The agent engineering platform.
Python agentsaiai-agentsanthropicchatgptdeepagentsenterpriseframeworkgeminigenerative-ailangchainlanggraphllmmultiagentopen-sourceopenaipydanticpythonragtypescript
docs: fireworks standard page (#23816)
Bagature787249af182
diff --git a/docs/docs/integrations/chat/fireworks.ipynb b/docs/docs/integrations/chat/fireworks.ipynbindex da519e8ba5..1e83aea7e3 100644--- a/docs/docs/integrations/chat/fireworks.ipynb+++ b/docs/docs/integrations/chat/fireworks.ipynb@@ -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."+ "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 | ✅ |  |  |\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": "raw",- "id": "4a7c795e",+ "cell_type": "code",+ "execution_count": null,+ "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",+ "metadata": {},+ "outputs": [],+ "source": [+ "import getpass\n",+ "import os\n",+ "\n",+ "os.environ[\"FIREWORKS_API_KEY\"] = getpass.getpass(\"Enter your Fireworks API key: \")"+ ]+ },+ {+ "cell_type": "markdown",+ "id": "72ee0c4b-9764-423a-9dbf-95129e185210","metadata": {},"source": [- "%pip install langchain-fireworks"+ "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": 1,- "id": "d00d850917865298",- "metadata": {- "collapsed": false,- "jupyter": {- "outputs_hidden": false- }- },+ "execution_count": null,+ "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",+ "metadata": {},"outputs": [],"source": [- "from langchain_core.messages import HumanMessage, SystemMessage\n",- "from langchain_fireworks import ChatFireworks"+ "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",+ "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""]},{"cell_type": "markdown",- "id": "f28ebf8b-f14f-46c7-9962-8b8dc42e31be",+ "id": "0730d6a1-c893-4840-9817-5e5251676d5d","metadata": {},"source": [- "# Setup\n",+ "### Installation\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)."+ "The LangChain Fireworks integration lives in the `langchain-fireworks` package:"]},{"cell_type": "code",- "execution_count": 2,- "id": "d096fb14-8acc-4047-9cd0-c842430c3a1d",+ "execution_count": null,+ "id": "652d6238-1f87-422a-b135-f5abbb8652fc","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\")"+ "%pip install -qU langchain-fireworks"]},{"cell_type": "markdown",- "id": "d8f13144-37cf-47a5-b5a0-e3cdf76d9a72",+ "id": "a38cde65-254d-4219-a441-068766c0d4b5","metadata": {},"source": [- "# Calling the Model Directly\n",+ "## Instantiation\n",+ "\n",+ "Now we can instantiate our model object and generate chat completions:\n","\n",- "You can call the model directly with a system and human message to get answers."+ "- TODO: Update model instantiation with relevant params."]},{"cell_type": "code",- "execution_count": 3,- "id": "72340871-ae2f-415f-b399-0777d32dc379",+ "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=\"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?\")"+ "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": 3,+ "execution_count": 2,"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])"+ "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": 5,- "id": "68c6b1fa-2ff7-4a63-8d88-3cec302180b8",+ "execution_count": 3,+ "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705","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"+ "name": "stdout",+ "output_type": "stream",+ "text": [+ "J'adore la programmation.\n"+ ]}],"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])"+ "print(ai_msg.content)"]},{"cell_type": "markdown",- "id": "8c44cb36",+ "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8","metadata": {},"source": [- "# Tool Calling\n",+ "## Chaining\n","\n",- "Fireworks offers the `FireFunction-v2` tool calling model. You can use it for structured output and function calling use cases:"+ "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"]},{"cell_type": "code",- "execution_count": 11,- "id": "ee2db682",+ "execution_count": 4,+ "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b","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"- ]+ "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 pprint import pprint\n",- "\n",- "from langchain_core.pydantic_v1 import BaseModel\n",- "\n",- "\n",- "class ExtractFields(BaseModel):\n",- " name: str\n",- " age: int\n",+ "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",- "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])"+ "chain = prompt | llm\n",+ "chain.invoke(\n",+ " {\n",+ " \"input_language\": \"English\",\n",+ " \"output_language\": \"German\",\n",+ " \"input\": \"I love programming.\",\n",+ " }\n",+ ")"]},{- "cell_type": "code",- "execution_count": null,- "id": "2321a4e6",+ "cell_type": "markdown",+ "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3","metadata": {},- "outputs": [],- "source": []+ "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,