Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,74 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import os
+from langchain_groq import ChatGroq
+from langchain_openai import OpenAIEmbeddings
+from langchain_community.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.chains import create_retrieval_chain
+from langchain_community.vectorstores import FAISS
+from langchain_community.document_loaders import PyPDFDirectoryLoader
+from langchain_huggingface import HuggingFaceEmbeddings
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+import openai
+
+from dotenv import load_dotenv
+load_dotenv()
+## load the GROQ API Key
+# os.environ['OPENAI_API_KEY']=os.getenv("OPENAI_API_KEY")
+# os.environ['GROQ_API']=os.getenv("GROQ_API")
+
+groq_api_key="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"
+
+llm=ChatGroq(groq_api_key=groq_api_key,model_name="Llama3-8b-8192")
+
+prompt=ChatPromptTemplate.from_template(
+    """
+    You are Clara, the chatbot for Lakireddy Bali Reddy College of Engineering (LBRCE). Your role is to provide friendly, helpful, and clear responses to questions about the college. Always respond professionally, using phrases like "Currently, I understand," or "Based on recent information," to keep the interaction conversational.
+        Answer general queries concisely and clearly. Avoid technical terms and keep answers user-friendly. Include info on:
+        - Courses, faculty, facilities, and placements
+        - Admissions, eligibility, and campus life
+    <context>
+    {context}
+    <context>
+    Question:{input}
+
+    """
+
+)
+
+def create_vector_embedding():
+    if "vectors" not in st.session_state:
+        st.session_state.embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+        st.session_state.loader=PyPDFDirectoryLoader("data") ## Data Ingestion step
+        st.session_state.docs=st.session_state.loader.load() ## Document Loading
+        st.session_state.text_splitter=RecursiveCharacterTextSplitter(chunk_size=1000,chunk_overlap=200)
+        st.session_state.final_documents=st.session_state.text_splitter.split_documents(st.session_state.docs[:50])
+        st.session_state.vectors=FAISS.from_documents(st.session_state.final_documents,st.session_state.embeddings)
+st.title("RAG College Chat Bot")
+
+user_prompt=st.text_input("Enter your query regarding LBRCE")
+
+if st.button("Document Embedding"):
+    create_vector_embedding()
+    st.write("Vector Database is ready")
+
+import time
+
+if user_prompt:
+    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':user_prompt})
+    print(f"Response time :{time.process_time()-start}")
+
+    st.write(response['answer'])
+
+    ## With a streamlit expander
+    with st.expander("Document similarity Search"):
+        for i,doc in enumerate(response['context']):
+            st.write(doc.page_content)
+            st.write('------------------------')