Create app.py

app.py

@@ -0,0 +1,67 @@
+import streamlit as st
+import os
+from langchain_community.document_loaders import PyPDFDirectoryLoader
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_huggingface import HuggingFaceEmbeddings   # FIXED: new package
+from langchain_chroma import Chroma
+from langchain_groq import ChatGroq
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.runnables import RunnablePassthrough
+from langchain_core.output_parsers import StrOutputParser
+
+st.title("📚 MCA Module AI Assistant")
+st.markdown("Ask anything about your Computer Vision modules!")
+
+groq_api_key = os.getenv("GROQ_API_KEY")
+llm = ChatGroq(model="llama-3.2-3b-preview", groq_api_key=groq_api_key)
+
+@st.cache_resource
+def prepare_vectorstore():
+    loader = PyPDFDirectoryLoader("mca modules/")
+    docs = loader.load()
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+    splits = text_splitter.split_documents(docs)
+    
+    embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
+    
+    return Chroma.from_documents(
+        documents=splits,
+        embedding=embeddings,
+        persist_directory="/tmp/chroma_db"   # FIXED: writable path on HF Spaces
+    )
+
+vectorstore = prepare_vectorstore()
+
+template = """You are an expert AI Assistant. Use the provided context to answer the question.
+Rules:
+1. If the user asks for a comparison or specific categories, use a Markdown TABLE.
+2. Use bolding for key terms.
+3. If the answer isn't in the context, say "I cannot find this in your modules."
+
+Context:
+{context}
+
+Question: {question}
+"""
+prompt = ChatPromptTemplate.from_template(template)
+rag_chain = (
+    {"context": vectorstore.as_retriever(), "question": RunnablePassthrough()}
+    | prompt | llm | StrOutputParser()
+)
+
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+if prompt_input := st.chat_input("What is covered in Module 1?"):
+    st.session_state.messages.append({"role": "user", "content": prompt_input})
+    with st.chat_message("user"):
+        st.markdown(prompt_input)
+
+    with st.chat_message("assistant"):
+        response = rag_chain.invoke(prompt_input)
+        st.markdown(response)
+        st.session_state.messages.append({"role": "assistant", "content": response})