File size: 3,265 Bytes
1f046cf ec17a93 1f046cf ec17a93 aa1c072 ec17a93 aa1c072 1f046cf ec17a93 1f046cf aa1c072 3a77dd9 1f046cf aa1c072 720c2e4 aa1c072 720c2e4 49910f5 720c2e4 |
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 |
import streamlit as st
import os
from langchain_groq import ChatGroq
from langchain.embeddings import HuggingFaceEmbeddings
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
import time
# Retrieve API keys from environment variables
huggingfacehub_api_token = os.getenv("HUGGINGFACEHUB_API_TOKEN")
groq_api_key = os.getenv("GROQ_API_KEY")
# Check if keys are retrieved correctly
if not huggingfacehub_api_token:
st.error("HUGGINGFACEHUB_API_TOKEN environment variable is not set")
st.stop()
if not groq_api_key:
st.error("GROQ_API_KEY environment variable is not set")
st.stop()
# Initialize ChatGroq LLM with error handling
try:
llm = ChatGroq(api_key=groq_api_key, model_name="Llama3-8b-8192")
except Exception as e:
st.error(f"Failed to initialize ChatGroq LLM: {e}")
st.stop()
st.title("DataScience Chatgroq With Llama3")
prompt = ChatPromptTemplate.from_template(
"""
Answer the questions based on the provided context only.
Please provide the most accurate response based on the question.
<context>
{context}
<context>
Questions: {input}
"""
)
def vector_embedding():
if "vectors" not in st.session_state:
st.session_state.embeddings = HuggingFaceEmbeddings()
st.session_state.loader = PyPDFDirectoryLoader("./Data_Science") # Data Ingestion
st.session_state.docs = st.session_state.loader.load() # Document Loading
st.session_state.text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200) # Chunk Creation
st.session_state.final_documents = st.session_state.text_splitter.split_documents(st.session_state.docs[:20]) # Splitting
st.session_state.vectors = FAISS.from_documents(st.session_state.final_documents, st.session_state.embeddings) # Vector HuggingFace embeddings
st.write("Vector Store DB Is Ready")
else:
st.write("Vectors already initialized.")
prompt1 = st.text_input("Enter Your Question From Documents")
if st.button("Documents Embedding"):
vector_embedding()
if prompt1:
if "vectors" not in st.session_state:
st.error("Vectors are not initialized. Please click 'Documents Embedding' first.")
else:
document_chain = create_stuff_documents_chain(llm, prompt)
retriever = st.session_state.vectors.as_retriever()
retrieval_chain = create_retrieval_chain(retriever, document_chain)
try:
start = time.process_time()
response = retrieval_chain.invoke({'input': prompt1})
st.write("Response time: ", time.process_time() - start)
st.write(response['answer'])
with st.expander("Document Similarity Search"):
for i, doc in enumerate(response["context"]):
st.write(doc.page_content)
st.write("--------------------------------")
except Exception as e:
st.error(f"Failed to retrieve the answer: {e}") |