Groq chat model integration.

The Groq API is compatible to the OpenAI API with some limitations. View the full API ref at:

Setup: Install @langchain/groq and set an environment variable named GROQ_API_KEY.

npm install @langchain/groq
export GROQ_API_KEY="your-api-key"

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 .bind, or the second arg in .bindTools, like shown in the examples below:

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

// When calling `.bindTools`, call options should be passed via the second argument
const llmWithTools = llm.bindTools(
[...],
{
tool_choice: "auto",
}
);
Instantiate
import { ChatGroq } from '@langchain/groq';

const llm = new ChatGroq({
model: "mixtral-8x7b-32768",
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 {
  "content": "The French translation of \"I love programming\" is \"J'aime programmer\". In this sentence, \"J'aime\" is the first person singular conjugation of the French verb \"aimer\" which means \"to love\", and \"programmer\" is the French infinitive for \"to program\". I hope this helps! Let me know if you have any other questions.",
  "additional_kwargs": {},
  "response_metadata": {
    "tokenUsage": {
      "completionTokens": 82,
      "promptTokens": 20,
      "totalTokens": 102
    },
    "finish_reason": "stop"
  },
  "tool_calls": [],
  "invalid_tool_calls": []
}

Streaming Chunks
for await (const chunk of await llm.stream(input)) {
console.log(chunk);
}
AIMessageChunk {
  "content": "",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": "The",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": " French",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": " translation",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": " of",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": " \"",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": "I",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": " love",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
...
AIMessageChunk {
  "content": ".",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": null
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": "",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": "stop"
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}

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 {
  "content": "The French translation of \"I love programming\" is \"J'aime programmer\". In this sentence, \"J'aime\" is the first person singular conjugation of the French verb \"aimer\" which means \"to love\", and \"programmer\" is the French infinitive for \"to program\". I hope this helps! Let me know if you have any other questions.",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": "stop"
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}

Bind tools
import { z } from 'zod';

const llmForToolCalling = new ChatGroq({
model: "llama3-groq-70b-8192-tool-use-preview",
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_cd34'
  },
  {
    name: 'GetWeather',
    args: { location: 'New York, NY' },
    type: 'tool_call',
    id: 'call_68rf'
  },
  {
    name: 'GetPopulation',
    args: { location: 'Los Angeles, CA' },
    type: 'tool_call',
    id: 'call_f81z'
  },
  {
    name: 'GetPopulation',
    args: { location: 'New York, NY' },
    type: 'tool_call',
    id: 'call_8byt'
  }
]

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 don't cats play poker in the wild?",
  punchline: 'Because there are too many cheetahs.'
}

Hierarchy

Constructors

Methods

  • Convert a runnable to a tool. Return a new instance of RunnableToolLike which contains the runnable, name, description and schema.

    Type Parameters

    • T extends BaseLanguageModelInput = BaseLanguageModelInput

    Parameters

    • fields: {
          description?: string;
          name?: string;
          schema: ZodType<T, ZodTypeDef, T>;
      }
      • Optionaldescription?: string

        The description of the tool. Falls back to the description on the Zod schema if not provided, or undefined if neither are provided.

      • Optionalname?: string

        The name of the tool. If not provided, it will default to the name of the runnable.

      • schema: ZodType<T, ZodTypeDef, T>

        The Zod schema for the input of the tool. Infers the Zod type from the input type of the runnable.

    Returns RunnableToolLike<ZodType<ToolCall | T, ZodTypeDef, ToolCall | T>, AIMessageChunk>

    An instance of RunnableToolLike which is a runnable that can be used as a tool.

  • Assigns new fields to the dict output of this runnable. Returns a new runnable.

    Parameters

    • mapping: RunnableMapLike<Record<string, unknown>, Record<string, unknown>>

    Returns Runnable<any, any, RunnableConfig<Record<string, any>>>

  • Default implementation of batch, which calls invoke N times. Subclasses should override this method if they can batch more efficiently.

    Parameters

    • inputs: BaseLanguageModelInput[]

      Array of inputs to each batch call.

    • Optionaloptions: Partial<ChatGroqCallOptions> | Partial<ChatGroqCallOptions>[]

      Either a single call options object to apply to each batch call or an array for each call.

    • OptionalbatchOptions: RunnableBatchOptions & {
          returnExceptions?: false;
      }

    Returns Promise<AIMessageChunk[]>

    An array of RunOutputs, or mixed RunOutputs and errors if batchOptions.returnExceptions is set

  • Parameters

    • inputs: BaseLanguageModelInput[]
    • Optionaloptions: Partial<ChatGroqCallOptions> | Partial<ChatGroqCallOptions>[]
    • OptionalbatchOptions: RunnableBatchOptions & {
          returnExceptions: true;
      }

    Returns Promise<(Error | AIMessageChunk)[]>

  • Parameters

    Returns Promise<(Error | AIMessageChunk)[]>

  • Bind arguments to a Runnable, returning a new Runnable.

    Parameters

    Returns Runnable<BaseLanguageModelInput, AIMessageChunk, ChatGroqCallOptions>

    A new RunnableBinding that, when invoked, will apply the bound args.

  • Bind tool-like objects to this chat model.

    Parameters

    • tools: ChatGroqToolType[]

      A list of tool definitions to bind to this chat model. Can be a structured tool, an OpenAI formatted tool, or an object matching the provider's specific tool schema.

    • Optionalkwargs: Partial<ChatGroqCallOptions>

      Any additional parameters to bind.

    Returns Runnable<BaseLanguageModelInput, AIMessageChunk, ChatGroqCallOptions>

  • Parameters

    • Optional_: RunnableConfig<Record<string, any>>

    Returns Graph

  • Parameters

    • content: MessageContent

    Returns Promise<number>

  • Invokes the chat model with a single input.

    Parameters

    • input: BaseLanguageModelInput

      The input for the language model.

    • Optionaloptions: ChatGroqCallOptions

      The call options.

    Returns Promise<AIMessageChunk>

    A Promise that resolves to a BaseMessageChunk.

  • Pick keys from the dict output of this runnable. Returns a new runnable.

    Parameters

    • keys: string | string[]

    Returns Runnable<any, any, RunnableConfig<Record<string, any>>>

  • Create a new runnable sequence that runs each individual runnable in series, piping the output of one runnable into another runnable or runnable-like.

    Type Parameters

    • NewRunOutput

    Parameters

    • coerceable: RunnableLike<AIMessageChunk, NewRunOutput, RunnableConfig<Record<string, any>>>

      A runnable, function, or object whose values are functions or runnables.

    Returns Runnable<BaseLanguageModelInput, Exclude<NewRunOutput, Error>, RunnableConfig<Record<string, any>>>

    A new runnable sequence.

  • Stream output in chunks.

    Parameters

    Returns Promise<IterableReadableStream<AIMessageChunk>>

    A readable stream that is also an iterable.

  • Generate a stream of events emitted by the internal steps of the runnable.

    Use to create an iterator over StreamEvents that provide real-time information about the progress of the runnable, including StreamEvents from intermediate results.

    A StreamEvent is a dictionary with the following schema:

    • event: string - Event names are of the format: on_[runnable_type]_(start|stream|end).
    • name: string - The name of the runnable that generated the event.
    • run_id: string - Randomly generated ID associated with the given execution of the runnable that emitted the event. A child runnable that gets invoked as part of the execution of a parent runnable is assigned its own unique ID.
    • tags: string[] - The tags of the runnable that generated the event.
    • metadata: Record<string, any> - The metadata of the runnable that generated the event.
    • data: Record<string, any>

    Below is a table that illustrates some events that might be emitted by various chains. Metadata fields have been omitted from the table for brevity. Chain definitions have been included after the table.

    ATTENTION This reference table is for the V2 version of the schema.

    +----------------------+-----------------------------+------------------------------------------+
    | event                | input                       | output/chunk                             |
    +======================+=============================+==========================================+
    | on_chat_model_start  | {"messages": BaseMessage[]} |                                          |
    +----------------------+-----------------------------+------------------------------------------+
    | on_chat_model_stream |                             | AIMessageChunk("hello")                  |
    +----------------------+-----------------------------+------------------------------------------+
    | on_chat_model_end    | {"messages": BaseMessage[]} | AIMessageChunk("hello world")            |
    +----------------------+-----------------------------+------------------------------------------+
    | on_llm_start         | {'input': 'hello'}          |                                          |
    +----------------------+-----------------------------+------------------------------------------+
    | on_llm_stream        |                             | 'Hello'                                  |
    +----------------------+-----------------------------+------------------------------------------+
    | on_llm_end           | 'Hello human!'              |                                          |
    +----------------------+-----------------------------+------------------------------------------+
    | on_chain_start       |                             |                                          |
    +----------------------+-----------------------------+------------------------------------------+
    | on_chain_stream      |                             | "hello world!"                           |
    +----------------------+-----------------------------+------------------------------------------+
    | on_chain_end         | [Document(...)]             | "hello world!, goodbye world!"           |
    +----------------------+-----------------------------+------------------------------------------+
    | on_tool_start        | {"x": 1, "y": "2"}          |                                          |
    +----------------------+-----------------------------+------------------------------------------+
    | on_tool_end          |                             | {"x": 1, "y": "2"}                       |
    +----------------------+-----------------------------+------------------------------------------+
    | on_retriever_start   | {"query": "hello"}          |                                          |
    +----------------------+-----------------------------+------------------------------------------+
    | on_retriever_end     | {"query": "hello"}          | [Document(...), ..]                      |
    +----------------------+-----------------------------+------------------------------------------+
    | on_prompt_start      | {"question": "hello"}       |                                          |
    +----------------------+-----------------------------+------------------------------------------+
    | on_prompt_end        | {"question": "hello"}       | ChatPromptValue(messages: BaseMessage[]) |
    +----------------------+-----------------------------+------------------------------------------+
    

    The "on_chain_*" events are the default for Runnables that don't fit one of the above categories.

    In addition to the standard events above, users can also dispatch custom events.

    Custom events will be only be surfaced with in the v2 version of the API!

    A custom event has following format:

    +-----------+------+------------------------------------------------------------+
    | Attribute | Type | Description                                                |
    +===========+======+============================================================+
    | name      | str  | A user defined name for the event.                         |
    +-----------+------+------------------------------------------------------------+
    | data      | Any  | The data associated with the event. This can be anything.  |
    +-----------+------+------------------------------------------------------------+
    

    Here's an example:

    import { RunnableLambda } from "@langchain/core/runnables";
    import { dispatchCustomEvent } from "@langchain/core/callbacks/dispatch";
    // Use this import for web environments that don't support "async_hooks"
    // and manually pass config to child runs.
    // import { dispatchCustomEvent } from "@langchain/core/callbacks/dispatch/web";

    const slowThing = RunnableLambda.from(async (someInput: string) => {
    // Placeholder for some slow operation
    await new Promise((resolve) => setTimeout(resolve, 100));
    await dispatchCustomEvent("progress_event", {
    message: "Finished step 1 of 2",
    });
    await new Promise((resolve) => setTimeout(resolve, 100));
    return "Done";
    });

    const eventStream = await slowThing.streamEvents("hello world", {
    version: "v2",
    });

    for await (const event of eventStream) {
    if (event.event === "on_custom_event") {
    console.log(event);
    }
    }

    Parameters

    • input: BaseLanguageModelInput
    • options: Partial<ChatGroqCallOptions> & {
          version: "v1" | "v2";
      }
    • OptionalstreamOptions: Omit<EventStreamCallbackHandlerInput, "autoClose">

    Returns IterableReadableStream<StreamEvent>

  • Parameters

    • input: BaseLanguageModelInput
    • options: Partial<ChatGroqCallOptions> & {
          encoding: "text/event-stream";
          version: "v1" | "v2";
      }
    • OptionalstreamOptions: Omit<EventStreamCallbackHandlerInput, "autoClose">

    Returns IterableReadableStream<Uint8Array>

  • Stream all output from a runnable, as reported to the callback system. This includes all inner runs of LLMs, Retrievers, Tools, etc. Output is streamed as Log objects, which include a list of jsonpatch ops that describe how the state of the run has changed in each step, and the final state of the run. The jsonpatch ops can be applied in order to construct state.

    Parameters

    • input: BaseLanguageModelInput
    • Optionaloptions: Partial<ChatGroqCallOptions>
    • OptionalstreamOptions: Omit<LogStreamCallbackHandlerInput, "autoClose">

    Returns AsyncGenerator<RunLogPatch, any, unknown>

  • Default implementation of transform, which buffers input and then calls stream. Subclasses should override this method if they can start producing output while input is still being generated.

    Parameters

    • generator: AsyncGenerator<BaseLanguageModelInput, any, unknown>
    • options: Partial<ChatGroqCallOptions>

    Returns AsyncGenerator<AIMessageChunk, any, unknown>

  • Bind config to a Runnable, returning a new Runnable.

    Parameters

    • config: RunnableConfig<Record<string, any>>

      New configuration parameters to attach to the new runnable.

    Returns Runnable<BaseLanguageModelInput, AIMessageChunk, ChatGroqCallOptions>

    A new RunnableBinding with a config matching what's passed.

  • Create a new runnable from the current one that will try invoking other passed fallback runnables if the initial invocation fails.

    Parameters

    • fields: {
          fallbacks: Runnable<BaseLanguageModelInput, AIMessageChunk, RunnableConfig<Record<string, any>>>[];
      } | Runnable<BaseLanguageModelInput, AIMessageChunk, RunnableConfig<Record<string, any>>>[]

    Returns RunnableWithFallbacks<BaseLanguageModelInput, AIMessageChunk>

    A new RunnableWithFallbacks.

  • Bind lifecycle listeners to a Runnable, returning a new Runnable. The Run object contains information about the run, including its id, type, input, output, error, startTime, endTime, and any tags or metadata added to the run.

    Parameters

    • params: {
          onEnd?: ((run: Run, config?: RunnableConfig<Record<string, any>>) => void | Promise<void>);
          onError?: ((run: Run, config?: RunnableConfig<Record<string, any>>) => void | Promise<void>);
          onStart?: ((run: Run, config?: RunnableConfig<Record<string, any>>) => void | Promise<void>);
      }

      The object containing the callback functions.

      • OptionalonEnd?: ((run: Run, config?: RunnableConfig<Record<string, any>>) => void | Promise<void>)

        Called after the runnable finishes running, with the Run object.

          • (run, config?): void | Promise<void>
          • Parameters

            • run: Run
            • Optionalconfig: RunnableConfig<Record<string, any>>

            Returns void | Promise<void>

      • OptionalonError?: ((run: Run, config?: RunnableConfig<Record<string, any>>) => void | Promise<void>)

        Called if the runnable throws an error, with the Run object.

          • (run, config?): void | Promise<void>
          • Parameters

            • run: Run
            • Optionalconfig: RunnableConfig<Record<string, any>>

            Returns void | Promise<void>

      • OptionalonStart?: ((run: Run, config?: RunnableConfig<Record<string, any>>) => void | Promise<void>)

        Called before the runnable starts running, with the Run object.

          • (run, config?): void | Promise<void>
          • Parameters

            • run: Run
            • Optionalconfig: RunnableConfig<Record<string, any>>

            Returns void | Promise<void>

    Returns Runnable<BaseLanguageModelInput, AIMessageChunk, ChatGroqCallOptions>

  • Add retry logic to an existing runnable.

    Parameters

    • Optionalfields: {
          onFailedAttempt?: RunnableRetryFailedAttemptHandler;
          stopAfterAttempt?: number;
      }
      • OptionalonFailedAttempt?: RunnableRetryFailedAttemptHandler
      • OptionalstopAfterAttempt?: number

    Returns RunnableRetry<BaseLanguageModelInput, AIMessageChunk, ChatGroqCallOptions>

    A new RunnableRetry that, when invoked, will retry according to the parameters.

  • Type Parameters

    • RunOutput extends Record<string, any> = Record<string, any>

    Parameters

    • outputSchema: Record<string, any> | ZodType<RunOutput, ZodTypeDef, RunOutput>
    • Optionalconfig: StructuredOutputMethodOptions<false>

    Returns Runnable<BaseLanguageModelInput, RunOutput, RunnableConfig<Record<string, any>>>

  • Type Parameters

    • RunOutput extends Record<string, any> = Record<string, any>

    Parameters

    • outputSchema: Record<string, any> | ZodType<RunOutput, ZodTypeDef, RunOutput>
    • Optionalconfig: StructuredOutputMethodOptions<true>

    Returns Runnable<BaseLanguageModelInput, {
        parsed: RunOutput;
        raw: BaseMessage;
    }, RunnableConfig<Record<string, any>>>