blob42
/
langchain
forked from Archives/langchain
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Improve chat prompt template docs (#3719)

Browse Source 
Add a few more explanations and examples.
fix_agent_callbacks
engkheng 1 year ago committed by GitHub
parent 22770f5202
commit f37a932b24
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 265 additions and 21 deletions
Show Stats Download Patch File Download Diff File

286
docs/modules/prompts/chat_prompt_template.ipynb
Unescape Escape View File

@ -1,22 +1,28 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"id": "6488fdaf",
"metadata": {},
"source": [
"# Chat Prompt Template\n",
"\n",
"Chat Models takes a list of chat messages as input - this list commonly referred to as a prompt.\n",
"Typically this is not simply a hardcoded list of messages but rather a combination of a template, some examples, and user input.\n",
"LangChain provides several classes and functions to make constructing and working with prompts easy.\n"
"[Chat Models](../models/chat.rst) takes a list of chat messages as input - this list commonly referred to as a prompt.\n",
"These chat messages differ from raw string (which you would pass into a [LLM](../models/llms.rst) model) in that every message is associated with a role.\n",
"\n",
"For example, in OpenAI [Chat Completion API](https://platform.openai.com/docs/guides/chat/introduction), a chat message can be associated with the AI, human or system role. The model is supposed to follow instruction from system chat message more closely.\n",
"\n",
"Therefore, LangChain provides several related prompt templates to make constructing and working with prompts easily. You are encouraged to use these chat related prompt templates instead of `PromptTemplate` when querying chat models to fully exploit the potential of underlying chat model.\n"
]
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 35,
"id": "7647a621",
"metadata": {},
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.prompts import (\n",
@ -38,16 +44,18 @@
"id": "acb4a2f6",
"metadata": {},
"source": [
"You can make use of templating by using a `MessagePromptTemplate`. You can build a `ChatPromptTemplate` from one or more `MessagePromptTemplates`. You can use `ChatPromptTemplate`'s `format_prompt` -- this returns a `PromptValue`, which you can convert to a string or Message object, depending on whether you want to use the formatted value as input to an llm or chat model.\n",
"To create a message template associated with a role, you use `MessagePromptTemplate`. \n",
"\n",
"For convenience, there is a `from_template` method exposed on the template. If you were to use this template, this is what it would look like:"
]
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 36,
"id": "3124f5e9",
"metadata": {},
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"template=\"You are a helpful assistant that translates {input_language} to {output_language}.\"\n",
@ -56,11 +64,47 @@
"human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)"
]
},
{
"cell_type": "markdown",
"id": "c8b08cda-7c57-4c15-a1e5-80627cfa9cbd",
"metadata": {},
"source": [
"If you wanted to construct the `MessagePromptTemplate` more directly, you could create a PromptTemplate outside and then pass it in, eg:"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "9c7e2e6f",
"execution_count": 37,
"id": "5a8d249e",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"prompt=PromptTemplate(\n",
" template=\"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
" input_variables=[\"input_language\", \"output_language\"],\n",
")\n",
"system_message_prompt_2 = SystemMessagePromptTemplate(prompt=prompt)\n",
"\n",
"assert system_message_prompt == system_message_prompt_2"
]
},
{
"cell_type": "markdown",
"id": "96836c5c-41f8-4073-95ac-ea1daab2e00e",
"metadata": {},
"source": [
"After that, you can build a `ChatPromptTemplate` from one or more `MessagePromptTemplates`. You can use `ChatPromptTemplate`'s `format_prompt` -- this returns a `PromptValue`, which you can convert to a string or Message object, depending on whether you want to use the formatted value as input to an llm or chat model."
]
},
{
"cell_type": "code",
"execution_count": 38,
"id": "9c7e2e6f",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
@ -69,7 +113,7 @@
" HumanMessage(content='I love programming.', additional_kwargs={})]"
]
},
"execution_count": 3,
"execution_count": 38,
"metadata": {},
"output_type": "execute_result"
}
@ -82,25 +126,225 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "0dbdf94f",
"id": "0899f681-012e-4687-a754-199a9a396738",
"metadata": {
"tags": []
},
"source": [
"## Format output\n",
"\n",
"The output of the format method is available as string, list of messages and `ChatPromptValue`"
]
},
{
"cell_type": "markdown",
"id": "584166de-0c31-4bc9-bf7a-5b359e7173d8",
"metadata": {},
"source": [
"If you wanted to construct the MessagePromptTemplate more directly, you could create a PromptTemplate outside and then pass it in, eg:"
"As string:"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "5a8d249e",
"execution_count": 39,
"id": "2f6c7ad1-def5-41dc-a4fe-3731dc8917f9",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"'System: You are a helpful assistant that translates English to French.\\nHuman: I love programming.'"
]
},
"execution_count": 39,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"output = chat_prompt.format(input_language=\"English\", output_language=\"French\", text=\"I love programming.\")\n",
"output"
]
},
{
"cell_type": "code",
"execution_count": 40,
"id": "144b3368-43f3-49fa-885f-3f3470e9ab7e",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# or alternatively \n",
"output_2 = chat_prompt.format_prompt(input_language=\"English\", output_language=\"French\", text=\"I love programming.\").to_string()\n",
"\n",
"assert output == output_2"
]
},
{
"cell_type": "markdown",
"id": "51970399-c2e1-4c9b-8003-6f5b1236fda8",
"metadata": {},
"source": [
"As `ChatPromptValue`"
]
},
{
"cell_type": "code",
"execution_count": 41,
"id": "681ce4a7-d972-4cdf-ac77-ec35182fd352",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"ChatPromptValue(messages=[SystemMessage(content='You are a helpful assistant that translates English to French.', additional_kwargs={}), HumanMessage(content='I love programming.', additional_kwargs={})])"
]
},
"execution_count": 41,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chat_prompt.format_prompt(input_language=\"English\", output_language=\"French\", text=\"I love programming.\")"
]
},
{
"cell_type": "markdown",
"id": "61041810-4418-4406-9c8a-91c9034c9752",
"metadata": {},
"source": [
"As list of Message objects"
]
},
{
"cell_type": "code",
"execution_count": 44,
"id": "4ec2f166-1ef9-4071-8c37-fcfbd3f4bc29",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"[SystemMessage(content='You are a helpful assistant that translates English to French.', additional_kwargs={}),\n",
" HumanMessage(content='I love programming.', additional_kwargs={})]"
]
},
"execution_count": 44,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"chat_prompt.format_prompt(input_language=\"English\", output_language=\"French\", text=\"I love programming.\").to_messages()"
]
},
{
"cell_type": "markdown",
"id": "73dcd3a2-ad6d-4b7b-ab21-1d9e417f959e",
"metadata": {},
"source": [
"## Different types of `MessagePromptTemplate`\n",
"\n",
"LangChain provides different types of `MessagePromptTemplate`. The most commonly used are `AIMessagePromptTemplate`, `SystemMessagePromptTemplate` and `HumanMessagePromptTemplate`, which create an AI message, system message and human message respectively.\n",
"\n",
"However, in cases where the chat model supports taking chat message with arbitrary role, you can use `ChatMessagePromptTemplate`, which allows user to specify the role name."
]
},
{
"cell_type": "code",
"execution_count": 45,
"id": "55a21b1f-9cdc-4072-a41d-695b00dd11e6",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"ChatMessage(content='May the force be with you', additional_kwargs={}, role='Jedi')"
]
},
"execution_count": 45,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain.prompts import ChatMessagePromptTemplate\n",
"\n",
"prompt = \"May the {subject} be with you\"\n",
"\n",
"chat_message_prompt = ChatMessagePromptTemplate.from_template(role=\"Jedi\", template=prompt)\n",
"chat_message_prompt.format(subject=\"force\")"
]
},
{
"cell_type": "markdown",
"id": "cd6bf82b-4709-4683-b215-6b7c468f3347",
"metadata": {},
"source": [
"LangChain also provides `MessagesPlaceholder`, which gives you full control of what messages to be rendered during formatting. This can be useful when you are uncertain of what role you should be using for your message prompt templates or when you wish to insert a list of messages during formatting."
]
},
{
"cell_type": "code",
"execution_count": 46,
"id": "9f034650-5e50-4bc3-80f8-5e428ca6444d",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"prompt=PromptTemplate(\n",
" template=\"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
" input_variables=[\"input_language\", \"output_language\"],\n",
")\n",
"system_message_prompt = SystemMessagePromptTemplate(prompt=prompt)"
"from langchain.prompts import MessagesPlaceholder\n",
"\n",
"human_prompt = \"Summarize our conversation so far in {word_count} words.\"\n",
"human_message_template = HumanMessagePromptTemplate.from_template(human_prompt)\n",
"\n",
"chat_prompt = ChatPromptTemplate.from_messages([MessagesPlaceholder(variable_name=\"conversation\"), human_message_template])"
]
},
{
"cell_type": "code",
"execution_count": 47,
"id": "9789e8e7-b3f9-4391-a85c-373e576107b3",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"[HumanMessage(content='What is the best way to learn programming?', additional_kwargs={}),\n",
" AIMessage(content='1. Choose a programming language: Decide on a programming language that you want to learn. \\n\\n2. Start with the basics: Familiarize yourself with the basic programming concepts such as variables, data types and control structures.\\n\\n3. Practice, practice, practice: The best way to learn programming is through hands-on experience', additional_kwargs={}),\n",
" HumanMessage(content='Summarize our conversation so far in 10 words.', additional_kwargs={})]"
]
},
"execution_count": 47,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"human_message = HumanMessage(content=\"What is the best way to learn programming?\")\n",
"ai_message = AIMessage(content=\"\"\"\\\n",
"1. Choose a programming language: Decide on a programming language that you want to learn. \n",
"\n",
"2. Start with the basics: Familiarize yourself with the basic programming concepts such as variables, data types and control structures.\n",
"\n",
"3. Practice, practice, practice: The best way to learn programming is through hands-on experience\\\n",
"\"\"\")\n",
"\n",
"chat_prompt.format_prompt(conversation=[human_message, ai_message], word_count=\"10\").to_messages()"
]
}
],
@ -120,7 +364,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
"version": "3.10.10"
}
},
"nbformat": 4,

Write Preview
Loading…
Cancel
Save