Upload 2 files

app.py

@@ -0,0 +1,71 @@
+import streamlit as st
+import os
+from langchain_groq import ChatGroq
+from langchain_openai import OpenAIEmbeddings
+from langchain_community.embeddings import HuggingFaceBgeEmbeddings
+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 GROQ API KEY 
+groq_api_key=os.getenv('GROQ_API_KEY')
+
+st.title("Chatgroq With Llama3 Demo")
+
+llm=ChatGroq(groq_api_key=groq_api_key,
+             model_name="Llama3-8b-8192")
+
+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=HuggingFaceBgeEmbeddings(model_name="BAAI/bge-small-en-v1.5",
+                                                            model_kwargs={'device':'cpu'},
+                                                            encode_kwargs={'normalize_embeddings':True})
+        st.session_state.loader=PyPDFDirectoryLoader("./us_census") ## 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
+
+
+prompt1=st.text_input("Enter Your Question From Documents")
+
+
+if st.button("Documents Embedding"):
+    vector_embedding()
+    st.write("Vector Store DB Is Ready")
+
+
+import time
+if prompt1:
+    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()
+    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("--------------------------------")

requirements.txt

@@ -0,0 +1,24 @@
+langchain_openai 
+langchain_core
+python-dotenv
+streamlit
+langchain_community
+langserve
+fastapi
+uvicorn
+sse_starlette
+bs4
+pypdf
+chromadb
+faiss-cpu
+groq
+cassio
+beautifulsoup4
+langchain-groq
+wikipedia
+arxiv
+langchainhub
+sentence_transformers
+PyPDF2
+langchain-objectbox
+langchain