{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"authorship_tag": "ABX9TyMcuy0u2XnwzWnARu0WjaRq",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\")
"
]
},
{
"cell_type": "markdown",
"source": [
"# Install Packages and Setup Variables"
],
"metadata": {
"id": "v9bpz99INAc1"
}
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "BeuFJKlj9jKz",
"outputId": "4c3a9772-cb7d-4fc1-d0e4-64186861e3e5"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m15.7/15.7 MB\u001b[0m \u001b[31m12.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m225.4/225.4 kB\u001b[0m \u001b[31m7.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m51.7/51.7 kB\u001b[0m \u001b[31m2.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m35.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.9/75.9 kB\u001b[0m \u001b[31m1.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.1/3.1 MB\u001b[0m \u001b[31m35.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m143.0/143.0 kB\u001b[0m \u001b[31m12.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m76.9/76.9 kB\u001b[0m \u001b[31m6.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m3.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.4/49.4 kB\u001b[0m \u001b[31m2.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
"tensorflow-probability 0.22.0 requires typing-extensions<4.6.0, but you have typing-extensions 4.9.0 which is incompatible.\u001b[0m\u001b[31m\n",
"\u001b[0m"
]
}
],
"source": [
"!pip install -q llama-index==0.9.21 openai==1.6.0 cohere==4.39 tiktoken==0.5.2"
]
},
{
"cell_type": "code",
"source": [
"import os\n",
"\n",
"# Set the \"OPENAI_API_KEY\" in the Python environment. Will be used by OpenAI client later.\n",
"os.environ[\"OPENAI_API_KEY\"] = \"\""
],
"metadata": {
"id": "XuzgSNqcABpV"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"# Load Dataset"
],
"metadata": {
"id": "f5eV5EnvNCMM"
}
},
{
"cell_type": "markdown",
"source": [
"## Download"
],
"metadata": {
"id": "q-7mRQ-mNJlm"
}
},
{
"cell_type": "markdown",
"source": [
"The dataset includes several articles from the TowardsAI blog, which provide an in-depth explanation of the LLaMA2 model."
],
"metadata": {
"id": "3PsdOdMUNmEi"
}
},
{
"cell_type": "code",
"source": [
"!wget https://raw.githubusercontent.com/AlaFalaki/tutorial_notebooks/main/data/mini-dataset.json"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "3ImRCP7pACaI",
"outputId": "9a63bdea-54f7-4923-ccbb-cab03b312774"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"--2023-12-25 17:33:36-- https://raw.githubusercontent.com/AlaFalaki/tutorial_notebooks/main/data/mini-dataset.json\n",
"Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.110.133, 185.199.108.133, 185.199.111.133, ...\n",
"Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.110.133|:443... connected.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 25361 (25K) [text/plain]\n",
"Saving to: ‘mini-dataset.json’\n",
"\n",
"mini-dataset.json 100%[===================>] 24.77K --.-KB/s in 0.006s \n",
"\n",
"2023-12-25 17:33:37 (3.76 MB/s) - ‘mini-dataset.json’ saved [25361/25361]\n",
"\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"## Read File"
],
"metadata": {
"id": "bZZLK_wyEc-L"
}
},
{
"cell_type": "code",
"source": [
"import json\n",
"\n",
"# Load the file as a JSON\n",
"with open('./mini-dataset.json', 'r') as file:\n",
" data = json.load(file)\n",
"\n",
"# The number of chunks in the dataset.\n",
"len( data['chunks'] )"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "miUqycqAEfr7",
"outputId": "10005d5f-15c0-4565-a58a-6cb7e466acb4"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"22"
]
},
"metadata": {},
"execution_count": 16
}
]
},
{
"cell_type": "code",
"source": [
"# Flatten the JSON variable to a list of texts.\n",
"texts = [item['text'] for item in data['chunks']]"
],
"metadata": {
"id": "Mq5WKj0QEfpk"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"# Generate Embedding"
],
"metadata": {
"id": "f86yksB9K571"
}
},
{
"cell_type": "code",
"source": [
"from llama_index import Document\n",
"\n",
"# Convert the texts to Document objects so the LlamaIndex framework can process them.\n",
"documents = [Document(text=t) for t in texts]"
],
"metadata": {
"id": "iXrr5-tnEfm9"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"from llama_index import VectorStoreIndex\n",
"\n",
"# Build index / generate embeddings using OpenAI.\n",
"index = VectorStoreIndex.from_documents(documents)"
],
"metadata": {
"id": "qQit27lBEfkV"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Save the generated embeddings.\n",
"# index.storage_context.persist(persist_dir=\"indexes\")"
],
"metadata": {
"id": "xxB0A9ZYM-OD"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"# Query Dataset"
],
"metadata": {
"id": "3DoUxd8KK--Q"
}
},
{
"cell_type": "code",
"source": [
"# Define a query engine that is responsible for retrieving related pieces of text,\n",
"# and using a LLM to formulate the final answer.\n",
"query_engine = index.as_query_engine()"
],
"metadata": {
"id": "bUaNH97dEfh9"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"response = query_engine.query(\n",
" \"How many parameters LLaMA2 model has?\"\n",
")\n",
"print(response)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "tEgFx_aeFS5e",
"outputId": "9133bd0c-f0c5-4124-9c4b-ab6c4c32b07a"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"The Llama 2 model has four different model sizes: 7 billion, 13 billion, 34 billion, and 70 billion parameters.\n"
]
}
]
}
]
}