File size: 4,071 Bytes
7fbc363 a50b0b8 7fbc363 d8b6e07 47d9c0b 7fbc363 000e3c2 9f679b8 000e3c2 7fbc363 000e3c2 f3cb278 a9df1a3 000e3c2 7fbc363 000e3c2 7fbc363 8f8811d 8c6917a 5bd0ed8 000e3c2 8f8811d f3cb278 5bd0ed8 |
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 |
import gradio as gr
import os
from langchain.chains import RetrievalQA
from langchain.llms import OpenAI
from langchain.document_loaders import PyPDFLoader
from langchain.document_loaders import DirectoryLoader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import Chroma
from gpt_index import SimpleDirectoryReader, GPTListIndex, GPTSimpleVectorIndex, LLMPredictor, PromptHelper, ServiceContext
#from langchain import OpenAI
#import gradio as gr
import sys
# Set the path of your new directory
dir_path = "./docs"
os.environ["OPENAI_API_KEY"]
# Create the directory using the os module
os.makedirs(dir_path, exist_ok=True)
def construct_index(directory_path):
max_input_size = 4096
num_outputs = 512
max_chunk_overlap = 20
chunk_size_limit = 600
prompt_helper = PromptHelper(max_input_size, num_outputs, max_chunk_overlap, chunk_size_limit=chunk_size_limit)
#llm_predictor = LLMPredictor(llm=OpenAI(temperature=0.4, model_name="text-davinci-003", max_tokens=num_outputs))
llm_predictor = LLMPredictor(llm=OpenAI(temperature=0, model_name="gpt-3.5-turbo", max_tokens=num_outputs))
service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor, prompt_helper=prompt_helper)
documents = SimpleDirectoryReader(directory_path).load_data()
index = GPTSimpleVectorIndex.from_documents(documents, service_context=service_context) #, llm_predictor=llm_predictor, prompt_helper=prompt_helper)
index.save_to_disk('index.json')
return index
def chatbot(input_text):
index = GPTSimpleVectorIndex.load_from_disk('index.json')
response = index.query(input_text, response_mode="compact")
return response.response
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)
loader = DirectoryLoader(dir_path, glob="**/*.pdf") #, loader_cls=PDFLoader)
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"]]
#index = construct_index("docs")
index = construct_index(dir_path)
# Describe principles
# rephrase the questions example
# Examples
# examples_questions = gr.Examples(["What is Sofidy to Tikehau?", "What is TSO2 ?"])
# 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(fn=chatbot,
# inputs=[openai_key, prompt, chain_type, k], outputs=[output_text, output_docs],
# title="TikehauGPT Question Answering with PDF File and OpenAI",
# description="Tikehau URDs.").launch(debug = True)
gr.Interface(fn=chatbot,
inputs= prompt, outputs="text",
title="TKO GPT for URDs - experimental",
description="Tikehau URDs.").launch(debug = True)
|