Merge pull request #699 from mihaly-hazag/w5_excercise_hm

W5 excercise

week5/community-contributions/w5_excercise.ipynb

@@ -0,0 +1,120 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "25868a51",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from dotenv import load_dotenv\n",
+    "from openai import OpenAI\n",
+    "import gradio as gr"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "805b6abc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Initialize OpenAI and constants\n",
+    "load_dotenv(override=True)\n",
+    "api_key = os.getenv('OPENAI_API_KEY')\n",
+    "MODEL = 'gpt-4o-mini'\n",
+    "openai = OpenAI()\n",
+    "\n",
+    "db_name = \"vector_db\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "382f71f2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import WebBaseLoader\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain_openai import OpenAIEmbeddings, ChatOpenAI\n",
+    "from langchain_chroma import Chroma\n",
+    "from langchain.memory import ConversationBufferMemory\n",
+    "from langchain.chains import ConversationalRetrievalChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e41daa2f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = WebBaseLoader([\"https://en.wikipedia.org/wiki/Solar_System\",\n",
+    "                        \"https://en.wikipedia.org/wiki/Star_Wars_(film)\"])\n",
+    "docs = loader.load()\n",
+    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)\n",
+    "chunks = text_splitter.split_documents(docs)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a21e1776",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embeddings = OpenAIEmbeddings()\n",
+    "\n",
+    "if os.path.exists(db_name):\n",
+    "    Chroma(persist_directory=db_name, embedding_function=embeddings).delete_collection()\n",
+    "\n",
+    "vectorstore = Chroma.from_documents(documents=chunks, embedding=embeddings, persist_directory=db_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fb072ee8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# create a new Chat with OpenAI\n",
+    "llm = ChatOpenAI(temperature=0.7, model_name=MODEL)\n",
+    "memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)\n",
+    "retriever = vectorstore.as_retriever()\n",
+    "conversation_chain = ConversationalRetrievalChain.from_llm(llm=llm, retriever=retriever, memory=memory)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0531ff73",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def chat(question, history):\n",
+    "    result = conversation_chain.invoke({\"question\": question})\n",
+    "    return result[\"answer\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a87fe151",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "view = gr.ChatInterface(chat, type=\"messages\").launch(inbrowser=True)"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}