github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-08-31 02:11:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: anthropic partner package docs (#18109)

Browse Source
This commit is contained in:
Erick Friis
2024-02-26 09:51:44 -08:00
committed by GitHub
parent b1d9ce541d
commit f5cf6975ba
3 changed files with 200 additions and 322 deletions
Download Patch File Download Diff File Expand all files Collapse all files

209
docs/docs/integrations/chat/anthropic.ipynb
View File

@@ -17,40 +17,44 @@
"source": [
"# ChatAnthropic\n",
"\n",
"This notebook covers how to get started with Anthropic chat models."
"This notebook covers how to get started with Anthropic chat models.\n",
"\n",
"## Setup\n",
"\n",
"For setup instructions, please see the Installation and Environment Setup sections of the [Anthropic Platform page](/docs/integrations/platforms/anthropic.mdx)."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "d4a7c55d-b235-4ca4-a579-c90cc9570da9",
"metadata": {
"ExecuteTime": {
"end_time": "2024-01-19T11:25:00.590587Z",
"start_time": "2024-01-19T11:25:00.127293Z"
},
"tags": []
},
"execution_count": null,
"id": "91be2e12",
"metadata": {},
"outputs": [],
"source": [
"from langchain_community.chat_models import ChatAnthropic\n",
"from langchain_core.prompts import ChatPromptTemplate"
"%pip install -qU langchain-anthropic"
]
},
{
"cell_type": "markdown",
"id": "584ed5ec",
"metadata": {},
"source": [
"## Environment Setup\n",
"\n",
"We'll need to get a [Anthropic](https://console.anthropic.com/settings/keys) and set the `ANTHROPIC_API_KEY` environment variable:"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "70cf04e8-423a-4ff6-8b09-f11fb711c817",
"metadata": {
"ExecuteTime": {
"end_time": "2024-01-19T11:25:04.349676Z",
"start_time": "2024-01-19T11:25:03.964930Z"
},
"tags": []
},
"execution_count": null,
"id": "01578ae3",
"metadata": {},
"outputs": [],
"source": [
"chat = ChatAnthropic(temperature=0, model_name=\"claude-2\")"
"import os\n",
"from getpass import getpass\n",
"\n",
"os.environ[\"ANTHROPIC_API_KEY\"] = getpass()"
]
},
{
@@ -82,7 +86,9 @@
"outputs": [
{
"data": {
"text/plain": "AIMessage(content=' 저는 파이썬을 좋아합니다.')"
"text/plain": [
"AIMessage(content=' 저는 파이썬을 좋아합니다.')"
]
},
"execution_count": 3,
"metadata": {},
@@ -90,6 +96,11 @@
}
],
"source": [
"from langchain_anthropic import ChatAnthropic\n",
"from langchain_core.prompts import ChatPromptTemplate\n",
"\n",
"chat = ChatAnthropic(temperature=0, model_name=\"claude-2\")\n",
"\n",
"system = (\n",
" \"You are a helpful assistant that translates {input_language} to {output_language}.\"\n",
")\n",
@@ -128,7 +139,9 @@
"outputs": [
{
"data": {
"text/plain": "AIMessage(content=\" Why don't bears like fast food? Because they can't catch it!\")"
"text/plain": [
"AIMessage(content=\" Why don't bears like fast food? Because they can't catch it!\")"
]
},
"execution_count": 4,
"metadata": {},
@@ -189,154 +202,6 @@
"for chunk in chain.stream({}):\n",
" print(chunk.content, end=\"\", flush=True)"
]
},
{
"cell_type": "markdown",
"id": "3737fc8d",
"metadata": {},
"source": [
"# ChatAnthropicMessages\n",
"\n",
"LangChain also offers the beta Anthropic Messages endpoint through the new `langchain-anthropic` package."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c253883f",
"metadata": {},
"outputs": [],
"source": [
"%pip install --upgrade --quiet langchain-anthropic"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "07c47c2a",
"metadata": {
"ExecuteTime": {
"end_time": "2024-01-19T11:25:25.288133Z",
"start_time": "2024-01-19T11:25:24.438968Z"
}
},
"outputs": [
{
"data": {
"text/plain": "AIMessage(content='파이썬을 사랑합니다.')"
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain_anthropic import ChatAnthropicMessages\n",
"\n",
"chat = ChatAnthropicMessages(model_name=\"claude-instant-1.2\")\n",
"system = (\n",
" \"You are a helpful assistant that translates {input_language} to {output_language}.\"\n",
")\n",
"human = \"{text}\"\n",
"prompt = ChatPromptTemplate.from_messages([(\"system\", system), (\"human\", human)])\n",
"\n",
"chain = prompt | chat\n",
"chain.invoke(\n",
" {\n",
" \"input_language\": \"English\",\n",
" \"output_language\": \"Korean\",\n",
" \"text\": \"I love Python\",\n",
" }\n",
")"
]
},
{
"cell_type": "markdown",
"id": "19e53d75935143fd",
"metadata": {
"collapsed": false
},
"source": [
"ChatAnthropicMessages also requires the anthropic_api_key argument, or the ANTHROPIC_API_KEY environment variable must be set. \n",
"\n",
"ChatAnthropicMessages also supports async and streaming functionality:"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "e20a139d30e3d333",
"metadata": {
"ExecuteTime": {
"end_time": "2024-01-19T11:25:26.012325Z",
"start_time": "2024-01-19T11:25:25.288358Z"
},
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": "AIMessage(content='파이썬을 사랑합니다.')"
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"await chain.ainvoke(\n",
" {\n",
" \"input_language\": \"English\",\n",
" \"output_language\": \"Korean\",\n",
" \"text\": \"I love Python\",\n",
" }\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "6f34f1073d7e7120",
"metadata": {
"ExecuteTime": {
"end_time": "2024-01-19T11:25:28.323455Z",
"start_time": "2024-01-19T11:25:26.012040Z"
},
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Here are some of the most famous tourist attractions in Japan:\n",
"\n",
"- Tokyo Tower - A communication and observation tower in Tokyo modeled after the Eiffel Tower. It offers stunning views of the city.\n",
"\n",
"- Mount Fuji - Japan's highest and most famous mountain. It's a iconic symbol of Japan and a UNESCO World Heritage Site. \n",
"\n",
"- Itsukushima Shrine (Miyajima) - A shrine located on an island in Hiroshima prefecture, known for its \"floating\" torii gate that seems to float on water during high tide.\n",
"\n",
"- Himeji Castle - A UNESCO World Heritage Site famous for having withstood numerous battles without destruction to its intricate white walls and sloping, triangular roofs. \n",
"\n",
"- Kawaguchiko Station - Near Mount Fuji, this area is known for its scenic Fuji Five Lakes region. \n",
"\n",
"- Hiroshima Peace Memorial Park and Museum - Commemorates the world's first atomic bombing in Hiroshima on August 6, 1945. \n",
"\n",
"- Arashiyama Bamboo Grove - A renowned bamboo forest located in Kyoto that draws many visitors.\n",
"\n",
"- Kegon Falls - One of Japan's largest waterfalls"
]
}
],
"source": [
"prompt = ChatPromptTemplate.from_messages(\n",
" [(\"human\", \"Give me a list of famous tourist attractions in Japan\")]\n",
")\n",
"chain = prompt | chat\n",
"for chunk in chain.stream({}):\n",
" print(chunk.content, end=\"\", flush=True)"
]
}
],
"metadata": {

143
docs/docs/integrations/llms/anthropic.ipynb Normal file
View File

@@ -0,0 +1,143 @@
{
"cells": [
{
"cell_type": "raw",
"id": "602a52a4",
"metadata": {},
"source": [
"---\n",
"sidebar_label: Anthropic\n",
"---"
]
},
{
"cell_type": "markdown",
"id": "9597802c",
"metadata": {},
"source": [
"# AnthropicLLM\n",
"\n",
"This example goes over how to use LangChain to interact with `Anthropic` models.\n",
"\n",
"## Installation"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "59c710c4",
"metadata": {},
"outputs": [],
"source": [
"%pip install -qU langchain-anthropic"
]
},
{
"cell_type": "markdown",
"id": "560a2f9254963fd7",
"metadata": {
"collapsed": false
},
"source": [
"## Environment Setup\n",
"\n",
"We'll need to get a [Anthropic](https://console.anthropic.com/settings/keys) and set the `ANTHROPIC_API_KEY` environment variable:"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "035dea0f",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"import os\n",
"from getpass import getpass\n",
"\n",
"os.environ[\"ANTHROPIC_API_KEY\"] = getpass()"
]
},
{
"cell_type": "markdown",
"id": "1891df96eb076e1a",
"metadata": {
"collapsed": false
},
"source": [
"## Usage"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "98f70927a87e4745",
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"'\\nLangChain is a decentralized blockchain network that leverages AI and machine learning to provide language translation services.'"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain_anthropic import AnthropicLLM\n",
"from langchain_core.prompts import PromptTemplate\n",
"\n",
"template = \"\"\"Question: {question}\n",
"\n",
"Answer: Let's think step by step.\"\"\"\n",
"\n",
"prompt = PromptTemplate.from_template(template)\n",
"\n",
"model = AnthropicLLM(model=\"claude-2.1\")\n",
"\n",
"chain = prompt | model\n",
"\n",
"chain.invoke({\"question\": \"What is LangChain?\"})"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a52f765c",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3.11.1 64-bit",
"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": "3.11.4"
},
"vscode": {
"interpreter": {
"hash": "e971737741ff4ec9aff7dc6155a1060a59a8a6d52c757dbbe66bf8ee389494b1"
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}

170
docs/docs/integrations/platforms/anthropic.mdx
View File

@@ -5,169 +5,39 @@ All functionality related to Anthropic models.
[Anthropic](https://www.anthropic.com/) is an AI safety and research company, and is the creator of Claude.
This page covers all integrations between Anthropic models and LangChain.
## Prompting Overview
## Installation
Claude is chat-based model, meaning it is trained on conversation data.
However, it is a text based API, meaning it takes in single string.
It expects this string to be in a particular format.
This means that it is up the user to ensure that is the case.
LangChain provides several utilities and helper functions to make sure prompts that you write -
whether formatted as a string or as a list of messages - end up formatted correctly.
To use Anthropic models, you will need to install the `langchain-anthropic` package.
You can do this with the following command:
Specifically, Claude is trained to fill in text for the Assistant role as part of an ongoing dialogue
between a human user (`Human:`) and an AI assistant (`Assistant:`). Prompts sent via the API must contain
`\n\nHuman:` and `\n\nAssistant:` as the signals of who's speaking.
The final turn must always be `\n\nAssistant:` - the input string cannot have `\n\nHuman:` as the final role.
```
pip install langchain-anthropic
```
Because Claude is chat-based but accepts a string as input, it can be treated as either a LangChain `ChatModel` or `LLM`.
This means there are two wrappers in LangChain - `ChatAnthropic` and `Anthropic`.
It is generally recommended to use the `ChatAnthropic` wrapper, and format your prompts as `ChatMessage`s (we will show examples of this below).
This is because it keeps your prompt in a general format that you can easily then also use with other models (should you want to).
However, if you want more fine-grained control over the prompt, you can use the `Anthropic` wrapper - we will show and example of this as well.
The `Anthropic` wrapper however is deprecated, as all functionality can be achieved in a more generic way using `ChatAnthropic`.
## Prompting Best Practices
Anthropic models have several prompting best practices compared to OpenAI models.
**No System Messages**
Anthropic models are not trained on the concept of a "system message".
We have worked with the Anthropic team to handle them somewhat appropriately (a Human message with an `admin` tag)
but this is largely a hack and it is recommended that you do not use system messages.
**AI Messages Can Continue**
A completion from Claude is a continuation of the last text in the string which allows you further control over Claude's output.
For example, putting words in Claude's mouth in a prompt like this:
`\n\nHuman: Tell me a joke about bears\n\nAssistant: What do you call a bear with no teeth?`
This will return a completion like this `A gummy bear!` instead of a whole new assistant message with a different random bear joke.
## Environment Setup
To use Anthropic models, you will need to set the `ANTHROPIC_API_KEY` environment variable.
You can get an Anthropic API key [here](https://console.anthropic.com/settings/keys)
## `ChatAnthropic`
`ChatAnthropic` is a subclass of LangChain's `ChatModel`, meaning it works best with `ChatPromptTemplate`.
`ChatAnthropic` is a subclass of LangChain's `ChatModel`.
You can import this wrapper with the following code:
```
from langchain_community.chat_models import ChatAnthropic
model = ChatAnthropic()
from langchain_anthropic import ChatAnthropic
model = ChatAnthropic(model='claude-2.1')
```
When working with ChatModels, it is preferred that you design your prompts as `ChatPromptTemplate`s.
Here is an example below of doing that:
Read more in the [ChatAnthropic documentation](/docs/integrations/chat/anthropic).
```
from langchain_core.prompts import ChatPromptTemplate
## `AnthropicLLM`
prompt = ChatPromptTemplate.from_messages([
("system", "You are a helpful chatbot"),
("human", "Tell me a joke about {topic}"),
])
```
`AnthropicLLM` is a subclass of LangChain's `LLM`. It is a wrapper around Anthropic's
text-based completion endpoints.
You can then use this in a chain as follows:
```python
from langchain_anthropic import AnthropicLLM
```
chain = prompt | model
chain.invoke({"topic": "bears"})
```
How is the prompt actually being formatted under the hood? We can see that by running the following code
```
prompt_value = prompt.format_prompt(topic="bears")
model.convert_prompt(prompt_value)
```
This produces the following formatted string:
```
'\n\nYou are a helpful chatbot\n\nHuman: Tell me a joke about bears\n\nAssistant:'
```
We can see that under the hood LangChain is not appending any prefix/suffix to `SystemMessage`'s. This is because Anthropic has no concept of `SystemMessage`.
Anthropic requires all prompts to end with assistant messages. This means if the last message is not an assistant message, the suffix `Assistant:` will automatically be inserted.
If you decide instead to use a normal PromptTemplate (one that just works on a single string) let's take a look at
what happens:
```
from langchain.prompts import PromptTemplate
prompt = PromptTemplate.from_template("Tell me a joke about {topic}")
prompt_value = prompt.format_prompt(topic="bears")
model.convert_prompt(prompt_value)
```
This produces the following formatted string:
```
'\n\nHuman: Tell me a joke about bears\n\nAssistant:'
```
We can see that it automatically adds the Human and Assistant tags.
What is happening under the hood?
First: the string gets converted to a single human message. This happens generically (because we are using a subclass of `ChatModel`).
Then, similarly to the above example, an empty Assistant message is getting appended.
This is Anthropic specific.
## [Deprecated] `Anthropic`
This `Anthropic` wrapper is subclassed from `LLM`.
We can import it with:
```
from langchain_community.llms import Anthropic
model = Anthropic()
```
This model class is designed to work with normal PromptTemplates. An example of that is below:
```
prompt = PromptTemplate.from_template("Tell me a joke about {topic}")
chain = prompt | model
chain.invoke({"topic": "bears"})
```
Let's see what is going on with the prompt templating under the hood!
```
prompt_value = prompt.format_prompt(topic="bears")
model.convert_prompt(prompt_value)
```
This outputs the following
```
'\n\nHuman: Tell me a joke about bears\n\nAssistant: Sure, here you go:\n'
```
Notice that it adds the Human tag at the start of the string, and then finishes it with `\n\nAssistant: Sure, here you go:`.
The extra `Sure, here you go` was added on purpose by the Anthropic team.
What happens if we have those symbols in the prompt directly?
```
prompt = PromptTemplate.from_template("Human: Tell me a joke about {topic}")
prompt_value = prompt.format_prompt(topic="bears")
model.convert_prompt(prompt_value)
```
This outputs:
```
'\n\nHuman: Tell me a joke about bears'
```
We can see that we detect that the user is trying to use the special tokens, and so we don't do any formatting.
## `ChatAnthropicMessages` (Beta)
`ChatAnthropicMessages` uses the beta release of Anthropic's new Messages API.
You can use it from the `langchain-anthropic` package, which you can install with `pip install langchain-anthropic`.
For more information, see the [ChatAnthropicMessages docs](../chat/anthropic#chatanthropicmessages)
model = AnthropicLLM(model='claude-2.1')
```