Namespace: openaicompatible

Functions

ChatTextGenerator

▸ ChatTextGenerator(settings): OpenAICompatibleChatModel

Create a text generation model that calls an API that is compatible with OpenAI's chat API.

Please note that many providers implement the API with slight differences, which can cause unexpected errors and different behavior in less common scenarios.

Parameters

Name	Type
settings	OpenAICompatibleChatSettings

Returns

OpenAICompatibleChatModel

See

https://platform.openai.com/docs/api-reference/chat/create

Example

const model = openaicompatible.ChatTextGenerator({
  model: "provider-specific-model-name",
  temperature: 0.7,
  maxGenerationTokens: 500,
});

const text = await generateText({
  model,
  prompt: [
    openai.ChatMessage.user(
      "Write a short story about a robot learning to love:"
    ),
  ]
});

Defined in

packages/modelfusion/src/model-provider/openai-compatible/OpenAICompatibleFacade.ts:114

---

CompletionTextGenerator

▸ CompletionTextGenerator(settings): OpenAICompatibleCompletionModel

Create a text generation model that calls an API that is compatible with OpenAI's completion API.

Please note that many providers implement the API with slight differences, which can cause unexpected errors and different behavior in less common scenarios.

Parameters

Name	Type
settings	OpenAICompatibleChatSettings

Returns

OpenAICompatibleCompletionModel

See

https://platform.openai.com/docs/api-reference/completions/create

Example

const model = openaicompatible.CompletionTextGenerator({
  model: "provider-specific-model-name",
  temperature: 0.7,
  maxGenerationTokens: 500,
});

const text = await generateText({
  model,
  prompt: "Write a short story about a robot learning to love:"
});

Defined in

packages/modelfusion/src/model-provider/openai-compatible/OpenAICompatibleFacade.ts:82

---

FireworksAIApi

▸ FireworksAIApi(settings?): FireworksAIApiConfiguration

Configuration for the Fireworks.ai API.

It calls the API at https://api.fireworks.ai/inference/v1 and uses the FIREWORKS_API_KEY api key environment variable.

Parameters

Name	Type
settings	Omit<BaseUrlPartsApiConfigurationOptions, "baseUrl"> & { baseUrl?: string | Partial<UrlParts> } & { apiKey?: string }

Returns

FireworksAIApiConfiguration

See

https://readme.fireworks.ai/docs/openai-compatibility

Defined in

packages/modelfusion/src/model-provider/openai-compatible/OpenAICompatibleFacade.ts:22

---

PerplexityApi

▸ PerplexityApi(settings?): PerplexityApiConfiguration

Configuration for the Perplexity API.

It calls the API at https://api.perplexity.ai/ and uses the PERPLEXITY_API_KEY api key environment variable.

Parameters

Name	Type
settings	Omit<BaseUrlPartsApiConfigurationOptions, "baseUrl"> & { baseUrl?: string | Partial<UrlParts> } & { apiKey?: string }

Returns

PerplexityApiConfiguration

See

https://docs.perplexity.ai/reference/post_chat_completions

Defined in

packages/modelfusion/src/model-provider/openai-compatible/OpenAICompatibleFacade.ts:37

---

TextEmbedder

▸ TextEmbedder(settings): OpenAICompatibleTextEmbeddingModel

Create a text embedding model that calls the OpenAI embedding API.

Parameters

Name	Type
settings	OpenAICompatibleTextEmbeddingModelSettings

Returns

OpenAICompatibleTextEmbeddingModel

A new instance of OpenAITextEmbeddingModel.

See

https://platform.openai.com/docs/api-reference/embeddings

Example

const embeddings = await embedMany({
  model: openaicompatible.TextEmbedder({ model: "provider-specific-model-name" }),
  values: [
    "At first, Nox didn't know what to do with the pup.",
    "He keenly observed and absorbed everything around him, from the birds in the sky to the trees in the forest.",
  ]
});

Defined in

packages/modelfusion/src/model-provider/openai-compatible/OpenAICompatibleFacade.ts:134

---

TogetherAIApi

▸ TogetherAIApi(settings?): TogetherAIApiConfiguration

Configuration for the Together.ai API.

It calls the API at https://api.together.xyz/v1 and uses the TOGETHER_API_KEY api key environment variable.

Parameters

Name	Type
settings	Omit<BaseUrlPartsApiConfigurationOptions, "baseUrl"> & { baseUrl?: string | Partial<UrlParts> } & { apiKey?: string }

Returns

TogetherAIApiConfiguration

See

https://docs.together.ai/docs/openai-api-compatibility

Defined in

packages/modelfusion/src/model-provider/openai-compatible/OpenAICompatibleFacade.ts:52