Spaces:
Sleeping
Sleeping
import streamlit as st | |
import os | |
from langchain_groq import ChatGroq | |
from langchain_openai import OpenAIEmbeddings | |
from langchain.text_splitter import RecursiveCharacterTextSplitter | |
from langchain.chains.combine_documents import create_stuff_documents_chain | |
from langchain_core.prompts import ChatPromptTemplate | |
from langchain.chains import create_retrieval_chain | |
from langchain_community.vectorstores import FAISS | |
from langchain_community.document_loaders import PyPDFDirectoryLoader | |
from dotenv import load_dotenv | |
load_dotenv() | |
## load the GroqAPI Key | |
os.environ['OPENAI_API_KEY']=os.getenv("OPENAI_API_KEY") | |
groq_api_key = os.getenv('GROQ_API_KEY') | |
st.title("ChatBot Demo for Error Codes") | |
llm=ChatGroq(groq_api_key=groq_api_key, | |
model="Llama3-8b-8192") | |
prompt = ChatPromptTemplate.from_template( | |
""" | |
Answer the question based on the provided context only. | |
Please provide the most accurate response based on the question. | |
<context> | |
{context} | |
<context> | |
Question: {input} | |
""" | |
) | |
def vector_embedding(): | |
if "vectors" not in st.session_state: | |
st.session_state.embeddings = OpenAIEmbeddings() | |
st.session_state.loader = PyPDFDirectoryLoader("./data") | |
st.session_state.docs = st.session_state.loader.load() | |
st.session_state.text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200) | |
st.session_state.final_documents = st.session_state.text_splitter.split_documents(st.session_state.docs[:20]) | |
st.session_state.vectors = FAISS.from_documents(st.session_state.final_documents, st.session_state.embeddings ) | |
prompt1=st.text_input("Enter your question from Documents") | |
if st.button("Documents Embedding"): | |
vector_embedding() | |
st.write("VectorStore DB is ready") | |
import time | |
if prompt1: | |
start = time.process_time() | |
document_chain = create_stuff_documents_chain(llm, prompt) | |
retriever = st.session_state.vectors.as_retriever() | |
retrieval_chain = create_retrieval_chain(retriever, document_chain) | |
response = retrieval_chain.invoke({'input': prompt1}) | |
print("Response time : ", time.process_time() - start) | |
st.write(response['answer']) | |
# With a Streamlit expander | |
with st.expander("Document Similarity Search"): | |
# Find the relevant chunks | |
for i, doc in enumerate(response["context"]): | |
st.write(doc.page_content) | |
st.write("------------------------------------") | |