forked from Archives/langchain
131 lines
3.2 KiB
Plaintext
131 lines
3.2 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "872bb8b5",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Transformation Chain\n",
|
|
"\n",
|
|
"This notebook showcases using a generic transformation chain.\n",
|
|
"\n",
|
|
"As an example, we will create a dummy transformation that takes in a super long text, filters the text to only the first 3 paragraphs, and then passes that into an LLMChain to summarize those."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"id": "bbbb4330",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.chains import TransformChain, LLMChain, SimpleSequentialChain\n",
|
|
"from langchain.llms import OpenAI\n",
|
|
"from langchain.prompts import PromptTemplate"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "8ae5937c",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"with open(\"../../state_of_the_union.txt\") as f:\n",
|
|
" state_of_the_union = f.read()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "98739592",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def transform_func(inputs: dict) -> dict:\n",
|
|
" text = inputs[\"text\"]\n",
|
|
" shortened_text = \"\\n\\n\".join(text.split(\"\\n\\n\")[:3])\n",
|
|
" return {\"output_text\": shortened_text}\n",
|
|
"\n",
|
|
"transform_chain = TransformChain(input_variables=[\"text\"], output_variables=[\"output_text\"], transform=transform_func)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"id": "e9397934",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"template = \"\"\"Summarize this text:\n",
|
|
"\n",
|
|
"{output_text}\n",
|
|
"\n",
|
|
"Summary:\"\"\"\n",
|
|
"prompt = PromptTemplate(input_variables=[\"output_text\"], template=template)\n",
|
|
"llm_chain = LLMChain(llm=OpenAI(), prompt=prompt)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"id": "06f51f17",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"sequential_chain = SimpleSequentialChain(chains=[transform_chain, llm_chain])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"id": "f7caa1ee",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"' The speaker addresses the nation, noting that while last year they were kept apart due to COVID-19, this year they are together again. They are reminded that regardless of their political affiliations, they are all Americans.'"
|
|
]
|
|
},
|
|
"execution_count": 7,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"sequential_chain.run(state_of_the_union)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "e3ca6409",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"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": "3.9.1"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|