5c2b5 cff9147 397c421 0a98570 37b2fc4 fe7c8df b956157 b4e5268 b956157 b4e5268 b956157 b4e5268 b48a9c3 ab55f29 |
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 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 |
import os
import torch
from transformers import (
AutoTokenizer,
AutoModelForCausalLM,
BitsAndBytesConfig,
pipeline
)
import streamlit as st
from langchain_community.vectorstores import FAISS
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.llms import HuggingFacePipeline
from transformers import BitsAndBytesConfig
from langchain.prompts import PromptTemplate
from langchain.schema.runnable import RunnablePassthrough
from langchain.chains import LLMChain
import transformers
import transformers
from transformers import pipeline
from datasets import load_dataset
import transformers
model_name='mistralai/Mistral-7B-Instruct-v0.1'
from huggingface_hub import login
login(token=st.secrets["HF_TOKEN"])
from ctransformers import AutoModelForCausalLM, AutoTokenizer
# model loading.
model = AutoModelForCausalLM.from_pretrained("TheBloke/Mistral-7B-Instruct-v0.1-GGUF",
model_file="mistral-7b-instruct-v0.1.Q5_K_M.gguf",
model_type="mistral",
max_new_tokens=1048,
temperature=0.00,
hf=True
)
#initializes a tokenizer for the specified LLM model.
tokenizer = AutoTokenizer.from_pretrained(model)
dataset= load_dataset("mery22/testub/test-1.pdf")
loader = PyPDFLoader(dataset)
data = loader.load()
text_splitter1 = CharacterTextSplitter(chunk_size=512, chunk_overlap=0,separator="\n\n")
texts = text_splitter1.split_documents(data)
db = FAISS.from_documents(texts,
HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L12-v2'))
# Connect query to FAISS index using a retriever
retriever = db.as_retriever(
search_type="mmr",
search_kwargs={'k': 1}
)
from langchain.llms import HuggingFacePipeline
from langchain.prompts import PromptTemplate
from langchain.embeddings.huggingface import HuggingFaceEmbeddings
text_generation_pipeline = transformers.pipeline(
model=model,
tokenizer=tokenizer,
task="text-generation",
temperature=0.02,
repetition_penalty=1.1,
return_full_text=True,
max_new_tokens=512,
)
prompt_template = """
### [INST]
Instruction: You are a Q&A assistant. Your goal is to answer questions as accurately as possible based on the instructions and context provided without using prior knowledge.You answer in FRENCH
Analyse carefully the context and provide a direct answer based on the context.
Answer in french only
{context}
Vous devez répondre aux questions en français.
### QUESTION:
{question}
[/INST]
Answer in french only
Vous devez répondre aux questions en français.
"""
mistral_llm = HuggingFacePipeline(pipeline=text_generation_pipeline)
# Create prompt from prompt template
prompt = PromptTemplate(
input_variables=["question"],
template=prompt_template,
)
# Create llm chain
llm_chain = LLMChain(llm=mistral_llm, prompt=prompt)
from langchain.chains import RetrievalQA
retriever.search_kwargs = {'k':1}
qa = RetrievalQA.from_chain_type(
llm=mistral_llm,
chain_type="stuff",
retriever=retriever,
chain_type_kwargs={"prompt": prompt},
)
import streamlit as st
# Streamlit interface
st.title("Chatbot Interface")
# Define function to handle user input and display chatbot response
def chatbot_response(user_input):
response = qa.get_answer(user_input)
return response
# Streamlit components
user_input = st.text_input("You:", "")
submit_button = st.button("Send")
# Handle user input
if submit_button:
if user_input.strip() != "":
bot_response = chatbot_response(user_input)
st.text_area("Bot:", value=bot_response, height=200)
else:
st.warning("Please enter a message.") |