Namespace: Agentic

Agentic RAG

The Agentic class allows to define a pipeline of actions to be executed in sequence. Each action can be of different types:

predict: ask a question to the LLM model and extract information in a JSON response
find: search for a set of results based on a query
ask: perform a Nuclia RAG call based on a query
web: fetch a web page and extract information based on CSS selectors
api: call an API and extract information based on a JSON path
user: wait for a user entry

Example:

  const agentic = nucliaApi.knowledgeBox.createAgenticRAGPipeline({
   START: {
     action: {
       type: 'predict',
       query: 'Does the following question refers to a specific reference document? QUESTION: "{{query}}"',
       outputs: {
         reference: {
           type: 'string',
           description: 'The name of the reference document if any, and just an empty string if none.',
         },
       },
     },
     next: [
       { stepId: 'finddoc', if: '`{{START.reference}}` !== ""' },
       { stepId: 'domain', if: '`{{START.reference}}` == ""' },
     ],
   },
   finddoc: {
     action: {
       type: 'find',
       query: '{{START.reference}}',
       features: [Search.Features.KEYWORD],
       options: {
         fields: ['a/title'],
       },
     },
     next: [{ stepId: 'domain' }],
   },
   domain: {
     action: {
       type: 'predict',
       query:
         'What is the domain of the question among the following categories: "ART", "SCIENCE" ? QUESTION: "{{query}}"',
       outputs: {
         domain: { type: 'string', description: 'The domain of the question.' },
       },
     },
     next: [{ stepId: 'answer' }],
   },
   answer: {
     action: {
       type: 'ask',
       query: '{{query}}',
       options: {
         filters: ['/classification.labels/domain/{{domain.domain}}'],
         resource_filters: ['{{finddoc.results.resources.[0].id}}'],
       },
     },
   },
 });
 agentic
   .run({
     query,
   })
   .subscribe((res) => console.log(agentic.context));
 agentic.status.subscribe((res) => console.log(res));
 * ```

## Table of contents

### Classes

- [Pipeline](../classes/Agentic.Pipeline.md)

### Interfaces

- [APIAction](../interfaces/Agentic.APIAction.md)
- [AskAction](../interfaces/Agentic.AskAction.md)
- [Event](../interfaces/Agentic.Event.md)
- [FindAction](../interfaces/Agentic.FindAction.md)
- [Output](../interfaces/Agentic.Output.md)
- [OutputArray](../interfaces/Agentic.OutputArray.md)
- [PredictAction](../interfaces/Agentic.PredictAction.md)
- [Step](../interfaces/Agentic.Step.md)
- [UserEventAction](../interfaces/Agentic.UserEventAction.md)
- [WebAction](../interfaces/Agentic.WebAction.md)

### Type Aliases

- [Action](Agentic.md#action)
- [Steps](Agentic.md#steps)

## Type Aliases

### Action

Ƭ **Action**: [`PredictAction`](../interfaces/Agentic.PredictAction.md) \| [`FindAction`](../interfaces/Agentic.FindAction.md) \| [`AskAction`](../interfaces/Agentic.AskAction.md) \| [`WebAction`](../interfaces/Agentic.WebAction.md) \| [`APIAction`](../interfaces/Agentic.APIAction.md) \| [`UserEventAction`](../interfaces/Agentic.UserEventAction.md)

#### Defined in

[libs/sdk-core/src/lib/db/search/agentic.ts:134](https://github.com/nuclia/frontend/blob/55a20097/libs/sdk-core/src/lib/db/search/agentic.ts#L134)

___

### Steps

Ƭ **Steps**: `Object`

#### Index signature

▪ [stepId: `string`]: [`Step`](../interfaces/Agentic.Step.md)

#### Defined in

[libs/sdk-core/src/lib/db/search/agentic.ts:148](https://github.com/nuclia/frontend/blob/55a20097/libs/sdk-core/src/lib/db/search/agentic.ts#L148)