langchain.js
    Preparing search index...

    Class ChatFireworks

    Wrapper around Fireworks API for large language models fine-tuned for chat

    Fireworks API is compatible to the OpenAI API with some limitations described in https://readme.fireworks.ai/docs/openai-compatibility.

    To use, you should have the FIREWORKS_API_KEY environment variable set.

    Setup: Install @langchain/community and set a environment variable called FIREWORKS_API_KEY.

    npm install @langchain/community
    export FIREWORKS_API_KEY="your-api-key"

    Because the Fireworks API extends OpenAI's, the call option type is the same.

    Runtime args can be passed as the second argument to any of the base runnable methods .invoke. .stream, .batch, etc. They can also be passed via .withConfig, or the second arg in .bindTools, like shown in the examples below:

    // When calling `.withConfig`, call options should be passed via the first argument
    const llmWithArgsBound = llm.withConfig({
      stop: ["\n"],
      tools: [...],
    });

    // When calling `.bindTools`, call options should be passed via the second argument
    const llmWithTools = llm.bindTools(
      [...],
      {
        stop: ["\n"],
      }
    );
    Instantiate 
    import { ChatFireworks } from '@langchain/community/chat_models/fireworks';

    const llm = new ChatFireworks({
      model: "command-r-plus",
      temperature: 0,
      // other params...
    });

    Invoking 
    const input = `Translate "I love programming" into French.`;

    // Models also accept a list of chat messages or a formatted prompt
    const result = await llm.invoke(input);
    console.log(result);

    AIMessage {
  "id": "dbc233df-532e-4aaa-8995-9d6ea65fea15",
  "content": "The translation of \"I love programming\" into French is:\n\n\"J'adore la programmation.\"\n\nHere's a breakdown of the translation:\n\n* \"I\" is translated to \"Je\" (but in informal writing, it's common to use \"J'\" instead of \"Je\" when it's followed by a vowel)\n* \"love\" is translated to \"adore\"\n* \"programming\" is translated to \"la programmation\"\n\nSo, the complete translation is \"J'adore la programmation.\"",
  "additional_kwargs": {},
  "response_metadata": {
    "tokenUsage": {
      "completionTokens": 105,
      "promptTokens": 19,
      "totalTokens": 124
    },
    "finish_reason": "stop"
  },
  "tool_calls": [],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "input_tokens": 19,
    "output_tokens": 105,
    "total_tokens": 124
  }
}

    Streaming Chunks 
    for await (const chunk of await llm.stream(input)) {
      console.log(chunk);
    }

    AIMessageChunk {
  "id": "ed5fc403-b7ed-4447-819f-f9645ea0277c",
  "content": "",
  "additional_kwargs": {},
  "response_metadata": {
    "prompt": 0,
    "completion": 0,
    "finish_reason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "id": "ed5fc403-b7ed-4447-819f-f9645ea0277c",
  "content": "The translation",
  "additional_kwargs": {},
  "response_metadata": {
    "prompt": 0,
    "completion": 0,
    "finish_reason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "id": "ed5fc403-b7ed-4447-819f-f9645ea0277c",
  "content": " of \"",
  "additional_kwargs": {},
  "response_metadata": {
    "prompt": 0,
    "completion": 0,
    "finish_reason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "id": "ed5fc403-b7ed-4447-819f-f9645ea0277c",
  "content": "I love",
  "additional_kwargs": {},
  "response_metadata": {
    "prompt": 0,
    "completion": 0,
    "finish_reason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "id": "ed5fc403-b7ed-4447-819f-f9645ea0277c",
  "content": " programming\"",
  "additional_kwargs": {},
  "response_metadata": {
    "prompt": 0,
    "completion": 0,
    "finish_reason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "id": "ed5fc403-b7ed-4447-819f-f9645ea0277c",
  "content": " into French",
  "additional_kwargs": {},
  "response_metadata": {
    "prompt": 0,
    "completion": 0,
    "finish_reason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "id": "ed5fc403-b7ed-4447-819f-f9645ea0277c",
  "content": " is:\n\n",
  "additional_kwargs": {},
  "response_metadata": {
    "prompt": 0,
    "completion": 0,
    "finish_reason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "id": "ed5fc403-b7ed-4447-819f-f9645ea0277c",
  "content": "\"J",
  "additional_kwargs": {},
  "response_metadata": {
    "prompt": 0,
    "completion": 0,
    "finish_reason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
...
AIMessageChunk {
  "id": "ed5fc403-b7ed-4447-819f-f9645ea0277c",
  "content": "ation.\"",
  "additional_kwargs": {},
  "response_metadata": {
    "prompt": 0,
    "completion": 0,
    "finish_reason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "id": "ed5fc403-b7ed-4447-819f-f9645ea0277c",
  "content": "",
  "additional_kwargs": {},
  "response_metadata": {
    "prompt": 0,
    "completion": 0,
    "finish_reason": "stop"
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": "",
  "additional_kwargs": {},
  "response_metadata": {},
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "input_tokens": 19,
    "output_tokens": 105,
    "total_tokens": 124
  }
}

    Aggregate Streamed Chunks 
    import { AIMessageChunk } from '@langchain/core/messages';
    import { concat } from '@langchain/core/utils/stream';

    const stream = await llm.stream(input);
    let full: AIMessageChunk | undefined;
    for await (const chunk of stream) {
      full = !full ? chunk : concat(full, chunk);
    }
    console.log(full);

    AIMessageChunk {
  "id": "9b80e5af-0f50-4fb7-b700-6d431a819556",
  "content": "The translation of \"I love programming\" into French is:\n\n\"J'adore la programmation.\"\n\nHere's a breakdown of the translation:\n\n* \"I\" is translated to \"Je\" (but in informal writing, it's common to use \"J'\" instead of \"Je\" when it's followed by a vowel)\n* \"love\" is translated to \"adore\"\n* \"programming\" is translated to \"la programmation\"\n\nSo, the complete translation is \"J'adore la programmation.\"",
  "additional_kwargs": {},
  "response_metadata": {
    "prompt": 0,
    "completion": 0,
    "finish_reason": "stop"
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "input_tokens": 19,
    "output_tokens": 105,
    "total_tokens": 124
  }
}

    Bind tools 
    import { z } from 'zod';

    const llmForToolCalling = new ChatFireworks({
      // Use a model with tool calling capability
      model: "accounts/fireworks/models/firefunction-v2",
      temperature: 0,
      // other params...
    });
    const GetWeather = {
      name: "GetWeather",
      description: "Get the current weather in a given location",
      schema: z.object({
        location: z.string().describe("The city and state, e.g. San Francisco, CA")
      }),
    }

    const GetPopulation = {
      name: "GetPopulation",
      description: "Get the current population in a given location",
      schema: z.object({
        location: z.string().describe("The city and state, e.g. San Francisco, CA")
      }),
    }

    const llmWithTools = llmForToolCalling.bindTools([GetWeather, GetPopulation]);
    const aiMsg = await llmWithTools.invoke(
      "Which city is hotter today and which is bigger: LA or NY?"
    );
    console.log(aiMsg.tool_calls);

    [
  {
    name: 'GetWeather',
    args: { location: 'Los Angeles, CA' },
    type: 'tool_call',
    id: 'call_9DE0WnhgKDbxu6HyHOkDQFub'
  },
  {
    name: 'GetWeather',
    args: { location: 'New York, NY' },
    type: 'tool_call',
    id: 'call_58lcAPTqQyiqepxynwARhGs8'
  },
  {
    name: 'GetPopulation',
    args: { location: 'Los Angeles, CA' },
    type: 'tool_call',
    id: 'call_r0m6AFoqaMvPp4Zt5aEAc0oE'
  },
  {
    name: 'GetPopulation',
    args: { location: 'New York, NY' },
    type: 'tool_call',
    id: 'call_mENaPG1ryOF44BmaW4VkBaSi'
  }
]

    Structured Output 
    import { z } from 'zod';

    const Joke = z.object({
      setup: z.string().describe("The setup of the joke"),
      punchline: z.string().describe("The punchline to the joke"),
      rating: z.number().optional().describe("How funny the joke is, from 1 to 10")
    }).describe('Joke to tell user.');

    const structuredLlm = llmForToolCalling.withStructuredOutput(Joke, { name: "Joke" });
    const jokeResult = await structuredLlm.invoke("Tell me a joke about cats");
    console.log(jokeResult);

    {
  setup: 'Why did the cat join a band?',
  punchline: 'Because it wanted to be the purr-cussionist!',
  rating: 8
}

    Usage Metadata 
    const aiMsgForMetadata = await llm.invoke(input);
    console.log(aiMsgForMetadata.usage_metadata);

    { input_tokens: 277, output_tokens: 8, total_tokens: 285 }

    Response Metadata 
    const aiMsgForResponseMetadata = await llm.invoke(input);
    console.log(aiMsgForResponseMetadata.response_metadata);

    {
  tokenUsage: { completionTokens: 8, promptTokens: 277, totalTokens: 285 },
  finish_reason: 'stop'
}

    Hierarchy

    Index

    Constructors

    constructor

    Properties

    apiKey? fireworksApiKey? lc_serializable

    Accessors

    lc_secrets

    Methods

    _llmType completionWithRetry getLsParams toJSON lc_name

    Constructors

    • Parameters

      • Optionalfields: any

      Returns ChatFireworks

    Properties

    apiKey?: string
    fireworksApiKey?: string
    lc_serializable: boolean = true

    Accessors

    • get lc_secrets(): undefined | { [key: string]: string }

      Returns undefined | { [key: string]: string }

    Methods

    _llmType

    • _llmType(): string

      Returns string

    • Parameters

      • request: ChatCompletionCreateParamsStreaming
      • Optionaloptions: RequestOptions

      Returns Promise<AsyncIterable<ChatCompletionChunk, any, any>>

    • Parameters

      • request: ChatCompletionCreateParamsNonStreaming
      • Optionaloptions: RequestOptions

      Returns Promise<ChatCompletion>

    • Parameters

      • options: unknown

      Returns LangSmithParams

    • Returns any

    • Returns string

    Settings

    Member Visibility

    On This Page

    Constructor argsRuntime argsExamples
    Constructors
    Properties
    Accessors
    Methods