Skip to content

Latest commit

 

History

History
90 lines (61 loc) · 4.49 KB

cohere.md

File metadata and controls

90 lines (61 loc) · 4.49 KB
Raw

Cohere

Cohere

Trial Keys Available: Cohere is an AI company specializing in large language models (LLMs) designed for enterprise use. They offer a platform that allows developers to leverage pre-built models or create custom models tailored to specific business needs. Cohere's technology empowers businesses to integrate natural language processing capabilities into their applications, streamlining tasks such as text generation, analysis, and understanding. Their focus on enterprise solutions sets them apart, providing secure and customizable AI tools to improve efficiency and productivity across various industries.

Interface Name

  • cohere

Example Usage

const { LLMInterface } = require('llm-interface');

LLMInterface.setApiKey({'cohere': process.env.COHERE_API_KEY});

async function main() {
  try {
    const response = await LLMInterface.sendMessage('cohere', 'Explain the importance of low latency LLMs.');
    console.log(response.results);
  } catch (error) {
    console.error(error);
    throw error;
  }
}

main();

Model Aliases

The following model aliases are provided for this provider.

  • default: command-r
  • large: command-r-plus
  • small: command-light
  • agent: command-r-plus

Embeddings Model Aliases

  • default: embed-english-v3.0
  • large: embed-english-v3.0
  • small: embed-english-light-v3.0

Options

The following parameters can be passed through options.

  • chat_history: Details not available, please refer to the LLM provider documentation.
  • connectors: Details not available, please refer to the LLM provider documentation.
  • conversation_id: Details not available, please refer to the LLM provider documentation.
  • documents: Details not available, please refer to the LLM provider documentation.
  • force_single_step: Details not available, please refer to the LLM provider documentation.
  • frequency_penalty: Penalizes new tokens based on their existing frequency in the text so far, reducing the likelihood of repeating the same line. Positive values reduce the frequency of tokens appearing in the generated text.
  • k: Details not available, please refer to the LLM provider documentation.
  • max_input_tokens: Details not available, please refer to the LLM provider documentation.
  • max_tokens: The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length.
  • p: Details not available, please refer to the LLM provider documentation.
  • preamble: Details not available, please refer to the LLM provider documentation.
  • presence_penalty: Penalizes new tokens based on whether they appear in the text so far, encouraging the model to talk about new topics. Positive values increase the likelihood of new tokens appearing in the generated text.
  • prompt_truncation: Details not available, please refer to the LLM provider documentation.
  • seed: A random seed for reproducibility. If specified, the system will attempt to sample deterministically, ensuring repeated requests with the same seed and parameters return the same result. Determinism is not guaranteed.
  • stop_sequences: Sequences that indicate to the model when to stop generating further tokens.
  • stream: If set, partial message deltas will be sent, similar to ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message.
  • temperature: Controls the randomness of the AI's responses. A higher temperature results in more random outputs, while a lower temperature makes the output more focused and deterministic. Generally, it is recommended to alter this or top_p, but not both.
  • tool_results: Details not available, please refer to the LLM provider documentation.
  • tools: A list of external tools available for the AI to use in generating responses.

Features

  • Streaming
  • Tools
  • Embeddings

Getting an API Key

Commercial with Free Trial:The Cohere API offers trial keys with rate limits. These keys are not intended for commercial use.

To get an API key, first create a Cohere account, then visit the link below.

Cohere Documentation

Cohere documentation is available here.