@arizeai/phoenix-mcp

{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "4kPKrMTP_n_j" }, "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", "<h1 align=\"center\">Setting up Sessions</h1>\n", "\n", "A Session is a sequence of traces representing a single session (e.g. a session or a thread). Each response is represented as it's own trace, but these traces are linked together by being part of the same session.\n", "To associate traces together, you need to pass in a special metadata key where the value is the unique identifier for that thread.\n", "\n", "In this tutorial we will setup sessions using OpenAI and OpenInference instrumentation." ] }, { "cell_type": "markdown", "metadata": { "id": "9y1DA5uu_n_k" }, "source": [ "## 1. Install Dependencies and Import Libraries\n", "\n", "Install dependencies." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "!pip install \"openai>=1.0.0\" arize-phoenix jsonschema openinference-instrumentation-openai openinference-instrumentation opentelemetry-api opentelemetry-sdk openinference-semantic-conventions" ] }, { "cell_type": "markdown", "metadata": { "id": "u9xTBlt__n_l" }, "source": [ "## Configure Your OpenAI API Key and Instantiate Your OpenAI Client\n", "\n", "Set your OpenAI API key if it is not already set as an environment variable." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import os\n", "from getpass import getpass\n", "\n", "from openai import OpenAI\n", "\n", "if not (openai_api_key := os.getenv(\"OPENAI_API_KEY\")):\n", " openai_api_key = getpass(\"🔑 Enter your OpenAI API key: \")\n", "client = OpenAI(api_key=openai_api_key)" ] }, { "cell_type": "markdown", "metadata": { "id": "hY0NliPg_n_l" }, "source": [ "## Instrument Your OpenAI Client\n", "\n", "Instrument your OpenAI client with a tracer that emits telemetry data in OpenInference format. [OpenInference](https://arize-ai.github.io/open-inference-spec/trace/) is an open standard for capturing and storing LLM application traces that enables LLM applications to seamlessly integrate with LLM observability solutions such as Phoenix." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from openinference.instrumentation.openai import OpenAIInstrumentor\n", "\n", "from phoenix.otel import register\n", "\n", "tracer_provider = register(project_name=\"openai-sessions-example\")\n", "OpenAIInstrumentor().instrument(tracer_provider=tracer_provider)" ] }, { "cell_type": "markdown", "metadata": { "id": "MhVjxN_R_n_l" }, "source": [ "## Run Phoenix in the Background\n", "\n", "Launch Phoenix as a background session to collect the trace data emitted by your instrumented OpenAI client. Note that Phoenix should be run in a container in a production environment." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import phoenix as px\n", "\n", "px.launch_app().view()" ] }, { "cell_type": "markdown", "metadata": { "id": "VoLsIY9o_n_m" }, "source": [ "## Create a bare-bones Agent\n", "\n", "Let's create the outline of an agent that will leverage OpenAI." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "import uuid\n", "\n", "from openinference.instrumentation import using_session\n", "from openinference.semconv.trace import SpanAttributes\n", "from opentelemetry import trace\n", "\n", "session_id = str(uuid.uuid4())\n", "\n", "tracer = trace.get_tracer(__name__)\n", "\n", "\n", "@tracer.start_as_current_span(\n", " name=\"agent\", attributes={SpanAttributes.OPENINFERENCE_SPAN_KIND: \"agent\"}\n", ")\n", "def assistant(\n", " messages: list[dict],\n", " session_id: str,\n", "):\n", " current_span = trace.get_current_span()\n", " current_span.set_attribute(SpanAttributes.SESSION_ID, session_id)\n", " current_span.set_attribute(SpanAttributes.INPUT_VALUE, messages[-1].get(\"content\"))\n", "\n", " # Propagate the session_id down to spans crated by the OpenAI instrumentation\n", " # This is not strictly necessary, but it helps to correlate the spans to the same session\n", " with using_session(session_id):\n", " response = (\n", " client.chat.completions.create(\n", " model=\"gpt-3.5-turbo\",\n", " messages=[{\"role\": \"system\", \"content\": \"You are a helpful assistant.\"}] + messages,\n", " )\n", " .choices[0]\n", " .message\n", " )\n", "\n", " current_span.set_attribute(SpanAttributes.OUTPUT_VALUE, response.content)\n", " return response\n", "\n", "\n", "messages = [{\"role\": \"user\", \"content\": \"hi! im bob\"}]\n", "response = assistant(\n", " messages,\n", " session_id=session_id,\n", ")\n", "messages = messages + [response, {\"role\": \"user\", \"content\": \"what's my name?\"}]\n", "response = assistant(\n", " messages,\n", " session_id=session_id,\n", ")\n", "messages = messages + [response, {\"role\": \"user\", \"content\": \"what's 4+5?\"}]\n", "response = assistant(\n", " messages,\n", " session_id=session_id,\n", ")" ] } ], "metadata": { "language_info": { "name": "python" } }, "nbformat": 4, "nbformat_minor": 0 }