Spaces:
Runtime error
Runtime error
File size: 2,900 Bytes
e5b5f0b |
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 |
import os
import pathlib
import re
import streamlit as st
from streamlit_chat import message
from langchain.docstore.document import Document
from langchain.document_loaders import TextLoader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import FAISS
st.set_page_config(
page_title="LLM Chatbot"
)
st.header(" LLM Chatbot on Custom data")
st.sidebar.header("Instructions")
st.sidebar.info(
'''This is a web application that allows you to interact with
your custom data
'''
)
st.sidebar.info('''Enter a query in the text box and press enter
to receive a response''')
st.sidebar.info('''
This project works perfectly even on your own data
''')
os.environ["OPENAI_API_KEY"] = "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"
from langchain.prompts.chat import (
ChatPromptTemplate,
SystemMessagePromptTemplate,
HumanMessagePromptTemplate,
)
from langchain.chat_models import ChatOpenAI
from langchain.chains import RetrievalQAWithSourcesChain
# Initialize Streamlit
st.title("Stanlito AI Chatbot")
# Set the data store directory
DATA_STORE_DIR = "data_store"
# Upload the files `$DATA_STORE_DIR/index.faiss` and `$DATA_STORE_DIR/index.pkl` to local
if os.path.exists(DATA_STORE_DIR):
vector_store = FAISS.load_local(
DATA_STORE_DIR,
OpenAIEmbeddings()
)
else:
st.write(f"Missing files. Upload index.faiss and index.pkl files to {DATA_STORE_DIR} directory first")
# Define system template
system_template = """Use the following pieces of context to answer the user's question.
Take note of the sources and include them in the answer in the format: "SOURCES: source1", use "SOURCES" in capital letters regardless of the number of sources.
If you don't know the answer, just say "I don't know", don't try to make up an answer.
----------------
{summaries}"""
# Create the prompt
messages = [
SystemMessagePromptTemplate.from_template(system_template),
HumanMessagePromptTemplate.from_template("{question}")
]
prompt = ChatPromptTemplate.from_messages(messages)
# Load the language model
llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0,
max_tokens=256) # Modify model_name if you have access to GPT-4
# Create the chain
chain_type_kwargs = {"prompt": prompt}
chain = RetrievalQAWithSourcesChain.from_chain_type(
llm=llm,
chain_type="stuff",
retriever=vector_store.as_retriever(),
return_source_documents=True,
chain_type_kwargs=chain_type_kwargs
)
# Define function to print the result
def print_result(result):
output_text = f"""### Question:
{query}
Answer:
{result['answer']}
"""
st.markdown(output_text)
# Get user input
query = st.text_input("Ask a question")
# Process user input
if query:
result = chain(query)
print_result(result)
|