docs: fireworks standard page (#23816)

This commit is contained in:
Bagatur 2024-07-03 10:33:05 -04:00 committed by GitHub
parent 27aa4d38bf
commit e787249af1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "raw",
"id": "529aeba9",
"id": "afaf8039",
"metadata": {},
"source": [
"---\n",
@ -11,197 +11,243 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "642fd21c-600a-47a1-be96-6e1438b421a9",
"id": "e49f1e0d",
"metadata": {},
"source": [
"# ChatFireworks\n",
"\n",
">[Fireworks](https://app.fireworks.ai/) accelerates product development on generative AI by creating an innovative AI experiment and production platform. \n",
"This doc help you get started with Fireworks AI [chat models](/docs/concepts/#chat-models). For detailed documentation of all ChatFireworks features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_fireworks.chat_models.ChatFireworks.html).\n",
"\n",
"This example goes over how to use LangChain to interact with `ChatFireworks` models."
]
},
{
"cell_type": "raw",
"id": "4a7c795e",
"metadata": {},
"source": [
"%pip install langchain-fireworks"
"Fireworks AI is an AI inference platform to run and customize models. For a list of all models served by Fireworks see the [Fireworks docs](https://fireworks.ai/models).\n",
"\n",
"## Overview\n",
"### Integration details\n",
"\n",
"| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/chat/fireworks) | Package downloads | Package latest |\n",
"| :--- | :--- | :---: | :---: | :---: | :---: | :---: |\n",
"| [ChatFireworks](https://api.python.langchain.com/en/latest/chat_models/langchain_fireworks.chat_models.ChatFireworks.html) | [langchain-fireworks](https://api.python.langchain.com/en/latest/fireworks_api_reference.html) | ❌ | beta | ✅ | ![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) |\n",
"\n",
"### Model features\n",
"| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
"| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |\n",
"| ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ | \n",
"\n",
"## Setup\n",
"\n",
"To access Fireworks models you'll need to create a Fireworks account, get an API key, and install the `langchain-fireworks` integration package.\n",
"\n",
"### Credentials\n",
"\n",
"Head to (ttps://fireworks.ai/login to sign up to Fireworks and generate an API key. Once you've done this set the FIREWORKS_API_KEY environment variable:"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "d00d850917865298",
"metadata": {
"collapsed": false,
"jupyter": {
"outputs_hidden": false
}
},
"outputs": [],
"source": [
"from langchain_core.messages import HumanMessage, SystemMessage\n",
"from langchain_fireworks import ChatFireworks"
]
},
{
"cell_type": "markdown",
"id": "f28ebf8b-f14f-46c7-9962-8b8dc42e31be",
"metadata": {},
"source": [
"# 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",
"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 [app.fireworks.ai](https://app.fireworks.ai)."
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "d096fb14-8acc-4047-9cd0-c842430c3a1d",
"execution_count": null,
"id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
"metadata": {},
"outputs": [],
"source": [
"import getpass\n",
"import os\n",
"\n",
"if \"FIREWORKS_API_KEY\" not in os.environ:\n",
" os.environ[\"FIREWORKS_API_KEY\"] = getpass.getpass(\"Fireworks API Key:\")\n",
"\n",
"# Initialize a Fireworks chat model\n",
"chat = ChatFireworks(model=\"accounts/fireworks/models/mixtral-8x7b-instruct\")"
"os.environ[\"FIREWORKS_API_KEY\"] = getpass.getpass(\"Enter your Fireworks API key: \")"
]
},
{
"cell_type": "markdown",
"id": "d8f13144-37cf-47a5-b5a0-e3cdf76d9a72",
"id": "72ee0c4b-9764-423a-9dbf-95129e185210",
"metadata": {},
"source": [
"# Calling the Model Directly\n",
"If you want to get automated 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": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
"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": "0730d6a1-c893-4840-9817-5e5251676d5d",
"metadata": {},
"source": [
"### Installation\n",
"\n",
"You can call the model directly with a system and human message to get answers."
"The LangChain Fireworks integration lives in the `langchain-fireworks` package:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "652d6238-1f87-422a-b135-f5abbb8652fc",
"metadata": {},
"outputs": [],
"source": [
"%pip install -qU langchain-fireworks"
]
},
{
"cell_type": "markdown",
"id": "a38cde65-254d-4219-a441-068766c0d4b5",
"metadata": {},
"source": [
"## Instantiation\n",
"\n",
"Now we can instantiate our model object and generate chat completions:\n",
"\n",
"- TODO: Update model instantiation with relevant params."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
"metadata": {},
"outputs": [],
"source": [
"from langchain_fireworks import ChatFireworks\n",
"\n",
"llm = ChatFireworks(\n",
" model=\"accounts/fireworks/models/llama-v3-70b-instruct\",\n",
" temperature=0,\n",
" max_tokens=None,\n",
" timeout=None,\n",
" max_retries=2,\n",
" # other params...\n",
")"
]
},
{
"cell_type": "markdown",
"id": "2b4f3e15",
"metadata": {},
"source": [
"## Invocation"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "62e0dbc3",
"metadata": {
"tags": []
},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content=\"J'adore la programmation.\", response_metadata={'token_usage': {'prompt_tokens': 35, 'total_tokens': 44, 'completion_tokens': 9}, 'model_name': 'accounts/fireworks/models/llama-v3-70b-instruct', 'system_fingerprint': '', 'finish_reason': 'stop', 'logprobs': None}, id='run-df28e69a-ff30-457e-a743-06eb14d01cb0-0', usage_metadata={'input_tokens': 35, 'output_tokens': 9, 'total_tokens': 44})"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"messages = [\n",
" (\n",
" \"system\",\n",
" \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
" ),\n",
" (\"human\", \"I love programming.\"),\n",
"]\n",
"ai_msg = llm.invoke(messages)\n",
"ai_msg"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "72340871-ae2f-415f-b399-0777d32dc379",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content=\"Hello! I'm an AI language model, a helpful assistant designed to chat and assist you with any questions or information you might need. I'm here to make your experience as smooth and enjoyable as possible. How can I assist you today?\")"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# ChatFireworks Wrapper\n",
"system_message = SystemMessage(content=\"You are to chat with the user.\")\n",
"human_message = HumanMessage(content=\"Who are you?\")\n",
"\n",
"chat.invoke([system_message, human_message])"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "68c6b1fa-2ff7-4a63-8d88-3cec302180b8",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content=\"I'm an AI and do not have the ability to experience the weather firsthand. However,\")"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Setting additional parameters: temperature, max_tokens, top_p\n",
"chat = ChatFireworks(\n",
" model=\"accounts/fireworks/models/mixtral-8x7b-instruct\",\n",
" temperature=1,\n",
" max_tokens=20,\n",
")\n",
"system_message = SystemMessage(content=\"You are to chat with the user.\")\n",
"human_message = HumanMessage(content=\"How's the weather today?\")\n",
"chat.invoke([system_message, human_message])"
]
},
{
"cell_type": "markdown",
"id": "8c44cb36",
"metadata": {},
"source": [
"# Tool Calling\n",
"\n",
"Fireworks offers the `FireFunction-v2` tool calling model. You can use it for structured output and function calling use cases:"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "ee2db682",
"id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'function': {'arguments': '{\"name\": \"Erick\", \"age\": 27}',\n",
" 'name': 'ExtractFields'},\n",
" 'id': 'call_J0WYP2TLenaFw3UeVU0UnWqx',\n",
" 'index': 0,\n",
" 'type': 'function'}\n"
"J'adore la programmation.\n"
]
}
],
"source": [
"from pprint import pprint\n",
"print(ai_msg.content)"
]
},
{
"cell_type": "markdown",
"id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
"metadata": {},
"source": [
"## Chaining\n",
"\n",
"from langchain_core.pydantic_v1 import BaseModel\n",
"\n",
"\n",
"class ExtractFields(BaseModel):\n",
" name: str\n",
" age: int\n",
"\n",
"\n",
"chat = ChatFireworks(\n",
" model=\"accounts/fireworks/models/firefunction-v2\",\n",
").bind_tools([ExtractFields])\n",
"\n",
"result = chat.invoke(\"I am a 27 year old named Erick\")\n",
"\n",
"pprint(result.additional_kwargs[\"tool_calls\"][0])"
"We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2321a4e6",
"execution_count": 4,
"id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
"metadata": {},
"outputs": [],
"source": []
"outputs": [
{
"data": {
"text/plain": [
"AIMessage(content='Ich liebe das Programmieren.', response_metadata={'token_usage': {'prompt_tokens': 30, 'total_tokens': 37, 'completion_tokens': 7}, 'model_name': 'accounts/fireworks/models/llama-v3-70b-instruct', 'system_fingerprint': '', 'finish_reason': 'stop', 'logprobs': None}, id='run-ff3f91ad-ed81-4acf-9f59-7490dc8d8f48-0', usage_metadata={'input_tokens': 30, 'output_tokens': 7, 'total_tokens': 37})"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain_core.prompts import ChatPromptTemplate\n",
"\n",
"prompt = ChatPromptTemplate.from_messages(\n",
" [\n",
" (\n",
" \"system\",\n",
" \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
" ),\n",
" (\"human\", \"{input}\"),\n",
" ]\n",
")\n",
"\n",
"chain = prompt | llm\n",
"chain.invoke(\n",
" {\n",
" \"input_language\": \"English\",\n",
" \"output_language\": \"German\",\n",
" \"input\": \"I love programming.\",\n",
" }\n",
")"
]
},
{
"cell_type": "markdown",
"id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
"metadata": {},
"source": [
"## API reference\n",
"\n",
"For detailed documentation of all ChatFireworks features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_fireworks.chat_models.ChatFireworks.html"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"display_name": "poetry-venv-2",
"language": "python",
"name": "python3"
"name": "poetry-venv-2"
},
"language_info": {
"codemirror_mode": {
@ -213,7 +259,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.4"
"version": "3.11.9"
}
},
"nbformat": 4,