File size: 1,992 Bytes
47e3742 af75aba 47e3742 af75aba 47e3742 af75aba |
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 |
import streamlit as st
from langchain.llms import HuggingFaceHub
import os
from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS
from langchain.chat_models import ChatOpenAI
from langchain.chains.question_answering import load_qa_chain
st.set_page_config('preguntaDOC')
st.header("Pregunta a tu PDF")
OPENAI_API_KEY = st.text_input('OpenAI API Key', type='password')
pdf_obj = st.file_uploader("Carga tu documento", type="pdf", on_change=st.cache_resource.clear)
@st.cache_resource
def create_embeddings(pdf):
pdf_reader = PdfReader(pdf)
text = ""
for page in pdf_reader.pages:
text += page.extract_text()
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=800,
chunk_overlap=100,
length_function=len
)
chunks = text_splitter.split_text(text)
# embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2")
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/paraphrase-multilingual-mpnet-base-v2")
knowledge_base = FAISS.from_texts(chunks, embeddings)
return knowledge_base
if pdf_obj:
knowledge_base = create_embeddings(pdf_obj)
user_question = st.text_input("Haz una pregunta sobre tu PDF:")
if user_question:
os.environ["HUGGINGFACEHUB_API_TOKEN"] = ""
docs = knowledge_base.similarity_search(user_question, 3)
# llm = ChatOpenAI(model_name='gpt-3.5-turbo')
# llm = HuggingFaceHub(repo_id="lmsys/vicuna-7b-v1.1", model_kwargs={"temperature":0.5, "max_length":512})
llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512})
chain = load_qa_chain(llm, chain_type="stuff")
respuesta = chain.run(input_documents=docs, question=user_question)
st.write(respuesta) |