Cohere

To process a large amount of data based on context and input from the user using Cohere Provider.

Cohere is a powerful natural language processing model developed by Cohere Technologies. It is based on the GPT (Generative Pre-trained Transformer) architecture and is specifically designed for language understanding tasks. The model has been trained on a large corpus of text data and can generate coherent and contextually relevant responses to a wide range of questions and prompts.

The Cohere component allows you to integrate Cohere into your Flows. You can customize the parameters used by Cohere component, and also specify the context of knowledge that the Cohere component operates on, as well as provide the input query. Both the context and the query are given to the Cohere component by specifying Diaflow component identifiers. For example, the above screenshot shows the default user message of {{in-0}} which is a Text Input component.

The Cohere component has the identifier of co-X, where X represents the instance number of the Cohere component.

The Cohere component has the following parameters that can be specified directly on the UI component.

Parameter NameDescription

Model

Specifies the version of Cohere model to use. Available options: - Cohere

System/Instruction

Describes how you want the Cohere model to respond. For example, you can specify the role, manner and rules that Cohere should adhere to.

Prompt

Describes the context and user query in terms of component ID's of other Diaflow components. You can specify the context and the user query here. For example, to specify the user query we can reference the first instance of a Text Input component by using the double curly bracket syntax {{in-0}}.

Component Inputs

The Cohere component has the following input connections.

Input NameDescriptionConstraints

From Data loaders/Data source/VectorDB

This input connection represents the context information for the Anthropic model.

Must originate from a Data Loader/Data Source or VectorDB component.

From Input

This input connection represents the user query for the Cohere model.

Must originate from a component that generates a text string as output such as a Python or Text Input component.

Component Outputs

The Cohere component has the following output connections.

Output Name FormatDescriptionConstraints

To Output

This output connection contains the text result of the Anthropic component.

Can be connected to any component that accepts a string input.

The Cohere component has the following configuration options.

Configuration Option NameDescription

Description

This is a user supplied textual description of Cohere component.

Credentials

You can specify to use your own Cohere credentials or alternatively you can use Diaflow's default credentials.

Enable Caching

This option determines whether the results of the component are cached. This means that on the next run of the Flow, Diaflow will utilize the previous computed component output, as long as the inputs have not changed.

Caching Time

Only applicable if the "Enable Caching" option has been enabled. This parameter controls how long Diaflow will wait before automatically clearing the cache.

Clear Cache

Only applicable if the "Enable Caching" option has been enabled. Clicking this button will clear the cache.

Use Cases

The following is a simple use case of the Cohere component, where the Cohere component is being used to provide the user the ability to ask the Cohere component questions via a Text Input component.

Last updated