\n",
"\n",
"In this tutorial we will learn how to launch Phoenix and upload traces using the client.\n",
"\n",
"As of Phoenix version `3.22.0`, the client has a `log_traces` method that allows you to upload a `TraceDataset` directly."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"First, let's download an example `TraceDataset`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from urllib.request import urlopen\n",
"\n",
"from phoenix.trace.trace_dataset import TraceDataset\n",
"from phoenix.trace.utils import json_lines_to_df\n",
"\n",
"traces_url = \"https://storage.googleapis.com/arize-phoenix-assets/datasets/unstructured/llm/context-retrieval/trace.jsonl\"\n",
"with urlopen(traces_url) as response:\n",
" lines = [line.decode(\"utf-8\") for line in response.readlines()]\n",
"trace_ds = TraceDataset(json_lines_to_df(lines))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Launch Phoenix. You can open use Phoenix within your notebook or in a separate browser window by opening the URL."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import phoenix as px\n",
"\n",
"(session := px.launch_app()).view()\n",
"session_url = session.url"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Create a client and use `log_traces` to upload the `TraceDataset`. We can optionally add these traces to a specific project."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"client = px.Client(endpoint=session_url)\n",
"client.log_traces(trace_ds, project_name=\"old-traces\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"You should now see a view like this.\n",
"\n",
""
]
}
],
"metadata": {
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 2
}