LLM_Engineering_OLD/week5/community-contributions/day5-autoshop-AI.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ba2779af-84ef-4227-9e9e-6eaf0df87e77",
   "metadata": {},
   "outputs": [],
   "source": [
    "# imports\n",
    "\n",
    "import os\n",
    "import glob\n",
    "from dotenv import load_dotenv\n",
    "import gradio as gr\n",
    "import json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "802137aa-8a74-45e0-a487-d1974927d7ca",
   "metadata": {},
   "outputs": [],
   "source": [
    "# imports for langchain, plotly and Chroma\n",
    "\n",
    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
    "from langchain.schema import Document\n",
    "from langchain_openai import OpenAIEmbeddings, ChatOpenAI\n",
    "from langchain_chroma import Chroma\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.manifold import TSNE\n",
    "import numpy as np \n",
    "import plotly.graph_objects as go\n",
    "from langchain.memory import ConversationBufferMemory\n",
    "from langchain.chains import ConversationalRetrievalChain"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "58c85082-e417-4708-9efe-81a5d55d1424",
   "metadata": {},
   "outputs": [],
   "source": [
    "# price is a factor for our company, so we're going to use a low cost model\n",
    "\n",
    "MODEL = \"gpt-4o-mini\"\n",
    "db_name = \"vector_db\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ee78efcb-60fe-449e-a944-40bab26261af",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load environment variables in a file called .env\n",
    "\n",
    "load_dotenv(override=True)\n",
    "os.environ['OPENAI_API_KEY'] = os.getenv('OPENAI_API_KEY', 'your-key-if-not-using-env')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b14e6c30-37c6-4eac-845b-5471aa75f587",
   "metadata": {},
   "outputs": [],
   "source": [
    "##Load json\n",
    "with open(\"knowledge-base/auto_shop.json\", 'r') as f: #place auto_shop.json file inside your knowledge-base folder\n",
    "    data = json.load(f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "408bc620-477f-47fd-b9e8-ab9d21843ecd",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Convert to Langchain\n",
    "documents = []\n",
    "for item in data:\n",
    "    content = item[\"content\"]\n",
    "    metadata = item.get(\"metadata\", {})\n",
    "    documents.append(Document(page_content=content, metadata=metadata))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0371d472-cd14-4967-bc09-9b78e233809f",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Chunk documents\n",
    "splitter = RecursiveCharacterTextSplitter(chunk_size=300, chunk_overlap=50, separators=[\"\\n\\n\", \"\\n\", \",\", \" \", \"\"])\n",
    "chunks = splitter.split_documents(documents)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "91c2404b-b3c9-4c7f-b199-9895e429a3da",
   "metadata": {},
   "outputs": [],
   "source": [
    "doc_types = set(chunk.metadata['source'] for chunk in chunks)\n",
    "#print(f\"Document types found: {', '.join(doc_types)}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "78998399-ac17-4e28-b15f-0b5f51e6ee23",
   "metadata": {},
   "outputs": [],
   "source": [
    "embeddings = OpenAIEmbeddings()\n",
    "\n",
    "# Delete if already exists\n",
    "\n",
    "if os.path.exists(db_name):\n",
    "    Chroma(persist_directory=db_name, embedding_function=embeddings).delete_collection()\n",
    "\n",
    "# Create vectorstore\n",
    "\n",
    "vectorstore = Chroma.from_documents(documents=chunks, embedding=embeddings, persist_directory=db_name)\n",
    "#print(f\"Vectorstore created with {vectorstore._collection.count()} documents\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ff2e7687-60d4-4920-a1d7-a34b9f70a250",
   "metadata": {},
   "outputs": [],
   "source": [
    "# # Let's investigate the vectors. Use for debugging if needed\n",
    "\n",
    "# collection = vectorstore._collection\n",
    "# count = collection.count()\n",
    "\n",
    "# sample_embedding = collection.get(limit=1, include=[\"embeddings\"])[\"embeddings\"][0]\n",
    "# dimensions = len(sample_embedding)\n",
    "# print(f\"There are {count:,} vectors with {dimensions:,} dimensions in the vector store\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "129c7d1e-0094-4479-9459-f9360b95f244",
   "metadata": {},
   "outputs": [],
   "source": [
    "# create a new Chat with OpenAI\n",
    "llm = ChatOpenAI(temperature=0.7, model_name=MODEL)\n",
    "\n",
    "\n",
    "memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)\n",
    "\n",
    "# the retriever is an abstraction over the VectorStore that will be used during RAG\n",
    "retriever = vectorstore.as_retriever()\n",
    "\n",
    "# putting it together: set up the conversation chain with the GPT 3.5 LLM, the vector store and memory\n",
    "conversation_chain = ConversationalRetrievalChain.from_llm(llm=llm, retriever=retriever, memory=memory)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bbbcb659-13ce-47ab-8a5e-01b930494964",
   "metadata": {},
   "source": [
    "## Now we will bring this up in Gradio using the Chat interface -"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c3536590-85c7-4155-bd87-ae78a1467670",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Wrapping that in a function\n",
    "\n",
    "def chat(question, history):\n",
    "    result = conversation_chain.invoke({\"question\": question})\n",
    "    return result[\"answer\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b252d8c1-61a8-406d-b57a-8f708a62b014",
   "metadata": {},
   "outputs": [],
   "source": [
    "# And in Gradio:\n",
    "\n",
    "view = gr.ChatInterface(chat, type=\"messages\").launch(inbrowser=True)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}