forked from Archives/langchain
version 0.0.49 (#436)
Harrison Chase
1 year ago
committed by
GitHub
parent
f8b605293f
commit
0c5d3fd894
@ -1,11 +1,22 @@
|
||||
Memory
|
||||
======
|
||||
|
||||
The examples here are all related to working with the concept of Memory in LangChain.
|
||||
The examples here all highlight how to use memory in different ways.
|
||||
|
||||
`Adding Memory <memory/adding_memory.ipynb>`_: How to add a memory component to any chain.
|
||||
|
||||
`Conversational Memory Types <memory/conversational_memory.ipynb>`_: An overview of the different types of conversation memory you can load and use with a conversation-like chain.
|
||||
|
||||
`Conversational Memory Customization <memory/conversational_customization.ipynb>`_: How to customize existing conversation memory components.
|
||||
|
||||
`Custom Memory <memory/custom_memory.ipynb>`_: How to write your own custom memory component.
|
||||
|
||||
`Adding Memory to Agents <memory/agent_with_memory.ipynb>`_: How to add a memory component to any agent.
|
||||
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:glob:
|
||||
:caption: Memory
|
||||
:hidden:
|
||||
|
||||
memory/*
|
||||
@ -0,0 +1,262 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "69e35d6f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Conversational Memory Customization\n",
|
||||
"\n",
|
||||
"This notebook walks through a few ways to customize conversational memory.\n",
|
||||
"\n",
|
||||
"The main way to do so is by changing the AI prefix in the conversation summary. By default, this is set to \"AI\", but you can set this to be anything you want. Note that if you change this, you should also change the prompt used in the chain to reflect this naming change. Let's walk through an example of that in the example below."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "0f964494",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.chains import ConversationChain\n",
|
||||
"from langchain.chains.conversation.memory import ConversationBufferMemory\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"llm = OpenAI(temperature=0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "d0e66d87",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Here it is by default set to \"AI\"\n",
|
||||
"conversation = ConversationChain(\n",
|
||||
" llm=llm, \n",
|
||||
" verbose=True, \n",
|
||||
" memory=ConversationBufferMemory()\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "f8fa6999",
|
||||
"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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi there!\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" Hi there! It's nice to meet you. How can I help you today?\""
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.predict(input=\"Hi there!\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "de213386",
|
||||
"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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi there!\n",
|
||||
"AI: Hi there! It's nice to meet you. How can I help you today?\n",
|
||||
"Human: What's the weather?\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' The current weather is sunny and warm with a temperature of 75 degrees Fahrenheit. The forecast for the next few days is sunny with temperatures in the mid-70s.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.predict(input=\"What's the weather?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"id": "585949eb",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Now we can override it and set it to \"AI Assistant\"\n",
|
||||
"from langchain.prompts.prompt import PromptTemplate\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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"{history}\n",
|
||||
"Human: {input}\n",
|
||||
"AI Assistant:\"\"\"\n",
|
||||
"PROMPT = PromptTemplate(\n",
|
||||
" input_variables=[\"history\", \"input\"], template=template\n",
|
||||
")\n",
|
||||
"conversation = ConversationChain(\n",
|
||||
" prompt=PROMPT,\n",
|
||||
" llm=llm, \n",
|
||||
" verbose=True, \n",
|
||||
" memory=ConversationBufferMemory(ai_prefix=\"AI Assistant\")\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "1bb9bc53",
|
||||
"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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi there!\n",
|
||||
"AI Assistant:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" Hi there! It's nice to meet you. How can I help you today?\""
|
||||
]
|
||||
},
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.predict(input=\"Hi there!\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"id": "d9241923",
|
||||
"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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi there!\n",
|
||||
"AI Assistant: Hi there! It's nice to meet you. How can I help you today?\n",
|
||||
"Human: What's the weather?\n",
|
||||
"AI Assistant:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' The current weather is sunny and warm with a temperature of 75 degrees Fahrenheit. The forecast for the rest of the day is sunny with a high of 78 degrees and a low of 65 degrees.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.predict(input=\"What's the weather?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "1023b6ef",
|
||||
"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": "3.10.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@ -0,0 +1,724 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d31df93e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Conversational Memory\n",
|
||||
"\n",
|
||||
"This notebook walks through the different types of memory you can use with the `ConversationChain`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d051c1da",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### ConversationBufferMemory (default)\n",
|
||||
"By default, the `ConversationChain` uses `ConversationBufferMemory`: a simple type of memory that remembers all previous inputs/outputs and adds them to the context that is passed. Let's take a look at using this chain (setting `verbose=True` so we can see the prompt)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "54301321",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.chains import ConversationChain\n",
|
||||
"from langchain.chains.conversation.memory import ConversationBufferMemory\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"conversation = ConversationChain(\n",
|
||||
" llm=llm, \n",
|
||||
" verbose=True, \n",
|
||||
" memory=ConversationBufferMemory()\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "ae046bff",
|
||||
"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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi there!\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" Hi there! It's nice to meet you. How can I help you today?\""
|
||||
]
|
||||
},
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.predict(input=\"Hi there!\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "d8e2a6ff",
|
||||
"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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi there!\n",
|
||||
"AI: Hi there! It's nice to meet you. How can I help you today?\n",
|
||||
"Human: I'm doing well! Just having a conversation with an AI.\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" That's great! It's always nice to have a conversation with someone new. What would you like to talk about?\""
|
||||
]
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.predict(input=\"I'm doing well! Just having a conversation with an AI.\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "15eda316",
|
||||
"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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi there!\n",
|
||||
"AI: Hi there! It's nice to meet you. How can I help you today?\n",
|
||||
"Human: I'm doing well! Just having a conversation with an AI.\n",
|
||||
"AI: That's great! It's always nice to have a conversation with someone new. What would you like to talk about?\n",
|
||||
"Human: Tell me about yourself.\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" Sure! I'm an AI created to help people with their everyday tasks. I'm programmed to understand natural language and provide helpful information. I'm also constantly learning and updating my knowledge base so I can provide more accurate and helpful answers.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.predict(input=\"Tell me about yourself.\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4fad9448",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### ConversationSummaryMemory\n",
|
||||
"Now let's take a look at using a slightly more complex type of memory - `ConversationSummaryMemory`. This type of memory creates a summary of the conversation over time. This can be useful for condensing information from the conversation over time.\n",
|
||||
"\n",
|
||||
"Let's walk through an example, again setting `verbose=True` so we can see the prompt."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "f60a2fe8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chains.conversation.memory import ConversationSummaryMemory"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "b7274f2c",
|
||||
"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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi, what's up?\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" Hi there! I'm doing great. I'm currently helping a customer with a technical issue. How about you?\""
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation_with_summary = ConversationChain(\n",
|
||||
" llm=llm, \n",
|
||||
" memory=ConversationSummaryMemory(llm=OpenAI()),\n",
|
||||
" verbose=True\n",
|
||||
")\n",
|
||||
"conversation_with_summary.predict(input=\"Hi, what's up?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "a6b6b88f",
|
||||
"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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"The human greeted the AI, to which the AI replied that it was doing great and was helping a customer with a technical issue.\n",
|
||||
"Human: Tell me more about it!\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' Sure! The customer was having trouble with their computer not connecting to the internet. I was able to help them troubleshoot the issue and get them connected. It was a great feeling to be able to help them out!'"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation_with_summary.predict(input=\"Tell me more about it!\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "dad869fe",
|
||||
"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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"The human greeted the AI, to which the AI replied that it was doing great and was helping a customer with a technical issue. The AI explained the customer was having trouble with their computer not connecting to the internet and that it was a great feeling to be able to help them out and get them connected.\n",
|
||||
"Human: Very cool -- what is the scope of the project?\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" The scope of the project is to help the customer troubleshoot their computer and get it connected to the internet. I'm currently helping them identify the source of the issue and then providing them with the necessary steps to get their computer connected.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation_with_summary.predict(input=\"Very cool -- what is the scope of the project?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "6eecf9d9",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# ConversationBufferWindowMemory\n",
|
||||
"\n",
|
||||
"`ConversationBufferWindowMemory` keeps a list of the interactions of the conversation over time. It only uses the last K interactions. This can be useful for keeping a sliding window of the most recent interactions, so the buffer does not get too large\n",
|
||||
"\n",
|
||||
"Let's walk through an example, again setting `verbose=True` so we can see the prompt."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "2dac7769",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chains.conversation.memory import ConversationBufferWindowMemory"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "0b9da4cd",
|
||||
"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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi, what's up?\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" Hi there! I'm doing great. I'm currently helping a customer with a technical issue. How about you?\""
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation_with_summary = ConversationChain(\n",
|
||||
" llm=llm, \n",
|
||||
" # We set a low k=2, to only keep the last 2 interactions in memory\n",
|
||||
" memory=ConversationBufferWindowMemory(k=2), \n",
|
||||
" verbose=True\n",
|
||||
")\n",
|
||||
"conversation_with_summary.predict(input=\"Hi, what's up?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "90f73431",
|
||||
"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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"Human: Hi, what's up?\n",
|
||||
"AI: Hi there! I'm doing great. I'm currently helping a customer with a technical issue. How about you?\n",
|
||||
"Human: What's their issues?\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" The customer is having trouble connecting to their Wi-Fi network. I'm helping them troubleshoot the issue and get them connected.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation_with_summary.predict(input=\"What's their issues?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "cbb499e7",
|
||||
"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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"Human: Hi, what's up?\n",
|
||||
"AI: Hi there! I'm doing great. I'm currently helping a customer with a technical issue. How about you?\n",
|
||||
"Human: What's their issues?\n",
|
||||
"AI: The customer is having trouble connecting to their Wi-Fi network. I'm helping them troubleshoot the issue and get them connected.\n",
|
||||
"Human: Is it going well?\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" Yes, it's going well so far. We've already identified the problem and are now working on a solution.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation_with_summary.predict(input=\"Is it going well?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "0d209cfe",
|
||||
"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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"Human: What's their issues?\n",
|
||||
"AI: The customer is having trouble connecting to their Wi-Fi network. I'm helping them troubleshoot the issue and get them connected.\n",
|
||||
"Human: Is it going well?\n",
|
||||
"AI: Yes, it's going well so far. We've already identified the problem and are now working on a solution.\n",
|
||||
"Human: What's the solution?\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" The solution is to reset the router and reconfigure the settings. We're currently in the process of doing that.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Notice here that the first interaction does not appear.\n",
|
||||
"conversation_with_summary.predict(input=\"What's the solution?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a6d2569f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# ConversationSummaryBufferMemory\n",
|
||||
"\n",
|
||||
"`ConversationSummaryBufferMemory` combines the last two ideas. It keeps a buffer of recent interactions in memory, but rather than just completely flushing old interactions it compiles them into a summary and uses both. Unlike the previous implementation though, it uses token length rather than number of interactions to determine when to flush interactions.\n",
|
||||
"\n",
|
||||
"Let's walk through an example, again setting `verbose=True` so we can see the prompt."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "e583a661",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chains.conversation.memory import ConversationSummaryBufferMemory"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "ebd68c10",
|
||||
"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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi, what's up?\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" Hi there! I'm doing great. I'm currently helping a customer with a technical issue. How about you?\""
|
||||
]
|
||||
},
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation_with_summary = ConversationChain(\n",
|
||||
" llm=llm, \n",
|
||||
" # We set a very low max_token_limit for the purposes of testing.\n",
|
||||
" memory=ConversationSummaryBufferMemory(llm=OpenAI(), max_token_limit=40),\n",
|
||||
" verbose=True\n",
|
||||
")\n",
|
||||
"conversation_with_summary.predict(input=\"Hi, what's up?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"id": "86207a61",
|
||||
"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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"Human: Hi, what's up?\n",
|
||||
"AI: Hi there! I'm doing great. I'm currently helping a customer with a technical issue. How about you?\n",
|
||||
"Human: Just working on writing some documentation!\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' That sounds like a lot of work. What kind of documentation are you writing?'"
|
||||
]
|
||||
},
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation_with_summary.predict(input=\"Just working on writing some documentation!\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"id": "76a0ab39",
|
||||
"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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"The human asked the AI what it was up to and the AI replied that it was helping a customer with a technical issue.\n",
|
||||
"Human: Just working on writing some documentation!\n",
|
||||
"AI: That sounds like a lot of work. What kind of documentation are you writing?\n",
|
||||
"Human: For LangChain! Have you heard of it?\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' Yes, I have heard of LangChain. It is a blockchain-based language learning platform. Can you tell me more about the documentation you are writing?'"
|
||||
]
|
||||
},
|
||||
"execution_count": 16,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# We can see here that there is a summary of the conversation and then some previous interactions\n",
|
||||
"conversation_with_summary.predict(input=\"For LangChain! Have you heard of it?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"id": "8c669db1",
|
||||
"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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"The human asked the AI what it was up to and the AI replied that it was helping a customer with a technical issue. The human mentioned they were writing documentation for LangChain, a blockchain-based language learning platform, and the AI had heard of it and asked for more information.\n",
|
||||
"\n",
|
||||
"Human: Haha nope, although a lot of people confuse it for that\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' Oh, I see. So what is LangChain then?'"
|
||||
]
|
||||
},
|
||||
"execution_count": 17,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# We can see here that the summary and the buffer are updated\n",
|
||||
"conversation_with_summary.predict(input=\"Haha nope, although a lot of people confuse it for that\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "f71f40ba",
|
||||
"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": "3.10.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@ -1,333 +1,197 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d31df93e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Memory\n",
|
||||
"So far, all the chains and agents we've gone through have been stateless. But often, you may want a chain or agent to have some concept of \"memory\" so that it may remember information about its previous interactions. The clearest and simple example of this is when designing a chatbot - you want it to remember previous messages so it can use context from that to have a better conversation. This would be a type of \"short-term memory\". On the more complex side, you could imagine a chain/agent remembering key pieces of information over time - this would be a form of \"long-term memory\". For more concrete ideas on the latter, see this [awesome paper](https://memprompt.com/).\n",
|
||||
"\n",
|
||||
"LangChain provides several specially created chains just for this purpose. This notebook walks through using one of those chains (the `ConversationChain`) with two different types of memory."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d051c1da",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### ConversationChain with default memory\n",
|
||||
"By default, the `ConversationChain` has a simple type of memory that remembers all previous inputs/outputs and adds them to the context that is passed. Let's take a look at using this chain (setting `verbose=True` so we can see the prompt)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "ae046bff",
|
||||
"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;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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi there!\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' Hello! How are you today?'"
|
||||
]
|
||||
},
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain import OpenAI, ConversationChain\n",
|
||||
"\n",
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"conversation = ConversationChain(llm=llm, verbose=True)\n",
|
||||
"\n",
|
||||
"conversation.predict(input=\"Hi there!\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "d8e2a6ff",
|
||||
"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;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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi there!\n",
|
||||
"AI: Hello! How are you today?\n",
|
||||
"Human: I'm doing well! Just having a conversation with an AI.\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" That's great! What would you like to talk about?\""
|
||||
]
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.predict(input=\"I'm doing well! Just having a conversation with an AI.\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "15eda316",
|
||||
"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;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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi there!\n",
|
||||
"AI: Hello! How are you today?\n",
|
||||
"Human: I'm doing well! Just having a conversation with an AI.\n",
|
||||
"AI: That's great! What would you like to talk about?\n",
|
||||
"Human: Tell me about yourself.\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' I am an AI created to provide information and support to humans. I enjoy learning and exploring new things.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.predict(input=\"Tell me about yourself.\")"
|
||||
]
|
||||
},
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d31df93e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Memory\n",
|
||||
"So far, all the chains and agents we've gone through have been stateless. But often, you may want a chain or agent to have some concept of \"memory\" so that it may remember information about its previous interactions. The clearest and simple example of this is when designing a chatbot - you want it to remember previous messages so it can use context from that to have a better conversation. This would be a type of \"short-term memory\". On the more complex side, you could imagine a chain/agent remembering key pieces of information over time - this would be a form of \"long-term memory\". For more concrete ideas on the latter, see this [awesome paper](https://memprompt.com/).\n",
|
||||
"\n",
|
||||
"LangChain provides several specially created chains just for this purpose. This notebook walks through using one of those chains (the `ConversationChain`) with two different types of memory."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d051c1da",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### ConversationChain with default memory\n",
|
||||
"By default, the `ConversationChain` has a simple type of memory that remembers all previous inputs/outputs and adds them to the context that is passed. Let's take a look at using this chain (setting `verbose=True` so we can see the prompt)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "ae046bff",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4fad9448",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### ConversationChain with ConversationSummaryMemory\n",
|
||||
"Now let's take a look at using a slightly more complex type of memory - `ConversationSummaryMemory`. This type of memory creates a summary of the conversation over time. This can be useful for condensing information from the conversation over time.\n",
|
||||
"\n",
|
||||
"Let's walk through an example, again setting `verbose=True` so we can see the prompt."
|
||||
]
|
||||
"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;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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi there!\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "f60a2fe8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chains.conversation.memory import ConversationSummaryMemory"
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' Hello! How are you today?'"
|
||||
]
|
||||
},
|
||||
},
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain import OpenAI, ConversationChain\n",
|
||||
"\n",
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"conversation = ConversationChain(llm=llm, verbose=True)\n",
|
||||
"\n",
|
||||
"conversation.predict(input=\"Hi there!\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "d8e2a6ff",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "b7274f2c",
|
||||
"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;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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi, what's up?\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"\\n\\nI'm doing well, thank you for asking. I'm currently working on a project that I'm really excited about.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation_with_summary = ConversationChain(llm=llm, memory=ConversationSummaryMemory(llm=OpenAI()), verbose=True)\n",
|
||||
"conversation_with_summary.predict(input=\"Hi, what's up?\")"
|
||||
]
|
||||
"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;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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi there!\n",
|
||||
"AI: Hello! How are you today?\n",
|
||||
"Human: I'm doing well! Just having a conversation with an AI.\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "a6b6b88f",
|
||||
"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;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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"The human and artificial intelligence are talking. The human asked the AI what it is doing, and the AI said that it is working on a project that it is excited about.\n",
|
||||
"Human: Tell me more about it!\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"\\n\\nI'm working on a project that I'm really excited about. It's a lot of work, but I think it's going to be really great when it's finished. I can't wait to show it to you!\""
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation_with_summary.predict(input=\"Tell me more about it!\")"
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" That's great! What would you like to talk about?\""
|
||||
]
|
||||
},
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.predict(input=\"I'm doing well! Just having a conversation with an AI.\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "15eda316",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "dad869fe",
|
||||
"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;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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"The human and artificial intelligence are talking. The human asked the AI what it is doing, and the AI said that it is working on a project that it is excited about. The AI said that the project is a lot of work, but it is going to be great when it is finished.\n",
|
||||
"Human: Very cool -- what is the scope of the project?\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'\\n\\nThe project is quite large in scope. It involves a lot of data analysis and work with artificial intelligence algorithms.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation_with_summary.predict(input=\"Very cool -- what is the scope of the project?\")"
|
||||
]
|
||||
"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;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. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
|
||||
"\n",
|
||||
"Current conversation:\n",
|
||||
"\n",
|
||||
"Human: Hi there!\n",
|
||||
"AI: Hello! How are you today?\n",
|
||||
"Human: I'm doing well! Just having a conversation with an AI.\n",
|
||||
"AI: That's great! What would you like to talk about?\n",
|
||||
"Human: Tell me about yourself.\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5c8735cc",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### More Resources on Memory\n",
|
||||
"\n",
|
||||
"This just scratches the surface of what you can do with memory. For more examples on things like how to implement custom memory classes, how to add memory to a custom LLM chain and how to use memory with an agent, please see the [How-To: Memory](../../examples/memory) section. For even more advanced ideas on memory (which will hopefully be included in LangChain soon!) see the [MemPrompt](https://memprompt.com/) paper."
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' I am an AI created to provide information and support to humans. I enjoy learning and exploring new things.'"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "436dda66",
|
||||
"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"
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.predict(input=\"Tell me about yourself.\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5c8735cc",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### More Resources on Memory\n",
|
||||
"\n",
|
||||
"This just scratches the surface of what you can do with memory. \n",
|
||||
"\n",
|
||||
"For more concrete examples of conversational memory, please this [this notebook](../../examples/memory/conversational_memory.ipynb)\n",
|
||||
"\n",
|
||||
"For more examples on things like how to implement custom memory classes, how to add memory to a custom LLM chain and how to use memory with an agent, please see the [How-To: Memory](../../examples/memory) section. \n",
|
||||
"\n",
|
||||
"For even more advanced ideas on memory (which will hopefully be included in LangChain soon!) see the [MemPrompt](https://memprompt.com/) paper."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "436dda66",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.8"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
|
||||
Loading…
Reference in New Issue