@arizeai/phoenix-mcp

{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "<center>\n", " <p style=\"text-align:center\">\n", " <img alt=\"phoenix logo\" src=\"https://storage.googleapis.com/arize-phoenix-assets/assets/phoenix-logo-light.svg\" width=\"200\"/>\n", " <br>\n", " <a href=\"https://arize.com/docs/phoenix/\">Docs</a>\n", " |\n", " <a href=\"https://github.com/Arize-ai/phoenix\">GitHub</a>\n", " |\n", " <a href=\"https://arize-ai.slack.com/join/shared_invite/zt-2w57bhem8-hq24MB6u7yE_ZF_ilOYSBw#/shared-invite/email\">Community</a>\n", " </p>\n", "</center>\n", "\n", "# Google GenAI SDK - Building a Sequential Agent" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Install Dependencies" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "!pip install -q google-genai arize-phoenix-otel openinference-instrumentation-google-genai" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Connect to Arize Phoenix" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import os\n", "from getpass import getpass\n", "\n", "from google import genai\n", "\n", "from phoenix.otel import register\n", "\n", "if \"PHOENIX_API_KEY\" not in os.environ:\n", " os.environ[\"PHOENIX_API_KEY\"] = getpass(\"🔑 Enter your Phoenix API key: \")\n", "\n", "if \"PHOENIX_COLLECTOR_ENDPOINT\" not in os.environ:\n", " os.environ[\"PHOENIX_COLLECTOR_ENDPOINT\"] = getpass(\"🔑 Enter your Phoenix Collector Endpoint\")\n", "\n", "tracer_provider = register(auto_instrument=True, project_name=\"google-genai-sequential-agent\")\n", "tracer = tracer_provider.get_tracer(__name__)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Authenticate with Google Vertex AI" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "!gcloud auth login" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# Create a client using the Vertex AI API, you could also use the Google GenAI API instead here\n", "client = genai.Client(vertexai=True, project=\"<ADD YOUR GCP PROJECT ID>\", location=\"us-central1\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Sequential Agent" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# --- 1. Define helper methods ---\n", "\n", "\n", "def get_model(model_name):\n", " \"\"\"Instantiate and return a model.\"\"\"\n", " return model_name\n", "\n", "\n", "@tracer.chain\n", "def research_topic(client, model, user_input):\n", " \"\"\"Research a topic based on user input.\"\"\"\n", " research_prompt = (\n", " \"You are a research assistant.\\n\"\n", " \"Provide a comprehensive overview of the following topic.\\n\"\n", " \"Include key facts, historical context, and current relevance.\\n\"\n", " \"Keep your response to 3-4 paragraphs.\\n\"\n", " \"User Input: \"\n", " )\n", " research_response = client.models.generate_content(\n", " model=model,\n", " contents=research_prompt + user_input,\n", " )\n", " return research_response.text.strip()\n", "\n", "\n", "@tracer.chain\n", "def identify_key_points(client, model, research):\n", " \"\"\"Extract key points from the research.\"\"\"\n", " key_points_prompt = (\n", " \"You are a research summarizer.\\n\"\n", " \"Extract 5-7 key points from the following research.\\n\"\n", " \"Format each point as a bullet point with a brief explanation.\\n\\n\"\n", " f\"Research:\\n{research}\"\n", " )\n", " key_points_response = client.models.generate_content(model=model, contents=key_points_prompt)\n", " return key_points_response.text.strip()\n", "\n", "\n", "@tracer.chain\n", "def generate_future_directions(client, model, research, key_points):\n", " \"\"\"Generate future research directions based on the research and key points.\"\"\"\n", " future_prompt = (\n", " \"You are a research strategist.\\n\"\n", " \"Based on the research and key points provided, suggest 3-4 promising future research directions.\\n\"\n", " \"For each direction, explain its potential significance and impact.\\n\\n\"\n", " f\"Research:\\n{research}\\n\\n\"\n", " f\"Key Points:\\n{key_points}\\n\\n\"\n", " )\n", " future_response = client.models.generate_content(model=model, contents=future_prompt)\n", " return future_response.text.strip()\n", "\n", "\n", "# --- 2. Main execution ---\n", "@tracer.agent()\n", "def run_agent(user_input):\n", " # Instantiate the models\n", " research_model = get_model(\"gemini-2.0-flash-001\")\n", "\n", " # Step 1: Generate the initial research\n", " initial_research = research_topic(client, research_model, user_input)\n", "\n", " # Step 2: Identify key points from the research\n", " extracted_key_points = identify_key_points(client, research_model, initial_research)\n", "\n", " # Step 3: Generate future research directions\n", " future_directions = generate_future_directions(\n", " client, research_model, initial_research, extracted_key_points\n", " )\n", "\n", " # Display the results\n", " print(\"=== Initial Research ===\\n\")\n", " print(initial_research)\n", " print(\"\\n=== Key Points ===\\n\")\n", " print(extracted_key_points)\n", " print(\"\\n=== Future Research Directions ===\\n\")\n", " print(future_directions)\n", "\n", " return {\n", " \"research\": initial_research,\n", " \"key_points\": extracted_key_points,\n", " \"future_directions\": future_directions,\n", " }\n", "\n", "\n", "run_agent(user_input=input(\"Please enter a topic you'd like to research: \"))" ] } ], "metadata": { "language_info": { "name": "python" } }, "nbformat": 4, "nbformat_minor": 2 }