Feature - Portkey tracing integration

examples/tracing/portkey/portkey_tracing.ipynb

@@ -0,0 +1,152 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openlayer-ai/openlayer-python/blob/main/examples/tracing/portkey/portkey_tracing.ipynb)\n",
+        "\n",
+        "\n",
+        "# <a id=\"top\">Portkey monitoring quickstart</a>\n",
+        "\n",
+        "This notebook illustrates how to get started monitoring Portkey completions with Openlayer.\n",
+        "\n",
+        "Portkey provides a unified interface to call 100+ LLM APIs using the same input/output format. This integration allows you to trace and monitor completions across all supported providers through a single interface.\n",
+        "\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "!pip install openlayer portkey-ai"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 1. Set the environment variables\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "from portkey_ai import Portkey\n",
+        "\n",
+        "\n",
+        "# Set your Portkey API keys\n",
+        "os.environ['PORTKEY_API_KEY'] = \"YOUR_PORTKEY_API_HERE\"\n",
+        "\n",
+        "# Openlayer env variables\n",
+        "os.environ[\"OPENLAYER_API_KEY\"] = \"YOUR_OPENLAYER_API_KEY_HERE\"\n",
+        "os.environ[\"OPENLAYER_INFERENCE_PIPELINE_ID\"] = \"YOUR_OPENLAYER_INFERENCE_PIPELINE_ID_HERE\"\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 2. Enable Portkey tracing\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 5,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from openlayer.lib import trace_portkey\n",
+        "\n",
+        "# Enable openlayer tracing for all Portkey completions\n",
+        "trace_portkey()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 3. Use Portkey normally - tracing happens automatically!\n",
+        "\n",
+        "### Basic completion with OpenAI\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "# Basic portkey client initialization\n",
+        "portkey = Portkey(\n",
+        "    api_key = os.environ['PORTKEY_API_KEY'],\n",
+        "    config = \"YOUR_PORTKEY_CONFIG_ID_HERE\", # optional your portkey config id\n",
+        ")\n",
+        "\n",
+        "# Basic portkey LLM call\n",
+        "response = portkey.chat.completions.create(\n",
+        "    #model = \"@YOUR_PORTKEY_SLUG/YOUR_MODEL_NAME\", # optional if giving config\n",
+        "    messages = [\n",
+        "        {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n",
+        "        {\"role\": \"user\", \"content\": \"Write a poem on Argentina, least 500 words.\"}\n",
+        "    ]\n",
+        ")\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 3. View your traces\n",
+        "\n",
+        "Once you've run the examples above, you can:\n",
+        "\n",
+        "1. **Visit your OpenLayer dashboard** to see all the traced completions\n",
+        "2. **Analyze performance** across different models and providers\n",
+        "3. **Monitor costs** and token usage\n",
+        "4. **Debug issues** with detailed request/response logs\n",
+        "5. **Compare models** side-by-side\n",
+        "\n",
+        "The traces will include:\n",
+        "- **Request details**: Model, parameters, messages\n",
+        "- **Response data**: Generated content, token counts, latency\n",
+        "- **Provider information**: Which underlying service was used\n",
+        "- **Custom metadata**: Any additional context you provide\n",
+        "\n",
+        "For more information, check out:\n",
+        "- [OpenLayer Documentation](https://docs.openlayer.com/)\n",
+        "- [Portkey Documentation](https://portkey.ai/docs)\n",
+        "- [Portkey AI Gateway](https://portkey.ai/docs/product/ai-gateway)\n",
+        "- [Portkey Supported Providers](https://portkey.ai/docs/api-reference/inference-api/supported-providers)\n"
+      ]
+    }
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3",
+      "language": "python",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.9.6"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}

src/openlayer/lib/__init__.py

@@ -14,6 +14,7 @@
     "trace_oci_genai",
     "trace_oci",  # Alias for backward compatibility
     "trace_litellm",
+    "trace_portkey",
     "trace_google_adk",
     "unpatch_google_adk",
     "update_current_trace",
@@ -192,6 +193,41 @@ def trace_litellm():
     return litellm_tracer.trace_litellm()
 
 
+# ---------------------------------- Portkey ---------------------------------- #
+def trace_portkey():
+    """Enable tracing for Portkey completions.
+
+    This function patches Portkey's chat.completions.create to automatically trace
+    all OpenAI-compatible completions routed via the Portkey AI Gateway.
+
+    Example:
+        >>> from portkey_ai import Portkey
+        >>> from openlayer.lib import trace_portkey
+        >>> # Enable openlayer tracing for all Portkey completions
+        >>> trace_portkey()
+        >>> # Basic portkey client initialization    
+        >>> portkey = Portkey(
+        >>>     api_key = os.environ['PORTKEY_API_KEY'],
+        >>>     config = "YOUR_PORTKEY_CONFIG_ID", # optional your portkey config id
+        >>> )
+        >>> # use portkey normally - tracing happens automatically
+        >>> response = portkey.chat.completions.create(
+        >>>     #model = "@YOUR_PORTKEY_SLUG/YOUR_MODEL_NAME", # optional if giving config
+        >>>     messages = [
+        >>>         {"role": "system", "content": "You are a helpful assistant."},
+        >>>         {"role": "user", "content": "Write a poem on Argentina, least 100 words."}
+        >>>     ]
+        >>> )
+    """
+    # pylint: disable=import-outside-toplevel
+    try:
+        from portkey_ai import Portkey  # noqa: F401
+    except ImportError:
+        raise ImportError("portkey-ai is required for Portkey tracing. Install with: pip install portkey-ai")
+
+    from .integrations import portkey_tracer
+
+    return portkey_tracer.trace_portkey()
 # ------------------------------ Google ADK ---------------------------------- #
 def trace_google_adk():
     """Enable tracing for Google Agent Development Kit (ADK).