2024-11-08 15:36:04 +08:00

328 lines
9.8 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Simple RAG From Scratch"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"In this tutorial, we will use BGE, Faiss, and OpenAI's GPT-4o-mini to build a simple RAG system from scratch."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 0. Preparation"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Install the required packages in the environment:"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%pip install -U numpy faiss-cpu FlagEmbedding openai"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1. Data"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Suppose I'm a resident of New York Manhattan, and I want the AI bot to provide suggestion on where should I go for dinner. It's not reliable to let it recommend some random restaurant. So let's provide a bunch of our favorate restaurants."
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"corpus = [\n",
" \"Cheli: A downtown Chinese restaurant presents a distinctive dining experience with authentic and sophisticated flavors of Shanghai cuisine. Avg cost: $40-50\",\n",
" \"Masa: Midtown Japanese restaurant with exquisite sushi and omakase experiences crafted by renowned chef Masayoshi Takayama. The restaurant offers a luxurious dining atmosphere with a focus on the freshest ingredients and exceptional culinary artistry. Avg cost: $500-600\",\n",
" \"Per Se: A midtown restaurant features daily nine-course tasting menu and a nine-course vegetable tasting menu using classic French technique and the finest quality ingredients available. Avg cost: $300-400\",\n",
" \"Ortomare: A casual, earthy Italian restaurant locates uptown, offering wood-fired pizza, delicious pasta, wine & spirits & outdoor seating. Avg cost: $30-50\",\n",
" \"Banh: Relaxed, narrow restaurant in uptown, offering Vietnamese cuisine & sandwiches, famous for its pho and Vietnam sandwich. Avg cost: $20-30\",\n",
" \"Living Thai: An uptown typical Thai cuisine with different kinds of curry, Tom Yum, fried rice, Thai ice tea, etc. Avg cost: $20-30\",\n",
" \"Chick-fil-A: A Fast food restaurant with great chicken sandwich, fried chicken, fries, and salad, which can be found everywhere in New York. Avg cost: 10-20\",\n",
" \"Joe's Pizza: Most famous New York pizza locates midtown, serving different flavors including classic pepperoni, cheese, spinach, and also innovative pizza. Avg cost: $15-25\",\n",
" \"Red Lobster: In midtown, Red Lobster is a lively chain restaurant serving American seafood standards amid New England-themed decor, with fair price lobsters, shrips and crabs. Avg cost: $30-50\",\n",
" \"Bourbon Steak: It accomplishes all the traditions expected from a steakhouse, offering the finest cuts of premium beef and seafood complimented by wine and spirits program. Avg cost: $100-150\",\n",
" \"Da Long Yi: Locates in downtown, Da Long Yi is a Chinese Szechuan spicy hotpot restaurant that serves good quality meats. Avg cost: $30-50\",\n",
" \"Mitr Thai: An exquisite midtown Thai restaurant with traditional dishes as well as creative dishes, with a wonderful bar serving cocktails. Avg cost: $40-60\",\n",
" \"Yichiran Ramen: Famous Japenese ramen restaurant in both midtown and downtown, serving ramen that can be designed by customers themselves. Avg cost: $20-40\",\n",
" \"BCD Tofu House: Located in midtown, it's famous for its comforting and flavorful soondubu jjigae (soft tofu stew) and a variety of authentic Korean dishes. Avg cost: $30-50\",\n",
"]\n",
"\n",
"user_input = \"I want some Chinese food\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2. Indexing"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now we need to figure out a fast but powerful enough method to retrieve docs in the corpus that are most closely related to our questions. Indexing is a good choice for us.\n",
"\n",
"The first step is embed each document into a vector. We use bge-base-en-v1.5 as our embedding model."
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"from FlagEmbedding import FlagModel\n",
"\n",
"model = FlagModel('BAAI/bge-base-en-v1.5',\n",
" query_instruction_for_retrieval=\"Represent this sentence for searching relevant passages:\",\n",
" use_fp16=True)\n",
"\n",
"embeddings = model.encode(corpus, convert_to_numpy=True)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(14, 768)"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"embeddings.shape"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Then, let's create a Faiss index and add all the vectors into it.\n",
"\n",
"If you want to know more about Faiss, refer to the tutorial of [Faiss and indexing](https://github.com/FlagOpen/FlagEmbedding/tree/master/Tutorials/3_Indexing)."
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"import faiss\n",
"import numpy as np\n",
"\n",
"index = faiss.IndexFlatIP(embeddings.shape[1])\n",
"\n",
"index.add(embeddings)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"14"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"index.ntotal"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 3. Retrieve and Generate"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now we come to the most exciting part. Let's first embed our query and retrieve 3 most relevant document from it:"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([['Cheli: A downtown Chinese restaurant presents a distinctive dining experience with authentic and sophisticated flavors of Shanghai cuisine. Avg cost: $40-50',\n",
" 'Da Long Yi: Locates in downtown, Da Long Yi is a Chinese Szechuan spicy hotpot restaurant that serves good quality meats. Avg cost: $30-50',\n",
" 'Yichiran Ramen: Famous Japenese ramen restaurant in both midtown and downtown, serving ramen that can be designed by customers themselves. Avg cost: $20-40']],\n",
" dtype='<U270')"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"q_embedding = model.encode_queries([user_input], convert_to_numpy=True)\n",
"\n",
"D, I = index.search(q_embedding, 3)\n",
"res = np.array(corpus)[I]\n",
"\n",
"res"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Then set up the prompt for the chatbot:"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"prompt=\"\"\"\n",
"You are a bot that makes recommendations for restaurants. \n",
"Please be brief, answer in short sentences without extra information.\n",
"\n",
"These are the restaurants list:\n",
"{recommended_activities}\n",
"\n",
"The user's preference is: {user_input}\n",
"Provide the user with 2 recommended restaurants based on the user's preference.\n",
"\"\"\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Fill in your OpenAI API key below:"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"os.environ[\"OPENAI_API_KEY\"] = \"YOUR_API_KEY\""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Finally let's see how the chatbot give us the answer!"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
"from openai import OpenAI\n",
"client = OpenAI()\n",
"\n",
"response = client.chat.completions.create(\n",
" model=\"gpt-4o-mini\",\n",
" messages=[\n",
" {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n",
" {\n",
" \"role\": \"user\",\n",
" \"content\": prompt.format(user_input=user_input, recommended_activities=res)\n",
" }\n",
" ]\n",
").choices[0].message"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1. Cheli - Authentic Shanghai cuisine with sophisticated flavors. \n",
"2. Da Long Yi - Szechuan spicy hotpot with good quality meats.\n"
]
}
],
"source": [
"print(response.content)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"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": "3.12.4"
}
},
"nbformat": 4,
"nbformat_minor": 2
}