Spaces:
Sleeping
Sleeping
File size: 2,384 Bytes
c7058bc 7372149 c7058bc 7372149 57c9d91 7372149 c7058bc 68de5df c7058bc 7372149 57c9d91 7372149 57c9d91 c7058bc 7372149 57c9d91 c7058bc |
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 |
import gradio as gr
import PyPDF2
#rom langchain.embeddings.openai import OpenAIEmbeddings
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores.faiss import FAISS
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain import HuggingFaceHub
from langchain.document_loaders import UnstructuredPDFLoader
from langchain.indexes import VectorstoreIndexCreator
from langchain import OpenAI, VectorDBQA
import os
openai_api_key = os.environ["OPENAI_API_KEY"]
def pdf_to_text(pdf_file, query):
# Open the PDF file in binary mode
with open(pdf_file.name, 'rb') as pdf_file:
# Create a PDF reader object
pdf_reader = PyPDF2.PdfReader(pdf_file)
# Create an empty string to store the text
text = ""
# Loop through each page of the PDF
for page_num in range(len(pdf_reader.pages)):
# Get the page object
page = pdf_reader.pages[page_num]
# Extract the texst from the page and add it to the text variable
text += page.extract_text()
#embedding step
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
texts = text_splitter.split_text(text)
embeddings = HuggingFaceEmbeddings()
#vector store
vectorstore = FAISS.from_texts(texts, embeddings)
llm = HuggingFaceHub(repo_id="google/flan-t5-xl", model_kwargs={"temperature":0, "max_length":512})
loaders = UnstructuredPDFLoader(pdf_file)
index = VectorstoreIndexCreator(
embedding=HuggingFaceEmbeddings(),
text_splitter=CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)).from_loaders(loaders)
#inference
qa = VectorDBQA.from_chain_type(llm=llm, chain_type="stuff", vectorstore=vectorstore)
from langchain.chains import RetrievalQA
chain = RetrievalQA.from_chain_type(llm=llm,
chain_type="stuff",
retriever=index.vectorstore.as_retriever(),
input_key="question")
return chain.run(query)
# Define the Gradio interface
pdf_input = gr.inputs.File(label="PDF File")
query_input = gr.inputs.Textbox(label="Query")
outputs = gr.outputs.Textbox(label="Chatbot Response")
interface = gr.Interface(fn=pdf_to_text, inputs=[pdf_input, query_input], outputs=outputs)
# Run the interface
interface.launch(debug = True) |