Spaces:
Runtime error
Runtime error
File size: 2,237 Bytes
203e2cd 4771719 203e2cd |
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 |
import gradio as gr
import os
from langchain.chains import RetrievalQA
from langchain.llms import OpenAI
from langchain.document_loaders import PyPDFLoader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import Chroma
def qa_system(pdf_file, openai_key, prompt, chain_type, k):
os.environ["OPENAI_API_KEY"] = openai_key
# load document
loader = PyPDFLoader(pdf_file.name)
documents = loader.load()
# split the documents into chunks
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
texts = text_splitter.split_documents(documents)
# select which embeddings we want to use
embeddings = OpenAIEmbeddings()
# create the vectorestore to use as the index
db = Chroma.from_documents(texts, embeddings)
# expose this index in a retriever interface
retriever = db.as_retriever(search_type="similarity", search_kwargs={"k": k})
# create a chain to answer questions
qa = RetrievalQA.from_chain_type(
llm=OpenAI(), chain_type=chain_type, retriever=retriever, return_source_documents=True)
# get the result
result = qa({"query": prompt})
return result['result'], [doc.page_content for doc in result["source_documents"]]
# define the Gradio interface
input_file = gr.inputs.File(label="PDF File")
openai_key = gr.inputs.Textbox(label="OpenAI API Key", type="password")
prompt = gr.inputs.Textbox(label="Question Prompt")
chain_type = gr.inputs.Radio(['stuff', 'map_reduce', "refine", "map_rerank"], label="Chain Type")
k = gr.inputs.Slider(minimum=1, maximum=5, default=1, label="Number of Relevant Chunks")
output_text = gr.outputs.Textbox(label="Answer")
output_docs = gr.outputs.Textbox(label="Relevant Source Text")
gr.Interface(qa_system, inputs=[input_file, openai_key, prompt, chain_type, k], outputs=[output_text, output_docs],
title="Question Answering with PDF File and OpenAI",
description="Upload a PDF file, enter your OpenAI API key, type a question prompt, select a chain type, and choose the number of relevant chunks to use for the answer.").launch(debug = True)
|