From c2c3655fb3c4260a3ea49d5200e7ec65194ef214 Mon Sep 17 00:00:00 2001
From: aashahid <sp21-bcs-034@cuilahore.edu.pk>
Date: Wed, 29 Oct 2025 02:44:11 +0500
Subject: [PATCH] Add Week 5 submission for muhammad_qasim_sheikh

---
 .../Week 5/Day 5/rag.ipynb                    | 178 ++++++++++++++++++
 1 file changed, 178 insertions(+)
 create mode 100644 community-contributions/muhammad_qasim_sheikh/Week 5/Day 5/rag.ipynb

diff --git a/community-contributions/muhammad_qasim_sheikh/Week 5/Day 5/rag.ipynb b/community-contributions/muhammad_qasim_sheikh/Week 5/Day 5/rag.ipynb
new file mode 100644
index 0000000..28229d7
--- /dev/null
+++ b/community-contributions/muhammad_qasim_sheikh/Week 5/Day 5/rag.ipynb	
@@ -0,0 +1,178 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "7015d967",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from dotenv import load_dotenv\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.chains import ConversationalRetrievalChain\n",
+    "from langchain.memory import ConversationBufferMemory\n",
+    "from langchain.vectorstores import Chroma\n",
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.document_loaders import DirectoryLoader, TextLoader\n",
+    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain_experimental.text_splitter import SemanticChunker\n",
+    "from langchain.schema import Document\n",
+    "import gradio as gr\n",
+    "import glob"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "87646db6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "load_dotenv(override=True)\n",
+    "api_key = os.getenv('OPENAI_API_KEY')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1019e3b8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "file_paths = glob.glob(\"knowledge_base/**/*.md\", recursive=True)\n",
+    "\n",
+    "documents = []\n",
+    "for path in file_paths:\n",
+    "    with open(path, \"r\", encoding=\"utf-8\") as f:\n",
+    "        text = f.read()\n",
+    "        doc_type = os.path.basename(os.path.dirname(path)) \n",
+    "\n",
+    "        documents.append(\n",
+    "            Document(\n",
+    "                page_content=text,\n",
+    "                metadata={\n",
+    "                    \"doc_type\": doc_type,\n",
+    "                },\n",
+    "            )\n",
+    "        )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "54527a21",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embeddings = OpenAIEmbeddings(model=\"text-embedding-3-small\", openai_api_key=api_key)\n",
+    "\n",
+    "# text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)\n",
+    "text_splitter = SemanticChunker(embeddings)\n",
+    "chunks = text_splitter.split_documents(documents)\n",
+    "\n",
+    "print(f\"Total number of chunks: {len(chunks)}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "15579dda",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "vectorstore = Chroma.from_documents(\n",
+    "    documents=chunks,\n",
+    "    embedding=embeddings,\n",
+    "    persist_directory=\"chroma_db\"\n",
+    ")\n",
+    "vectorstore.persist()\n",
+    "print(\"Chroma vector store built.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ca3b4d55",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = ChatOpenAI(model=\"gpt-4o-mini\", temperature=0, openai_api_key=api_key)\n",
+    "memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)\n",
+    "retriever = vectorstore.as_retriever()\n",
+    "conversation_chain = ConversationalRetrievalChain.from_llm(\n",
+    "    llm=llm,\n",
+    "    retriever=retriever,\n",
+    "    memory=memory,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "94b3a75a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query = \"Tell me about Langchain.\"\n",
+    "result = conversation_chain({\"question\": query})\n",
+    "\n",
+    "print(\"Answer:\")\n",
+    "print(result[\"answer\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e814f910",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def rag_chat(query, history):\n",
+    "    response = conversation_chain({\"question\": query})\n",
+    "    answer = response[\"answer\"]\n",
+    "    return answer\n",
+    "\n",
+    "with gr.Blocks(theme=gr.themes.Soft()) as rag_ui:\n",
+    "    gr.Markdown(\"# RAG Chat Assistant\")\n",
+    "    gr.Markdown(\"Ask questions about your Markdown knowledge base.\")\n",
+    "    chat_box = gr.ChatInterface(\n",
+    "        fn=rag_chat,\n",
+    "        title=\"RAG Knowledge Base Assistant\",\n",
+    "        description=\"Chat with your Markdown-based knowledge base using RAG.\"\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "eef8d2ee",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "rag_ui.launch(debug=True, share=True)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llm-engineering",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}