FireworksEmbeddings 통합

LangChain JavaScript로 FireworksEmbeddings 임베딩 모델과 통합하는 방법을 안내할게요.

출처: 문서

본문

이 문서는 LangChain으로 FireworksEmbeddings 임베딩 모델을 시작하는 데 도움을 줘요. FireworksEmbeddings 기능과 구성 옵션에 대한 자세한 문서는 API 레퍼런스를 참고하세요.

개요

통합 세부 정보

클래스	패키지	Local	Py 지원	Downloads	Version
`FireworksEmbeddings`	`@langchain/fireworks`	❌	✅

설정

Fireworks 임베딩 모델에 접근하려면 Fireworks 계정을 만들고 API 키를 받은 뒤 @langchain/fireworks 통합 패키지를 설치해야 해요.

자격 증명

fireworks.ai에서 Fireworks에 가입하고 API 키를 생성하세요. 완료되면 FIREWORKS_API_KEY 환경 변수를 설정하세요:

export FIREWORKS_API_KEY="your-api-key"

모델 호출의 자동 추적(tracing)을 원한다면 아래 주석을 해제해 LangSmith API 키를 설정할 수도 있어요:

# export LANGSMITH_TRACING="true"
# export LANGSMITH_API_KEY="your-api-key"

설치

LangChain FireworksEmbeddings 통합은 @langchain/fireworks 패키지에 있어요:

```bash npm theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}} npm install @langchain/fireworks @langchain/core ```

yarn add @langchain/fireworks @langchain/core

pnpm add @langchain/fireworks @langchain/core

인스턴스 생성

이제 모델 객체를 생성하고 텍스트를 임베딩할 수 있어요:

import { FireworksEmbeddings } from "@langchain/fireworks";

const embeddings = new FireworksEmbeddings({
  model: "nomic-ai/nomic-embed-text-v1.5",
});

인덱싱 및 검색

임베딩 모델은 데이터 인덱싱과 나중 검색 모두의 일부로, 검색 증강 생성(RAG) 흐름에서 자주 사용돼요. 더 자세한 지침은 Learn 탭의 RAG 튜토리얼을 참고하세요.

아래에서 위에서 초기화한 embeddings 객체로 데이터를 인덱싱하고 검색하는 방법을 확인하세요. 이 예제에서는 데모 MemoryVectorStore를 사용해 샘플 문서를 인덱싱하고 검색할 거예요.

// Create a vector store with a sample text
import { MemoryVectorStore } from "@langchain/classic/vectorstores/memory";

const text = "LangChain is the framework for building context-aware reasoning applications";

const vectorstore = await MemoryVectorStore.fromDocuments(
  [{ pageContent: text, metadata: {} }],
  embeddings,
);

// Use the vector store as a retriever that returns a single document
const retriever = vectorstore.asRetriever(1);

// Retrieve the most similar text
const retrievedDocuments = await retriever.invoke("What is LangChain?");

retrievedDocuments[0].pageContent;

"LangChain is the framework for building context-aware reasoning applications"

직접 사용

내부적으로 vectorstore와 retriever 구현은 fromDocuments에 사용된 텍스트와 retriever의 invoke 연산에 대해 각각 embeddings.embedDocument(...) 와 embeddings.embedQuery(...)를 호출해 임베딩을 만들어요.

이 메서드들을 직접 호출해 자신의 사용 사례에 대한 임베딩을 얻을 수 있어요.

단일 텍스트 임베딩

embedQuery로 검색을 위한 쿼리를 임베딩할 수 있어요. 이는 쿼리에 특화된 벡터 표현을 생성해요:

const singleVector = await embeddings.embedQuery(text);

console.log(singleVector.slice(0, 100));

[
        0.01666259765625,      0.011688232421875,          -0.1181640625,
          -0.10205078125,       0.05438232421875,      -0.08905029296875,
      -0.018096923828125,    0.00952911376953125,         -0.08056640625,
     -0.0283050537109375,   -0.01512908935546875,     0.0312042236328125,
        0.08197021484375,      0.022552490234375,  0.0012683868408203125,
         0.0133056640625,      -0.04327392578125,  -0.004322052001953125,
       -0.02410888671875, -0.0012350082397460938,      -0.04632568359375,
        0.02996826171875,    -0.0134124755859375,     -0.037811279296875,
        0.07672119140625,      0.021759033203125,     0.0179290771484375,
  -0.0002741813659667969,       -0.0582275390625,    -0.0224456787109375,
   0.0027675628662109375,     -0.017425537109375,   -0.01520538330078125,
    -0.01146697998046875,     -0.055267333984375,           -0.083984375,
       0.056793212890625,  -0.003383636474609375,     -0.034271240234375,
        0.05108642578125,   -0.01018524169921875,        0.0462646484375,
   0.0012178421020507812,   0.005779266357421875,        0.0684814453125,
     0.00797271728515625,    -0.0176544189453125,    0.00257110595703125,
       0.059539794921875,      -0.06573486328125,        -0.075439453125,
     -0.0247344970703125,    -0.0276947021484375,   0.003940582275390625,
        0.02630615234375,        0.0660400390625,        0.0157470703125,
       0.033050537109375,          -0.0478515625,      -0.03338623046875,
       0.050384521484375,       0.07757568359375,        -0.045166015625,
        0.07586669921875,  0.0021915435791015625,     0.0237579345703125,
      -0.052703857421875,       0.05023193359375,    -0.0274810791015625,
  -0.0025081634521484375,         0.019287109375,      -0.03802490234375,
      0.0216217041015625,      0.025360107421875,         -0.04443359375,
      -0.029205322265625,  -0.002414703369140625,      0.027130126953125,
       0.028961181640625,         0.078857421875, -0.0009660720825195312,
       0.017608642578125,       0.05755615234375,    -0.0285797119140625,
      0.0039215087890625,  -0.006908416748046875,      -0.05364990234375,
    -0.01342010498046875,       -0.0247802734375,       0.08331298828125,
       0.032928466796875,    0.00543975830078125,    -0.0168304443359375,
      -0.050018310546875,         -0.05908203125,      0.031951904296875,
     -0.0200347900390625,      0.019134521484375,     -0.018035888671875,
    -0.01178741455078125
]

여러 텍스트 임베딩

embedDocuments로 인덱싱을 위한 여러 텍스트를 임베딩할 수 있어요. 이 메서드에 사용되는 내부는 쿼리 임베딩과 다를 수 있지만(다를 필요는 없음) 있어요:

const text2 = "LangGraph is a library for building stateful, multi-actor applications with LLMs";

const vectors = await embeddings.embedDocuments([text, text2]);

console.log(vectors[0].slice(0, 100));
console.log(vectors[1].slice(0, 100));

[
       0.016632080078125,    0.01165008544921875,          -0.1181640625,
       -0.10186767578125,       0.05438232421875,      -0.08905029296875,
     -0.0180511474609375,    0.00957489013671875,         -0.08056640625,
           -0.0283203125,    -0.0151214599609375,        0.0311279296875,
        0.08184814453125,     0.0225982666015625,  0.0012750625610351562,
        0.01336669921875,     -0.043365478515625,  -0.004322052001953125,
       -0.02410888671875, -0.0012559890747070312,     -0.046356201171875,
      0.0298919677734375,     -0.013458251953125,      -0.03765869140625,
        0.07672119140625,     0.0217132568359375,     0.0179290771484375,
  -0.0002269744873046875,       -0.0582275390625,          -0.0224609375,
    0.002834320068359375,    -0.0174407958984375,   -0.01512908935546875,
    -0.01146697998046875,     -0.055206298828125,      -0.08404541015625,
         0.0567626953125, -0.0033092498779296875,     -0.034271240234375,
        0.05108642578125,     -0.010101318359375,      0.046173095703125,
   0.0011806488037109375,      0.005706787109375,       0.06854248046875,
      0.0079193115234375,    -0.0176239013671875,   0.002552032470703125,
       0.059539794921875,      -0.06573486328125,      -0.07537841796875,
       -0.02484130859375,     -0.027740478515625,   0.003925323486328125,
            0.0263671875,        0.0660400390625,     0.0156402587890625,
       0.033050537109375,     -0.047821044921875,       -0.0333251953125,
       0.050445556640625,       0.07757568359375,     -0.045257568359375,
        0.07586669921875,  0.0021724700927734375,     0.0237274169921875,
      -0.052703857421875,      0.050323486328125,       -0.0274658203125,
  -0.0024662017822265625,     0.0194244384765625,      -0.03802490234375,
        0.02166748046875,      0.025360107421875,     -0.044464111328125,
     -0.0292816162109375, -0.0025119781494140625,     0.0271148681640625,
       0.028961181640625,         0.078857421875, -0.0008907318115234375,
       0.017669677734375,           0.0576171875,    -0.0285797119140625,
      0.0039825439453125,   -0.00687408447265625,       -0.0535888671875,
     -0.0134735107421875,    -0.0247650146484375,        0.0831298828125,
       0.032989501953125,   0.005443572998046875,    -0.0167999267578125,
      -0.050018310546875,     -0.059051513671875,        0.0318603515625,
     -0.0200958251953125,     0.0191192626953125,    -0.0180206298828125,
    -0.01175689697265625
]
[
       -0.02667236328125,      0.036651611328125,         -0.1630859375,
        -0.0904541015625,     -0.022430419921875,       -0.095458984375,
      -0.037628173828125,    0.00473785400390625,    -0.046051025390625,
      0.0109710693359375,        0.0113525390625,    0.0254364013671875,
        0.09368896484375,     0.0144195556640625, -0.007564544677734375,
  -0.0014705657958984375, -0.0007691383361816406,    -0.015716552734375,
     -0.0242156982421875,     -0.024871826171875,      0.00885009765625,
   0.0012922286987304688,      0.023712158203125,    -0.054595947265625,
        0.06329345703125,        0.0289306640625,    0.0233612060546875,
        -0.0374755859375,       -0.0489501953125,    -0.029510498046875,
      0.0173492431640625,     0.0171356201171875,     -0.01629638671875,
        -0.0352783203125,     -0.039398193359375,     -0.11138916015625,
      0.0296783447265625,   -0.01467132568359375, 0.0009188652038574219,
       0.048187255859375,     -0.010650634765625,               0.03125,
    0.005214691162109375,        -0.015869140625,      0.06939697265625,
        -0.0428466796875,     0.0266571044921875,        0.044189453125,
       0.049957275390625,     -0.054290771484375,    0.0107574462890625,
       -0.03265380859375,    -0.0109100341796875,   -0.0144805908203125,
        0.03936767578125,       0.07989501953125,    -0.056976318359375,
      0.0308380126953125,     -0.035125732421875,    -0.038848876953125,
        0.10748291015625,       0.01129150390625,      -0.0665283203125,
        0.09710693359375,       0.03143310546875,   -0.0104522705078125,
      -0.062469482421875,      0.021148681640625,     -0.00970458984375,
       -0.06756591796875,       0.01019287109375,      0.00433349609375,
       0.032928466796875,      0.020233154296875,     -0.01336669921875,
      -0.015472412109375,    -0.0175933837890625,   -0.0142364501953125,
   -0.007450103759765625,          0.03759765625,  0.003551483154296875,
         0.0069580078125,      0.042266845703125, -0.007488250732421875,
        0.01922607421875,         0.007080078125,   -0.0255889892578125,
   -0.007686614990234375,       -0.0848388671875,     0.058563232421875,
       0.021148681640625,      0.034393310546875,   0.01087188720703125,
     -0.0196380615234375,      -0.09515380859375,       0.0054931640625,
      -0.012481689453125,   0.003322601318359375,    -0.019683837890625,
     -0.0307159423828125
]

API 레퍼런스

모든 FireworksEmbeddings 기능과 구성에 대한 자세한 문서는 API 레퍼런스를 참고하세요.

[Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers. [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/javascript/integrations/embeddings/fireworks.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).

더 알아보기

이 문서를 MCP로 연결하면 Claude, VSCode 등에서 실시간 답변을 받을 수 있어요.
GitHub에서 이 페이지 편집하기 또는 이슈 제출하기.