forked from Archives/langchain
add memory to llm chain notebook (#193)
Harrison Chase
2 years ago
committed by
GitHub
parent
199794086d
commit
f18a08f58d
@ -0,0 +1,177 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "00695447",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Adding Memory To an LLMChain\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use the Memory class with an arbitrary chain. For the purposes of this walkthrough, we will add `ConversationBufferMemory` to a `LLMChain`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "9f1aaf47",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chains.conversation.memory import ConversationBufferMemory\n",
|
||||
"from langchain import OpenAI, LLMChain, PromptTemplate"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4b066ced",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The most important step is setting up the prompt correctly. In the below prompt, we have two input keys: one for the actual input, another for the input from the Memory class. Importantly, we make sure the keys in the PromptTemplate and the ConversationBufferMemory match up (`chat_history`)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "e5501eda",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"template = \"\"\"You are a chatbot having a conversation with a human.\n",
|
||||
"\n",
|
||||
"{chat_history}\n",
|
||||
"Human: {human_input}\n",
|
||||
"Chatbot:\"\"\"\n",
|
||||
"\n",
|
||||
"prompt = PromptTemplate(\n",
|
||||
" input_variables=[\"chat_history\", \"human_input\"], \n",
|
||||
" template=template\n",
|
||||
")\n",
|
||||
"memory = ConversationBufferMemory(dynamic_key=\"chat_history\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "f6566275",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm_chain = LLMChain(\n",
|
||||
" llm=OpenAI(), \n",
|
||||
" prompt=prompt, \n",
|
||||
" verbose=True, \n",
|
||||
" memory=memory,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "e2b189dc",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mYou are a chatbot having a conversation with a human.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Human: Hi there my friend\n",
|
||||
"Chatbot:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'\\n\\nHi there my friend! Thank you for talking with me.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"llm_chain.predict(human_input=\"Hi there my friend\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "a902729f",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mYou are a chatbot having a conversation with a human.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Human: Hi there my friend\n",
|
||||
"AI: \n",
|
||||
"\n",
|
||||
"Hi there my friend! Thank you for talking with me.\n",
|
||||
"Human: Not to bad - how are you?\n",
|
||||
"Chatbot:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"\\n\\nI'm doing well, thank you for asking. How about you?\""
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"llm_chain.predict(human_input=\"Not to bad - how are you?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "ae5309bb",
|
||||
"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": "3.7.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
Loading…
Reference in New Issue