replace gpt-3.5 with gemini-1.5-flash

notebooks/04-RAG_with_VectorStore.ipynb

@@ -20,27 +20,38 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 1,
+      "execution_count": null,
       "metadata": {
         "id": "QPJzr-I9XQ7l"
       },
       "outputs": [],
       "source": [
-        "!pip install -q llama-index==0.10.5 llama-index-vector-stores-chroma==0.1.7 langchain==0.1.17 langchain-chroma==0.1.0 langchain_openai==0.1.5 openai==1.12.0 cohere==4.47 tiktoken==0.6.0 chromadb==0.4.22"
+        "!pip install -q llama-index==0.10.49 llama-index-vector-stores-chroma==0.1.9 llama-index-llms-gemini==0.1.11 google-generativeai==0.5.4 langchain==0.1.17 langchain-chroma==0.1.0 langchain_openai==0.1.5 openai==1.35.3 chromadb==0.5.3"
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": 2,
+      "execution_count": 1,
       "metadata": {
         "id": "riuXwpSPcvWC"
       },
       "outputs": [],
       "source": [
         "import os\n",
+        "from dotenv import load_dotenv\n",
         "\n",
-        "# Set the \"OPENAI_API_KEY\" in the Python environment. Will be used by OpenAI client later.\n",
-        "os.environ[\"OPENAI_API_KEY\"] = \"<YOUR_OPENAI_KEY>\""
+        "load_dotenv(\".env\")\n",
+        "\n",
+        "# Here we look for the OPENAI_API_KEY in the environment variables\n",
+        "OPENAI_API_KEY = os.getenv(\"OPENAI_API_KEY\")\n",
+        "if not OPENAI_API_KEY:\n",
+        "    # If it's not found, you can set it manually\n",
+        "    os.environ[\"OPENAI_API_KEY\"] = \"<YOUR_OPENAI_KEY>\"\n",
+        "\n",
+        "# Get your GOOGLE_API_KEY from https://aistudio.google.com/app/apikey\n",
+        "GOOGLE_API_KEY = os.getenv(\"GOOGLE_API_KEY\")\n",
+        "if not GOOGLE_API_KEY:\n",
+        "    os.environ[\"GOOGLE_API_KEY\"] = \"<YOUR_GOOGLE_KEY>\""
       ]
     },
     {
@@ -72,7 +83,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 3,
+      "execution_count": 2,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
@@ -87,7 +98,7 @@
           "text": [
             "  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current\n",
             "                                 Dload  Upload   Total   Spent    Left  Speed\n",
-            "100  169k  100  169k    0     0   277k      0 --:--:-- --:--:-- --:--:--  281k\n"
+            "100  169k  100  169k    0     0  1581k      0 --:--:-- --:--:-- --:--:-- 1584k\n"
           ]
         }
       ],
@@ -106,7 +117,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 4,
+      "execution_count": 3,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
@@ -116,14 +127,11 @@
       },
       "outputs": [
         {
-          "data": {
-            "text/plain": [
-              "841"
-            ]
-          },
-          "execution_count": 4,
-          "metadata": {},
-          "output_type": "execute_result"
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "171044\n"
+          ]
         }
       ],
       "source": [
@@ -132,14 +140,16 @@
         "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",
+        "with open(\"./mini-dataset.csv\", mode=\"r\", encoding=\"utf-8\") as file:\n",
+        "    csv_reader = csv.reader(file)\n",
         "\n",
-        "  for row in csv_reader:\n",
-        "    text += row[0]\n",
+        "    for idx, row in enumerate(csv_reader):\n",
+        "        if idx == 0:\n",
+        "            continue\n",
+        "        text += row[1]\n",
         "\n",
         "# The number of characters in the dataset.\n",
-        "len( text )"
+        "print(len(text))"
       ]
     },
     {
@@ -153,7 +163,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 5,
+      "execution_count": 4,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
@@ -163,14 +173,11 @@
       },
       "outputs": [
         {
-          "data": {
-            "text/plain": [
-              "2"
-            ]
-          },
-          "execution_count": 5,
-          "metadata": {},
-          "output_type": "execute_result"
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "335\n"
+          ]
         }
       ],
       "source": [
@@ -179,9 +186,9 @@
         "\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",
+        "    chunks.append(text[i : i + chunk_size])\n",
         "\n",
-        "len( chunks )"
+        "print(len(chunks))"
       ]
     },
     {
@@ -243,6 +250,7 @@
       "source": [
         "from llama_index.vector_stores.chroma import ChromaVectorStore\n",
         "from llama_index.core 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)"
@@ -254,13 +262,29 @@
       "metadata": {
         "id": "WsD52wtrlESi"
       },
-      "outputs": [],
+      "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "/Users/omar/Documents/ai_repos/ai-tutor-rag-system/env/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+            "  from .autonotebook import tqdm as notebook_tqdm\n",
+            "Parsing nodes: 100%|██████████| 335/335 [00:00<00:00, 8031.85it/s]\n",
+            "Generating embeddings: 100%|██████████| 335/335 [00:03<00:00, 97.24it/s] \n"
+          ]
+        }
+      ],
       "source": [
         "from llama_index.core import VectorStoreIndex\n",
+        "from llama_index.core.node_parser import SentenceSplitter\n",
+        "from llama_index.embeddings.openai import OpenAIEmbedding\n",
         "\n",
-        "# Add the documents to the database and create Index / embeddings\n",
+        "# Build index / generate embeddings using OpenAI embedding model\n",
         "index = VectorStoreIndex.from_documents(\n",
-        "    documents, storage_context=storage_context\n",
+        "    documents,\n",
+        "    embed_model=OpenAIEmbedding(model=\"text-embedding-3-small\"),\n",
+        "    storage_context=storage_context,\n",
+        "    show_progress=True,\n",
         ")"
       ]
     },
@@ -281,12 +305,14 @@
       },
       "outputs": [],
       "source": [
-        "from llama_index.llms.openai import OpenAI\n",
         "# Define a query engine that is responsible for retrieving related pieces of text,\n",
         "# and using a LLM to formulate the final answer.\n",
         "\n",
-        "llm = OpenAI(temperature=0, model=\"gpt-3.5-turbo\", max_tokens=512)\n",
-        "query_engine = index.as_query_engine(llm=llm)"
+        "from llama_index.llms.gemini import Gemini\n",
+        "\n",
+        "llm = Gemini(model=\"models/gemini-1.5-flash\", temperature=1, max_tokens=512)\n",
+        "\n",
+        "query_engine = index.as_query_engine(llm=llm, similarity_top_k=5)"
       ]
     },
     {
@@ -304,14 +330,13 @@
           "name": "stdout",
           "output_type": "stream",
           "text": [
-            "The LLaMA2 model has 7 billion parameters.\n"
+            "The LLaMA2 model has four different sizes: 7 billion, 13 billion, 34 billion, and 70 billion parameters. \n",
+            "\n"
           ]
         }
       ],
       "source": [
-        "response = query_engine.query(\n",
-        "    \"How many parameters LLaMA2 model has?\"\n",
-        ")\n",
+        "response = query_engine.query(\"How many parameters LLaMA2 model has?\")\n",
         "print(response)"
       ]
     },
@@ -333,6 +358,7 @@
       "outputs": [],
       "source": [
         "from langchain.schema.document import Document\n",
+        "\n",
         "# Convert the chunks to Document objects so the LangChain framework can process them.\n",
         "documents = [Document(page_content=t) for t in chunks]"
       ]
@@ -356,6 +382,7 @@
       "source": [
         "from langchain_chroma import Chroma\n",
         "from langchain_openai import OpenAIEmbeddings\n",
+        "\n",
         "# Add the documents to chroma DB and create Index / embeddings\n",
         "\n",
         "embeddings = OpenAIEmbeddings(model=\"text-embedding-ada-002\")\n",
@@ -363,7 +390,7 @@
         "    documents=documents,\n",
         "    embedding=embeddings,\n",
         "    persist_directory=\"./mini-chunked-dataset\",\n",
-        "    collection_name=\"mini-chunked-dataset\"\n",
+        "    collection_name=\"mini-chunked-dataset\",\n",
         ")"
       ]
     },
@@ -378,20 +405,21 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 14,
+      "execution_count": null,
       "metadata": {
         "id": "-H64YLxshM2b"
       },
       "outputs": [],
       "source": [
         "from langchain_openai import ChatOpenAI\n",
+        "\n",
         "# Initializing the LLM model\n",
         "llm = ChatOpenAI(temperature=0, model=\"gpt-3.5-turbo\", max_tokens=512)"
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": 16,
+      "execution_count": null,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
@@ -399,24 +427,15 @@
         "id": "AxBqPNtthPaa",
         "outputId": "93c9ad64-1cd1-4f52-c51e-6f3ec5d6542d"
       },
-      "outputs": [
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            "The LLaMA-2 model has 7 billion parameters.\n"
-          ]
-        }
-      ],
+      "outputs": [],
       "source": [
         "from langchain.chains import RetrievalQA\n",
+        "\n",
         "query = \"How many parameters LLaMA2 model has?\"\n",
         "retriever = chroma_db.as_retriever(search_kwargs={\"k\": 2})\n",
         "# Define a RetrievalQA chain that is responsible for retrieving related pieces of text,\n",
         "# and using a LLM to formulate the final answer.\n",
-        "chain = RetrievalQA.from_chain_type(llm=llm,\n",
-        "                                    chain_type=\"stuff\",\n",
-        "                                    retriever=retriever)\n",
+        "chain = RetrievalQA.from_chain_type(llm=llm, chain_type=\"stuff\", retriever=retriever)\n",
         "\n",
         "response = chain(query)\n",
         "print(response[\"result\"])"
@@ -441,7 +460,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.11.8"
+      "version": "3.12.3"
     }
   },
   "nbformat": 4,