langchain/docs/extras/modules/memory/how_to/kg.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

357 lines
9.3 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"id": "44c9933a",
"metadata": {},
"source": [
"# Conversation Knowledge Graph Memory\n",
"\n",
"This type of memory uses a knowledge graph to recreate memory.\n",
"\n",
"Let's first walk through how to use the utilities"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "f71f40ba",
"metadata": {},
"outputs": [],
"source": [
"from langchain.memory import ConversationKGMemory\n",
"from langchain.llms import OpenAI"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "2f4a3c85",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)\n",
"memory = ConversationKGMemory(llm=llm)\n",
"memory.save_context({\"input\": \"say hi to sam\"}, {\"output\": \"who is sam\"})\n",
"memory.save_context({\"input\": \"sam is a friend\"}, {\"output\": \"okay\"})"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "72283b4f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'history': 'On Sam: Sam is friend.'}"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"memory.load_memory_variables({\"input\": \"who is sam\"})"
]
},
{
"cell_type": "markdown",
"id": "0c8ff11e",
"metadata": {},
"source": [
"We can also get the history as a list of messages (this is useful if you are using this with a chat model)."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "44df43af",
"metadata": {},
"outputs": [],
"source": [
"memory = ConversationKGMemory(llm=llm, return_messages=True)\n",
"memory.save_context({\"input\": \"say hi to sam\"}, {\"output\": \"who is sam\"})\n",
"memory.save_context({\"input\": \"sam is a friend\"}, {\"output\": \"okay\"})"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "4726b1c8",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'history': [SystemMessage(content='On Sam: Sam is friend.', additional_kwargs={})]}"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"memory.load_memory_variables({\"input\": \"who is sam\"})"
]
},
{
"cell_type": "markdown",
"id": "dc956b0e",
"metadata": {},
"source": [
"We can also more modularly get current entities from a new message (will use previous messages as context.)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "36331ca5",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['Sam']"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"memory.get_current_entities(\"what's Sams favorite color?\")"
]
},
{
"cell_type": "markdown",
"id": "e8749134",
"metadata": {},
"source": [
"We can also more modularly get knowledge triplets from a new message (will use previous messages as context.)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "b02d44db",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[KnowledgeTriple(subject='Sam', predicate='favorite color', object_='red')]"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"memory.get_knowledge_triplets(\"her favorite color is red\")"
]
},
{
"cell_type": "markdown",
"id": "f7a02ef3",
"metadata": {},
"source": [
"## Using in a chain\n",
"Let's now use this in a chain!"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "b462baf1",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)\n",
"from langchain.prompts.prompt import PromptTemplate\n",
"from langchain.chains import ConversationChain\n",
"\n",
"template = \"\"\"The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
"If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
"\n",
"Relevant Information:\n",
"\n",
"{history}\n",
"\n",
"Conversation:\n",
"Human: {input}\n",
"AI:\"\"\"\n",
"prompt = PromptTemplate(input_variables=[\"history\", \"input\"], template=template)\n",
"conversation_with_kg = ConversationChain(\n",
" llm=llm, verbose=True, prompt=prompt, memory=ConversationKGMemory(llm=llm)\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "97efaf38",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
"If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
"\n",
"Relevant Information:\n",
"\n",
"\n",
"\n",
"Conversation:\n",
"Human: Hi, what's up?\n",
"AI:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\" Hi there! I'm doing great. I'm currently in the process of learning about the world around me. I'm learning about different cultures, languages, and customs. It's really fascinating! How about you?\""
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation_with_kg.predict(input=\"Hi, what's up?\")"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "55b5bcad",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
"If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
"\n",
"Relevant Information:\n",
"\n",
"\n",
"\n",
"Conversation:\n",
"Human: My name is James and I'm helping Will. He's an engineer.\n",
"AI:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\" Hi James, it's nice to meet you. I'm an AI and I understand you're helping Will, the engineer. What kind of engineering does he do?\""
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation_with_kg.predict(\n",
" input=\"My name is James and I'm helping Will. He's an engineer.\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "9981e219",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
"If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
"\n",
"Relevant Information:\n",
"\n",
"On Will: Will is an engineer.\n",
"\n",
"Conversation:\n",
"Human: What do you know about Will?\n",
"AI:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"' Will is an engineer.'"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation_with_kg.predict(input=\"What do you know about Will?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8c09a239",
"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
}