using gemini in colab with langchain

21_langchain_ecosystem/langchain/02_gemini_colab_helloworld/gemini_langchain_helloworld.ipynb

@@ -0,0 +1,96 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "source": [
+        "# First, install necessary packages for LangChain and Google Generative AI\n",
+        "!pip install langchain_core\n",
+        "!pip install langchain_google_genai"
+      ],
+      "metadata": {
+        "collapsed": true,
+        "id": "2GYbrBvnvEQh"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\n",
+        "import os\n",
+        "from google.colab import userdata\n",
+        "\n",
+        "# Retrieve your Google API key from a secure location (Colab secret storage)\n",
+        "# Replace 'YOUR_SECRET_NAME' with the name of the environment variable storing your API key\n",
+        "google_api_key: str = userdata.get('GOOGLE_API_KEY')"
+      ],
+      "metadata": {
+        "id": "wFSgVJ4dvNxB"
+      },
+      "execution_count": 4,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from langchain_google_genai import ChatGoogleGenerativeAI\n",
+        "\n",
+        "# Create an instance of the Google Generative AI model (LLM)\n",
+        "# - 'api_key' is required to authenticate with Google's API\n",
+        "# - 'model' specifies the version of the AI model to use (gemini-1.5-flash in this case)\n",
+        "# - 'temperature' controls the randomness of the responses (lower values = more focused responses)\n",
+        "llm: ChatGoogleGenerativeAI = ChatGoogleGenerativeAI(\n",
+        "    api_key=google_api_key,\n",
+        "    model=\"gemini-1.5-flash\",\n",
+        "    temperature=0.2,\n",
+        ")"
+      ],
+      "metadata": {
+        "id": "KLWNhgjw1zrk"
+      },
+      "execution_count": 5,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "# Test the model by sending a simple \"hi\" message and print the AI's response\n",
+        "# The 'invoke' method is used to query the model and get a response\n",
+        "response: str = llm.invoke(\"hi\")\n",
+        "print(response)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "NkORDhrU__e3",
+        "outputId": "00a39bc2-778f-445a-f1e2-7bf41c3d4f2e"
+      },
+      "execution_count": 6,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "content='Hi there! How can I help you today? \\n' additional_kwargs={} response_metadata={'prompt_feedback': {'block_reason': 0, 'safety_ratings': []}, 'finish_reason': 'STOP', 'safety_ratings': [{'category': 'HARM_CATEGORY_SEXUALLY_EXPLICIT', 'probability': 'NEGLIGIBLE', 'blocked': False}, {'category': 'HARM_CATEGORY_HATE_SPEECH', 'probability': 'NEGLIGIBLE', 'blocked': False}, {'category': 'HARM_CATEGORY_HARASSMENT', 'probability': 'NEGLIGIBLE', 'blocked': False}, {'category': 'HARM_CATEGORY_DANGEROUS_CONTENT', 'probability': 'NEGLIGIBLE', 'blocked': False}]} id='run-89af641a-5e89-42e3-b0a8-648d0ee614d1-0' usage_metadata={'input_tokens': 2, 'output_tokens': 11, 'total_tokens': 13}\n"
+          ]
+        }
+      ]
+    }
+  ]
+}

21_langchain_ecosystem/langchain/02_gemini_colab_helloworld/readme.md

@@ -0,0 +1,56 @@
+# Google Gemini API with LangChain and Google Colab:
+
+**Prerequisites:**
+
+- A Google Cloud Platform account with a project enabled for the Gemini API.
+- A Google Colab notebook.
+- Python 3.6 or later installed.
+- The following Python libraries installed:
+    - `langchain_core`
+    - `langchain_google_genai`
+
+**Steps:**
+
+1. **Create a Google Colab Notebook:**
+   - Open Google Colab (colab.research.google.com) and create a new notebook.
+
+2. **Install Required Libraries:**
+   - In the first cell of the notebook, run the following code to install the necessary libraries:
+
+   ```python
+   !pip install langchain_core
+   !pip install langchain_google_genai
+   ```
+
+3. **Create project with Google Cloud Platform:**
+   - Visit your google cloud account and create new project or use an existing one: [GOOGLE CLOUD ACCOUNT](https://console.cloud.google.com/projectcreate)
+
+   - ![Create Project](google_project.jpg)
+   - ![Select Project](google_project_1.jpg)
+   - ![Check Project](google_project_2.jpg)
+
+
+4. **Create Google API key in Google AI Studio:**
+   - Visit your google AI Studio account and create API KEY : [GOOGLE AI STUDIO](https://aistudio.google.com/app/apikey)
+
+   - ![Create API KEY](google_key_14.jpg)
+   - ![Create API KEY](google_key_15.jpg)
+
+5. **Example code:**
+
+   ```python
+   import os
+   from google.colab import userdata
+   from langchain_google_genai import ChatGoogleGenerativeAI
+
+   # Replace 'YOUR_SECRET_NAME' with the actual name of your secret
+   google_api_key = userdata.get('GOOGLE_API_KEY')
+
+   llm = ChatGoogleGenerativeAI(
+      api_key=google_api_key,
+      model="gemini-1.5-flash",
+      temperature=0.2,
+   )
+
+   print(llm.invoke("hi"))
+   ```