Spaces:
Runtime error
Runtime error
File size: 3,203 Bytes
85a8047 |
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 |
import streamlit as st
import os
from langchain_nvidia_ai_endpoints import NVIDIAEmbeddings, ChatNVIDIA
from langchain_community.document_loaders import WebBaseLoader
from langchain.embeddings import OllamaEmbeddings
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain.chains import create_retrieval_chain
from langchain_community.vectorstores import FAISS
from langchain_community.document_loaders import PyPDFDirectoryLoader
import time
import requests
import os
from dotenv import load_dotenv
load_dotenv()
## load the Groq API key
os.environ['NVIDIA_API_KEY'] = os.environ.get('api_key')
def vector_embedding():
if "vectors" not in st.session_state:
st.session_state.embeddings = NVIDIAEmbeddings()
st.session_state.loader = PyPDFDirectoryLoader("./documents") # Data Ingestion
st.session_state.docs = st.session_state.loader.load() # Document Loading
st.session_state.text_splitter = RecursiveCharacterTextSplitter(chunk_size=700, chunk_overlap=50) # Chunk Creation
st.session_state.final_documents = st.session_state.text_splitter.split_documents(st.session_state.docs) # Splitting
print("hEllo")
st.session_state.vectors = FAISS.from_documents(st.session_state.final_documents, st.session_state.embeddings) # Vector OpenAI embeddings
st.title("Ayurvedic Chatbot using Nvidia NIM")
llm = ChatNVIDIA(model="meta/llama3-70b-instruct")
prompt = ChatPromptTemplate.from_template(
"""
Answer the questions based on the provided context only.
Please provide the most accurate response based on the question.
Give a detailed answer for the question.
<context>
{context}
<context>
Questions:{input}
"""
)
prompt1 = st.text_input("Enter Your Question From related to Ayurvedic Herbs?")
if st.button("Documents Embedding"):
vector_embedding()
st.write("Vector Store DB Is Ready")
if prompt1:
# Ensure vectors are initialized before proceeding
if "vectors" not in st.session_state:
st.warning("Please embed the documents first by clicking the 'Documents Embedding' button.")
else:
document_chain = create_stuff_documents_chain(llm, prompt)
retriever = st.session_state.vectors.as_retriever()
retrieval_chain = create_retrieval_chain(retriever, document_chain)
start = time.process_time()
try:
response = retrieval_chain.invoke({'input': prompt1})
except requests.exceptions.SSLError as e:
st.error("SSL error occurred: {}".format(e))
response = None
if response:
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("--------------------------------")
|