Archives/langchain
2
0
Fork 1
mirror of https://github.com/hwchase17/langchain synced 2024-11-10 01:10:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

[docs]: LLM integration pages (#25005)

Browse Source
This commit is contained in:
Isaac Francisco 2024-08-13 14:50:45 -07:00 committed by GitHub
parent 9d08369442
commit 0478f7f5e4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 253 additions and 135 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
docs/docs/integrations/llms/anthropic.ipynb
View File

@ -23,7 +23,7 @@
"# AnthropicLLM\n",
"\n",
":::caution\n",
"You are currently on a page documenting the use of Anthropic legacy Claude 2 models as [text completion models](/docs/concepts/#llms). The latest and most popular Anthropic models are [chat completion models](/docs/concepts/#chat-models).\n",
"You are currently on a page documenting the use of Anthropic legacy Claude 2 models as [text completion models](/docs/concepts/#llms). The latest and most popular Anthropic models are [chat completion models](/docs/concepts/#chat-models), and the text completion models have been deprecated.\n",
"\n",
"You are probably looking for [this page instead](/docs/integrations/chat/anthropic/).\n",
":::\n",
@ -115,14 +115,6 @@
"\n",
"chain.invoke({\"question\": \"What is LangChain?\"})"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a52f765c",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {

64
docs/docs/integrations/llms/cohere.ipynb
View File

@ -15,7 +15,14 @@
"\n",
">[Cohere](https://cohere.ai/about) is a Canadian startup that provides natural language processing models that help companies improve human-machine interactions.\n",
"\n",
"Head to the [API reference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.cohere.Cohere.html) for detailed documentation of all attributes and methods."
"Head to the [API reference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.cohere.Cohere.html) for detailed documentation of all attributes and methods.\n",
"\n",
"## Overview\n",
"### Integration details\n",
"\n",
"| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/llms/cohere/) | Package downloads | Package latest |\n",
"| :--- | :--- | :---: | :---: | :---: | :---: | :---: |\n",
"| [Cohere](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.cohere.Cohere.html) | [langchain_community](https://api.python.langchain.com/en/latest/community_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_community?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_community?style=flat-square&label=%20) |\n"
]
},
{
@ -29,34 +36,43 @@
"\n",
"The integration lives in the `langchain-community` package. We also need to install the `cohere` package itself. We can install these with:\n",
"\n",
"```bash\n",
"pip install -U langchain-community langchain-cohere\n",
"```\n",
"### Credentials\n",
"\n",
"We'll also need to get a [Cohere API key](https://cohere.com/) and set the `COHERE_API_KEY` environment variable:"
"We'll need to get a [Cohere API key](https://cohere.com/) and set the `COHERE_API_KEY` environment variable:"
]
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": null,
"id": "3f5dc9d7-65e3-4b5b-9086-3327d016cfe0",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" ········\n"
]
}
],
"outputs": [],
"source": [
"import getpass\n",
"import os\n",
"\n",
"os.environ[\"COHERE_API_KEY\"] = getpass.getpass()"
"if \"COHERE_API_KEY\" not in os.environ:\n",
" os.environ[\"COHERE_API_KEY\"] = getpass.getpass()"
]
},
{
"cell_type": "markdown",
"id": "ff211537",
"metadata": {},
"source": [
"### Installation"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "318454f9",
"metadata": {},
"outputs": [],
"source": [
"pip install -U langchain-community langchain-cohere"
]
},
{
@ -83,7 +99,7 @@
"id": "0b4e02bf-5beb-48af-a2a2-52cbcd8ebed6",
"metadata": {},
"source": [
"## Usage\n",
"## Invocation\n",
"\n",
"Cohere supports all [LLM](/docs/how_to#llms) functionality:"
]
@ -199,6 +215,8 @@
"id": "39198f7d-6fc8-4662-954a-37ad38c4bec4",
"metadata": {},
"source": [
"## Chaining\n",
"\n",
"You can also easily combine with a prompt template for easy structuring of user input. We can do this using [LCEL](/docs/concepts#langchain-expression-language-lcel)"
]
},
@ -237,12 +255,14 @@
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4797d719",
"cell_type": "markdown",
"id": "ac5fcbed",
"metadata": {},
"outputs": [],
"source": []
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all `Cohere` llm features and configurations head to the API reference: https://api.python.langchain.com/en/latest/llms/langchain_community.llms.cohere.Cohere.html"
]
}
],
"metadata": {

109
docs/docs/integrations/llms/fireworks.ipynb
View File

@ -15,7 +15,14 @@
"\n",
">[Fireworks](https://app.fireworks.ai/) accelerates product development on generative AI by creating an innovative AI experiment and production platform. \n",
"\n",
"This example goes over how to use LangChain to interact with `Fireworks` models."
"This example goes over how to use LangChain to interact with `Fireworks` models.\n",
"\n",
"## Overview\n",
"### Integration details\n",
"\n",
"| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.1/docs/integrations/llms/fireworks/) | Package downloads | Package latest |\n",
"| :--- | :--- | :---: | :---: | :---: | :---: | :---: |\n",
"| [Fireworks](https://api.python.langchain.com/en/latest/llms/langchain_fireworks.llms.Fireworks.html#langchain_fireworks.llms.Fireworks) | [langchain_fireworks](https://api.python.langchain.com/en/latest/fireworks_api_reference.html) | ❌ | ❌ | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_fireworks?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_fireworks?style=flat-square&label=%20) |"
]
},
{
@ -24,29 +31,18 @@
"id": "fb345268",
"metadata": {},
"outputs": [],
"source": [
"%pip install -qU langchain-fireworks"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "60b6dbb2",
"metadata": {},
"outputs": [],
"source": [
"from langchain_fireworks import Fireworks"
]
"source": []
},
{
"cell_type": "markdown",
"id": "ccff689e",
"metadata": {},
"source": [
"# Setup\n",
"## Setup\n",
"\n",
"1. Make sure the `langchain-fireworks` package is installed in your environment.\n",
"2. Sign in to [Fireworks AI](http://fireworks.ai) for the an API Key to access our models, and make sure it is set as the `FIREWORKS_API_KEY` environment variable.\n",
"### Credentials \n",
"\n",
"Sign in to [Fireworks AI](http://fireworks.ai) for the an API Key to access our models, and make sure it is set as the `FIREWORKS_API_KEY` environment variable.\n",
"3. Set up your model using a model id. If the model is not set, the default model is fireworks-llama-v2-7b-chat. See the full, most up-to-date model list on [fireworks.ai](https://fireworks.ai)."
]
},
@ -60,10 +56,46 @@
"import getpass\n",
"import os\n",
"\n",
"from langchain_fireworks import Fireworks\n",
"\n",
"if \"FIREWORKS_API_KEY\" not in os.environ:\n",
" os.environ[\"FIREWORKS_API_KEY\"] = getpass.getpass(\"Fireworks API Key:\")\n",
" os.environ[\"FIREWORKS_API_KEY\"] = getpass.getpass(\"Fireworks API Key:\")"
]
},
{
"cell_type": "markdown",
"id": "e42ced7e",
"metadata": {},
"source": [
"### Installation\n",
"\n",
"You need to install the `langchain_fireworks` python package for the rest of the notebook to work."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ca824723",
"metadata": {},
"outputs": [],
"source": [
"%pip install -qU langchain-fireworks"
]
},
{
"cell_type": "markdown",
"id": "acc24d0c",
"metadata": {},
"source": [
"## Instantiation"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d285fd7f",
"metadata": {},
"outputs": [],
"source": [
"from langchain_fireworks import Fireworks\n",
"\n",
"# Initialize a Fireworks model\n",
"llm = Fireworks(\n",
@ -74,10 +106,10 @@
},
{
"cell_type": "markdown",
"id": "acc24d0c",
"id": "a4c29f7b",
"metadata": {},
"source": [
"# Calling the Model Directly\n",
"## Invocation\n",
"\n",
"You can call the model directly with string prompts to get completions."
]
@ -98,11 +130,18 @@
}
],
"source": [
"# Single prompt\n",
"output = llm.invoke(\"Who's the best quarterback in the NFL?\")\n",
"print(output)"
]
},
{
"cell_type": "markdown",
"id": "b0283343",
"metadata": {},
"source": [
"### Invoking with multiple prompts"
]
},
{
"cell_type": "code",
"execution_count": 5,
@ -128,6 +167,14 @@
"print(output.generations)"
]
},
{
"cell_type": "markdown",
"id": "f18f5717",
"metadata": {},
"source": [
"### Invoking with additional parameters"
]
},
{
"cell_type": "code",
"execution_count": 7,
@ -158,7 +205,7 @@
"id": "137662a6",
"metadata": {},
"source": [
"# Simple Chain with Non-Chat Model"
"## Chaining"
]
},
{
@ -206,6 +253,8 @@
"id": "d0a29826",
"metadata": {},
"source": [
"## Streaming\n",
"\n",
"You can stream the output, if you want."
]
},
@ -233,12 +282,14 @@
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fcc0eecb",
"cell_type": "markdown",
"id": "692c5e76",
"metadata": {},
"outputs": [],
"source": []
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all `Fireworks` LLM features and configurations head to the API reference: https://api.python.langchain.com/en/latest/llms/langchain_fireworks.llms.Fireworks.html#langchain_fireworks.llms.Fireworks"
]
}
],
"metadata": {

203
docs/docs/integrations/llms/openai.ipynb
View File

@ -19,33 +19,86 @@
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "5d71df86-8a17-4283-83d7-4e46e7c06c44",
"metadata": {
"tags": []
},
"outputs": [],
"cell_type": "markdown",
"id": "74312161",
"metadata": {},
"source": [
"# get a token: https://platform.openai.com/account/api-keys\n",
"## Overview\n",
"\n",
"from getpass import getpass\n",
"### Integration details\n",
"| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/chat/openai) | Package downloads | Package latest |\n",
"| :--- | :--- | :---: | :---: | :---: | :---: | :---: |\n",
"| [ChatOpenAI](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.base.ChatOpenAI.html) | [langchain-openai](https://api.python.langchain.com/en/latest/openai_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-openai?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-openai?style=flat-square&label=%20) |\n",
"\n",
"OPENAI_API_KEY = getpass()"
"\n",
"## Setup\n",
"\n",
"To access OpenAI models you'll need to create an OpenAI account, get an API key, and install the `langchain-openai` integration package.\n",
"\n",
"### Credentials\n",
"\n",
"Head to https://platform.openai.com to sign up to OpenAI and generate an API key. Once you've done this set the OPENAI_API_KEY environment variable:"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "5472a7cd-af26-48ca-ae9b-5f6ae73c74d2",
"metadata": {
"tags": []
},
"outputs": [],
"execution_count": null,
"id": "efcdb2b6",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Enter your OpenAI API key: ········\n"
]
}
],
"source": [
"import getpass\n",
"import os\n",
"\n",
"os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY"
"if \"OPENAI_API_KEY\" not in os.environ:\n",
" os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"Enter your OpenAI API key: \")"
]
},
{
"cell_type": "markdown",
"id": "f5d528fa",
"metadata": {},
"source": [
"If you want to get automated best in-class tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "52fa46e8",
"metadata": {},
"outputs": [],
"source": [
"# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
"# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
]
},
{
"cell_type": "markdown",
"id": "0fad78d8",
"metadata": {},
"source": [
"### Installation\n",
"\n",
"The LangChain OpenAI integration lives in the `langchain-openai` package:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2e300149",
"metadata": {},
"outputs": [],
"source": [
"%pip install -qU langchain-openai"
]
},
{
@ -60,7 +113,11 @@
"OPENAI_ORGANIZATION = getpass()\n",
"\n",
"os.environ[\"OPENAI_ORGANIZATION\"] = OPENAI_ORGANIZATION\n",
"```"
"```\n",
"\n",
"## Instantiation\n",
"\n",
"Now we can instantiate our model object and generate chat completions:"
]
},
{
@ -72,74 +129,29 @@
},
"outputs": [],
"source": [
"from langchain_core.prompts import PromptTemplate\n",
"from langchain_openai import OpenAI"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "035dea0f",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"template = \"\"\"Question: {question}\n",
"from langchain_openai import OpenAI\n",
"\n",
"Answer: Let's think step by step.\"\"\"\n",
"\n",
"prompt = PromptTemplate.from_template(template)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "3f3458d9",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"llm = OpenAI()"
]
},
{
"cell_type": "markdown",
"id": "4fc152cd",
"id": "464003c1",
"metadata": {},
"source": [
"If you manually want to specify your OpenAI API key and/or organization ID, you can use the following:\n",
"```python\n",
"llm = OpenAI(openai_api_key=\"YOUR_API_KEY\", openai_organization=\"YOUR_ORGANIZATION_ID\")\n",
"```\n",
"Remove the openai_organization parameter should it not apply to you."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "a641dbd9",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"llm_chain = prompt | llm"
"## Invocation"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "9f844993",
"metadata": {
"tags": []
},
"id": "85b49da0",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"' Justin Bieber was born on March 1, 1994. The Super Bowl is typically played in late January or early February. So, we need to look at the Super Bowl from 1994. In 1994, the Super Bowl was Super Bowl XXVIII, played on January 30, 1994. The winning team of that Super Bowl was the Dallas Cowboys.'"
"\"\\n\\nI'm an AI language model created by OpenAI, so I don't have feelings or emotions. But thank you for asking! How can I assist you today?\""
]
},
"execution_count": 5,
@ -148,9 +160,37 @@
}
],
"source": [
"question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
"llm.invoke(\"Hello how are you?\")"
]
},
{
"cell_type": "markdown",
"id": "2b7e0dfc",
"metadata": {},
"source": [
"## Chaining"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "a641dbd9",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain_core.prompts import PromptTemplate\n",
"\n",
"llm_chain.invoke(question)"
"prompt = PromptTemplate(\"How to say {input} in {output_language}:\\n\")\n",
"\n",
"chain = prompt | llm\n",
"chain.invoke(\n",
" {\n",
" \"output_language\": \"German\",\n",
" \"input\": \"I love programming.\",\n",
" }\n",
")"
]
},
{
@ -158,6 +198,8 @@
"id": "58a9ddb1",
"metadata": {},
"source": [
"## Using a proxy\n",
"\n",
"If you are behind an explicit proxy, you can specify the http_client to pass through"
]
},
@ -168,11 +210,24 @@
"metadata": {},
"outputs": [],
"source": [
"pip install httpx\n",
"%pip install httpx\n",
"\n",
"import httpx\n",
"\n",
"openai = OpenAI(model_name=\"gpt-3.5-turbo-instruct\", http_client=httpx.Client(proxies=\"http://proxy.yourcompany.com:8080\"))"
"openai = OpenAI(\n",
" model_name=\"gpt-3.5-turbo-instruct\",\n",
" http_client=httpx.Client(proxies=\"http://proxy.yourcompany.com:8080\"),\n",
")"
]
},
{
"cell_type": "markdown",
"id": "73e207dd",
"metadata": {},
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all `OpenAI` llm features and configurations head to the API reference: https://api.python.langchain.com/en/latest/llms/langchain_openai.llms.base.OpenAI.html"
]
}
],
@ -192,7 +247,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.6"
"version": "3.11.9"
},
"vscode": {
"interpreter": {

2
libs/cli/langchain_cli/integration_template/docs/llms.ipynb
View File

@ -34,7 +34,7 @@
"\n",
"## Setup\n",
"\n",
"- [ ] TODO: Update with relevant info.\n",
"- TODO: Update with relevant info.\n",
"\n",
"To access __ModuleName__ models you'll need to create a/an __ModuleName__ account, get an API key, and install the `__package_name__` integration package.\n",
"\n",