Upload 2 files

.gitattributes

@@ -33,3 +33,4 @@ 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.pdf filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,57 @@
+import streamlit as st
+import os
+from langchain_groq import ChatGroq
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain_community.embeddings.yandex import YandexGPTEmbeddings
+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.vectorstores import FAISS
+from langchain_community.document_loaders import PyPDFLoader
+
+from dotenv import load_dotenv
+load_dotenv()
+
+#Load groq API Keys.
+groq_api_key = os.getenv("groq_api_key")
+
+st.title("ChatGroq with LLAMA3 Demo :sparkles:")
+
+llm = ChatGroq(groq_api_key=groq_api_key ,model_name = "llama3-8b-8192")
+
+prompt = ChatPromptTemplate.from_template(
+"""
+Answer the questions based on provided context only.
+Please provide Accurate response based on question and explain it widely.
+<context>
+{context}
+<context>
+Question : {input}
+"""
+)
+
+
+def vector_embeddings():
+    if "vectors" not in st.session_state:
+        st.session_state.embeddings = HuggingFaceEmbeddings()
+        st.session_state.loader = PyPDFLoader("us_census.pdf") # Data Injection
+        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]) # Document splitting
+        st.session_state.vectors = FAISS.from_documents(st.session_state.final_documents,st.session_state.embeddings) # vector Huggingface Embedding
+
+prompt1 = st.text_input("Enter the Question from your Mind : ")
+
+
+if st.button("Document Embeddings"):
+    vector_embeddings()
+    st.write("Vector store DB is Ready.")
+
+if prompt1:
+    document_chain = create_stuff_documents_chain(llm,prompt)
+    retriver = st.session_state.vectors.as_retriever()
+    retrival_chain = create_retrieval_chain(retriver,document_chain)
+
+    response = retrival_chain.invoke({'input':prompt1})
+    st.write(response['answer'])

us_census.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e4343c41dc08f071d5b92522b8bb49a588a1d943886e8f1b6b0da151d0884d9
+size 1154739