github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-06 21:43:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

Harrison/memory refactor (#1478)

Browse Source 
moves memory to own module, factors out common stuff
This commit is contained in:
Harrison Chase
2023-03-07 07:59:37 -08:00
committed by GitHub
parent df6865cd52
commit 7bec461782
44 changed files with 3084 additions and 1610 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/modules/chains/generic/sequential_chains.ipynb
View File

@@ -308,7 +308,7 @@
],
"source": [
"from langchain.chains import SequentialChain\n",
"from langchain.chains.base import SimpleMemory\n",
"from langchain.memory import SimpleMemory\n",
"\n",
"llm = OpenAI(temperature=.7)\n",
"template = \"\"\"You are a social media manager for a theater company. Given the title of play, the era it is set in, the date,time and location, the synopsis of the play, and the review of the play, it is your job to write a social media post for that play.\n",

192
docs/modules/chat/examples/memory.ipynb Normal file
View File

@@ -0,0 +1,192 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "9a9350a6",
"metadata": {},
"source": [
"# Memory\n",
"This notebook goes over how to use Memory with chat models. The main difference between this and Memory for LLMs is that rather than trying to condense all previous messages into a string, we can keep them as their own unique memory object."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "110935ae",
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts import (\n",
" ChatPromptTemplate, \n",
" MessagesPlaceholder, \n",
" SystemMessagePromptTemplate, \n",
" HumanMessagePromptTemplate\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "161b6629",
"metadata": {},
"outputs": [],
"source": [
"prompt = ChatPromptTemplate.from_messages([\n",
" SystemMessagePromptTemplate.from_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",
" MessagesPlaceholder(variable_name=\"history\"),\n",
" HumanMessagePromptTemplate.from_template(\"{input}\")\n",
"])"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "4976fbda",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains import ConversationChain\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.memory import ConversationBufferMemory"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "12a0bea6",
"metadata": {},
"outputs": [],
"source": [
"llm = ChatOpenAI(temperature=0)"
]
},
{
"cell_type": "markdown",
"id": "f6edcd6a",
"metadata": {},
"source": [
"We can now initialize the memory. Note that we set `return_messages=True` To denote that this should return a list of messages when appropriate"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "f55bea38",
"metadata": {},
"outputs": [],
"source": [
"memory = ConversationBufferMemory(return_messages=True)"
]
},
{
"cell_type": "markdown",
"id": "737e8c78",
"metadata": {},
"source": [
"We can now use this in the rest of the chain."
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "80152db7",
"metadata": {},
"outputs": [],
"source": [
"conversation = ConversationChain(memory=memory, prompt=prompt, llm=llm)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "ac68e766",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Hello! How can I assist you today?'"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation.predict(input=\"Hi there!\")"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "babb33d0",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\"That sounds like fun! I'm happy to chat with you. Is there anything specific you'd like to talk about?\""
]
},
"execution_count": 10,
"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": 11,
"id": "36f8a1dc",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"\"Sure! I am an AI language model created by OpenAI. I was trained on a large dataset of text from the internet, which allows me to understand and generate human-like language. I can answer questions, provide information, and even have conversations like this one. Is there anything else you'd like to know about me?\""
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation.predict(input=\"Tell me about yourself.\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "79fb460b",
"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
}

9
docs/modules/memory.rst
View File

@@ -2,18 +2,23 @@ Memory
==========================
By default, Chains and Agents are stateless,
meaning that they treat each incoming query independently.
meaning that they treat each incoming query independently (as are the underlying LLMs and chat models).
In some applications (chatbots being a GREAT example) it is highly important
to remember previous interactions, both at a short term but also at a long term level.
The concept of “Memory” exists to do exactly that.
LangChain provides memory components in two forms.
First, LangChain provides helper utilities for managing and manipulating previous chat messages.
These are designed to be modular and useful regardless of how they are used.
Secondly, LangChain provides easy ways to incorporate these utilities into chains.
The following sections of documentation are provided:
- `Getting Started <./memory/getting_started.html>`_: An overview of how to get started with different types of memory.
- `Key Concepts <./memory/key_concepts.html>`_: A conceptual guide going over the various concepts related to memory.
- `How-To Guides <./memory/how_to_guides.html>`_: A collection of how-to guides. These highlight how to work with different types of memory, as well as how to customize memory.
- `How-To Guides <./memory/how_to_guides.html>`_: A collection of how-to guides. These highlight different types of memory, as well as how to use memory in chains.

4
docs/modules/memory/examples/adding_memory.ipynb
View File

@@ -17,7 +17,7 @@
"metadata": {},
"outputs": [],
"source": [
"from langchain.chains.conversation.memory import ConversationBufferMemory\n",
"from langchain.memory import ConversationBufferMemory\n",
"from langchain import OpenAI, LLMChain, PromptTemplate"
]
},
@@ -167,7 +167,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
"version": "3.9.1"
}
},
"nbformat": 4,

4
docs/modules/memory/examples/adding_memory_chain_multiple_inputs.ipynb
View File

@@ -72,7 +72,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 1,
"id": "d3dc4ed5",
"metadata": {},
"outputs": [],
@@ -80,7 +80,7 @@
"from langchain.chains.question_answering import load_qa_chain\n",
"from langchain.llms import OpenAI\n",
"from langchain.prompts import PromptTemplate\n",
"from langchain.chains.conversation.memory import ConversationBufferMemory"
"from langchain.memory import ConversationBufferMemory"
]
},
{

6
docs/modules/memory/examples/agent_with_memory.ipynb
View File

@@ -22,13 +22,13 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 1,
"id": "8db95912",
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import ZeroShotAgent, Tool, AgentExecutor\n",
"from langchain.chains.conversation.memory import ConversationBufferMemory\n",
"from langchain.memory import ConversationBufferMemory\n",
"from langchain import OpenAI, LLMChain\n",
"from langchain.utilities import GoogleSearchAPIWrapper"
]
@@ -316,7 +316,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
"version": "3.9.1"
}
},
"nbformat": 4,

123
docs/modules/memory/examples/chatgpt_clone.ipynb
View File

@@ -14,7 +14,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 2,
"id": "a99acd89",
"metadata": {},
"outputs": [
@@ -24,9 +24,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -36,20 +36,19 @@
"\n",
"\n",
"Human: I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"```\n",
"$ pwd\n",
"/\n",
"/home/user\n",
"```\n"
]
}
],
"source": [
"from langchain import OpenAI, ConversationChain, LLMChain, PromptTemplate\n",
"from langchain.chains.conversation.memory import ConversationalBufferWindowMemory\n",
"from langchain.memory import ConversationBufferWindowMemory\n",
"\n",
"\n",
"template = \"\"\"Assistant is a large language model trained by OpenAI.\n",
@@ -74,7 +73,7 @@
" llm=OpenAI(temperature=0), \n",
" prompt=prompt, \n",
" verbose=True, \n",
" memory=ConversationalBufferWindowMemory(k=2),\n",
" memory=ConversationBufferWindowMemory(k=2),\n",
")\n",
"\n",
"output = chatgpt_chain.predict(human_input=\"I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.\")\n",
@@ -93,9 +92,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -110,9 +109,9 @@
"/\n",
"```\n",
"Human: ls ~\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"```\n",
"$ ls ~\n",
@@ -138,9 +137,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -161,9 +160,9 @@
"Desktop Documents Downloads Music Pictures Public Templates Videos\n",
"```\n",
"Human: cd ~\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
" \n",
"```\n",
"$ cd ~\n",
@@ -190,9 +189,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -214,9 +213,9 @@
"/home/user\n",
"```\n",
"Human: {Please make a file jokes.txt inside and put some jokes inside}\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
@@ -245,9 +244,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -272,9 +271,9 @@
"$ echo \"Why did the scarecrow win the Nobel Prize? Because he was outstanding in his field!\" >> jokes.txt\n",
"```\n",
"Human: echo -e \"x=lambda y:y*5+3;print('Result:' + str(x(6)))\" > run.py && python3 run.py\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
@@ -304,9 +303,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -332,9 +331,9 @@
"Result: 33\n",
"```\n",
"Human: echo -e \"print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])\" > run.py && python3 run.py\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
@@ -362,9 +361,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -391,9 +390,9 @@
"Human: echo -e \"echo 'Hello from Docker\" > entrypoint.sh && echo -e \"FROM ubuntu:20.04\n",
"COPY entrypoint.sh entrypoint.sh\n",
"ENTRYPOINT [\"/bin/sh\",\"entrypoint.sh\"]\">Dockerfile && docker build . -t my_docker_image && docker run -t my_docker_image\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
@@ -426,9 +425,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -459,9 +458,9 @@
"Hello from Docker\n",
"```\n",
"Human: nvidia-smi\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
@@ -502,9 +501,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -548,9 +547,9 @@
"|=============================================================================|\n",
"\n",
"Human: ping bbc.com\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
@@ -584,9 +583,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -630,9 +629,9 @@
"round-trip min/avg/max/stddev = 14.945/14.945/14.945/0.000 ms\n",
"```\n",
"Human: curl -fsSL \"https://api.github.com/repos/pytorch/pytorch/releases/latest\" | jq -r '.tag_name' | sed 's/[^0-9\\.\\-]*//g'\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
@@ -659,9 +658,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -691,9 +690,9 @@
"1.8.1\n",
"```\n",
"Human: lynx https://www.deepmind.com/careers\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
@@ -726,9 +725,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -757,9 +756,9 @@
"Explore our current openings and apply today. We look forward to hearing from you.\n",
"```\n",
"Human: curl https://chat.openai.com/chat\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
" \n",
"\n",
"```\n",
@@ -799,9 +798,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -843,9 +842,9 @@
"</html>\n",
"```\n",
"Human: curl --header \"Content-Type:application/json\" --request POST --data '{\"message\": \"What is artificial intelligence?\"}' https://chat.openai.com/chat\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\n",
"\n",
"```\n",
@@ -875,9 +874,9 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@@ -916,9 +915,9 @@
"}\n",
"```\n",
"Human: curl --header \"Content-Type:application/json\" --request POST --data '{\"message\": \"I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.\"}' https://chat.openai.com/chat\n",
"Assistant:\u001B[0m\n",
"Assistant:\u001b[0m\n",
"\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
" \n",
"\n",
"```\n",
@@ -961,7 +960,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
"version": "3.9.1"
}
},
"nbformat": 4,

56
docs/modules/memory/examples/conversational_agent.ipynb
View File

@@ -20,7 +20,7 @@
"outputs": [],
"source": [
"from langchain.agents import Tool\n",
"from langchain.chains.conversation.memory import ConversationBufferMemory\n",
"from langchain.memory import ConversationBufferMemory\n",
"from langchain import OpenAI\n",
"from langchain.utilities import GoogleSearchAPIWrapper\n",
"from langchain.agents import initialize_agent"
@@ -76,12 +76,12 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"Thought: Do I need to use a tool? No\n",
"AI: Hi Bob, nice to meet you! How can I help you today?\u001B[0m\n",
"AI: Hi Bob, nice to meet you! How can I help you today?\u001b[0m\n",
"\n",
"\u001B[1m> Finished chain.\u001B[0m\n"
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
@@ -111,12 +111,12 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"Thought: Do I need to use a tool? No\n",
"AI: Your name is Bob!\u001B[0m\n",
"AI: Your name is Bob!\u001b[0m\n",
"\n",
"\u001B[1m> Finished chain.\u001B[0m\n"
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
@@ -146,12 +146,12 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"Thought: Do I need to use a tool? No\n",
"AI: If you like Thai food, some great dinner options this week could include Thai green curry, Pad Thai, or a Thai-style stir-fry. You could also try making a Thai-style soup or salad. Enjoy!\u001B[0m\n",
"AI: If you like Thai food, some great dinner options this week could include Thai green curry, Pad Thai, or a Thai-style stir-fry. You could also try making a Thai-style soup or salad. Enjoy!\u001b[0m\n",
"\n",
"\u001B[1m> Finished chain.\u001B[0m\n"
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
@@ -181,16 +181,16 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"Thought: Do I need to use a tool? Yes\n",
"Action: Current Search\n",
"Action Input: Who won the World Cup in 1978\u001B[0m\n",
"Observation: \u001B[36;1m\u001B[1;3mThe Cup was won by the host nation, Argentina, who defeated the Netherlands 3–1 in the final, after extra time. The final was held at River Plate's home stadium ... Amid Argentina's celebrations, there was sympathy for the Netherlands, runners-up for the second tournament running, following a 3-1 final defeat at the Estadio ... The match was won by the Argentine squad in extra time by a score of 3–1. Mario Kempes, who finished as the tournament's top scorer, was named the man of the ... May 21, 2022 ... Argentina won the World Cup for the first time in their history, beating Netherlands 3-1 in the final. This edition of the World Cup was full of ... The adidas Golden Ball is presented to the best player at each FIFA World Cup finals. Those who finish as runners-up in the vote receive the adidas Silver ... Holders West Germany failed to beat Holland and Italy and were eliminated when Berti Vogts' own goal gave Austria a 3-2 victory. Holland thrashed the Austrians ... Jun 14, 2018 ... On a clear afternoon on 1 June 1978 at the revamped El Monumental stadium in Buenos Aires' Belgrano barrio, several hundred children in white ... Dec 15, 2022 ... The tournament couldn't have gone better for the ruling junta. Argentina went on to win the championship, defeating the Netherlands, 3-1, in the ... Nov 9, 2022 ... Host: Argentina Teams: 16. Format: Group stage, second round, third-place playoff, final. Matches: 38. Goals: 102. Winner: Argentina Feb 19, 2009 ... Argentina sealed their first World Cup win on home soil when they defeated the Netherlands in an exciting final that went to extra-time. For the ...\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3m Do I need to use a tool? No\n",
"AI: The last letter in your name is 'b'. Argentina won the World Cup in 1978.\u001B[0m\n",
"Action Input: Who won the World Cup in 1978\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mThe Cup was won by the host nation, Argentina, who defeated the Netherlands 3–1 in the final, after extra time. The final was held at River Plate's home stadium ... Amid Argentina's celebrations, there was sympathy for the Netherlands, runners-up for the second tournament running, following a 3-1 final defeat at the Estadio ... The match was won by the Argentine squad in extra time by a score of 3–1. Mario Kempes, who finished as the tournament's top scorer, was named the man of the ... May 21, 2022 ... Argentina won the World Cup for the first time in their history, beating Netherlands 3-1 in the final. This edition of the World Cup was full of ... The adidas Golden Ball is presented to the best player at each FIFA World Cup finals. Those who finish as runners-up in the vote receive the adidas Silver ... Holders West Germany failed to beat Holland and Italy and were eliminated when Berti Vogts' own goal gave Austria a 3-2 victory. Holland thrashed the Austrians ... Jun 14, 2018 ... On a clear afternoon on 1 June 1978 at the revamped El Monumental stadium in Buenos Aires' Belgrano barrio, several hundred children in white ... Dec 15, 2022 ... The tournament couldn't have gone better for the ruling junta. Argentina went on to win the championship, defeating the Netherlands, 3-1, in the ... Nov 9, 2022 ... Host: Argentina Teams: 16. Format: Group stage, second round, third-place playoff, final. Matches: 38. Goals: 102. Winner: Argentina Feb 19, 2009 ... Argentina sealed their first World Cup win on home soil when they defeated the Netherlands in an exciting final that went to extra-time. For the ...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m Do I need to use a tool? No\n",
"AI: The last letter in your name is 'b'. Argentina won the World Cup in 1978.\u001b[0m\n",
"\n",
"\u001B[1m> Finished chain.\u001B[0m\n"
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
@@ -220,16 +220,16 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"Thought: Do I need to use a tool? Yes\n",
"Action: Current Search\n",
"Action Input: Current temperature in Pomfret\u001B[0m\n",
"Observation: \u001B[36;1m\u001B[1;3mA mixture of rain and snow showers. High 39F. Winds NNW at 5 to 10 mph. Chance of precip 50%. Snow accumulations less than one inch. Pomfret, CT Weather Forecast, with current conditions, wind, air quality, and what to expect for the next 3 days. Pomfret Center Weather Forecasts. ... Pomfret Center, CT Weather Conditionsstar_ratehome ... Tomorrow's temperature is forecast to be COOLER than today. It is 46 degrees fahrenheit, or 8 degrees celsius and feels like 46 degrees fahrenheit. The barometric pressure is 29.78 - measured by inch of mercury units - ... Pomfret Weather Forecasts. ... Pomfret, MD Weather Conditionsstar_ratehome ... Tomorrow's temperature is forecast to be MUCH COOLER than today. Additional Headlines. En Español · Share |. Current conditions at ... Pomfret CT. Tonight ... Past Weather Information · Interactive Forecast Map. Pomfret MD detailed current weather report for 20675 in Charles county, Maryland. ... Pomfret, MD weather condition is Mostly Cloudy and 43°F. Mostly Cloudy. Hazardous Weather Conditions. Hazardous Weather Outlook · En Español · Share |. Current conditions at ... South Pomfret VT. Tonight. Pomfret Center, CT Weather. Current Report for Thu Jan 5 2023. As of 2:00 PM EST. 5-Day Forecast | Road Conditions. 45°F 7°c. Feels Like 44°F. Pomfret Center CT. Today. Today: Areas of fog before 9am. Otherwise, cloudy, with a ... Otherwise, cloudy, with a temperature falling to around 33 by 5pm.\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3m Do I need to use a tool? No\n",
"AI: The current temperature in Pomfret is 45°F (7°C) and it feels like 44°F.\u001B[0m\n",
"Action Input: Current temperature in Pomfret\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mA mixture of rain and snow showers. High 39F. Winds NNW at 5 to 10 mph. Chance of precip 50%. Snow accumulations less than one inch. Pomfret, CT Weather Forecast, with current conditions, wind, air quality, and what to expect for the next 3 days. Pomfret Center Weather Forecasts. ... Pomfret Center, CT Weather Conditionsstar_ratehome ... Tomorrow's temperature is forecast to be COOLER than today. It is 46 degrees fahrenheit, or 8 degrees celsius and feels like 46 degrees fahrenheit. The barometric pressure is 29.78 - measured by inch of mercury units - ... Pomfret Weather Forecasts. ... Pomfret, MD Weather Conditionsstar_ratehome ... Tomorrow's temperature is forecast to be MUCH COOLER than today. Additional Headlines. En Español · Share |. Current conditions at ... Pomfret CT. Tonight ... Past Weather Information · Interactive Forecast Map. Pomfret MD detailed current weather report for 20675 in Charles county, Maryland. ... Pomfret, MD weather condition is Mostly Cloudy and 43°F. Mostly Cloudy. Hazardous Weather Conditions. Hazardous Weather Outlook · En Español · Share |. Current conditions at ... South Pomfret VT. Tonight. Pomfret Center, CT Weather. Current Report for Thu Jan 5 2023. As of 2:00 PM EST. 5-Day Forecast | Road Conditions. 45°F 7°c. Feels Like 44°F. Pomfret Center CT. Today. Today: Areas of fog before 9am. Otherwise, cloudy, with a ... Otherwise, cloudy, with a temperature falling to around 33 by 5pm.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m Do I need to use a tool? No\n",
"AI: The current temperature in Pomfret is 45°F (7°C) and it feels like 44°F.\u001b[0m\n",
"\n",
"\u001B[1m> Finished chain.\u001B[0m\n"
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
@@ -272,7 +272,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
"version": "3.9.1"
}
},
"nbformat": 4,

4
docs/modules/memory/examples/conversational_customization.ipynb
View File

@@ -19,7 +19,7 @@
"source": [
"from langchain.llms import OpenAI\n",
"from langchain.chains import ConversationChain\n",
"from langchain.chains.conversation.memory import ConversationBufferMemory\n",
"from langchain.memory import ConversationBufferMemory\n",
"\n",
"\n",
"llm = OpenAI(temperature=0)"
@@ -379,7 +379,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
"version": "3.9.1"
}
},
"nbformat": 4,

6
docs/modules/memory/examples/custom_memory.ipynb
View File

@@ -25,7 +25,7 @@
"outputs": [],
"source": [
"from langchain import OpenAI, ConversationChain\n",
"from langchain.chains.base import Memory\n",
"from langchain.schema import BaseMemory\n",
"from pydantic import BaseModel\n",
"from typing import List, Dict, Any"
]
@@ -71,7 +71,7 @@
"metadata": {},
"outputs": [],
"source": [
"class SpacyEntityMemory(Memory, BaseModel):\n",
"class SpacyEntityMemory(BaseMemory, BaseModel):\n",
" \"\"\"Memory class for storing information about entities.\"\"\"\n",
"\n",
" # Define dictionary to store information about entities.\n",
@@ -290,7 +290,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
"version": "3.9.1"
}
},
"nbformat": 4,

7
docs/modules/memory/examples/multiple_memory.ipynb
View File

@@ -11,7 +11,7 @@
},
{
"cell_type": "code",
"execution_count": 12,
"execution_count": 1,
"id": "7d7de430",
"metadata": {},
"outputs": [],
@@ -19,7 +19,8 @@
"from langchain.llms import OpenAI\n",
"from langchain.prompts import PromptTemplate\n",
"from langchain.chains import ConversationChain\n",
"from langchain.chains.conversation.memory import ConversationBufferMemory, ConversationSummaryMemory, CombinedMemory\n",
"from langchain.memory import ConversationBufferMemory, CombinedMemory, ConversationSummaryMemory\n",
"\n",
"\n",
"conv_memory = ConversationBufferMemory(\n",
" memory_key=\"chat_history_lines\",\n",
@@ -159,7 +160,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
"version": "3.9.1"
}
},
"nbformat": 4,

926
docs/modules/memory/getting_started.ipynb
View File

File diff suppressed because it is too large Load Diff

15
docs/modules/memory/how_to_guides.rst
View File

@@ -1,15 +1,24 @@
How-To Guides
=============
The first set of examples all highlight different types of memory.
`Entity Memory <./types/entity_summary_memory.html>`_: How to use a type of memory that organizes information by entity.
.. toctree::
:maxdepth: 1
:glob:
:hidden:
./types/*
The examples here all highlight how to use memory in different ways.
`Adding Memory <./examples/adding_memory.html>`_: How to add a memory component to any single input chain.
`ChatGPT Clone <./examples/chatgpt_clone.html>`_: How to recreate ChatGPT with LangChain prompting + memory components.
`Entity Memory <./examples/entity_summary_memory.html>`_: How to use a type of memory that organizes information by entity.
`Adding Memory to Multi-Input Chain <./examples/adding_memory_chain_multiple_inputs.html>`_: How to add a memory component to any multiple input chain.
`Conversational Memory Customization <./examples/conversational_customization.html>`_: How to customize existing conversation memory components.

2
docs/modules/memory/key_concepts.md
View File

@@ -16,4 +16,4 @@ There are a few different ways to accomplish this:
A more complex form of memory is remembering information about specific entities in the conversation.
This is a more direct and organized way of remembering information over time.
Putting it a more structured form also has the benefit of allowing easy inspection of what is known about specific entities.
For a guide on how to use this type of memory, see [this notebook](./examples/entity_summary_memory.ipynb).
For a guide on how to use this type of memory, see [this notebook](types/entity_summary_memory.ipynb).

284
docs/modules/memory/types/buffer.ipynb Normal file
View File

@@ -0,0 +1,284 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "46196aa3",
"metadata": {},
"source": [
"## ConversationBufferMemory\n",
"\n",
"This notebook shows how to use `ConversationBufferMemory`. This memory allows for storing of messages and then extracts the messages in a variable.\n",
"\n",
"We can first extract it as a string."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "3bac84f3",
"metadata": {},
"outputs": [],
"source": [
"from langchain.memory import ConversationBufferMemory"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "cef35e7f",
"metadata": {},
"outputs": [],
"source": [
"memory = ConversationBufferMemory()\n",
"memory.save_context({\"input\": \"hi\"}, {\"ouput\": \"whats up\"})"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "2c9b39af",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'history': 'Human: hi\\nAI: whats up'}"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"memory.load_memory_variables({})"
]
},
{
"cell_type": "markdown",
"id": "567f7c16",
"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": 5,
"id": "a481a415",
"metadata": {},
"outputs": [],
"source": [
"memory = ConversationBufferMemory(return_messages=True)\n",
"memory.save_context({\"input\": \"hi\"}, {\"ouput\": \"whats up\"})"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "86a56348",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'history': [HumanMessage(content='hi', additional_kwargs={}),\n",
" AIMessage(content='whats up', additional_kwargs={})]}"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"memory.load_memory_variables({})"
]
},
{
"cell_type": "markdown",
"id": "d051c1da",
"metadata": {},
"source": [
"Finally, let's take a look at using this in a chain (setting `verbose=True` so we can see the prompt)."
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "54301321",
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms import OpenAI\n",
"from langchain.chains import ConversationChain\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": 16,
"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 chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\" Hi there! It's nice to meet you. How can I help you today?\""
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation.predict(input=\"Hi there!\")"
]
},
{
"cell_type": "code",
"execution_count": 17,
"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",
"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 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": 17,
"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": 18,
"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",
"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 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": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation.predict(input=\"Tell me about yourself.\")"
]
},
{
"cell_type": "markdown",
"id": "bd0146c2",
"metadata": {},
"source": [
"And that's it for the getting started! There are plenty of different types of memory, check out our examples to see them all"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "447c138d",
"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
}

310
docs/modules/memory/types/buffer_window.ipynb Normal file
View File

@@ -0,0 +1,310 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "716c8cab",
"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 first explore the basic functionality of this type of memory."
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "dc9d10b0",
"metadata": {},
"outputs": [],
"source": [
"from langchain.memory import ConversationBufferWindowMemory"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "2dac7769",
"metadata": {},
"outputs": [],
"source": [
"memory = ConversationBufferWindowMemory( k=1)\n",
"memory.save_context({\"input\": \"hi\"}, {\"ouput\": \"whats up\"})\n",
"memory.save_context({\"input\": \"not much you\"}, {\"ouput\": \"not much\"})"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "40664f10",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'history': 'Human: not much you\\nAI: not much'}"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"memory.load_memory_variables({})"
]
},
{
"cell_type": "markdown",
"id": "b1932b49",
"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": 8,
"id": "5fd077d5",
"metadata": {},
"outputs": [],
"source": [
"memory = ConversationBufferWindowMemory( k=1, return_messages=True)\n",
"memory.save_context({\"input\": \"hi\"}, {\"ouput\": \"whats up\"})\n",
"memory.save_context({\"input\": \"not much you\"}, {\"ouput\": \"not much\"})"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "b94b750f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'history': [HumanMessage(content='not much you', additional_kwargs={}),\n",
" AIMessage(content='not much', additional_kwargs={})]}"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"memory.load_memory_variables({})"
]
},
{
"cell_type": "markdown",
"id": "ac59a682",
"metadata": {},
"source": [
"Let's walk through an example, again setting `verbose=True` so we can see the prompt."
]
},
{
"cell_type": "code",
"execution_count": 12,
"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 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": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain.llms import OpenAI\n",
"from langchain.chains import ConversationChain\n",
"conversation_with_summary = ConversationChain(\n",
" llm=OpenAI(temperature=0), \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": 13,
"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 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": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation_with_summary.predict(input=\"What's their issues?\")"
]
},
{
"cell_type": "code",
"execution_count": 14,
"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 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": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation_with_summary.predict(input=\"Is it going well?\")"
]
},
{
"cell_type": "code",
"execution_count": 15,
"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 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": 15,
"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": "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
}

182
docs/modules/memory/examples/entity_summary_memory.ipynb → docs/modules/memory/types/entity_summary_memory.ipynb
View File

@@ -6,31 +6,129 @@
"metadata": {},
"source": [
"# Entity Memory\n",
"This notebook shows how to work with a memory module that remembers things about specific entities. It extracts information on entities (using LLMs) and builds up its knowledge about that entity over time (also using LLMs)."
"This notebook shows how to work with a memory module that remembers things about specific entities. It extracts information on entities (using LLMs) and builds up its knowledge about that entity over time (also using LLMs).\n",
"\n",
"Let's first walk through using this functionality."
]
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": 1,
"id": "7b165e71",
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms import OpenAI\n",
"from langchain.memory import ConversationEntityMemory\n",
"llm = OpenAI(temperature=0)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "25354d39",
"metadata": {},
"outputs": [],
"source": [
"memory = ConversationEntityMemory(llm=llm)\n",
"_input = {\"input\": \"Deven & Sam are working on a hackathon project\"}\n",
"memory.load_memory_variables(_input)\n",
"memory.save_context(\n",
" _input,\n",
" {\"ouput\": \" That sounds like a great project! What kind of project are they working on?\"}\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "71c75295",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'history': 'Human: Deven & Sam are working on a hackathon project\\nAI: That sounds like a great project! What kind of project are they working on?',\n",
" 'entities': {'Sam': 'Sam is working on a hackathon project with Deven.'}}"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"memory.load_memory_variables({\"input\": 'who is Sam'})"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "bb8a7943",
"metadata": {},
"outputs": [],
"source": [
"memory = ConversationEntityMemory(llm=llm, return_messages=True)\n",
"_input = {\"input\": \"Deven & Sam are working on a hackathon project\"}\n",
"memory.load_memory_variables(_input)\n",
"memory.save_context(\n",
" _input,\n",
" {\"ouput\": \" That sounds like a great project! What kind of project are they working on?\"}\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "a37ac236",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'history': [HumanMessage(content='Deven & Sam are working on a hackathon project', additional_kwargs={}),\n",
" AIMessage(content=' That sounds like a great project! What kind of project are they working on?', additional_kwargs={})],\n",
" 'entities': {'Sam': 'Sam is working on a hackathon project with Deven.'}}"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"memory.load_memory_variables({\"input\": 'who is Sam'})"
]
},
{
"cell_type": "markdown",
"id": "655ab2c4",
"metadata": {},
"source": [
"Let's now use it in a chain!"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "13471fbd",
"metadata": {},
"outputs": [],
"source": [
"from langchain import OpenAI, ConversationChain\n",
"from langchain.chains.conversation.memory import ConversationEntityMemory\n",
"from langchain.chains.conversation.prompt import ENTITY_MEMORY_CONVERSATION_TEMPLATE\n",
"from langchain.chains import ConversationChain\n",
"from langchain.memory import ConversationEntityMemory\n",
"from langchain.memory.prompt import ENTITY_MEMORY_CONVERSATION_TEMPLATE\n",
"from pydantic import BaseModel\n",
"from typing import List, Dict, Any"
]
},
{
"cell_type": "code",
"execution_count": 12,
"execution_count": 7,
"id": "183346e2",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)\n",
"conversation = ConversationChain(\n",
" llm=llm, \n",
" verbose=True,\n",
@@ -41,7 +139,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 8,
"id": "7eb1460a",
"metadata": {},
"outputs": [
@@ -79,7 +177,7 @@
"' That sounds like a great project! What kind of project are they working on?'"
]
},
"execution_count": 3,
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
@@ -90,7 +188,29 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 9,
"id": "dc1c0d5e",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'Deven': 'Deven is working on a hackathon project with Sam.',\n",
" 'Sam': 'Sam is working on a hackathon project with Deven.'}"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation.memory.store"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "46324ca8",
"metadata": {},
"outputs": [
@@ -129,7 +249,7 @@
"' That sounds like an interesting project! What kind of memory structures are they trying to add?'"
]
},
"execution_count": 4,
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
@@ -140,7 +260,7 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 11,
"id": "ff2ebf6b",
"metadata": {},
"outputs": [
@@ -161,7 +281,7 @@
"Overall, you are a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether the human needs help with a specific question or just wants to have a conversation about a particular topic, you are here to assist.\n",
"\n",
"Context:\n",
"{'Deven': 'Deven is working on a hackathon project with Sam to add more complex memory structures to Langchain.', 'Sam': 'Sam is working on a hackathon project with Deven to add more complex memory structures to Langchain.', 'Langchain': 'Langchain is a project that seeks to add more complex memory structures.', 'Key-Value Store': ''}\n",
"{'Deven': 'Deven is working on a hackathon project with Sam, attempting to add more complex memory structures to Langchain.', 'Sam': 'Sam is working on a hackathon project with Deven, trying to add more complex memory structures to Langchain.', 'Langchain': 'Langchain is a project that is trying to add more complex memory structures.', 'Key-Value Store': ''}\n",
"\n",
"Current conversation:\n",
"Human: Deven & Sam are working on a hackathon project\n",
@@ -181,7 +301,7 @@
"' That sounds like a great idea! How will the key-value store work?'"
]
},
"execution_count": 5,
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
@@ -192,7 +312,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 12,
"id": "56cfd4ba",
"metadata": {},
"outputs": [
@@ -213,7 +333,7 @@
"Overall, you are a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether the human needs help with a specific question or just wants to have a conversation about a particular topic, you are here to assist.\n",
"\n",
"Context:\n",
"{'Deven': 'Deven is working on a hackathon project with Sam to add more complex memory structures to Langchain, including a key-value store for entities mentioned so far in the conversation.', 'Sam': 'Sam is working on a hackathon project with Deven to add more complex memory structures to Langchain, including a key-value store for entities mentioned so far in the conversation.'}\n",
"{'Deven': 'Deven is working on a hackathon project with Sam, attempting to add more complex memory structures to Langchain, including a key-value store for entities mentioned so far in the conversation.', 'Sam': 'Sam is working on a hackathon project with Deven, trying to add more complex memory structures to Langchain, including a key-value store for entities mentioned so far in the conversation.'}\n",
"\n",
"Current conversation:\n",
"Human: Deven & Sam are working on a hackathon project\n",
@@ -232,10 +352,10 @@
{
"data": {
"text/plain": [
"' Deven and Sam are working on a hackathon project to add more complex memory structures to Langchain, including a key-value store for entities mentioned so far in the conversation. They seem to be very motivated and passionate about their project, and are working hard to make it a success.'"
"' Deven and Sam are working on a hackathon project together, attempting to add more complex memory structures to Langchain, including a key-value store for entities mentioned so far in the conversation.'"
]
},
"execution_count": 6,
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
@@ -263,19 +383,17 @@
"name": "stdout",
"output_type": "stream",
"text": [
"{'Deven': 'Deven is working on a hackathon project with Sam to add more '\n",
" 'complex memory structures to Langchain, including a key-value store '\n",
" 'for entities mentioned so far in the conversation.',\n",
" 'Key-Value Store': 'Key-Value Store: A data structure that stores values '\n",
" 'associated with a unique key, allowing for efficient '\n",
" 'retrieval of values. Deven and Sam are adding a key-value '\n",
" 'store for entities mentioned so far in the conversation.',\n",
" 'Langchain': 'Langchain is a project that seeks to add more complex memory '\n",
" 'structures, including a key-value store for entities mentioned '\n",
" 'so far in the conversation.',\n",
" 'Sam': 'Sam is working on a hackathon project with Deven to add more complex '\n",
" 'memory structures to Langchain, including a key-value store for '\n",
" 'entities mentioned so far in the conversation.'}\n"
"{'Deven': 'Deven is working on a hackathon project with Sam, attempting to add '\n",
" 'more complex memory structures to Langchain, including a key-value '\n",
" 'store for entities mentioned so far in the conversation.',\n",
" 'Key-Value Store': 'A key-value store that stores entities mentioned in the '\n",
" 'conversation.',\n",
" 'Langchain': 'Langchain is a project that is trying to add more complex '\n",
" 'memory structures, including a key-value store for entities '\n",
" 'mentioned so far in the conversation.',\n",
" 'Sam': 'Sam is working on a hackathon project with Deven, attempting to add '\n",
" 'more complex memory structures to Langchain, including a key-value '\n",
" 'store for entities mentioned so far in the conversation.'}\n"
]
}
],
@@ -451,7 +569,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
"version": "3.9.1"
}
},
"nbformat": 4,

300
docs/modules/memory/types/kg.ipynb Normal file
View File

@@ -0,0 +1,300 @@
{
"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": "1d9a5b18",
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(temperature=0)\n",
"memory = ConversationKGMemory(llm=llm)\n",
"memory.save_context({\"input\": \"say hi to sam\"}, {\"ouput\": \"who is sam\"})\n",
"memory.save_context({\"input\": \"sam is a friend\"}, {\"ouput\": \"okay\"})"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "3f5da288",
"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": "2ab23035",
"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": "43dbbc43",
"metadata": {},
"outputs": [],
"source": [
"memory = ConversationKGMemory(llm=llm, return_messages=True)\n",
"memory.save_context({\"input\": \"say hi to sam\"}, {\"ouput\": \"who is sam\"})\n",
"memory.save_context({\"input\": \"sam is a friend\"}, {\"ouput\": \"okay\"})"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "ef6a4f60",
"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": "5ba0dde9",
"metadata": {},
"source": [
"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(\n",
" input_variables=[\"history\", \"input\"], template=template\n",
")\n",
"conversation_with_kg = ConversationChain(\n",
" llm=llm, \n",
" verbose=True, \n",
" prompt=prompt,\n",
" 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(input=\"My name is James and I'm helping Will. He's an engineer.\")"
]
},
{
"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
}

262
docs/modules/memory/types/summary.ipynb Normal file
View File

@@ -0,0 +1,262 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "5d3f2f0f",
"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 first explore the basic functionality of this type of memory."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "a36c34d6",
"metadata": {},
"outputs": [],
"source": [
"from langchain.memory import ConversationSummaryMemory\n",
"from langchain.llms import OpenAI"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "89646c34",
"metadata": {},
"outputs": [],
"source": [
"memory = ConversationSummaryMemory(llm=OpenAI(temperature=0))\n",
"memory.save_context({\"input\": \"hi\"}, {\"ouput\": \"whats up\"})"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "dea210aa",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'history': '\\nThe human greets the AI, to which the AI responds.'}"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"memory.load_memory_variables({})"
]
},
{
"cell_type": "markdown",
"id": "3838fe93",
"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": "114dbef6",
"metadata": {},
"outputs": [],
"source": [
"memory = ConversationSummaryMemory(llm=OpenAI(temperature=0), return_messages=True)\n",
"memory.save_context({\"input\": \"hi\"}, {\"ouput\": \"whats up\"})"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "39c8c106",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'history': [SystemMessage(content='\\nThe human greets the AI and the AI responds with a casual greeting.', additional_kwargs={})]}"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"memory.load_memory_variables({})"
]
},
{
"cell_type": "markdown",
"id": "4fad9448",
"metadata": {},
"source": [
"Let's walk through an example of using this in a chain, again setting `verbose=True` so we can see the prompt."
]
},
{
"cell_type": "code",
"execution_count": 11,
"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 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": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain.llms import OpenAI\n",
"from langchain.chains import ConversationChain\n",
"llm = OpenAI(temperature=0)\n",
"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": 12,
"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 and asked how it was doing. The AI replied that it was doing great and was currently helping a customer with a technical issue.\n",
"Human: Tell me more about it!\n",
"AI:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\" Sure! The customer is having trouble with their computer not connecting to the internet. I'm helping them troubleshoot the issue and figure out what the problem is. So far, we've tried resetting the router and checking the network settings, but the issue still persists. We're currently looking into other possible solutions.\""
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation_with_summary.predict(input=\"Tell me more about it!\")"
]
},
{
"cell_type": "code",
"execution_count": 13,
"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 and asked how it was doing. The AI replied that it was doing great and was currently helping a customer with a technical issue where their computer was not connecting to the internet. The AI was troubleshooting the issue and had already tried resetting the router and checking the network settings, but the issue still persisted and they were looking into other possible solutions.\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": [
"\" The scope of the project is to troubleshoot the customer's computer issue and find a solution that will allow them to connect to the internet. We are currently exploring different possibilities and have already tried resetting the router and checking the network settings, but the issue still persists.\""
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation_with_summary.predict(input=\"Very cool -- what is the scope of the project?\")"
]
},
{
"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
}

290
docs/modules/memory/types/summary_buffer.ipynb Normal file
View File

@@ -0,0 +1,290 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "2e90817b",
"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 first walk through how to use the utilities"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "b8aec547",
"metadata": {},
"outputs": [],
"source": [
"from langchain.memory import ConversationSummaryBufferMemory\n",
"from langchain.llms import OpenAI\n",
"llm = OpenAI()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "2594c8f1",
"metadata": {},
"outputs": [],
"source": [
"memory = ConversationSummaryBufferMemory(llm=llm, max_token_limit=10)\n",
"memory.save_context({\"input\": \"hi\"}, {\"ouput\": \"whats up\"})\n",
"memory.save_context({\"input\": \"not much you\"}, {\"ouput\": \"not much\"})"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "a25087e0",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'history': 'System: \\nThe human greets the AI, to which the AI responds inquiring what is up.\\nHuman: not much you\\nAI: not much'}"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"memory.load_memory_variables({})"
]
},
{
"cell_type": "markdown",
"id": "3a6e7905",
"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": 10,
"id": "e439451f",
"metadata": {},
"outputs": [],
"source": [
"memory = ConversationSummaryBufferMemory(llm=llm, max_token_limit=10, return_messages=True)\n",
"memory.save_context({\"input\": \"hi\"}, {\"ouput\": \"whats up\"})\n",
"memory.save_context({\"input\": \"not much you\"}, {\"ouput\": \"not much\"})"
]
},
{
"cell_type": "markdown",
"id": "a6d2569f",
"metadata": {},
"source": [
"Let's walk through an example, again setting `verbose=True` so we can see the prompt."
]
},
{
"cell_type": "code",
"execution_count": 11,
"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 chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\" Hi there! I'm doing great. I'm spending some time learning about the latest developments in AI technology. How about you?\""
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain.chains import ConversationChain\n",
"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": 12,
"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 spending some time learning about the latest developments in AI technology. How about you?\n",
"Human: Just working on writing some documentation!\n",
"AI:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"' That sounds like a great use of your time. Do you have experience with writing documentation?'"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation_with_summary.predict(input=\"Just working on writing some documentation!\")"
]
},
{
"cell_type": "code",
"execution_count": 13,
"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",
"System: \n",
"The human asked the AI what it was up to and the AI responded that it was learning about the latest developments in AI technology.\n",
"Human: Just working on writing some documentation!\n",
"AI: That sounds like a great use of your time. Do you have experience with writing documentation?\n",
"Human: For LangChain! Have you heard of it?\n",
"AI:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"\" No, I haven't heard of LangChain. Can you tell me more about it?\""
]
},
"execution_count": 13,
"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": 14,
"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",
"System: \n",
"The human asked the AI what it was up to and the AI responded that it was learning about the latest developments in AI technology. The human then mentioned they were writing documentation, to which the AI responded that it sounded like a great use of their time and asked if they had experience with writing documentation.\n",
"Human: For LangChain! Have you heard of it?\n",
"AI: No, I haven't heard of LangChain. Can you tell me more about it?\n",
"Human: Haha nope, although a lot of people confuse it for that\n",
"AI:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"' Oh, okay. What is LangChain?'"
]
},
"execution_count": 14,
"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": "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
}