Upload 6 files

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+us_census/acsbr-016.pdf filter=lfs diff=lfs merge=lfs -text
+us_census/acsbr-017.pdf filter=lfs diff=lfs merge=lfs -text

app1.py

@@ -0,0 +1,76 @@
+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
+
+from dotenv import load_dotenv
+load_dotenv()
+
+## load the Groq API key
+os.environ['NVIDIA_API_KEY']=os.getenv("NVIDIA_API_KEY")
+
+def vector_embedding():
+
+    if "vectors" not in st.session_state:
+
+        st.session_state.embeddings=NVIDIAEmbeddings()
+        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=700,chunk_overlap=50) ## Chunk Creation
+        st.session_state.final_documents=st.session_state.text_splitter.split_documents(st.session_state.docs[:30]) #splitting
+        print("hEllo")
+        st.session_state.vectors=FAISS.from_documents(st.session_state.final_documents,st.session_state.embeddings) #vector OpenAI embeddings
+
+
+st.title("Nvidia NIM Demo")
+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
+<context>
+{context}
+<context>
+Questions:{input}
+
+"""
+)
+
+
+prompt1=st.text_input("Enter Your Question From Doduments")
+
+
+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 +1,8 @@
+openai
+langchain_nvidia_ai_endpoints
+langchain_community
+faiss-cpu
+python-dotenv
+streamlit
+pypdf
+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

us_census/acsbr-016.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efdd4140ab4bfd3801771525f4c784dedeaec7c4f83aaa382517aae37ea05eed
+size 2286774

us_census/acsbr-017.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cacfe8c64d32bf3a5a7729a271cbf7a526c3bea798c866e075af033f50d5d81
+size 1389492