From 3bd6a673b35eaf29fd53769ce03a0c4e7beb7583 Mon Sep 17 00:00:00 2001 From: Ravi Theja Date: Fri, 16 Feb 2024 20:46:39 +0530 Subject: [PATCH] Add Nomic Embedding cookbook (#10792) * Add Nomic Embedding cookbook * Update google colab link --- docs/examples/embeddings/nomic.ipynb | 485 ++++++++++++++++++++++++ docs/module_guides/models/embeddings.md | 1 + 2 files changed, 486 insertions(+) create mode 100644 docs/examples/embeddings/nomic.ipynb diff --git a/docs/examples/embeddings/nomic.ipynb b/docs/examples/embeddings/nomic.ipynb new file mode 100644 index 0000000000000..3ad2641c63b1f --- /dev/null +++ b/docs/examples/embeddings/nomic.ipynb @@ -0,0 +1,485 @@ +{ + "cells": [ + { + "attachments": {}, + "cell_type": "markdown", + "metadata": {}, + "source": [ + "\"Open" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Nomic Embedding\n", + "\n", + "Nomic has released v1.5 🪆🪆🪆 is capable of variable sized embeddings with matryoshka learning and an 8192 context, embedding dimensions between 64 and 768.\n", + "\n", + "In this notebook, we will explore using Nomic v1.5 embedding at different dimensions." + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Installation" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "%pip install -U llama-index llama-index-embeddings-nomic" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Setup API Keys" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "nomic_api_key = \"\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "import nest_asyncio\n", + "\n", + "nest_asyncio.apply()\n", + "\n", + "from llama_index.embeddings.nomic import NomicEmbedding" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### With dimension at 128" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "embed_model = NomicEmbedding(\n", + " api_key=nomic_api_key,\n", + " dimensionality=128,\n", + " model_name=\"nomic-embed-text-v1.5\",\n", + ")\n", + "\n", + "embedding = embed_model.get_text_embedding(\"Nomic Embeddings\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "128\n" + ] + } + ], + "source": [ + "print(len(embedding))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[0.05569458, 0.057922363, -0.30126953, -0.09832764, 0.05947876]" + ] + }, + "execution_count": null, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "embedding[:5]" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### With dimension at 256" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "embed_model = NomicEmbedding(\n", + " api_key=nomic_api_key,\n", + " dimensionality=256,\n", + " model_name=\"nomic-embed-text-v1.5\",\n", + ")\n", + "\n", + "embedding = embed_model.get_text_embedding(\"Nomic Embeddings\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "256\n" + ] + } + ], + "source": [ + "print(len(embedding))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[0.044708252, 0.04650879, -0.24182129, -0.07897949, 0.04776001]" + ] + }, + "execution_count": null, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "embedding[:5]" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### With dimension at 768" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "embed_model = NomicEmbedding(\n", + " api_key=nomic_api_key,\n", + " dimensionality=768,\n", + " model_name=\"nomic-embed-text-v1.5\",\n", + ")\n", + "\n", + "embedding = embed_model.get_text_embedding(\"Nomic Embeddings\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "768\n" + ] + } + ], + "source": [ + "print(len(embedding))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[0.027282715, 0.028381348, -0.14758301, -0.048187256, 0.029144287]" + ] + }, + "execution_count": null, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "embedding[:5]" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### You can still use v1 Nomic Embeddings\n", + "\n", + "It has 768 fixed embedding dimensions" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "embed_model = NomicEmbedding(\n", + " api_key=nomic_api_key, model_name=\"nomic-embed-text-v1\"\n", + ")\n", + "\n", + "embedding = embed_model.get_text_embedding(\"Nomic Embeddings\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "768\n" + ] + } + ], + "source": [ + "print(len(embedding))" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[0.0059013367, 0.03744507, 0.0035305023, -0.047180176, 0.0154418945]" + ] + }, + "execution_count": null, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "embedding[:5]" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Let's Build end to end RAG pipeline with Nomic v1.5 Embedding.\n", + "\n", + "We will use OpenAI for Generation step." + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Set Embedding model and llm." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "from llama_index.core import settings\n", + "from llama_index.core import VectorStoreIndex, SimpleDirectoryReader\n", + "from llama_index.llms.openai import OpenAI\n", + "\n", + "import os\n", + "\n", + "os.environ[\"OPENAI_API_KEY\"] = \"\"\n", + "\n", + "embed_model = NomicEmbedding(\n", + " api_key=nomic_api_key,\n", + " dimensionality=128,\n", + " model_name=\"nomic-embed-text-v1.5\",\n", + ")\n", + "\n", + "llm = OpenAI(model=\"gpt-3.5-turbo\")\n", + "\n", + "settings.llm = llm\n", + "settings.embed_model = embed_model" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Download Data" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "--2024-02-16 18:37:03-- https://raw.githubusercontent.com/run-llama/llama_index/main/docs/examples/data/paul_graham/paul_graham_essay.txt\n", + "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 2606:50c0:8001::154, 2606:50c0:8003::154, 2606:50c0:8000::154, ...\n", + "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|2606:50c0:8001::154|:443... connected.\n", + "HTTP request sent, awaiting response... 200 OK\n", + "Length: 75042 (73K) [text/plain]\n", + "Saving to: 'data/paul_graham/paul_graham_essay.txt'\n", + "\n", + "data/paul_graham/pa 100%[===================>] 73.28K --.-KB/s in 0.02s \n", + "\n", + "2024-02-16 18:37:03 (3.87 MB/s) - 'data/paul_graham/paul_graham_essay.txt' saved [75042/75042]\n", + "\n" + ] + } + ], + "source": [ + "!mkdir -p 'data/paul_graham/'\n", + "!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Load data" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "documents = SimpleDirectoryReader(\"./data/paul_graham\").load_data()" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Index creation" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "index = VectorStoreIndex.from_documents(documents)" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### Query Engine" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "query_engine = index.as_query_engine()" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "The author, growing up, worked on writing and programming. They wrote short stories and also tried writing programs on an IBM 1401 computer. Later, they got a microcomputer and started programming more extensively, writing simple games and a word processor.\n" + ] + } + ], + "source": [ + "response = query_engine.query(\"what did author do growing up?\")\n", + "print(response)" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "llama", + "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" + }, + "vscode": { + "interpreter": { + "hash": "b1d2a638b53f4d7129cb7686d8e3b97ae1d80a593a1618479f60cef5591ea888" + } + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/docs/module_guides/models/embeddings.md b/docs/module_guides/models/embeddings.md index 5aaf6dfad8754..85d284b0f0a18 100644 --- a/docs/module_guides/models/embeddings.md +++ b/docs/module_guides/models/embeddings.md @@ -233,4 +233,5 @@ maxdepth: 1 /examples/embeddings/text_embedding_inference.ipynb /examples/embeddings/together.ipynb /examples/embeddings/voyageai.ipynb +/examples/embeddings/nomic.ipynb ```