forked from Archives/langchain
add output parser
Harrison Chase
1 year ago
commit
a57e74996f
@ -0,0 +1,232 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ba5f8741",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Custom Agent\n",
|
||||
"\n",
|
||||
"This notebook goes through how to create your own custom agent.\n",
|
||||
"\n",
|
||||
"An agent consists of three parts:\n",
|
||||
" \n",
|
||||
" - Tools: The tools the agent has available to use.\n",
|
||||
" - LLMChain: The LLMChain that produces the text that is parsed in a certain way to determine which action to take.\n",
|
||||
" - The agent class itself: this parses the output of the LLMChain to determin which action to take.\n",
|
||||
" \n",
|
||||
" \n",
|
||||
"In this notebook we walk through two types of custom agents. The first type shows how to create a custom LLMChain, but still use an existing agent class to parse the output. The second shows how to create a custom agent class."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "6064f080",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Custom LLMChain\n",
|
||||
"\n",
|
||||
"The first way to create a custom agent is to use an existing Agent class, but use a custom LLMChain. This is the simplest way to create a custom Agent. It is highly reccomended that you work with the `ZeroShotAgent`, as at the moment that is by far the most generalizable one. \n",
|
||||
"\n",
|
||||
"Most of the work in creating the custom LLMChain comes down to the prompt. Because we are using an existing agent class to parse the output, it is very important that the prompt say to produce text in that format. However, besides those instructions, you can customize the prompt as you wish.\n",
|
||||
"\n",
|
||||
"To ensure that the prompt contains the appropriate instructions, we will utilize a helper method on that class. The helper method for the `ZeroShotAgent` takes the following arguments:\n",
|
||||
"\n",
|
||||
"- tools: List of tools the agent will have access to, used to format the prompt.\n",
|
||||
"- prefix: String to put before the list of tools.\n",
|
||||
"- suffix: String to put after the list of tools.\n",
|
||||
"- input_variables: List of input variables the final prompt will expect.\n",
|
||||
"\n",
|
||||
"For this exercise, we will give our agent access to Google Search, and we will customize it in that we will have it answer as a pirate."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "9af9734e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import ZeroShotAgent, Tool\n",
|
||||
"from langchain import OpenAI, SerpAPIChain, LLMChain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "becda2a1",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search = SerpAPIChain()\n",
|
||||
"tools = [\n",
|
||||
" Tool(\n",
|
||||
" name = \"Search\",\n",
|
||||
" func=search.run,\n",
|
||||
" description=\"useful for when you need to answer questions about current events\"\n",
|
||||
" )\n",
|
||||
"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "339b1bb8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"prefix = \"\"\"Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:\"\"\"\n",
|
||||
"suffix = \"\"\"Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Args\"\n",
|
||||
"\n",
|
||||
"Question: {input}\"\"\"\n",
|
||||
"\n",
|
||||
"prompt = ZeroShotAgent.create_prompt(\n",
|
||||
" tools, \n",
|
||||
" prefix=prefix, \n",
|
||||
" suffix=suffix, \n",
|
||||
" input_variables=[\"input\"]\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "59db7b58",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In case we are curious, we can now take a look at the final prompt template to see what it looks like when its all put together."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "e21d2098",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:\n",
|
||||
"\n",
|
||||
"Search: useful for when you need to answer questions about current events\n",
|
||||
"\n",
|
||||
"Use the following format:\n",
|
||||
"\n",
|
||||
"Question: the input question you must answer\n",
|
||||
"Thought: you should always think about what to do\n",
|
||||
"Action: the action to take, should be one of [Search]\n",
|
||||
"Action Input: the input to the action\n",
|
||||
"Observation: the result of the action\n",
|
||||
"... (this Thought/Action/Action Input/Observation can repeat N times)\n",
|
||||
"Thought: I now know the final answer\n",
|
||||
"Final Answer: the final answer to the original input question\n",
|
||||
"\n",
|
||||
"Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Args\"\n",
|
||||
"\n",
|
||||
"Question: {input}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(prompt.template)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "9b1cc2a2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "e4f5092f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "653b1617",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"How many people live in canada?\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look this up\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: How many people live in canada\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mThe current population of Canada is 38,533,678 as of Friday, November 25, 2022, based on Worldometer elaboration of the latest United Nations data. · Canada 2020 ...\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: Arrr, there be 38,533,678 people in Canada\u001b[0m\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Arrr, there be 38,533,678 people in Canada'"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\"How many people live in canada?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "90171b2b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Custom Agent Class\n",
|
||||
"\n",
|
||||
"Coming soon."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "adefb4c2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@ -0,0 +1,11 @@
|
||||
Memory
|
||||
======
|
||||
|
||||
The examples here are all related to working with the concept of Memory in LangChain.
|
||||
|
||||
.. toctree::
|
||||
:maxdepth: 1
|
||||
:glob:
|
||||
:caption: Memory
|
||||
|
||||
memory/*
|
||||
@ -0,0 +1,175 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "00695447",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Adding Memory To an LLMChain\n",
|
||||
"\n",
|
||||
"This notebook goes over how to use the Memory class with an LLMChain. For the purposes of this walkthrough, we will add the `ConversationBufferMemory` class, although this can be any memory class."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "9f1aaf47",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chains.conversation.memory import ConversationBufferMemory\n",
|
||||
"from langchain import OpenAI, LLMChain, PromptTemplate"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4b066ced",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The most important step is setting up the prompt correctly. In the below prompt, we have two input keys: one for the actual input, another for the input from the Memory class. Importantly, we make sure the keys in the PromptTemplate and the ConversationBufferMemory match up (`chat_history`)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "e5501eda",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"template = \"\"\"You are a chatbot having a conversation with a human.\n",
|
||||
"\n",
|
||||
"{chat_history}\n",
|
||||
"Human: {human_input}\n",
|
||||
"Chatbot:\"\"\"\n",
|
||||
"\n",
|
||||
"prompt = PromptTemplate(\n",
|
||||
" input_variables=[\"chat_history\", \"human_input\"], \n",
|
||||
" template=template\n",
|
||||
")\n",
|
||||
"memory = ConversationBufferMemory(memory_key=\"chat_history\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "f6566275",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm_chain = LLMChain(\n",
|
||||
" llm=OpenAI(), \n",
|
||||
" prompt=prompt, \n",
|
||||
" verbose=True, \n",
|
||||
" memory=memory,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "e2b189dc",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mYou are a chatbot having a conversation with a human.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Human: Hi there my friend\n",
|
||||
"Chatbot:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"' Hi there!'"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"llm_chain.predict(human_input=\"Hi there my friend\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "a902729f",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mYou are a chatbot having a conversation with a human.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Human: Hi there my friend\n",
|
||||
"AI: Hi there!\n",
|
||||
"Human: Not to bad - how are you?\n",
|
||||
"Chatbot:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"\\n\\nI'm doing well, thanks for asking. How about you?\""
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"llm_chain.predict(human_input=\"Not to bad - how are you?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "ae5309bb",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@ -0,0 +1,325 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "fa6802ac",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Adding Memory to an Agent\n",
|
||||
"\n",
|
||||
"This notebook goes over adding memory to an Agent. Before going through this notebook, please walkthrough the following notebooks, as this will build on top of both of them:\n",
|
||||
"\n",
|
||||
"- [Adding memory to an LLM Chain](adding_memory.ipynb)\n",
|
||||
"- [Custom Agents](../agents/custom_agent.ipynb)\n",
|
||||
"\n",
|
||||
"In order to add a memory to an agent we are going to the the following steps:\n",
|
||||
"\n",
|
||||
"1. We are going to create an LLMChain with memory.\n",
|
||||
"2. We are going to use that LLMChain to create a custom Agent.\n",
|
||||
"\n",
|
||||
"For the purposes of this exercise, we are going to create a simple custom Agent that has access to a search tool and utilizes the `ConversationBufferMemory` class."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "8db95912",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import ZeroShotAgent, Tool\n",
|
||||
"from langchain.chains.conversation.memory import ConversationBufferMemory\n",
|
||||
"from langchain import OpenAI, SerpAPIChain, LLMChain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "97ad8467",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search = SerpAPIChain()\n",
|
||||
"tools = [\n",
|
||||
" Tool(\n",
|
||||
" name = \"Search\",\n",
|
||||
" func=search.run,\n",
|
||||
" description=\"useful for when you need to answer questions about current events\"\n",
|
||||
" )\n",
|
||||
"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4ad2e708",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Notice the usage of the `chat_history` variable in the PromptTemplate, which matches up with the dynamic key name in the ConversationBufferMemory."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "e3439cd6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"prefix = \"\"\"Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\"\"\"\n",
|
||||
"suffix = \"\"\"Begin!\"\n",
|
||||
"\n",
|
||||
"{chat_history}\n",
|
||||
"Question: {input}\"\"\"\n",
|
||||
"\n",
|
||||
"prompt = ZeroShotAgent.create_prompt(\n",
|
||||
" tools, \n",
|
||||
" prefix=prefix, \n",
|
||||
" suffix=suffix, \n",
|
||||
" input_variables=[\"input\", \"chat_history\"]\n",
|
||||
")\n",
|
||||
"memory = ConversationBufferMemory(memory_key=\"chat_history\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "0021675b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can now construct the LLMChain, with the Memory object, and then create the agent."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "c56a0e73",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt, memory=memory)\n",
|
||||
"agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "ca4bc1fb",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"How many people live in canada?\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look up how many people live in canada\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: \"How many people live in canada?\"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mThe current population of Canada is 38,533,678 as of Friday, November 25, 2022, based on Worldometer elaboration of the latest United Nations data. · Canada 2020 ...\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: The current population of Canada is 38,533,678 as of Friday, November 25, 2022, based on Worldometer elaboration of the latest United Nations data.\u001b[0m\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The current population of Canada is 38,533,678 as of Friday, November 25, 2022, based on Worldometer elaboration of the latest United Nations data.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\"How many people live in canada?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "45627664",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To test the memory of this agent, we can ask a followup question that relies on information in the previous exchange to be answered correctly."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "eecc0462",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"what is their national anthem called?\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m\n",
|
||||
"AI: I should look up the name of Canada's national anthem\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: \"What is the name of Canada's national anthem?\"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAfter 100 years of tradition, O Canada was proclaimed Canada's national anthem in 1980. The music for O Canada was composed in 1880 by Calixa ...\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m\n",
|
||||
"AI: I now know the final answer\n",
|
||||
"Final Answer: After 100 years of tradition, O Canada was proclaimed Canada's national anthem in 1980. The music for O Canada was composed in 1880 by Calixa Lavallée.\u001b[0m\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"After 100 years of tradition, O Canada was proclaimed Canada's national anthem in 1980. The music for O Canada was composed in 1880 by Calixa Lavallée.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\"what is their national anthem called?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "cc3d0aa4",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can see that the agent remembered that the previous question was about Canada, and properly asked Google Search what the name of Canada's national anthem was.\n",
|
||||
"\n",
|
||||
"For fun, let's compare this to an agent that does NOT have memory."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "3359d043",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"prefix = \"\"\"Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\"\"\"\n",
|
||||
"suffix = \"\"\"Begin!\"\n",
|
||||
"\n",
|
||||
"Question: {input}\"\"\"\n",
|
||||
"\n",
|
||||
"prompt = ZeroShotAgent.create_prompt(\n",
|
||||
" tools, \n",
|
||||
" prefix=prefix, \n",
|
||||
" suffix=suffix, \n",
|
||||
" input_variables=[\"input\"]\n",
|
||||
")\n",
|
||||
"llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)\n",
|
||||
"agent_without_memory = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "970d23df",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"How many people live in canada?\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should look up how many people live in canada\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: \"How many people live in canada?\"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mThe current population of Canada is 38,533,678 as of Friday, November 25, 2022, based on Worldometer elaboration of the latest United Nations data. · Canada 2020 ...\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: The current population of Canada is 38,533,678\u001b[0m\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The current population of Canada is 38,533,678'"
|
||||
]
|
||||
},
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_without_memory.run(\"How many people live in canada?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "d9ea82f0",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"what is their national anthem called?\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I should probably look this up\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: \"What is the national anthem of [country]\"\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mMost nation states have an anthem, defined as \"a song, as of praise, devotion, or patriotism\"; most anthems are either marches or hymns in style.\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
|
||||
"Final Answer: The national anthem is called \"the national anthem.\"\u001b[0m\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'The national anthem is called \"the national anthem.\"'"
|
||||
]
|
||||
},
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_without_memory.run(\"what is their national anthem called?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "5b1f9223",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@ -0,0 +1,295 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "94e33ebe",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Custom Memory\n",
|
||||
"Although there are a few predefined types of memory in LangChain, it is highly possible you will want to add your own type of memory that is optimal for your application. This notebook covers how to do that."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "bdfd0305",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"For this notebook, we will add a custom memory type to `ConversationChain`. In order to add a custom memory class, we need to import the base memory class and subclass it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "6d787ef2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain import OpenAI, ConversationChain\n",
|
||||
"from langchain.chains.base import Memory\n",
|
||||
"from pydantic import BaseModel\n",
|
||||
"from typing import List, Dict, Any"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "9489e5e1",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In this example, we will write a custom memory class that uses spacy to extract entities and save information about them in a simple hash table. Then, during the conversation, we will look at the input text, extract any entities, and put any information about them into the context.\n",
|
||||
"\n",
|
||||
"* Please note that this implementation is pretty simple and brittle and probably not useful in a production setting. Its purpose is to showcase that you can add custom memory implementations.\n",
|
||||
"\n",
|
||||
"For this, we will need spacy."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "12bbed4e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# !pip install spacy\n",
|
||||
"# !python -m spacy download en_core_web_lg"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "ff065f58",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import spacy\n",
|
||||
"nlp = spacy.load('en_core_web_lg')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "1d45d429",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"class SpacyEntityMemory(Memory, BaseModel):\n",
|
||||
" \"\"\"Memory class for storing information about entities.\"\"\"\n",
|
||||
"\n",
|
||||
" # Define dictionary to store information about entities.\n",
|
||||
" entities: dict = {}\n",
|
||||
" # Define key to pass information about entities into prompt.\n",
|
||||
" memory_key: str = \"entities\"\n",
|
||||
"\n",
|
||||
" @property\n",
|
||||
" def memory_variables(self) -> List[str]:\n",
|
||||
" \"\"\"Define the variables we are providing to the prompt.\"\"\"\n",
|
||||
" return [self.memory_key]\n",
|
||||
"\n",
|
||||
" def load_memory_variables(self, inputs: Dict[str, Any]) -> Dict[str, str]:\n",
|
||||
" \"\"\"Load the memory variables, in this case the entity key.\"\"\"\n",
|
||||
" # Get the input text and run through spacy\n",
|
||||
" doc = nlp(inputs[list(inputs.keys())[0]])\n",
|
||||
" # Extract known information about entities, if they exist.\n",
|
||||
" entities = [self.entities[str(ent)] for ent in doc.ents if str(ent) in self.entities]\n",
|
||||
" # Return combined information about entities to put into context.\n",
|
||||
" return {self.memory_key: \"\\n\".join(entities)}\n",
|
||||
"\n",
|
||||
" def save_context(self, inputs: Dict[str, Any], outputs: Dict[str, str]) -> None:\n",
|
||||
" \"\"\"Save context from this conversation to buffer.\"\"\"\n",
|
||||
" # Get the input text and run through spacy\n",
|
||||
" text = inputs[list(inputs.keys())[0]]\n",
|
||||
" doc = nlp(text)\n",
|
||||
" # For each entity that was mentioned, save this information to the dictionary.\n",
|
||||
" for ent in doc.ents:\n",
|
||||
" ent_str = str(ent)\n",
|
||||
" if ent_str in self.entities:\n",
|
||||
" self.entities[ent_str] += f\"\\n{text}\"\n",
|
||||
" else:\n",
|
||||
" self.entities[ent_str] = text"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "429ba264",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We now define a prompt that takes in information about entities as well as user input"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "c05159b6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.prompts.prompt import PromptTemplate\n",
|
||||
"\n",
|
||||
"template = \"\"\"The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know. You are provided with information about entities the Human mentions, if relevant.\n",
|
||||
"\n",
|
||||
"Relevant entity information:\n",
|
||||
"{entities}\n",
|
||||
"\n",
|
||||
"Conversation:\n",
|
||||
"Human: {input}\n",
|
||||
"AI:\"\"\"\n",
|
||||
"prompt = PromptTemplate(\n",
|
||||
" input_variables=[\"entities\", \"input\"], template=template\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "db611041",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"And now we put it all together!"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "f08dc8ed",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"conversation = ConversationChain(llm=llm, prompt=prompt, verbose=True, memory=SpacyEntityMemory())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "92a5f685",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In the first example, with no prior knowledge about Harrison, the \"Relevant entity information\" section is empty."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "5b96e836",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know. You are provided with information about entities the Human mentions, if relevant.\n",
|
||||
"\n",
|
||||
"Relevant entity information:\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Conversation:\n",
|
||||
"Human: Harrison likes machine learning\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"\\n\\nThat's really interesting! I'm sure he has a lot of fun with it.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.predict(input=\"Harrison likes machine learning\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b1faa743",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now in the second example, we can see that it pulls in information about Harrison."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "4bca7070",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new chain...\u001b[0m\n",
|
||||
"Prompt after formatting:\n",
|
||||
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know. You are provided with information about entities the Human mentions, if relevant.\n",
|
||||
"\n",
|
||||
"Relevant entity information:\n",
|
||||
"Harrison likes machine learning\n",
|
||||
"\n",
|
||||
"Conversation:\n",
|
||||
"Human: What do you think Harrison's favorite subject in college was?\n",
|
||||
"AI:\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\" Harrison's favorite subject in college was machine learning.\""
|
||||
]
|
||||
},
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversation.predict(input=\"What do you think Harrison's favorite subject in college was?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "58b856e3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Again, please note that this implementation is pretty simple and brittle and probably not useful in a production setting. Its purpose is to showcase that you can add custom memory implementations."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "a1994600",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@ -0,0 +1,176 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f897c784",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Custom ExampleSelector\n",
|
||||
"\n",
|
||||
"This notebook goes over how to implement a custom ExampleSelector. ExampleSelectors are used to select examples to use in few shot prompts.\n",
|
||||
"\n",
|
||||
"An ExampleSelector must implement two methods:\n",
|
||||
"\n",
|
||||
"1. An `add_example` method which takes in an example and adds it into the ExampleSelector\n",
|
||||
"2. A `select_examples` method which takes in input variables (which are meant to be user input) and returns a list of examples to use in the few shot prompt.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"Let's implement a custom ExampleSelector that just selects two examples at random."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "1a945da1",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.prompts.example_selector.base import BaseExampleSelector\n",
|
||||
"from typing import Dict, List\n",
|
||||
"import numpy as np"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "62cf0ad7",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"class CustomExampleSelector(BaseExampleSelector):\n",
|
||||
" \n",
|
||||
" def __init__(self, examples: List[Dict[str, str]]):\n",
|
||||
" self.examples = examples\n",
|
||||
" \n",
|
||||
" def add_example(self, example: Dict[str, str]) -> None:\n",
|
||||
" \"\"\"Add new example to store for a key.\"\"\"\n",
|
||||
" self.examples.append(example)\n",
|
||||
"\n",
|
||||
" def select_examples(self, input_variables: Dict[str, str]) -> List[dict]:\n",
|
||||
" \"\"\"Select which examples to use based on the inputs.\"\"\"\n",
|
||||
" return np.random.choice(self.examples, size=2, replace=False)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "242d3213",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"examples = [{\"foo\": \"1\"}, {\"foo\": \"2\"}, {\"foo\": \"3\"}]\n",
|
||||
"example_selector = CustomExampleSelector(examples)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "2a038065",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Let's now try it out! We can select some examples and try adding examples."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "74fbbef5",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"array([{'foo': '2'}, {'foo': '3'}], dtype=object)"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"example_selector.select_examples({\"foo\": \"foo\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "9bbb5421",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"example_selector.add_example({\"foo\": \"4\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "c0eb9f22",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[{'foo': '1'}, {'foo': '2'}, {'foo': '3'}, {'foo': '4'}]"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"example_selector.examples"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "cc39b1e3",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"array([{'foo': '1'}, {'foo': '4'}], dtype=object)"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"example_selector.select_examples({\"foo\": \"foo\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "1739dd96",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@ -0,0 +1,153 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "9e9b7651",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Custom LLM\n",
|
||||
"\n",
|
||||
"This notebook goes over how to create a custom LLM wrapper, in case you want to use your own LLM or a different wrapper than one that is supported in LangChain.\n",
|
||||
"\n",
|
||||
"There is only one required thing that a custom LLM needs to implement:\n",
|
||||
"\n",
|
||||
"1. A `__call__` method that takes in a string, some optional stop words, and returns a string\n",
|
||||
"\n",
|
||||
"There is a second optional thing it can implement:\n",
|
||||
"\n",
|
||||
"1. An `_identifying_params` property that is used to help with printing of this class. Should return a dictionary.\n",
|
||||
"\n",
|
||||
"Let's implement a very simple custom LLM that just returns the first N characters of the input."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "a65696a0",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.llms.base import LLM\n",
|
||||
"from typing import Optional, List, Mapping, Any"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "d5ceff02",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"class CustomLLM(LLM):\n",
|
||||
" \n",
|
||||
" def __init__(self, n: int):\n",
|
||||
" self.n = n\n",
|
||||
" \n",
|
||||
" def __call__(self, prompt: str, stop: Optional[List[str]] = None) -> str:\n",
|
||||
" if stop is not None:\n",
|
||||
" raise ValueError(\"stop kwargs are not permitted.\")\n",
|
||||
" return prompt[:self.n]\n",
|
||||
" \n",
|
||||
" @property\n",
|
||||
" def _identifying_params(self) -> Mapping[str, Any]:\n",
|
||||
" \"\"\"Get the identifying parameters.\"\"\"\n",
|
||||
" return {\"n\": self.n}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "714dede0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can now use this as an any other LLM."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "10e5ece6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm = CustomLLM(n=10)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "8cd49199",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'This is a '"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"llm(\"This is a foobar thing\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "bbfebea1",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can also print the LLM and see its custom print."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "9c33fa19",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\u001b[1mCustomLLM\u001b[0m\n",
|
||||
"Params: {'n': 10}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(llm)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "6dac3f47",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@ -0,0 +1,116 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a37d9694",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Custom Prompt Template\n",
|
||||
"\n",
|
||||
"This notebook goes over how to create a custom prompt template, in case you want to create your own methodology for creating prompts.\n",
|
||||
"\n",
|
||||
"The only two requirements for all prompt templates are:\n",
|
||||
"\n",
|
||||
"1. They have a `input_variables` attribute that exposes what input variables this prompt template expects.\n",
|
||||
"2. They expose a `format` method which takes in keyword arguments corresponding to the expected `input_variables` and returns the formatted prompt.\n",
|
||||
"\n",
|
||||
"Let's imagine that we want to create a prompt template that takes in input variables and formats them into the template AFTER capitalizing them. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "26f796e5",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.prompts import BasePromptTemplate\n",
|
||||
"from pydantic import BaseModel"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "27919e96",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"class CustomPromptTemplate(BasePromptTemplate, BaseModel):\n",
|
||||
" template: str\n",
|
||||
" \n",
|
||||
" def format(self, **kwargs) -> str:\n",
|
||||
" capitalized_kwargs = {k: v.upper() for k, v in kwargs.items()}\n",
|
||||
" return self.template.format(**capitalized_kwargs)\n",
|
||||
" "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "76d1d84d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can now see that when we use this, the input variables get formatted."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "eed1ff28",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"prompt = CustomPromptTemplate(input_variables=[\"foo\"], template=\"Capitalized: {foo}\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "94892a3c",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Capitalized: LOWERCASE'"
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"prompt.format(foo=\"lowercase\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d3d9a7c7",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.7.6"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@ -1 +1 @@
|
||||
0.0.20
|
||||
0.0.22
|
||||
|
||||
Loading…
Reference in New Issue