Created using Colaboratory

notebooks/06-RAG_Improve_Chunking.ipynb

@@ -0,0 +1,380 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "authorship_tag": "ABX9TyOXQSTuXN8LHQooW46XZ9Xr",
+      "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": [
+        "<a href=\"https://colab.research.google.com/github/towardsai/ai-tutor-rag-system/blob/main/notebooks/06-RAG_Improve_Chunking.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {
+        "id": "QPJzr-I9XQ7l",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "outputId": "971cf4cb-ee33-477b-cc7d-d652b55b81f3"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m15.7/15.7 MB\u001b[0m \u001b[31m41.5 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[31m16.0 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[31m3.9 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[31m45.1 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[31m32.4 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[31m5.5 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[31m3.3 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[31m9.8 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[31m7.2 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[31m53.7 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[31m53.8 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[31m7.1 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[31m4.8 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[31m57.0 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[31m66.5 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[31m6.2 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[31m11.9 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[31m6.1 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[31m54.8 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[31m82.0 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[31m1.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m68.9/68.9 kB\u001b[0m \u001b[31m9.2 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[31m9.6 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[31m8.5 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[31m17.7 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[31m5.7 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[31m6.5 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[31m37.4 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[31m87.4 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[31m76.2 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[31m16.7 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[31m6.7 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[31m11.7 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",
+        "os.environ[\"OPENAI_API_KEY\"] = \"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\""
+      ],
+      "metadata": {
+        "id": "riuXwpSPcvWC"
+      },
+      "execution_count": 2,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Load the Dataset (CSV)"
+      ],
+      "metadata": {
+        "id": "I9JbAzFcjkpn"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!wget https://raw.githubusercontent.com/AlaFalaki/tutorial_notebooks/main/data/mini-dataset.csv"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "wl_pbPvMlv1h",
+        "outputId": "70f7f4be-7b80-431b-8570-f388eb21878f"
+      },
+      "execution_count": 3,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "--2023-12-26 19:25:41--  https://raw.githubusercontent.com/AlaFalaki/tutorial_notebooks/main/data/mini-dataset.csv\n",
+            "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.111.133, 185.199.109.133, 185.199.108.133, ...\n",
+            "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.111.133|:443... connected.\n",
+            "HTTP request sent, awaiting response... 200 OK\n",
+            "Length: 23689 (23K) [text/plain]\n",
+            "Saving to: ‘mini-dataset.csv’\n",
+            "\n",
+            "mini-dataset.csv    100%[===================>]  23.13K  --.-KB/s    in 0.007s  \n",
+            "\n",
+            "2023-12-26 19:25:41 (3.10 MB/s) - ‘mini-dataset.csv’ saved [23689/23689]\n",
+            "\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from llama_index import download_loader\n",
+        "\n",
+        "SimpleCSVReader = download_loader(\"SimpleCSVReader\")\n",
+        "\n",
+        "loader = SimpleCSVReader(encoding=\"ISO-8859-1\")\n",
+        "documents = loader.load_data(file='./mini-dataset.csv')"
+      ],
+      "metadata": {
+        "id": "0Q9sxuW0g3Gd"
+      },
+      "execution_count": 4,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Chunking"
+      ],
+      "metadata": {
+        "id": "S17g2RYOjmf2"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from llama_index import ServiceContext\n",
+        "from llama_index.embeddings.openai import OpenAIEmbedding\n",
+        "\n",
+        "# We use OpenAI's embedding model \"text-embedding-ada-002\"\n",
+        "embed_model = OpenAIEmbedding()\n",
+        "\n",
+        "# initialize service context (set chunk size)\n",
+        "service_context = ServiceContext.from_defaults(chunk_size=512, chunk_overlap=64, embed_model=embed_model)"
+      ],
+      "metadata": {
+        "id": "YizvmXPejkJE"
+      },
+      "execution_count": 5,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "### Test chunking"
+      ],
+      "metadata": {
+        "id": "ROMhNRvolTmI"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "node_parser = service_context.node_parser\n",
+        "\n",
+        "nodes = node_parser.get_nodes_from_documents(documents)\n",
+        "len( nodes )"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "Oe_ePZh7lVmQ",
+        "outputId": "8f9a2250-2c8f-4f92-f6e6-037f3a18cdbb"
+      },
+      "execution_count": 6,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "13"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 6
+        }
+      ]
+    },
+    {
+      "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 to save in-memory.\n",
+        "chroma_client = chromadb.PersistentClient(path=\"./mini-dataset\")\n",
+        "chroma_collection = chroma_client.create_collection(\"mini-dataset\")"
+      ],
+      "metadata": {
+        "id": "mXi56KTXk2sp"
+      },
+      "execution_count": 7,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from llama_index.vector_stores import ChromaVectorStore\n",
+        "from llama_index.storage.storage_context import StorageContext\n",
+        "\n",
+        "vector_store = ChromaVectorStore(chroma_collection=chroma_collection)\n",
+        "storage_context = StorageContext.from_defaults(vector_store=vector_store)"
+      ],
+      "metadata": {
+        "id": "jKXURvLtkuTS"
+      },
+      "execution_count": 8,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from llama_index import VectorStoreIndex\n",
+        "\n",
+        "index = VectorStoreIndex.from_documents(\n",
+        "    documents, storage_context=storage_context, service_context=service_context\n",
+        ")"
+      ],
+      "metadata": {
+        "id": "WsD52wtrlESi"
+      },
+      "execution_count": 9,
+      "outputs": []
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "# Query Dataset"
+      ],
+      "metadata": {
+        "id": "8JPD8yAinVSq"
+      }
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "query_engine = index.as_query_engine()"
+      ],
+      "metadata": {
+        "id": "mzS13x1ZlZ5X"
+      },
+      "execution_count": 10,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "response = query_engine.query(\n",
+        "    \"How many parameters LLaMA2 model has?\"\n",
+        ")\n"
+      ],
+      "metadata": {
+        "id": "sb8f_wwPnZcG"
+      },
+      "execution_count": 11,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "print(f\"Answer: \\n\\t{response}\\n\\n\\nSources:\")\n",
+        "\n",
+        "for idx, source in enumerate( response.source_nodes ):\n",
+        "  print(\">\", idx+1)\n",
+        "  print(source.node)\n",
+        "  print(source.score)\n",
+        "  print(\"_-\"*40)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "N3Ri8E5Dl4Ar",
+        "outputId": "6de37908-c3b0-41c9-e74e-8ad03b53ae6c"
+      },
+      "execution_count": 30,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Answer: \n",
+            "\tThe Llama 2 model is available in four different sizes: 7 billion, 13 billion, 34 billion, and 70 billion parameters.\n",
+            "\n",
+            "\n",
+            "Sources:\n",
+            "> 1\n",
+            "Node ID: c8db296d-ad40-4f56-b67a-15d5d5807b36\n",
+            "Text: Meta has once again pushed the boundaries of AI with the release\n",
+            "of Llama 2, the highly anticipated successor to its groundbreaking\n",
+            "Llama 1 language model. Boasting a range of cutting-edge features,\n",
+            "Llama 2 has already disrupted the AI landscape and poses a real\n",
+            "challenge to ChatGPTÕs dominance. In this article, we will dive into\n",
+            "the exciting wo...\n",
+            "0.7188979822197016\n",
+            "_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-\n",
+            "> 2\n",
+            "Node ID: 2c1194e4-df31-474f-85a4-b19d16b4ece7\n",
+            "Text: Source: Meta Llama 2 paper Finding the right balance between\n",
+            "helpfulness and safety when optimizing a model poses significant\n",
+            "challenges. While a highly helpful model may be capable of answering\n",
+            "any question, including sensitive ones like ÒHow do I build a bomb?Ó,\n",
+            "it also raises concerns about potential misuse. Thus, striking the\n",
+            "perfect equilib...\n",
+            "0.7130334174007259\n",
+            "_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-_-\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "print(response)"
+      ],
+      "metadata": {
+        "id": "hjYiWAocnalt"
+      },
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}