langchain/docs/extras/modules/chains/how_to/call_methods.ipynb
Davis Chase 87e502c6bc
Doc refactor (#6300)
Co-authored-by: jacoblee93 <jacoblee93@gmail.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
2023-06-16 11:52:56 -07:00

181 lines
4.1 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Different call methods\n",
"\n",
"All classes inherited from `Chain` offer a few ways of running chain logic. The most direct one is by using `__call__`:"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'adjective': 'corny',\n",
" 'text': 'Why did the tomato turn red? Because it saw the salad dressing!'}"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chat = ChatOpenAI(temperature=0)\n",
"prompt_template = \"Tell me a {adjective} joke\"\n",
"llm_chain = LLMChain(llm=chat, prompt=PromptTemplate.from_template(prompt_template))\n",
"\n",
"llm_chain(inputs={\"adjective\": \"corny\"})"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"By default, `__call__` returns both the input and output key values. You can configure it to only return output key values by setting `return_only_outputs` to `True`."
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'text': 'Why did the tomato turn red? Because it saw the salad dressing!'}"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"llm_chain(\"corny\", return_only_outputs=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"If the `Chain` only outputs one output key (i.e. only has one element in its `output_keys`), you can use `run` method. Note that `run` outputs a string instead of a dictionary."
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['text']"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# llm_chain only has one output key, so we can use run\n",
"llm_chain.output_keys"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Why did the tomato turn red? Because it saw the salad dressing!'"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"llm_chain.run({\"adjective\": \"corny\"})"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"In the case of one input key, you can input the string directly without specifying the input mapping."
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'adjective': 'corny',\n",
" 'text': 'Why did the tomato turn red? Because it saw the salad dressing!'}"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# These two are equivalent\n",
"llm_chain.run({\"adjective\": \"corny\"})\n",
"llm_chain.run(\"corny\")\n",
"\n",
"# These two are also equivalent\n",
"llm_chain(\"corny\")\n",
"llm_chain({\"adjective\": \"corny\"})"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Tips: You can easily integrate a `Chain` object as a `Tool` in your `Agent` via its `run` method. See an example [here](../agents/tools/custom_tools.html)."
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.11.3"
},
"vscode": {
"interpreter": {
"hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
}
}
},
"nbformat": 4,
"nbformat_minor": 4
}