client

Documentation

Index

• func WithBaseURL(baseURL string) core.ClientOption
• func WithHTTPClient(httpClient core.HTTPClient) core.ClientOption
• func WithHTTPHeader(httpHeader http.Header) core.ClientOption
• func WithToken(token string) core.ClientOption
• type Client
  • func NewClient(opts ...core.ClientOption) *Client
  • func (c *Client) Chat(ctx context.Context, request *v2.ChatRequest) (*v2.NonStreamedChatResponse, error)
  • func (c *Client) ChatStream(ctx context.Context, request *v2.ChatStreamRequest) (*core.Stream[v2.StreamedChatResponse], error)
  • func (c *Client) Classify(ctx context.Context, request *v2.ClassifyRequest) (*v2.ClassifyResponse, error)
  • func (c *Client) DetectLanguage(ctx context.Context, request *v2.DetectLanguageRequest) (*v2.DetectLanguageResponse, error)
  • func (c *Client) Detokenize(ctx context.Context, request *v2.DetokenizeRequest) (*v2.DetokenizeResponse, error)
  • func (c *Client) Embed(ctx context.Context, request *v2.EmbedRequest) (*v2.EmbedResponse, error)
  • func (c *Client) Generate(ctx context.Context, request *v2.GenerateRequest) (*v2.Generation, error)
  • func (c *Client) Rerank(ctx context.Context, request *v2.RerankRequest) (*v2.RerankResponse, error)
  • func (c *Client) Summarize(ctx context.Context, request *v2.SummarizeRequest) (*v2.SummarizeResponse, error)
  • func (c *Client) Tokenize(ctx context.Context, request *v2.TokenizeRequest) (*v2.TokenizeResponse, error)

Functions

func WithBaseURL

func WithBaseURL(baseURL string) core.ClientOption

WithBaseURL sets the client's base URL, overriding the default environment, if any.

func WithHTTPClient

func WithHTTPClient(httpClient core.HTTPClient) core.ClientOption

WithHTTPClient uses the given HTTPClient to issue all HTTP requests.

func WithHTTPHeader

func WithHTTPHeader(httpHeader http.Header) core.ClientOption

WithHTTPHeader adds the given http.Header to all requests issued by the client.

func WithToken

func WithToken(token string) core.ClientOption

WithToken sets the 'Authorization: Bearer <token>' header on every request.

Types

type Client

type Client struct {
	Connectors *connectors.Client
	// contains filtered or unexported fields
}

func NewClient

func NewClient(opts ...core.ClientOption) *Client

func (*Client) Chat

func (c *Client) Chat(ctx context.Context, request *v2.ChatRequest) (*v2.NonStreamedChatResponse, error)

The `chat` endpoint allows users to have conversations with a Large Language Model (LLM) from Cohere. Users can send messages as part of a persisted conversation using the `conversation_id` parameter, or they can pass in their own conversation history using the `chat_history` parameter. The endpoint features additional parameters such as connectors(https://docs.cohere.com/docs/connectors) and `documents` that enable conversations enriched by external knowledge. We call this "Retrieval Augmented Generation", or "RAG".

func (*Client) ChatStream

func (c *Client) ChatStream(ctx context.Context, request *v2.ChatStreamRequest) (*core.Stream[v2.StreamedChatResponse], error)

The `chat` endpoint allows users to have conversations with a Large Language Model (LLM) from Cohere. Users can send messages as part of a persisted conversation using the `conversation_id` parameter, or they can pass in their own conversation history using the `chat_history` parameter. The endpoint features additional parameters such as connectors(https://docs.cohere.com/docs/connectors) and `documents` that enable conversations enriched by external knowledge. We call this "Retrieval Augmented Generation", or "RAG".

func (*Client) Classify

func (c *Client) Classify(ctx context.Context, request *v2.ClassifyRequest) (*v2.ClassifyResponse, error)

This endpoint makes a prediction about which label fits the specified text inputs best. To make a prediction, Classify uses the provided `examples` of text + label pairs as a reference. Note: [Custom Models](/training-representation-models) trained on classification examples don't require the `examples` parameter to be passed in explicitly.

func (*Client) DetectLanguage

func (c *Client) DetectLanguage(ctx context.Context, request *v2.DetectLanguageRequest) (*v2.DetectLanguageResponse, error)

This endpoint identifies which language each of the provided texts is written in.

func (*Client) Detokenize

func (c *Client) Detokenize(ctx context.Context, request *v2.DetokenizeRequest) (*v2.DetokenizeResponse, error)

This endpoint takes tokens using byte-pair encoding and returns their text representation. To learn more about tokenization and byte pair encoding, see the tokens page.

func (*Client) Embed

func (c *Client) Embed(ctx context.Context, request *v2.EmbedRequest) (*v2.EmbedResponse, error)

This endpoint returns text embeddings. An embedding is a list of floating point numbers that captures semantic information about the text that it represents.

Embeddings can be used to create text classifiers as well as empower semantic search. To learn more about embeddings, see the embedding page.

If you want to learn more how to use the embedding model, have a look at the [Semantic Search Guide](/docs/semantic-search).

func (*Client) Generate

func (c *Client) Generate(ctx context.Context, request *v2.GenerateRequest) (*v2.Generation, error)

This endpoint generates realistic text conditioned on a given input.

func (*Client) Rerank

func (c *Client) Rerank(ctx context.Context, request *v2.RerankRequest) (*v2.RerankResponse, error)

This endpoint takes in a query and a list of texts and produces an ordered array with each text assigned a relevance score.

func (*Client) Summarize

func (c *Client) Summarize(ctx context.Context, request *v2.SummarizeRequest) (*v2.SummarizeResponse, error)

This endpoint generates a summary in English for a given text.

func (*Client) Tokenize

func (c *Client) Tokenize(ctx context.Context, request *v2.TokenizeRequest) (*v2.TokenizeResponse, error)

This endpoint splits input text into smaller units called tokens using byte-pair encoding (BPE). To learn more about tokenization and byte pair encoding, see the tokens page.