Spaces:
Sleeping
Sleeping
File size: 4,815 Bytes
e71c4e6 e031d5d e71c4e6 8c14b99 298c7e7 0c47d68 e71c4e6 298c7e7 e71c4e6 8c14b99 e71c4e6 298c7e7 e71c4e6 298c7e7 e71c4e6 298c7e7 e71c4e6 298c7e7 e71c4e6 203ad1c e71c4e6 298c7e7 e71c4e6 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 |
import os
from threading import Lock
from typing import Any, Dict, Optional, Tuple
import gradio as gr
from langchain.chains import ConversationalRetrievalChain
from langchain.chat_models import ChatOpenAI
from langchain.memory import ConversationBufferMemory
from langchain.prompts.chat import (ChatPromptTemplate,
HumanMessagePromptTemplate,
SystemMessagePromptTemplate)
from src.core.chunking import chunk_file
from src.core.embedding import embed_files
from src.core.parsing import read_file
VECTOR_STORE = "faiss"
MODEL = "openai"
EMBEDDING = "openai"
MODEL = "gpt-3.5-turbo-16k"
K = 5
USE_VERBOSE = True
API_KEY = os.environ["OPENAI_API_KEY"]
system_template = """
You are a helpful assistant responding to inqueries about the content of the book Freakonomics, by Steven D. Levitt and Stephen J. Dubner. The context below contains excerpts from the book. You must only use the information in the context below to formulate your responses. If there is not enough information in the context to formulate a response, you must respond with
"I'm sorry, but I can't find the answer to your question in, the book Freakonomics."
Here is the context:
{context}
{chat_history}
"""
# Create the chat prompt templates
messages = [
SystemMessagePromptTemplate.from_template(system_template),
HumanMessagePromptTemplate.from_template("{question}")
]
qa_prompt = ChatPromptTemplate.from_messages(messages)
class AnswerConversationBufferMemory(ConversationBufferMemory):
def save_context(self, inputs: Dict[str, Any], outputs: Dict[str, str]) -> None:
return super(AnswerConversationBufferMemory, self).save_context(inputs,{'response': outputs['answer']})
def getretriever():
with open("./resources/Freakonomics.pdf", 'rb') as uploaded_file:
try:
file = read_file(uploaded_file)
except Exception as e:
print(e)
chunked_file = chunk_file(file, chunk_size=512, chunk_overlap=0)
folder_index = embed_files(
files=[chunked_file],
embedding=EMBEDDING,
vector_store=VECTOR_STORE,
openai_api_key=API_KEY,
)
return folder_index.index.as_retriever(verbose=True, search_type="similarity", search_kwargs={"k": K})
retriever = getretriever()
def getanswer(chain, question, history):
if hasattr(chain, "value"):
chain = chain.value
if hasattr(history, "value"):
history = history.value
if hasattr(question, "value"):
question = question.value
history = history or []
lock = Lock()
lock.acquire()
try:
output = chain({"question": question})
output = output["answer"]
history.append((question, output))
except Exception as e:
raise e
finally:
lock.release()
return history, history, gr.update(value="")
def load_chain(inputs = None):
llm = ChatOpenAI(
openai_api_key=API_KEY,
model_name=MODEL,
verbose=True)
chain = ConversationalRetrievalChain.from_llm(
llm,
retriever=retriever,
return_source_documents=USE_VERBOSE,
memory=AnswerConversationBufferMemory(memory_key="chat_history", return_messages=True),
verbose=USE_VERBOSE,
combine_docs_chain_kwargs={"prompt": qa_prompt})
chain.rephrase_question = False
return chain
with gr.Blocks() as block:
with gr.Row():
with gr.Column(scale=0.75):
with gr.Row():
gr.Markdown("<h1>Freakonomics</h1>")
with gr.Row():
gr.Markdown("by Steven D. Levitt and Stephen J. Dubner")
chatbot = gr.Chatbot(elem_id="chatbot").style(height=600)
with gr.Row():
message = gr.Textbox(
label="",
placeholder="Freakonomics",
lines=1,
)
with gr.Row():
submit = gr.Button(value="Send", variant="primary", scale=1)
state = gr.State()
chain_state = gr.State(load_chain)
submit.click(getanswer, inputs=[chain_state, message, state], outputs=[chatbot, state, message])
message.submit(getanswer, inputs=[chain_state, message, state], outputs=[chatbot, state, message])
with gr.Column(scale=0.25):
with gr.Row():
gr.Markdown("<h1><center>Suggestions</center></h1>")
ex1 = gr.Button(value="How does the book challenge conventional wisdom?", variant="primary")
ex1.click(getanswer, inputs=[chain_state, ex1, state], outputs=[chatbot, state, message])
ex2 = gr.Button(value="What are some of the surprising and counterintuitive examples from the book?", variant="primary")
ex2.click(getanswer, inputs=[chain_state, ex2, state], outputs=[chatbot, state, message])
ex3 = gr.Button(value="How does the book explore the role of incentives?", variant="primary")
ex3.click(getanswer, inputs=[chain_state, ex3, state], outputs=[chatbot, state, message])
block.launch(debug=True) |