{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"authorship_tag": "ABX9TyNQkVEh0x7hcM9U+6JSEkSG",
"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": "5BGJ3fxhOk2V"
}
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "QPJzr-I9XQ7l",
"outputId": "9949a0e5-8bf2-4ae7-9921-1f9dfbece9ae"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m15.7/15.7 MB\u001b[0m \u001b[31m51.7 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[31m20.5 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[31m5.6 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[31m67.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m508.6/508.6 kB\u001b[0m \u001b[31m42.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m79.9/79.9 MB\u001b[0m \u001b[31m11.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m45.7/45.7 kB\u001b[0m \u001b[31m4.0 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[31m12.3 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[31m6.4 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[31m70.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.4/2.4 MB\u001b[0m \u001b[31m63.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.1/92.1 kB\u001b[0m \u001b[31m10.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.3/60.3 kB\u001b[0m \u001b[31m6.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.4/5.4 MB\u001b[0m \u001b[31m63.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.4/6.4 MB\u001b[0m \u001b[31m62.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m57.9/57.9 kB\u001b[0m \u001b[31m6.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m105.6/105.6 kB\u001b[0m \u001b[31m10.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.3/67.3 kB\u001b[0m \u001b[31m7.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
" Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
" Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m698.9/698.9 kB\u001b[0m \u001b[31m45.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m69.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m72.6/72.6 kB\u001b[0m \u001b[31m8.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.0/67.0 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[32m76.9/76.9 kB\u001b[0m \u001b[31m8.1 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[31m6.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m143.8/143.8 kB\u001b[0m \u001b[31m14.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m3.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.8/50.8 kB\u001b[0m \u001b[31m5.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m341.4/341.4 kB\u001b[0m \u001b[31m23.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.4/3.4 MB\u001b[0m \u001b[31m58.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m69.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m130.2/130.2 kB\u001b[0m \u001b[31m14.3 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[31m4.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.8/86.8 kB\u001b[0m \u001b[31m8.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h Building wheel for pypika (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
"\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 chromadb==0.4.21 kaleido==0.2.1 python-multipart==0.0.6"
]
},
{
"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": "riuXwpSPcvWC"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"# Load the Dataset (CSV)"
],
"metadata": {
"id": "I9JbAzFcjkpn"
}
},
{
"cell_type": "markdown",
"source": [
"## Download"
],
"metadata": {
"id": "_Tif8-JoRH68"
}
},
{
"cell_type": "markdown",
"source": [
"The dataset includes several articles from the TowardsAI blog, which provide an in-depth explanation of the LLaMA2 model. Read the dataset as a long string."
],
"metadata": {
"id": "4fQaa1LN1mXL"
}
},
{
"cell_type": "code",
"source": [
"!wget https://raw.githubusercontent.com/AlaFalaki/tutorial_notebooks/main/data/mini-dataset.csv"
],
"metadata": {
"id": "-QTUkdfJjY4N"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"## Read File"
],
"metadata": {
"id": "zk-4alIxROo8"
}
},
{
"cell_type": "code",
"source": [
"import csv\n",
"\n",
"text = \"\"\n",
"\n",
"# Load the file as a JSON\n",
"with open(\"./mini-dataset.csv\", mode=\"r\", encoding=\"ISO-8859-1\") as file:\n",
" csv_reader = csv.reader(file)\n",
"\n",
" for row in csv_reader:\n",
" text += row[0]\n",
"\n",
"# The number of characters in the dataset.\n",
"len( text )"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "7CYwRT6R0o0I",
"outputId": "6f0f05ae-c92f-45b2-bbc3-d12add118021"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"23632"
]
},
"metadata": {},
"execution_count": 4
}
]
},
{
"cell_type": "markdown",
"source": [
"# Chunking"
],
"metadata": {
"id": "S17g2RYOjmf2"
}
},
{
"cell_type": "code",
"source": [
"chunk_size = 512\n",
"chunks = []\n",
"\n",
"# Split the long text into smaller manageable chunks of 512 characters.\n",
"for i in range(0, len(text), chunk_size):\n",
" chunks.append(text[i:i + chunk_size])\n",
"\n",
"len( chunks )"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "STACTMUR1z9N",
"outputId": "8ce58d6b-a38d-48e3-8316-7435907488cf"
},
"execution_count": null,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"47"
]
},
"metadata": {},
"execution_count": 6
}
]
},
{
"cell_type": "code",
"source": [
"from llama_index import Document\n",
"\n",
"# Convert the chunks to Document objects so the LlamaIndex framework can process them.\n",
"documents = [Document(text=t) for t in chunks]"
],
"metadata": {
"id": "CtdsIUQ81_hT"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"# Save on Chroma"
],
"metadata": {
"id": "OWaT6rL7ksp8"
}
},
{
"cell_type": "code",
"source": [
"import chromadb\n",
"\n",
"# create client and a new collection\n",
"# chromadb.EphemeralClient saves data in-memory.\n",
"chroma_client = chromadb.PersistentClient(path=\"./mini-chunked-dataset\")\n",
"chroma_collection = chroma_client.create_collection(\"mini-chunked-dataset\")"
],
"metadata": {
"id": "mXi56KTXk2sp"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"from llama_index.vector_stores import ChromaVectorStore\n",
"from llama_index.storage.storage_context import StorageContext\n",
"\n",
"# Define a storage context object using the created vector database.\n",
"vector_store = ChromaVectorStore(chroma_collection=chroma_collection)\n",
"storage_context = StorageContext.from_defaults(vector_store=vector_store)"
],
"metadata": {
"id": "jKXURvLtkuTS"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"from llama_index import VectorStoreIndex\n",
"\n",
"# Add the documents to the database and create Index / embeddings\n",
"index = VectorStoreIndex.from_documents(\n",
" documents, storage_context=storage_context\n",
")"
],
"metadata": {
"id": "WsD52wtrlESi"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"# Query Dataset"
],
"metadata": {
"id": "8JPD8yAinVSq"
}
},
{
"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": "mzS13x1ZlZ5X"
},
"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": "AYsQ4uLN_Oxg",
"outputId": "bf2181ad-27f6-40a2-b792-8a2714a60c29"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"The Llama-2 model has three different sizes: 7B, 13B, and 70B.\n"
]
}
]
}
]
}