update

README.md

@@ -1,2 +1,14 @@
-# haystack-coookbook
-👩🏻‍🍳 A collection of example notebooks
+# 👩🏻‍🍳 Haystack Cookbook
+A collection of example notebooks using Haystack 👇
+
+| Name | Colab|
+| ---- | ---- |
+| Use Gemini Models with Vertex AI| <a href="https://colab.research.google.com/github/deepset-ai/haystack-cookbook/blob/main/vertexai-gemini-examples.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>|
+
+## How to Contribute to this repository
+
+If you have an example that uses Haystack, you can add it to this repository by creating a PR. You can also create a PR from Colab by creating a Fork of this repository and selecting "Save a Copy to GitHub". Once you add your example to your fork, you can create a PR onto this repository. 
+
+1. Add your Notebook
+2. Give a descriptive name to your file that includes the names of (if applicable) the model providers, databases the technologies you use in your example and/or the task you are completing in the example.
+3. Make sure to add a row in the table above 🎉

vertexai-gemini-examples.ipynb

@@ -1,15 +1,5 @@
 {
  "cells": [
- {
- "cell_type": "markdown",
- "metadata": {
- "id": "view-in-github",
- "colab_type": "text"
- },
- "source": [
- "<a href=\"https://colab.research.google.com/github/TuanaCelik/haystack-cookbook/blob/main/vertexai-gemini-examples.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
- ]
- },
  {
  "cell_type": "markdown",
  "metadata": {
@@ -28,6 +18,10 @@
  },
  {
  "cell_type": "markdown",
+ "metadata": {
+ "colab_type": "toc",
+ "id": "kWU_3yqtloif"
+ },
  "source": [
  ">[Haystack 2.0 💙 Google Gemini](#scrollTo=b2s1IpH6OGZQ)\n",
  "\n",
@@ -43,14 +37,13 @@
  "\n",
  ">>[Build a full Retrieval-Augmented Generation Pipeline with gemini-pro-vision](#scrollTo=Pi37EVlDenPw)\n",
  "\n"
- ],
- "metadata": {
- "colab_type": "toc",
- "id": "kWU_3yqtloif"
- }
+ ]
  },
  {
  "cell_type": "markdown",
+ "metadata": {
+ "id": "XromVwB1nQ76"
+ },
  "source": [
  "## Install dependencies\n",
  "\n",
@@ -59,10 +52,7 @@
  "First thing first we need to install our dependencies.\n",
  "\n",
  "(You can ignore the pip dependency error for `cohere` and `tiktoken`, that's irrelevant for our purposes.)"
- ],
- "metadata": {
- "id": "XromVwB1nQ76"
- }
+ ]
  },
  {
  "cell_type": "code",
@@ -124,23 +114,23 @@
  },
  {
  "cell_type": "markdown",
- "source": [
- "## Use `gemini-pro-vision`"
- ],
  "metadata": {
  "id": "08TA9zAQlqy6"
- }
+ },
+ "source": [
+ "## Use `gemini-pro-vision`"
+ ]
  },
  {
  "cell_type": "markdown",
+ "metadata": {
+ "id": "c1ynAXT5mI1s"
+ },
  "source": [
  "### Answer Questions\n",
  "\n",
  "Now that we setup everything we can create an instance of our Gemini component."
- ],
- "metadata": {
- "id": "c1ynAXT5mI1s"
- }
+ ]
  },
  {
  "cell_type": "code",
@@ -181,12 +171,12 @@
  },
  {
  "cell_type": "markdown",
- "source": [
- "### Answer Questions about Images"
- ],
  "metadata": {
  "id": "H3pU-t_7mPyH"
- }
+ },
+ "source": [
+ "### Answer Questions about Images"
+ ]
  },
  {
  "cell_type": "markdown",
@@ -224,25 +214,25 @@
  },
  {
  "cell_type": "markdown",
- "source": [
- "Next, let's run the `GeminiGenerator` component on it's own."
- ],
  "metadata": {
  "id": "tQsdovv2pWzh"
- }
+ },
+ "source": [
+ "Next, let's run the `GeminiGenerator` component on it's own."
+ ]
  },
  {
  "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "6jSBGEkmpPsN"
+ },
+ "outputs": [],
  "source": [
  "result = gemini.run(parts = [\"What can you tell me about this robots?\", *images])\n",
  "for answer in result[\"answers\"]:\n",
  " print(answer)"
- ],
- "metadata": {
- "id": "6jSBGEkmpPsN"
- },
- "execution_count": null,
- "outputs": []
+ ]
  },
  {
  "cell_type": "markdown",
@@ -255,15 +245,18 @@
  },
  {
  "cell_type": "markdown",
- "source": [
- "## Function Calling with `gemini-pro`"
- ],
  "metadata": {
  "id": "gLIIQ4PZmX-H"
- }
+ },
+ "source": [
+ "## Function Calling with `gemini-pro`"
+ ]
  },
  {
  "cell_type": "markdown",
+ "metadata": {
+ "id": "iCiSz840mfME"
+ },
  "source": [
  "With `gemini-pro`, we can also start introducing function calling!\n",
  "So let's see how we can do that 👇\n",
@@ -273,31 +266,28 @@
  "First we create our function definition and tool.\n",
  "\n",
  "For demonstration purposes, we're simply creating a `get_current_weather` function that returns an object which will _always_ tell us it's 'Sunny, and 21.8 degrees'.. If it's Celsius, that's a good day! ☀️"
- ],
- "metadata": {
- "id": "iCiSz840mfME"
- }
+ ]
  },
  {
  "cell_type": "code",
- "source": [
- "def get_current_weather(location: str, unit: str = \"celsius\"):\n",
- " return {\"weather\": \"sunny\", \"temperature\": 21.8, \"unit\": unit}"
- ],
+ "execution_count": null,
  "metadata": {
  "id": "4Wa_IoDDNg9V"
  },
- "execution_count": null,
- "outputs": []
+ "outputs": [],
+ "source": [
+ "def get_current_weather(location: str, unit: str = \"celsius\"):\n",
+ " return {\"weather\": \"sunny\", \"temperature\": 21.8, \"unit\": unit}"
+ ]
  },
  {
  "cell_type": "markdown",
- "source": [
- "Now we have to provide this function as a `Tool` to Gemini. So, first we need to create a `FunctionDeclaration` that _explains_ this function to Gemini 👇"
- ],
  "metadata": {
  "id": "GjapaK2yq-ce"
- }
+ },
+ "source": [
+ "Now we have to provide this function as a `Tool` to Gemini. So, first we need to create a `FunctionDeclaration` that _explains_ this function to Gemini 👇"
+ ]
  },
  {
  "cell_type": "code",
@@ -385,6 +375,11 @@
  },
  {
  "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "c-DurWKOOSOk"
+ },
+ "outputs": [],
  "source": [
  "\n",
  "weather = get_current_weather(**res[\"replies\"][0].content)\n",
@@ -393,42 +388,42 @@
  "\n",
  "res = gemini_chat.run(messages = messages)\n",
  "res[\"replies\"][0].content"
- ],
- "metadata": {
- "id": "c-DurWKOOSOk"
- },
- "execution_count": null,
- "outputs": []
+ ]
  },
  {
  "cell_type": "markdown",
- "source": [
- "Seems like the weather is nice and sunny, remember to put on your sunglasses. 😎"
- ],
  "metadata": {
  "id": "YsiwN7dbOwSW"
- }
+ },
+ "source": [
+ "Seems like the weather is nice and sunny, remember to put on your sunglasses. 😎"
+ ]
  },
  {
  "cell_type": "markdown",
- "source": [
- "## Build a full Retrieval-Augmented Generation Pipeline with `gemini-pro-vision`"
- ],
  "metadata": {
  "id": "Pi37EVlDenPw"
- }
+ },
+ "source": [
+ "## Build a full Retrieval-Augmented Generation Pipeline with `gemini-pro-vision`"
+ ]
  },
  {
  "cell_type": "markdown",
- "source": [
- "As a final exercise, let's add the `GeminiGenerator` to a full RAG pipeline. In the example below, we are building a RAG pipeline that does question answering on the web, using `gemini-pro-vision`"
- ],
  "metadata": {
  "id": "fQz9_N46hniU"
- }
+ },
+ "source": [
+ "As a final exercise, let's add the `GeminiGenerator` to a full RAG pipeline. In the example below, we are building a RAG pipeline that does question answering on the web, using `gemini-pro-vision`"
+ ]
  },
  {
  "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "43QF7y1PhRQn"
+ },
+ "outputs": [],
  "source": [
  "from haystack.components.fetchers.link_content import LinkContentFetcher\n",
  "from haystack.components.converters import HTMLToDocument\n",
@@ -468,24 +463,24 @@
  "pipeline.connect(\"splitter.documents\", \"ranker.documents\")\n",
  "pipeline.connect(\"ranker.documents\", \"prompt_builder.documents\")\n",
  "pipeline.connect(\"prompt_builder.prompt\", \"gemini\")"
- ],
- "metadata": {
- "id": "43QF7y1PhRQn"
- },
- "execution_count": null,
- "outputs": []
+ ]
  },
  {
  "cell_type": "markdown",
- "source": [
- "Let's try asking Gemini to tell us about Haystack 2.0 and how to use it."
- ],
  "metadata": {
  "id": "cGqt94B0fZi1"
- }
+ },
+ "source": [
+ "Let's try asking Gemini to tell us about Haystack 2.0 and how to use it."
+ ]
  },
  {
  "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "EhEx8xO7jMf9"
+ },
+ "outputs": [],
  "source": [
  "question = \"What do graphs have to do with Haystack?\"\n",
  "result = pipeline.run({\"prompt_builder\": {\"question\": question},\n",
@@ -494,27 +489,26 @@
  "\n",
  "for answer in result[\"gemini\"][\"answers\"]:\n",
  " print(answer)"
- ],
- "metadata": {
- "id": "EhEx8xO7jMf9"
- },
- "execution_count": null,
- "outputs": []
+ ]
  },
  {
  "cell_type": "markdown",
+ "metadata": {
+ "id": "xk2SAGT_l25K"
+ },
  "source": [
  "Now you've seen some of what Gemini can do, as well as how to integrate it with Haystack 2.0. If you want to learn more:\n",
  "- check out the Haystack [docs](https://docs.haystack.deepset.ai/v2.0/docs) or [tutorials](https://haystack.deepset.ai/tutorials)\n",
  "- Try out the [Gemini quickstart colab from Google](https://colab.research.google.com/github/google/generative-ai-docs/blob/main/site/en/tutorials/python_quickstart.ipynb#scrollTo=IqFXdgDFRvlU)\n",
  "- Participate in the [Advent of Haystack](https://haystack.deepset.ai/advent-of-haystack)"
- ],
- "metadata": {
- "id": "xk2SAGT_l25K"
- }
+ ]
  }
  ],
  "metadata": {
+ "colab": {
+ "include_colab_link": true,
+ "provenance": []
+ },
  "kernelspec": {
  "display_name": "google-vertex-haystack",
  "language": "python",
@@ -531,12 +525,8 @@
  "nbconvert_exporter": "python",
  "pygments_lexer": "ipython3",
  "version": "3.10.9"
- },
- "colab": {
- "provenance": [],
- "include_colab_link": true
  }
  },
  "nbformat": 4,
  "nbformat_minor": 0
-}
+}