2022-11-26 02:28:55 +00:00
{
"cells": [
{
"cell_type": "markdown",
"id": "00695447",
"metadata": {},
"source": [
"# Adding Memory To an LLMChain\n",
"\n",
2022-11-26 13:58:54 +00:00
"This notebook goes over how to use the Memory class with an LLMChain. For the purposes of this walkthrough, we will add the `ConversationBufferMemory` class, although this can be any memory class."
2022-11-26 02:28:55 +00:00
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "9f1aaf47",
"metadata": {},
"outputs": [],
"source": [
2023-03-07 15:59:37 +00:00
"from langchain.memory import ConversationBufferMemory\n",
2022-11-26 02:28:55 +00:00
"from langchain import OpenAI, LLMChain, PromptTemplate"
]
},
{
"cell_type": "markdown",
"id": "4b066ced",
"metadata": {},
"source": [
"The most important step is setting up the prompt correctly. In the below prompt, we have two input keys: one for the actual input, another for the input from the Memory class. Importantly, we make sure the keys in the PromptTemplate and the ConversationBufferMemory match up (`chat_history`)."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "e5501eda",
"metadata": {},
"outputs": [],
"source": [
"template = \"\"\"You are a chatbot having a conversation with a human.\n",
"\n",
"{chat_history}\n",
"Human: {human_input}\n",
"Chatbot:\"\"\"\n",
"\n",
"prompt = PromptTemplate(\n",
" input_variables=[\"chat_history\", \"human_input\"], \n",
" template=template\n",
")\n",
2022-11-26 13:58:54 +00:00
"memory = ConversationBufferMemory(memory_key=\"chat_history\")"
2022-11-26 02:28:55 +00:00
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "f6566275",
"metadata": {},
"outputs": [],
"source": [
"llm_chain = LLMChain(\n",
" llm=OpenAI(), \n",
" prompt=prompt, \n",
" verbose=True, \n",
" memory=memory,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "e2b189dc",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
Docs refactor (#480)
Big docs refactor! Motivation is to make it easier for people to find
resources they are looking for. To accomplish this, there are now three
main sections:
- Getting Started: steps for getting started, walking through most core
functionality
- Modules: these are different modules of functionality that langchain
provides. Each part here has a "getting started", "how to", "key
concepts" and "reference" section (except in a few select cases where it
didnt easily fit).
- Use Cases: this is to separate use cases (like summarization, question
answering, evaluation, etc) from the modules, and provide a different
entry point to the code base.
There is also a full reference section, as well as extra resources
(glossary, gallery, etc)
Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
2023-01-02 16:24:09 +00:00
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
2022-11-26 02:28:55 +00:00
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mYou are a chatbot having a conversation with a human.\n",
"\n",
"\n",
"Human: Hi there my friend\n",
"Chatbot:\u001b[0m\n",
"\n",
Docs refactor (#480)
Big docs refactor! Motivation is to make it easier for people to find
resources they are looking for. To accomplish this, there are now three
main sections:
- Getting Started: steps for getting started, walking through most core
functionality
- Modules: these are different modules of functionality that langchain
provides. Each part here has a "getting started", "how to", "key
concepts" and "reference" section (except in a few select cases where it
didnt easily fit).
- Use Cases: this is to separate use cases (like summarization, question
answering, evaluation, etc) from the modules, and provide a different
entry point to the code base.
There is also a full reference section, as well as extra resources
(glossary, gallery, etc)
Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
2023-01-02 16:24:09 +00:00
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n"
2022-11-26 02:28:55 +00:00
]
},
{
"data": {
"text/plain": [
Docs refactor (#480)
Big docs refactor! Motivation is to make it easier for people to find
resources they are looking for. To accomplish this, there are now three
main sections:
- Getting Started: steps for getting started, walking through most core
functionality
- Modules: these are different modules of functionality that langchain
provides. Each part here has a "getting started", "how to", "key
concepts" and "reference" section (except in a few select cases where it
didnt easily fit).
- Use Cases: this is to separate use cases (like summarization, question
answering, evaluation, etc) from the modules, and provide a different
entry point to the code base.
There is also a full reference section, as well as extra resources
(glossary, gallery, etc)
Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
2023-01-02 16:24:09 +00:00
"' Hi there, how are you doing today?'"
2022-11-26 02:28:55 +00:00
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"llm_chain.predict(human_input=\"Hi there my friend\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "a902729f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
Docs refactor (#480)
Big docs refactor! Motivation is to make it easier for people to find
resources they are looking for. To accomplish this, there are now three
main sections:
- Getting Started: steps for getting started, walking through most core
functionality
- Modules: these are different modules of functionality that langchain
provides. Each part here has a "getting started", "how to", "key
concepts" and "reference" section (except in a few select cases where it
didnt easily fit).
- Use Cases: this is to separate use cases (like summarization, question
answering, evaluation, etc) from the modules, and provide a different
entry point to the code base.
There is also a full reference section, as well as extra resources
(glossary, gallery, etc)
Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
2023-01-02 16:24:09 +00:00
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
2022-11-26 02:28:55 +00:00
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mYou are a chatbot having a conversation with a human.\n",
"\n",
"\n",
"Human: Hi there my friend\n",
Docs refactor (#480)
Big docs refactor! Motivation is to make it easier for people to find
resources they are looking for. To accomplish this, there are now three
main sections:
- Getting Started: steps for getting started, walking through most core
functionality
- Modules: these are different modules of functionality that langchain
provides. Each part here has a "getting started", "how to", "key
concepts" and "reference" section (except in a few select cases where it
didnt easily fit).
- Use Cases: this is to separate use cases (like summarization, question
answering, evaluation, etc) from the modules, and provide a different
entry point to the code base.
There is also a full reference section, as well as extra resources
(glossary, gallery, etc)
Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
2023-01-02 16:24:09 +00:00
"AI: Hi there, how are you doing today?\n",
2022-11-26 02:28:55 +00:00
"Human: Not to bad - how are you?\n",
"Chatbot:\u001b[0m\n",
"\n",
Docs refactor (#480)
Big docs refactor! Motivation is to make it easier for people to find
resources they are looking for. To accomplish this, there are now three
main sections:
- Getting Started: steps for getting started, walking through most core
functionality
- Modules: these are different modules of functionality that langchain
provides. Each part here has a "getting started", "how to", "key
concepts" and "reference" section (except in a few select cases where it
didnt easily fit).
- Use Cases: this is to separate use cases (like summarization, question
answering, evaluation, etc) from the modules, and provide a different
entry point to the code base.
There is also a full reference section, as well as extra resources
(glossary, gallery, etc)
Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
2023-01-02 16:24:09 +00:00
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n"
2022-11-26 02:28:55 +00:00
]
},
{
"data": {
"text/plain": [
Docs refactor (#480)
Big docs refactor! Motivation is to make it easier for people to find
resources they are looking for. To accomplish this, there are now three
main sections:
- Getting Started: steps for getting started, walking through most core
functionality
- Modules: these are different modules of functionality that langchain
provides. Each part here has a "getting started", "how to", "key
concepts" and "reference" section (except in a few select cases where it
didnt easily fit).
- Use Cases: this is to separate use cases (like summarization, question
answering, evaluation, etc) from the modules, and provide a different
entry point to the code base.
There is also a full reference section, as well as extra resources
(glossary, gallery, etc)
Co-authored-by: Shreya Rajpal <ShreyaR@users.noreply.github.com>
2023-01-02 16:24:09 +00:00
"\" I'm doing great, thank you for asking!\""
2022-11-26 02:28:55 +00:00
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"llm_chain.predict(human_input=\"Not to bad - how are you?\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ae5309bb",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
2023-03-07 15:59:37 +00:00
"version": "3.9.1"
2022-11-26 02:28:55 +00:00
}
},
"nbformat": 4,
"nbformat_minor": 5
}