"[PromptLayer](https://promptlayer.com) is a an LLM observability platform that lets you visualize requests, version prompts, and track usage. In this guide we will go over how to setup the `PromptLayerCallbackHandler`. \n",
"While PromptLayer does have LLMs that integrate directly with LangChain (e.g. [`PromptLayerOpenAI`](https://python.langchain.com/docs/integrations/llms/promptlayer_openai)), this callback is the recommended way to integrate PromptLayer with LangChain.\n",
"See [our docs](https://docs.promptlayer.com/languages/langchain) for more information."
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {
"tags": []
},
"source": [
"## Installation and Setup"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"!pip install promptlayer --upgrade"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### Getting API Credentials\n",
"\n",
"If you do not have a PromptLayer account, create one on [promptlayer.com](https://www.promptlayer.com). Then get an API key by clicking on the settings cog in the navbar and\n",
"set it as an environment variabled called `PROMPTLAYER_API_KEY`\n"
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### Usage\n",
"\n",
"Getting started with `PromptLayerCallbackHandler` is fairly simple, it takes two optional arguments:\n",
"1. `pl_tags` - an optional list of strings that will be tracked as tags on PromptLayer.\n",
"2. `pl_id_callback` - an optional function that will take `promptlayer_request_id` as an argument. This ID can be used with all of PromptLayer's tracking features to track, metadata, scores, and prompt usage."
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
"### Simple OpenAI Example\n",
"\n",
"In this simple example we use `PromptLayerCallbackHandler` with `ChatOpenAI`. We add a PromptLayer tag named `chatopenai`"
"In this example we unlock more of the power of PromptLayer.\n",
"\n",
"PromptLayer allows you to visually create, version, and track prompt templates. Using the [Prompt Registry](https://docs.promptlayer.com/features/prompt-registry), we can programatically fetch the prompt template called `example`.\n",
"\n",
"We also define a `pl_id_callback` function which takes in the `promptlayer_request_id` and logs a score, metadata and links the prompt template used. Read more about tracking on [our docs](https://docs.promptlayer.com/features/prompt-history/request-id)."
