The agent engineering platform.
Python agentsaiai-agentsanthropicchatgptdeepagentsenterpriseframeworkgeminigenerative-ailangchainlanggraphllmmultiagentopen-sourceopenaipydanticpythonragtypescript
docs: how to pass runtime secrets (#24450)
Bagaturf101c759ed0e
diff --git a/docs/docs/how_to/index.mdx b/docs/docs/how_to/index.mdxindex 2c9f8d51c6..90d359422a 100644--- a/docs/docs/how_to/index.mdx+++ b/docs/docs/how_to/index.mdx@@ -44,6 +44,7 @@ This highlights functionality that is core to using LangChain.- [How to: inspect runnables](/docs/how_to/inspect)- [How to: add fallbacks to a runnable](/docs/how_to/fallbacks)- [How to: migrate chains to LCEL](/docs/how_to/migrate_chains)+- [How to: pass runtime secrets to a runnable](/docs/how_to/runnable_runtime_secrets)## Components@@ -199,6 +200,7 @@ LangChain [Tools](/docs/concepts/#tools) contain a description of the tool (to p- [How to: return artifacts from a tool](/docs/how_to/tool_artifacts/)- [How to: convert Runnables to tools](/docs/how_to/convert_runnable_to_tool)- [How to: add ad-hoc tool calling capability to models](/docs/how_to/tools_prompting)+- [How to: pass in runtime secrets](/docs/how_to/runnable_runtime_secrets)### Multimodaldiff --git a/docs/docs/how_to/runnable_runtime_secrets.ipynb b/docs/docs/how_to/runnable_runtime_secrets.ipynbnew file mode 100644index 0000000000..819cdf1cbe--- /dev/null+++ b/docs/docs/how_to/runnable_runtime_secrets.ipynb@@ -0,0 +1,78 @@+{+ "cells": [+ {+ "cell_type": "markdown",+ "id": "6fcd2994-0092-4fa3-9bb1-c9c84babadc5",+ "metadata": {},+ "source": [+ "# How to pass runtime secrets to runnables\n",+ "\n",+ ":::info Requires `langchain-core >= 0.2.22`\n",+ "\n",+ ":::\n",+ "\n",+ "We can pass in secrets to our runnables at runtime using the `RunnableConfig`. Specifically we can pass in secrets with a `__` prefix to the `configurable` field. This will ensure that these secrets aren't traced as part of the invocation:"+ ]+ },+ {+ "cell_type": "code",+ "execution_count": 6,+ "id": "92e42e91-c277-49de-aa7a-dfb5c993c817",+ "metadata": {},+ "outputs": [+ {+ "data": {+ "text/plain": [+ "7"+ ]+ },+ "execution_count": 6,+ "metadata": {},+ "output_type": "execute_result"+ }+ ],+ "source": [+ "from langchain_core.runnables import RunnableConfig\n",+ "from langchain_core.tools import tool\n",+ "\n",+ "\n",+ "@tool\n",+ "def foo(x: int, config: RunnableConfig) -> int:\n",+ " \"\"\"Sum x and a secret int\"\"\"\n",+ " return x + config[\"configurable\"][\"__top_secret_int\"]\n",+ "\n",+ "\n",+ "foo.invoke({\"x\": 5}, {\"configurable\": {\"__top_secret_int\": 2, \"traced_key\": \"bar\"}})"+ ]+ },+ {+ "cell_type": "markdown",+ "id": "ae3a4fb9-2ce7-46b2-b654-35dff0ae7197",+ "metadata": {},+ "source": [+ "Looking at the LangSmith trace for this run, we can see that \"traced_key\" was recorded (as part of Metadata) while our secret int was not: https://smith.langchain.com/public/aa7e3289-49ca-422d-a408-f6b927210170/r"+ ]+ }+ ],+ "metadata": {+ "kernelspec": {+ "display_name": "poetry-venv-311",+ "language": "python",+ "name": "poetry-venv-311"+ },+ "language_info": {+ "codemirror_mode": {+ "name": "ipython",+ "version": 3+ },+ "file_extension": ".py",+ "mimetype": "text/x-python",+ "name": "python",+ "nbconvert_exporter": "python",+ "pygments_lexer": "ipython3",+ "version": "3.11.9"+ }+ },+ "nbformat": 4,+ "nbformat_minor": 5+}