Skip to main content
API docs by Redocly

Nuclia Understanding API (v1)

API reference for the Nuclia Understanding API. Requires a NUA API Key from the account management interface.

Processing

Ingest API endpoints to process data and get results back.

Download Binary File

Download a file referenced in an upload token

query Parameters
token
required
string (Token)

Responses

Response samples

Content type
application/json
null

Send Data To Process

Push data to process

Request Body schema: application/json
required
Kbid (string) or Kbid (null) (Kbid)
Uuid (string) or Uuid (null) (Uuid)
Title (string) or Title (null) (Title)
labels
Array of strings (Labels)
Default: []
Slug (string) or Slug (null) (Slug)
Source (string) or null
Userid (string) or Userid (null) (Userid)
object (Genericfield)
Default: {}
object (Filefield)
Default: {}
object (Linkfield)
Default: {}
object (Textfield)
Default: {}
object (Layoutfield)
Default: {}
object (Conversationfield)
Default: {}
PushProcessingOptions (object) or null
LearningConfig (object) or null
WebhookConfig (object) or null

Responses

Request samples

Content type
application/json
{
  • "kbid": "string",
  • "uuid": "string",
  • "title": "string",
  • "labels": [ ],
  • "slug": "string",
  • "source": "WEB",
  • "userid": "string",
  • "genericfield": { },
  • "filefield": { },
  • "linkfield": { },
  • "textfield": { },
  • "layoutfield": { },
  • "conversationfield": { },
  • "processing_options": {
    },
  • "learning_config": {
    },
  • "webhook_config": {
    }
}

Response samples

Content type
application/json
{
  • "seqid": 0,
  • "account_seq": 0,
  • "queue": "shared",
  • "uuid": "string",
  • "processing_id": "string"
}

Get Processed Data

Retreive status of processed and unprocessed payloads from a zone

query Parameters
Cursor (string) or Cursor (null) (Cursor)
limit
integer (Limit)
Default: 20
Scheduled (boolean) or Scheduled (null) (Scheduled)
Kbid (string) or Kbid (null) (Kbid)
sort_on
string (SortFields)
Default: "timestamp"
Enum: "timestamp" "scheduled_at" "completed_at"
sort_order
string (SortOrder)
Default: "asc"
Enum: "asc" "desc"

Responses

Response samples

Content type
application/json
{
  • "results": [
    ],
  • "cursor": "string"
}

Get Processed Data

Retreive status of processed and unprocessed payloads from a zone

path Parameters
processing_id
required
string (Processing Id)

Responses

Response samples

Content type
application/json
{
  • "processing_id": "string",
  • "resource_id": "string",
  • "kbid": "string",
  • "title": "string",
  • "labels": [
    ],
  • "completed": true,
  • "scheduled": true,
  • "timestamp": "2019-08-24T14:15:22Z",
  • "completed_at": "2019-08-24T14:15:22Z",
  • "scheduled_at": "2019-08-24T14:15:22Z",
  • "failed": false,
  • "retries": 0,
  • "schedule_eta": 0,
  • "schedule_order": 0,
  • "request": "string",
  • "response": "string"
}

Stream Processed Data

Retrieve SSE stream of processed data for a given processing ID.

path Parameters
processing_id
required
string (Processing Id)
query Parameters
Array of Data Types (strings) or Data Types (null) (Data Types)

Responses

Response samples

Content type
null

Upload Binary File

Upload a file using a multipart request

header Parameters
X-Filename (string) or X-Filename (null) (X-Filename)
Default:
X-Password (string) or X-Password (null) (X-Password)
X-Language (string) or X-Language (null) (X-Language)
X-Md5 (string) or X-Md5 (null) (X-Md5)

Responses

Response samples

Content type
application/json
null

Processing TUS uploads

Processing uploads using TUS protocol

Create New Upload

An empty POST request is used to create a new upload resource. The Upload-Length header indicates the size of the entire upload in bytes.

Responses

Response samples

Content type
application/json
null

Tus Server Information

Gather information about the Server’s current configuration such as enabled extensions, version...

path Parameters
required
Upload Id (string) or Upload Id (null) (Upload Id)

Responses

Response samples

Content type
application/json
{
  • "detail": [
    ]
}

Upload Information

Get information about a current download (completed upload size)

path Parameters
upload_id
required
string (Upload Id)

Responses

Response samples

Content type
application/json
null

Upload Data

Upload all bytes in the requests and append them in the specifyied offset

path Parameters
upload_id
required
string (Upload Id)

Responses

Response samples

Content type
application/json
null

Training

Training API endpoints to train custom models with your data.

Download Account Predictive Model File

Download the trained model or any other generated file as a result of a training task on a Knowledge Box

path Parameters
kbid
required
string (Kbid)
model_id
required
string (Model Id)
filename
required
string (Filename)
query Parameters
account_id
required
string (Account Id)

Responses

Response samples

Content type
application/json
null

Models

Models API

Account Assume Role For Bedrock Models

Start a new assume role authentication flow for an account

path Parameters
account_id
required
string (Account Id)

Responses

Response samples

Content type
application/json
{
  • "external_id": "string",
  • "aws_account_id": "string",
  • "role_name": "string"
}

Account Bedrock Models Authentication

Finish a new bedrock authentication flow for an account

path Parameters
account_id
required
string (Account Id)
Request Body schema: application/json
required
role_arn
required
string (Role Arn)

ARN of the role created in AWS IAM

Responses

Request samples

Content type
application/json
{
  • "role_arn": "string"
}

Response samples

Content type
application/json
null

Account Bedrock Models Authentication

Delete existing bedrock assume role configuration for an account

path Parameters
account_id
required
string (Account Id)

Responses

Response samples

Content type
application/json
null

Account Bedrock Models Authentication

Validate the bedrock assume role configuration for an account

path Parameters
account_id
required
string (Account Id)

Responses

Response samples

Content type
application/json
null

Learning Configuration Schema

Get available models

path Parameters
account_id
required
string (Account Id)
dataset_id
required
string (Dataset Id)

Responses

Response samples

Content type
application/json
{ }

Get Public Model Configuration On Account

Get details of a public model configuration on an account

path Parameters
account_id
required
string (Account Id)
model_id
required
string <uuid4> (Model Id)

Responses

Response samples

Content type
application/json
{
  • "id": "string",
  • "default_model_id": "string",
  • "description": "string",
  • "user_keys": {
    },
  • "user_prompts": {
    },
  • "assume_role": 0,
  • "kbids": [
    ]
}

Public Model Configuration Deletion On Account

Delete specific public model configuration from the account

path Parameters
account_id
required
string (Account Id)
model_id
required
string <uuid4> (Model Id)

Responses

Response samples

Content type
application/json
{
  • "detail": [
    ]
}

List Public Models Configured On An Account

List public models configured on an account

path Parameters
account_id
required
string (Account Id)

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Learning Configuration Schema

Get trained models

path Parameters
account_id
required
string (Account Id)
model_id
required
string <uuid4> (Model Id)

Responses

Response samples

Content type
application/json
{
  • "model_id": "string",
  • "account": "string",
  • "model_type": "GENERATIVE",
  • "trained_date": "2019-08-24T14:15:22Z",
  • "location": "string",
  • "trained_kbid": "string",
  • "model_types": [ ],
  • "log": "string",
  • "kbids": [
    ],
  • "openai_compat": {
    }
}

Model Deletion On Account

Delete specific model from account, destroying action

path Parameters
account_id
required
string (Account Id)
model_id
required
string <uuid4> (Model Id)

Responses

Response samples

Content type
application/json
{
  • "detail": [
    ]
}

Learning Configuration Models From Account

Get trained models

path Parameters
account_id
required
string (Account Id)

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Delete A Model From A Kb

Remove from availability a model from a KB

path Parameters
kbid
required
string (Kbid)
model_id
required
string (Model Id)
account_id
required
string (Account Id)

Responses

Response samples

Content type
application/json
{
  • "detail": [
    ]
}

Learning Configuration Schema

Get schema for creating a KB

path Parameters
account_id
required
string (Account Id)

Responses

Response samples

Content type
application/json
{
  • "semantic_model": {
    },
  • "semantic_models": {
    },
  • "default_semantic_model": {
    },
  • "anonymization_model": {
    },
  • "visual_labeling": {
    },
  • "generative_model": {
    },
  • "ner_model": {
    },
  • "relation_model": {
    },
  • "summary_model": {
    },
  • "summary": {
    },
  • "user_keys": {
    },
  • "user_prompts": {
    },
  • "summary_prompt": {
    },
  • "prefer_markdown_generative_response": {
    },
  • "semantic_graph_node_models": {
    },
  • "default_semantic_graph_node_model": {
    },
  • "semantic_graph_edge_models": {
    },
  • "default_semantic_graph_edge_model": {
    }
}

Learning Configuration Schema

Get available models onprem

path Parameters
kbid
required
string (Kbid)

Responses

Response samples

Content type
application/json
{ }

Add A Model To A Kb Onprem

Add a model to a KB to be used

path Parameters
kbid
required
string (Kbid)
Request Body schema: application/json
required
id
required
string (Id)

Responses

Request samples

Content type
application/json
{
  • "id": "string"
}

Response samples

Content type
application/json
null

Model Configuration

Get trained models

path Parameters
kbid
required
string (Kbid)
model_id
required
string (Model Id)

Responses

Response samples

Content type
application/json
{ }

Knowledge Boxes

Knowledge Boxes API

Knowledgebox Models Configuration

Current configuration of models assigned to a knowledgebox

path Parameters
kbid
required
string (Kbid)

Responses

Response samples

Content type
application/json
{
  • "resource_labelers_models": [
    ],
  • "paragraph_labelers_models": [
    ],
  • "intent_models": [
    ],
  • "visual_labeling": "disabled",
  • "ner_model": "multilingual",
  • "relation_model": "base",
  • "anonymization_model": "disabled",
  • "semantic_model": "string",
  • "semantic_models": [
    ],
  • "default_semantic_model": "string",
  • "semantic_graph_node_models": [
    ],
  • "default_semantic_graph_node_model": "string",
  • "semantic_graph_edge_models": [
    ],
  • "default_semantic_graph_edge_model": "string",
  • "semantic_vector_similarity": "DOT",
  • "semantic_vector_size": 1024,
  • "semantic_matryoshka_dims": [ ],
  • "semantic_threshold": 0.4,
  • "generative_model": "chatgpt-azure-4o",
  • "user_keys": {
    },
  • "user_prompts": {
    },
  • "summary": "extended",
  • "summary_model": "chatgpt-azure-4o",
  • "summary_prompt": {
    },
  • "prefer_markdown_generative_response": false,
  • "semantic_model_configs": { },
  • "semantic_graph_node_model_configs": { },
  • "semantic_graph_edge_model_configs": { }
}

Knowledgebox Models Add Configuration

Current configuration of models assigned to a knowledgebox

path Parameters
kbid
required
string (Kbid)
Request Body schema: application/json
required
AnonymizationModel (string) or Anonymization Model (string) (Anonymization Model)
Default: "disabled"
VisualLabeling (string) or Visual Labeling (string) (Visual Labeling)
Default: "disabled"
generative_model
string (Generative Model)
Default: "chatgpt-azure-4o"
NERModel (string) or Ner Model (string) (Ner Model)
Default: "multilingual"
RelationModel (string) or Relation Model (string) (Relation Model)
Default: "base"
UserLearningKeys (object) or null
UserPrompts (object) or null
Summary (string) or null
Default: "simple"
summary_model
string (Summary Model)
Default: "chatgpt-azure-4o"
SummaryPrompt (object) or null
prefer_markdown_generative_response
boolean (Prefer Markdown Generative Response)
Default: false
Default Semantic Model (string) or Default Semantic Model (null) (Default Semantic Model)

The default vector set / semantic model to use. Must be one of the models defined in the semantic_models field. If not provided, the first model in the list will be used.

SemanticModel (string) or null
Deprecated
Array of Semantic Models (strings) or Semantic Models (null) (Semantic Models)
Array of Semantic Graph Node Models (strings) or Semantic Graph Node Models (null) (Semantic Graph Node Models)
Default Semantic Graph Node Model (string) or Default Semantic Graph Node Model (null) (Default Semantic Graph Node Model)
Array of Semantic Graph Edge Models (strings) or Semantic Graph Edge Models (null) (Semantic Graph Edge Models)
Default Semantic Graph Edge Model (string) or Default Semantic Graph Edge Model (null) (Default Semantic Graph Edge Model)

Responses

Request samples

Content type
application/json
{
  • "anonymization_model": "disabled",
  • "visual_labeling": "disabled",
  • "generative_model": "chatgpt-azure-4o",
  • "ner_model": "multilingual",
  • "relation_model": "base",
  • "user_keys": {
    },
  • "user_prompts": {
    },
  • "summary": "simple",
  • "summary_model": "chatgpt-azure-4o",
  • "summary_prompt": {
    },
  • "prefer_markdown_generative_response": false,
  • "default_semantic_model": "string",
  • "semantic_model": "en-2024-04-24",
  • "semantic_models": [
    ],
  • "semantic_graph_node_models": [
    ],
  • "default_semantic_graph_node_model": "string",
  • "semantic_graph_edge_models": [
    ],
  • "default_semantic_graph_edge_model": "string"
}

Response samples

Content type
application/json
{
  • "resource_labelers_models": [
    ],
  • "paragraph_labelers_models": [
    ],
  • "intent_models": [
    ],
  • "visual_labeling": "disabled",
  • "ner_model": "multilingual",
  • "relation_model": "base",
  • "anonymization_model": "disabled",
  • "semantic_model": "string",
  • "semantic_models": [
    ],
  • "default_semantic_model": "string",
  • "semantic_graph_node_models": [
    ],
  • "default_semantic_graph_node_model": "string",
  • "semantic_graph_edge_models": [
    ],
  • "default_semantic_graph_edge_model": "string",
  • "semantic_vector_similarity": "DOT",
  • "semantic_vector_size": 1024,
  • "semantic_matryoshka_dims": [ ],
  • "semantic_threshold": 0.4,
  • "generative_model": "chatgpt-azure-4o",
  • "user_keys": {
    },
  • "user_prompts": {
    },
  • "summary": "extended",
  • "summary_model": "chatgpt-azure-4o",
  • "summary_prompt": {
    },
  • "prefer_markdown_generative_response": false,
  • "semantic_model_configs": { },
  • "semantic_graph_node_model_configs": { },
  • "semantic_graph_edge_model_configs": { }
}

Knowledgebox Models Update Configuration

Current configuration of models assigned to a knowledgebox

path Parameters
kbid
required
string (Kbid)
Request Body schema: application/json
required
AnonymizationModel (string) or Anonymization Model (string) (Anonymization Model)
Default: "disabled"
VisualLabeling (string) or Visual Labeling (string) (Visual Labeling)
Default: "disabled"
generative_model
string (Generative Model)
Default: "chatgpt-azure-4o"
NERModel (string) or Ner Model (string) (Ner Model)
Default: "multilingual"
RelationModel (string) or Relation Model (string) (Relation Model)
Default: "base"
UserLearningKeys (object) or null
UserPrompts (object) or null
Summary (string) or null
Default: "simple"
summary_model
string (Summary Model)
Default: "chatgpt-azure-4o"
SummaryPrompt (object) or null
prefer_markdown_generative_response
boolean (Prefer Markdown Generative Response)
Default: false
Default Semantic Model (string) or Default Semantic Model (null) (Default Semantic Model)

The default vector set / semantic model to use. Must be one of the models defined in the semantic_models field. If not provided, the first model in the list will be used.

Responses

Request samples

Content type
application/json
{
  • "anonymization_model": "disabled",
  • "visual_labeling": "disabled",
  • "generative_model": "chatgpt-azure-4o",
  • "ner_model": "multilingual",
  • "relation_model": "base",
  • "user_keys": {
    },
  • "user_prompts": {
    },
  • "summary": "simple",
  • "summary_model": "chatgpt-azure-4o",
  • "summary_prompt": {
    },
  • "prefer_markdown_generative_response": false,
  • "default_semantic_model": "string"
}

Response samples

Content type
application/json
{
  • "resource_labelers_models": [
    ],
  • "paragraph_labelers_models": [
    ],
  • "intent_models": [
    ],
  • "visual_labeling": "disabled",
  • "ner_model": "multilingual",
  • "relation_model": "base",
  • "anonymization_model": "disabled",
  • "semantic_model": "string",
  • "semantic_models": [
    ],
  • "default_semantic_model": "string",
  • "semantic_graph_node_models": [
    ],
  • "default_semantic_graph_node_model": "string",
  • "semantic_graph_edge_models": [
    ],
  • "default_semantic_graph_edge_model": "string",
  • "semantic_vector_similarity": "DOT",
  • "semantic_vector_size": 1024,
  • "semantic_matryoshka_dims": [ ],
  • "semantic_threshold": 0.4,
  • "generative_model": "chatgpt-azure-4o",
  • "user_keys": {
    },
  • "user_prompts": {
    },
  • "summary": "extended",
  • "summary_model": "chatgpt-azure-4o",
  • "summary_prompt": {
    },
  • "prefer_markdown_generative_response": false,
  • "semantic_model_configs": { },
  • "semantic_graph_node_model_configs": { },
  • "semantic_graph_edge_model_configs": { }
}

Knowledgebox Models Configuration

Delete a KB configuration

path Parameters
kbid
required
string (Kbid)

Responses

Response samples

Content type
application/json
{
  • "detail": [
    ]
}

Available Models For A Knowledge Box

Get all available models for a knowledge box grouped by provider

path Parameters
kbid
required
string (Kbid)

Responses

Response samples

Content type
application/json
{
  • "providers": {
    }
}

Learning Configuration Schema

Get jsonschema definition for learning_configuration field of knowledgebox creation payload

Responses

Response samples

Content type
application/json
{
  • "semantic_model": {
    },
  • "semantic_models": {
    },
  • "default_semantic_model": {
    },
  • "anonymization_model": {
    },
  • "visual_labeling": {
    },
  • "generative_model": {
    },
  • "ner_model": {
    },
  • "relation_model": {
    },
  • "summary_model": {
    },
  • "summary": {
    },
  • "user_keys": {
    },
  • "user_prompts": {
    },
  • "summary_prompt": {
    },
  • "prefer_markdown_generative_response": {
    },
  • "semantic_graph_node_models": {
    },
  • "default_semantic_graph_node_model": {
    },
  • "semantic_graph_edge_models": {
    },
  • "default_semantic_graph_edge_model": {
    }
}

Learning Configuration Schema

Get jsonschema definition for learning_configuration field of knowledgebox creation payload

Responses

Response samples

Content type
application/json
{
  • "semantic_model": {
    },
  • "semantic_models": {
    },
  • "default_semantic_model": {
    },
  • "anonymization_model": {
    },
  • "visual_labeling": {
    },
  • "generative_model": {
    },
  • "ner_model": {
    },
  • "relation_model": {
    },
  • "summary_model": {
    },
  • "summary": {
    },
  • "user_keys": {
    },
  • "user_prompts": {
    },
  • "summary_prompt": {
    },
  • "prefer_markdown_generative_response": {
    },
  • "semantic_graph_node_models": {
    },
  • "default_semantic_graph_node_model": {
    },
  • "semantic_graph_edge_models": {
    },
  • "default_semantic_graph_edge_model": {
    }
}

Learning Configuration Schema

Get jsonschema definition for learning_configuration field of knowledgebox update payload

path Parameters
kbid
required
string (Kbid)

Responses

Response samples

Content type
application/json
{
  • "semantic_model": {
    },
  • "semantic_models": {
    },
  • "default_semantic_model": {
    },
  • "anonymization_model": {
    },
  • "visual_labeling": {
    },
  • "generative_model": {
    },
  • "ner_model": {
    },
  • "relation_model": {
    },
  • "summary_model": {
    },
  • "summary": {
    },
  • "user_keys": {
    },
  • "user_prompts": {
    },
  • "summary_prompt": {
    },
  • "prefer_markdown_generative_response": {
    },
  • "semantic_graph_node_models": {
    },
  • "default_semantic_graph_node_model": {
    },
  • "semantic_graph_edge_models": {
    },
  • "default_semantic_graph_edge_model": {
    }
}

Predict

Predict API to get predictions from our models

Predict Chat

Chat interface for your NucliaDB

query Parameters
model
string (Model)
Default: "chatgpt-azure-4o"
header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false
Request Body schema: application/json
required
question
required
string (Question)
retrieval
boolean (Retrieval)
Default: true
user_id
string (User Id)
Default: "system"
System (string) or System (null) (System)
Array of objects (Chat History)
Default: []
Array of objects (Context)
Default: []
Array of Query Context (strings) or Query Context (object) (Query Context)
Default: {}
object (Query Context Order)
Default: {}
Truncate (boolean) or Truncate (null) (Truncate)
Default: true
UserPrompt (object) or null
Citations (boolean) or CitationsType (string) or Citations (null) (Citations)

Whether to include citations in the response. If set to None or False, no citations will be computed. If set to True or 'default', citations will be computed after answer generation and send as a separate CitationsGenerativeResponse chunk. If set to 'llm_footnotes', citations will be included in the LLM's response as markdown-styled footnotes. A FootnoteCitationsGenerativeResponse chunk will also be sent to map footnote ids to context keys in the query_context.

Citation Threshold (number) or Citation Threshold (null) (Citation Threshold)

If citations is set to True or 'default', this will be the similarity threshold. Value between 0 and 1, lower values will produce more citations. If not set, it will be set to the optimized threshold found by Nuclia.

Generative Model (string) or Generative Model (null) (Generative Model)
Max Tokens (integer) or Max Tokens (null) (Max Tokens)
Array of Query Context Images (objects) or Query Context Images (object) (Query Context Images)
Default: {}
Prefer Markdown (boolean) or Prefer Markdown (null) (Prefer Markdown)
Json Schema (object) or Json Schema (null) (Json Schema)
format_prompt
boolean (Format Prompt)
Default: true
rerank_context
boolean (Rerank Context)
Default: false

Whether to reorder the query context based on a reranker. This option will also make it so the first response will contain the scores given for each context piece.

Array of objects (Tools)

List of tools to choose

any (Tool Choice)
Default: {"type":"required"}

Tool choice strategy. auto: The model decides whether to use a tool or not based on the prompt and available tools. required (default): A tool must be used.none: Disables tool usage even if tools are provided.forced: Forces the use of a specific tool provided in name.Important: Not all model providers support all tool choice strategies, its a best effort feature.

Seed (integer) or Seed (null) (Seed)

Seed use for the generative model for a deterministic output.

Reasoning (object) or Reasoning (boolean) (Reasoning)
Default: false

Reasoning options for the generative model. Set to True to enable default reasoning, False to disable, or provide a Reasoning object for custom options.

image_generation
boolean (Image Generation)
Default: false

Whether to enable image generation in the response.

Responses

Request samples

Content type
application/json
{
  • "question": "string",
  • "retrieval": true,
  • "user_id": "system",
  • "system": "string",
  • "chat_history": [ ],
  • "context": [ ],
  • "query_context": { },
  • "query_context_order": { },
  • "truncate": true,
  • "user_prompt": {
    },
  • "citations": true,
  • "citation_threshold": 1,
  • "generative_model": "string",
  • "max_tokens": 0,
  • "query_context_images": { },
  • "prefer_markdown": true,
  • "json_schema": { },
  • "format_prompt": true,
  • "rerank_context": false,
  • "tools": [
    ],
  • "tool_choice": {
    },
  • "seed": 0,
  • "reasoning": false,
  • "image_generation": false
}

Response samples

Content type
application/json
null

Predict Chat Kbid

Chat interface for your NucliaDB

path Parameters
kbid
required
string (Kbid)
header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false
Request Body schema: application/json
required
question
required
string (Question)
retrieval
boolean (Retrieval)
Default: true
user_id
string (User Id)
Default: "system"
System (string) or System (null) (System)
Array of objects (Chat History)
Default: []
Array of objects (Context)
Default: []
Array of Query Context (strings) or Query Context (object) (Query Context)
Default: {}
object (Query Context Order)
Default: {}
Truncate (boolean) or Truncate (null) (Truncate)
Default: true
UserPrompt (object) or null
Citations (boolean) or CitationsType (string) or Citations (null) (Citations)

Whether to include citations in the response. If set to None or False, no citations will be computed. If set to True or 'default', citations will be computed after answer generation and send as a separate CitationsGenerativeResponse chunk. If set to 'llm_footnotes', citations will be included in the LLM's response as markdown-styled footnotes. A FootnoteCitationsGenerativeResponse chunk will also be sent to map footnote ids to context keys in the query_context.

Citation Threshold (number) or Citation Threshold (null) (Citation Threshold)

If citations is set to True or 'default', this will be the similarity threshold. Value between 0 and 1, lower values will produce more citations. If not set, it will be set to the optimized threshold found by Nuclia.

Generative Model (string) or Generative Model (null) (Generative Model)
Max Tokens (integer) or Max Tokens (null) (Max Tokens)
Array of Query Context Images (objects) or Query Context Images (object) (Query Context Images)
Default: {}
Prefer Markdown (boolean) or Prefer Markdown (null) (Prefer Markdown)
Json Schema (object) or Json Schema (null) (Json Schema)
format_prompt
boolean (Format Prompt)
Default: true
rerank_context
boolean (Rerank Context)
Default: false

Whether to reorder the query context based on a reranker. This option will also make it so the first response will contain the scores given for each context piece.

Array of objects (Tools)

List of tools to choose

any (Tool Choice)
Default: {"type":"required"}

Tool choice strategy. auto: The model decides whether to use a tool or not based on the prompt and available tools. required (default): A tool must be used.none: Disables tool usage even if tools are provided.forced: Forces the use of a specific tool provided in name.Important: Not all model providers support all tool choice strategies, its a best effort feature.

Seed (integer) or Seed (null) (Seed)

Seed use for the generative model for a deterministic output.

Reasoning (object) or Reasoning (boolean) (Reasoning)
Default: false

Reasoning options for the generative model. Set to True to enable default reasoning, False to disable, or provide a Reasoning object for custom options.

image_generation
boolean (Image Generation)
Default: false

Whether to enable image generation in the response.

Responses

Request samples

Content type
application/json
{
  • "question": "string",
  • "retrieval": true,
  • "user_id": "system",
  • "system": "string",
  • "chat_history": [ ],
  • "context": [ ],
  • "query_context": { },
  • "query_context_order": { },
  • "truncate": true,
  • "user_prompt": {
    },
  • "citations": true,
  • "citation_threshold": 1,
  • "generative_model": "string",
  • "max_tokens": 0,
  • "query_context_images": { },
  • "prefer_markdown": true,
  • "json_schema": { },
  • "format_prompt": true,
  • "rerank_context": false,
  • "tools": [
    ],
  • "tool_choice": {
    },
  • "seed": 0,
  • "reasoning": false,
  • "image_generation": false
}

Response samples

Content type
application/json
null

Chat Completions

OpenAI-compatible chat completions

header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false
Request Body schema: application/json
required
required
Array of ChatCompletionDeveloperMessageParam (object) or ChatCompletionSystemMessageParam (object) or ChatCompletionUserMessageParam (object) or ChatCompletionAssistantMessageParam (object) or ChatCompletionToolMessageParam (object) or ChatCompletionFunctionMessageParam (object) (Messages)
Model (string) or Model (null) (Model)
stream
boolean (Stream)
Default: false
Max Tokens (integer) or Max Tokens (null) (Max Tokens)
Seed (integer) or Seed (null) (Seed)
Temperature (number) or Temperature (null) (Temperature)
Top P (number) or Top P (null) (Top P)
User (string) or User (null) (User)
Array of Tools (objects) or Tools (null) (Tools)
Tool Choice (string) or ChatCompletionAllowedToolChoiceParam (object) or ChatCompletionNamedToolChoiceParam (object) or ChatCompletionNamedToolChoiceCustomParam (object) or Tool Choice (null) (Tool Choice)
ResponseFormatText (object) or ResponseFormatJSONSchema (object) or ResponseFormatJSONObject (object) or Response Format (null) (Response Format)
Json Schema (object) or Json Schema (null) (Json Schema)
Reasoning Effort (string) or Reasoning Effort (null) (Reasoning Effort)
Image Generation (boolean) or Image Generation (null) (Image Generation)
Truncate (boolean) or Truncate (null) (Truncate)
property name*
additional property
any

Responses

Request samples

Content type
application/json
{
  • "messages": [
    ],
  • "model": "string",
  • "stream": false,
  • "max_tokens": 0,
  • "seed": 0,
  • "temperature": 0,
  • "top_p": 0,
  • "user": "string",
  • "tools": [
    ],
  • "tool_choice": "none",
  • "response_format": {
    },
  • "json_schema": { },
  • "reasoning_effort": "minimal",
  • "image_generation": true,
  • "truncate": true
}

Response samples

Content type
application/json
null

Predict Sentences

Get the vector of a sentence

header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false
Request Body schema: application/json
required
required
Array of Input (strings) or Input (string) (Input)
Model (string) or Model (null) (Model)

Responses

Request samples

Content type
application/json
{
  • "input": [
    ],
  • "model": "string"
}

Response samples

Content type
application/json
{
  • "object": "list",
  • "data": [
    ],
  • "model": "string",
  • "usage": {
    }
}

List Models

OpenAI-compatible chat completions

Responses

Response samples

Content type
application/json
{
  • "object": "list",
  • "data": [
    ],
  • "has_more": false
}

Get Model

OpenAI-compatible chat completions

path Parameters
model_id
required
string (Model Id)

Responses

Response samples

Content type
application/json
{
  • "name": "string",
  • "title": "string",
  • "description": "string",
  • "config": {
    },
  • "features": {
    },
  • "metadata": {
    }
}

Predict Query Deprecated

Get the vector of a sentence. This endpoint is deprecated, please use the POST endpoint instead.

query Parameters
Text (string) or Text (null) (Text)

Text to process

semantic_model
string (Semantic Model)
Default: "multilingual-2024-05-06"
token_model
string (Token Model)
Default: "multilingual"
generative_model
string (Generative Model)
Default: "chatgpt-azure-4o"
rephrase
boolean (Rephrase)
Default: false
Rephrase Prompt (string) or Rephrase Prompt (null) (Rephrase Prompt)
Examples: rephrase_prompt=Rephrase this question so its better for retrieval, and keep the rephrased question in the same language as the original. QUESTION: {question} Please return ONLY the question without any explanation. Just the rephrased question. rephrase_prompt=Rephrase this question so its better for retrieval, identify any part numbers and append them to the end of the question separated by a commas. QUESTION: {question} Please return ONLY the question without any explanation.

Prompt to rephrase the sentence, if not provided, the default prompt will be used. It must include the {question} placeholder. The placeholder will be replaced with the original question.

agentic_entities
boolean (Agentic Entities)
Default: false

If true, the model will return the entities detected in the sentence guided by an already defined Graph Extraction Agent in the Knowledge Box.

header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false

Responses

Response samples

Content type
application/json
{
  • "language": "string",
  • "stop_words": [
    ],
  • "semantic_threshold": 0,
  • "semantic_thresholds": {
    },
  • "visual_llm": true,
  • "max_context": 0,
  • "entities": {
    },
  • "sentence": {
    },
  • "graph_nodes": {
    },
  • "query": "string",
  • "rephrased_query": ""
}

Predict Query Post

Preprocess a query.

header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false
Request Body schema: application/json
required
Text (string) or Text (null) (Text)

The query text to be processed

Image (object) or null

Image to be considered as part of the query. Even if the rephrase parameter is set to false, the rephrasing process will occur, combining the provided text with the image's visual features in the rephrased query.

rephrase
boolean (Rephrase)
Default: false

If true, the model will rephrase the input text before processing

Rephrase Prompt (string) or Rephrase Prompt (null) (Rephrase Prompt)

Custom prompt for rephrasing the input text

generative_model
string (Generative Model)
Default: "chatgpt-azure-4o"

The generative model to use for rephrasing.

Array of Semantic Models (strings) or Semantic Models (null) (Semantic Models)

Semantic models to compute the sentence vector for, if not provided, it will only compute the sentence vector for default semantic model in the Knowledge box's configuration.

agentic_entities
boolean (Agentic Entities)
Default: false

If true, the model will return the entities detected in the sentence guided by an already defined Graph Extraction Agent in the Knowledge Box.

Array of Graph Nodes (strings) or Graph Nodes (null) (Graph Nodes)

List of graph node names to compute embeddings for. If not provided, no graph node embeddings will be computed.

Array of Semantic Graph Node Models (strings) or Semantic Graph Node Models (null) (Semantic Graph Node Models)

Semantic models to compute graph node embeddings for. If not provided, it will only compute embeddings for the default graph semantic model in the Knowledge box's configuration.

token_model
string (Token Model)
Default: "multilingual"

The NER model to use for extracting entities from the input text.

semantic_model
string (Semantic Model)
Default: "multilingual-2024-05-06"

Semantic model to compute the sentence vector for.

Responses

Request samples

Content type
application/json
{
  • "text": "string",
  • "query_image": {
    },
  • "rephrase": false,
  • "rephrase_prompt": "Rephrase this question so its better for retrieval, and keep the rephrased question in the same language as the original.\nQUESTION: {question}\nPlease return ONLY the question without any explanation. Just the rephrased question.",
  • "generative_model": "chatgpt-azure-4o",
  • "semantic_models": [
    ],
  • "agentic_entities": false,
  • "graph_nodes": [
    ],
  • "semantic_graph_node_models": [
    ],
  • "token_model": "multilingual",
  • "semantic_model": "multilingual-2024-05-06"
}

Response samples

Content type
application/json
{
  • "language": "string",
  • "stop_words": [
    ],
  • "semantic_threshold": 0,
  • "semantic_thresholds": {
    },
  • "visual_llm": true,
  • "max_context": 0,
  • "entities": {
    },
  • "sentence": {
    },
  • "graph_nodes": {
    },
  • "query": "string",
  • "rephrased_query": ""
}

Predict Query Kbid Deprecated

Get the vector of a sentence

path Parameters
kbid
required
string (Kbid)
query Parameters
Text (string) or Text (null) (Text)

Text to process

Array of Semantic Models (strings) or Semantic Models (null) (Semantic Models)

Semantic models to compute the sentence vector for, if not provided, it will only compute the sentence vector for default semantic model in the Knowledge box's configuration.

Array of Graph Nodes (strings) or Graph Nodes (null) (Graph Nodes)

List of graph node names to compute embeddings for. If not provided, no graph node embeddings will be computed.

Array of Semantic Graph Node Models (strings) or Semantic Graph Node Models (null) (Semantic Graph Node Models)

Semantic models to compute graph node embeddings for. If not provided, it will only compute embeddings for the default graph semantic model in the Knowledge box's configuration.

generative_model
string (Generative Model)
Default: "chatgpt-azure-4o-mini"
rephrase
boolean (Rephrase)
Default: false
Rephrase Prompt (string) or Rephrase Prompt (null) (Rephrase Prompt)
Examples: rephrase_prompt=Rephrase this question so its better for retrieval, and keep the rephrased question in the same language as the original. QUESTION: {question} Please return ONLY the question without any explanation. Just the rephrased question. rephrase_prompt=Rephrase this question so its better for retrieval, identify any part numbers and append them to the end of the question separated by a commas. QUESTION: {question} Please return ONLY the question without any explanation.

Prompt to rephrase the sentence, if not provided, the default prompt will be used. It must include the {question} placeholder. The placeholder will be replaced with the original question.

agentic_entities
boolean (Agentic Entities)
Default: false

If true, the model will return the entities detected in the sentence guided by an already defined Graph Extraction Agent in the Knowledge Box.

header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false

Responses

Response samples

Content type
application/json
{
  • "language": "string",
  • "stop_words": [
    ],
  • "semantic_threshold": 0,
  • "semantic_thresholds": {
    },
  • "visual_llm": true,
  • "max_context": 0,
  • "entities": {
    },
  • "sentence": {
    },
  • "graph_nodes": {
    },
  • "query": "string",
  • "rephrased_query": ""
}

Predict Query Post Kbid

Get the vector of a sentence

path Parameters
kbid
required
string (Kbid)
header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false
Request Body schema: application/json
required
Text (string) or Text (null) (Text)

The query text to be processed

Image (object) or null

Image to be considered as part of the query. Even if the rephrase parameter is set to false, the rephrasing process will occur, combining the provided text with the image's visual features in the rephrased query.

rephrase
boolean (Rephrase)
Default: false

If true, the model will rephrase the input text before processing

Rephrase Prompt (string) or Rephrase Prompt (null) (Rephrase Prompt)

Custom prompt for rephrasing the input text

Generative Model (string) or Generative Model (null) (Generative Model)

The generative model to use for rephrasing

Array of Semantic Models (strings) or Semantic Models (null) (Semantic Models)

Semantic models to compute the sentence vector for, if not provided, it will only compute the sentence vector for default semantic model in the Knowledge box's configuration.

agentic_entities
boolean (Agentic Entities)
Default: false

If true, the model will return the entities detected in the sentence guided by an already defined Graph Extraction Agent in the Knowledge Box.

Array of Graph Nodes (strings) or Graph Nodes (null) (Graph Nodes)

List of graph node names to compute embeddings for. If not provided, no graph node embeddings will be computed.

Array of Semantic Graph Node Models (strings) or Semantic Graph Node Models (null) (Semantic Graph Node Models)

Semantic models to compute graph node embeddings for. If not provided, it will only compute embeddings for the default graph semantic model in the Knowledge box's configuration.

Responses

Request samples

Content type
application/json
{
  • "text": "string",
  • "query_image": {
    },
  • "rephrase": false,
  • "rephrase_prompt": "Rephrase this question so its better for retrieval, and keep the rephrased question in the same language as the original.\nQUESTION: {question}\nPlease return ONLY the question without any explanation. Just the rephrased question.",
  • "generative_model": "string",
  • "semantic_models": [
    ],
  • "agentic_entities": false,
  • "graph_nodes": [
    ],
  • "semantic_graph_node_models": [
    ]
}

Response samples

Content type
application/json
{
  • "language": "string",
  • "stop_words": [
    ],
  • "semantic_threshold": 0,
  • "semantic_thresholds": {
    },
  • "visual_llm": true,
  • "max_context": 0,
  • "entities": {
    },
  • "sentence": {
    },
  • "graph_nodes": {
    },
  • "query": "string",
  • "rephrased_query": ""
}

Predict Remi

The REMi model is a model that computes metrics for a given question, answer and contexts. The metrics computed are:

  • Answer Relevance: Measures the relevance of the generated answer to the user query, in a scale of 0 to 5.
  • Context Relevance: Measures the relevance of the retrieved context to the user query, in a scale of 0 to 5.
  • Groundedness: Measures the degree to which the generated answer is grounded in the retrieved context, in a scale of 0 to 5.

More information about REMi metrics and how to interpret in the following link: https://nuclia.com/developers/remi-open-source-rag-evaluation-model/

header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false
Request Body schema: application/json
required
user_id
required
string (The user ID of the user making the request)
(The question or query that the user asked (string)) or (The question or query that the user asked (null)) (The question or query that the user asked)
The answer that the model provided (string) or The answer that the model provided (null) (The answer that the model provided)
Array of The contexts that the model used to generate the answer (strings) or The contexts that the model used to generate the answer (null) (The contexts that the model used to generate the answer)

Responses

Request samples

Content type
application/json
{
  • "user_id": "string",
  • "question": "string",
  • "answer": "string",
  • "contexts": [
    ]
}

Response samples

Content type
application/json
{
  • "time": 0,
  • "answer_relevance": {
    },
  • "context_relevance": [
    ],
  • "groundedness": [
    ],
  • "consumption": {
    }
}

Predict Remi Kbid

The REMi model is a model that computes metrics for a given question, answer and contexts. The metrics computed are:

  • Answer Relevance: Measures the relevance of the generated answer to the user query, in a scale of 0 to 5.
  • Context Relevance: Measures the relevance of the retrieved context to the user query, in a scale of 0 to 5.
  • Groundedness: Measures the degree to which the generated answer is grounded in the retrieved context, in a scale of 0 to 5.

More information about REMi metrics and how to interpret in the following link: https://nuclia.com/developers/remi-open-source-rag-evaluation-model/

path Parameters
kbid
required
string (Kbid)
header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false
Request Body schema: application/json
required
user_id
required
string (The user ID of the user making the request)
(The question or query that the user asked (string)) or (The question or query that the user asked (null)) (The question or query that the user asked)
The answer that the model provided (string) or The answer that the model provided (null) (The answer that the model provided)
Array of The contexts that the model used to generate the answer (strings) or The contexts that the model used to generate the answer (null) (The contexts that the model used to generate the answer)

Responses

Request samples

Content type
application/json
{
  • "user_id": "string",
  • "question": "string",
  • "answer": "string",
  • "contexts": [
    ]
}

Response samples

Content type
application/json
{
  • "time": 0,
  • "answer_relevance": {
    },
  • "context_relevance": [
    ],
  • "groundedness": [
    ],
  • "consumption": {
    }
}

Predict Rephrase

Rephrase interface for your NucliaDB

query Parameters
model
string (Model)
Default: "chatgpt-azure-4o"
Request Body schema: application/json
required
question
required
string (Question)
Array of objects (Chat History)
Array of objects (Context)
Array of User Context (strings) or User Context (null) (User Context)
user_id
string (User Id)
Default: "system"
Generative model (string) or Generative model (null) (Generative model)

The generative model to use for the rephrase endpoint. If not provided, the model configured for the Knowledge Box is used.

Prompt (string) or Prompt (null) (Prompt)

Prompt to send the model to rephrase the sentence, if not provided, the default prompt will be used. It must include the {question} placeholder. The placeholder will be replaced with the original question. It will only be used if no user_context is provided.

Chat History Relevance Threshold (number) or Chat History Relevance Threshold (null) (Chat History Relevance Threshold)

Responses

Request samples

Content type
application/json
{
  • "question": "string",
  • "chat_history": [
    ],
  • "context": [
    ],
  • "user_context": [
    ],
  • "user_id": "system",
  • "generative_model": "string",
  • "prompt": "Rephrase this question so its better for retrieval, and keep the rephrased question in the same language as the original.\nQUESTION: {question}\nPlease return ONLY the question without any explanation. Just the rephrased question.",
  • "chat_history_relevance_threshold": 1
}

Response samples

Content type
application/json
"string"

Predict Rephrase Kbid

Rephrase interface for your NucliaDB with Container

path Parameters
kbid
required
string (Kbid)
Request Body schema: application/json
required
question
required
string (Question)
Array of objects (Chat History)
Array of objects (Context)
Array of User Context (strings) or User Context (null) (User Context)
user_id
string (User Id)
Default: "system"
Generative model (string) or Generative model (null) (Generative model)

The generative model to use for the rephrase endpoint. If not provided, the model configured for the Knowledge Box is used.

Prompt (string) or Prompt (null) (Prompt)

Prompt to send the model to rephrase the sentence, if not provided, the default prompt will be used. It must include the {question} placeholder. The placeholder will be replaced with the original question. It will only be used if no user_context is provided.

Chat History Relevance Threshold (number) or Chat History Relevance Threshold (null) (Chat History Relevance Threshold)

Responses

Request samples

Content type
application/json
{
  • "question": "string",
  • "chat_history": [
    ],
  • "context": [
    ],
  • "user_context": [
    ],
  • "user_id": "system",
  • "generative_model": "string",
  • "prompt": "Rephrase this question so its better for retrieval, and keep the rephrased question in the same language as the original.\nQUESTION: {question}\nPlease return ONLY the question without any explanation. Just the rephrased question.",
  • "chat_history_relevance_threshold": 1
}

Response samples

Content type
application/json
null

Predict Rerank

Rerank your results

header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false
Request Body schema: application/json
required
question
required
string (Question)
user_id
required
string (User Id)
object (Context)
Default: {}

Responses

Request samples

Content type
application/json
{
  • "question": "string",
  • "user_id": "string",
  • "context": { }
}

Response samples

Content type
application/json
{
  • "context_scores": {
    },
  • "consumption": {
    }
}

Predict Rerank Kbid

Rerank your results

path Parameters
kbid
required
string (Kbid)
header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false
Request Body schema: application/json
required
question
required
string (Question)
user_id
required
string (User Id)
object (Context)
Default: {}

Responses

Request samples

Content type
application/json
{
  • "question": "string",
  • "user_id": "string",
  • "context": { }
}

Response samples

Content type
application/json
{
  • "context_scores": {
    },
  • "consumption": {
    }
}

Predict Sentence

Get the vector of a sentence

query Parameters
text
required
string (Text)
model
string (Model)
Default: "multilingual-2024-05-06"
header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false

Responses

Response samples

Content type
application/json
{
  • "data": [
    ],
  • "vectors": {
    },
  • "time": 0,
  • "timings": {
    },
  • "consumption": {
    }
}

Predict Sentence Kbid

Get the vector of a sentence

path Parameters
kbid
required
string (Kbid)
query Parameters
text
required
string (Text)
Array of Models (strings) or Models (null) (Models)

Semantic models to compute the sentence vector for, if not provided, it will only compute the sentence vector for default semantic model in the Knowledge box's configuration.

header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false

Responses

Response samples

Content type
application/json
{
  • "data": [
    ],
  • "vectors": {
    },
  • "time": 0,
  • "timings": {
    },
  • "consumption": {
    }
}

Predict Sentences

Generate the vectors of multiple texts in batch

header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false
Request Body schema: application/json
required
texts
required
Array of strings (Texts)
Model (string) or Model (null) (Model)

Responses

Request samples

Content type
application/json
{
  • "texts": [
    ],
  • "model": "string"
}

Response samples

Content type
application/json
{
  • "vectors": [
    ],
  • "time": 0,
  • "timings": {
    },
  • "consumption": {
    }
}

Predict Summarize

Get summarized answers via NUA

query Parameters
model
string (Model)
Default: "chatgpt-azure-4o"
header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false
Request Body schema: application/json
required
required
object (Resources)
summary_kind
string (SummaryKind)
Default: "simple"
Enum: "simple" "extended"
User Prompt (string) or User Prompt (null) (User Prompt)
Default: ""
Generative Model (string) or Generative Model (null) (Generative Model)

Responses

Request samples

Content type
application/json
{
  • "resources": {
    },
  • "summary_kind": "simple",
  • "user_prompt": "",
  • "generative_model": "string"
}

Response samples

Content type
application/json
{
  • "resources": {
    },
  • "summary": "",
  • "consumption": {
    }
}

Predict Summarize Kbid

Get summarized answers via NUA with Container

path Parameters
kbid
required
string (Kbid)
header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false
Request Body schema: application/json
required
required
object (Resources)
summary_kind
string (SummaryKind)
Default: "simple"
Enum: "simple" "extended"
User Prompt (string) or User Prompt (null) (User Prompt)
Default: ""
Generative Model (string) or Generative Model (null) (Generative Model)

Responses

Request samples

Content type
application/json
{
  • "resources": {
    },
  • "summary_kind": "simple",
  • "user_prompt": "",
  • "generative_model": "string"
}

Response samples

Content type
application/json
{
  • "resources": {
    },
  • "summary": "",
  • "consumption": {
    }
}

Predict Tokens

Get tokens of a sentence

query Parameters
text
required
string (Text)
model
string (Model)
Default: "multilingual"
header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false

Responses

Response samples

Content type
application/json
{
  • "tokens": [ ],
  • "time": 0,
  • "input_tokens": 0,
  • "consumption": {
    }
}

Predict Tokens Kbid

Get tokens of a sentence with Container

path Parameters
kbid
required
string (Kbid)
query Parameters
text
required
string (Text)
header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false

Responses

Response samples

Content type
application/json
{
  • "tokens": [ ],
  • "time": 0,
  • "input_tokens": 0,
  • "consumption": {
    }
}

Collector

Collector API

Feedback Avalaible Months

List of months within the last year with feedback data

path Parameters
kbid
required
string (Kbid)

Responses

Response samples

Content type
application/json
null

Get Feedback

Given a month, returns a csv with all the feedback data from it

path Parameters
kbid
required
string (Kbid)
month
required
string (Month)

Responses

Response samples

Content type
application/json
null

Datasets

Delete Dataset

Deletes a dataset

path Parameters
dataset_id
required
string (Dataset Id)
account_id
required
string (Account Id)

Responses

Response samples

Content type
application/json
{
  • "detail": [
    ]
}

Get Dataset

Get a dataset

path Parameters
dataset_id
required
string (Dataset Id)
account_id
required
string (Account Id)

Responses

Response samples

Content type
application/json
{
  • "id": "string"
}

Upload Partition Account

Upload a partition of a dataset

path Parameters
dataset_id
required
string (Dataset Id)
account_id
required
string (Account Id)
partition_id
required
string (Partition Id)
header Parameters
content-length
required
integer (Content-Length)

Responses

Response samples

Content type
application/json
{
  • "detail": [
    ]
}

Delete Dataset Partition

Deletes a partition of a dataset

path Parameters
dataset_id
required
string (Dataset Id)
partition_id
required
string (Partition Id) ^[a-zA-Z0-9-_]+$
account_id
required
string (Account Id)

Responses

Response samples

Content type
application/json
{
  • "detail": [
    ]
}

Delete Dataset Partitions

Deletes all partitions of a dataset

path Parameters
dataset_id
required
string (Dataset Id)
account_id
required
string (Account Id)

Responses

Response samples

Content type
application/json
{
  • "detail": [
    ]
}

Create Dataset Account

Creates a new dataset

path Parameters
account_id
required
string (Account Id)
Request Body schema: application/json
required
name
required
string (Name)
required
object (DatasetFilter)
type
required
string (Task-Input)
Enum: "PARAGRAPH_CLASSIFICATION" "FIELD_CLASSIFICATION" "SENTENCE_CLASSIFICATION" "TOKEN_CLASSIFICATION" "IMAGE_CLASSIFICATION" "PARAGRAPH_STREAMING" "QUESTION_ANSWER_STREAMING" "FIELD_STREAMING"

Responses

Request samples

Content type
application/json
{
  • "name": "string",
  • "filter": {
    },
  • "type": "PARAGRAPH_CLASSIFICATION"
}

Response samples

Content type
application/json
{
  • "id": "string"
}

List Datasets

Lists all datasets

path Parameters
account_id
required
string (Account Id)

Responses

Response samples

Content type
application/json
{
  • "datasets": [
    ]
}

Dataset Delete

Deletes a dataset

path Parameters
dataset_id
required
string (Dataset Id)

Responses

Response samples

Content type
application/json
{
  • "detail": [
    ]
}

Upload Partition

Upload a partition of a dataset

path Parameters
dataset_id
required
string (Dataset Id)
partition_id
required
string (Partition Id)
header Parameters
content-length
required
integer (Content-Length)

Responses

Response samples

Content type
application/json
{
  • "detail": [
    ]
}

Create Dataset

Creates a new dataset

Request Body schema: application/json
required
name
required
string (Name)
required
object (DatasetFilter)
type
required
string (Task-Input)
Enum: "PARAGRAPH_CLASSIFICATION" "FIELD_CLASSIFICATION" "SENTENCE_CLASSIFICATION" "TOKEN_CLASSIFICATION" "IMAGE_CLASSIFICATION" "PARAGRAPH_STREAMING" "QUESTION_ANSWER_STREAMING" "FIELD_STREAMING"

Responses

Request samples

Content type
application/json
{
  • "name": "string",
  • "filter": {
    },
  • "type": "PARAGRAPH_CLASSIFICATION"
}

Response samples

Content type
application/json
{
  • "id": "string"
}

Downloads

Delete Download Request

Delete a download request by its ID

path Parameters
agent_id
required
string (Agent Id)
request_id
required
string (Request Id)

Responses

Response samples

Content type
application/json
null

Get Download Request Status

Get status of an audit download request by its ID

path Parameters
agent_id
required
string (Agent Id)
request_id
required
string (Request Id)

Responses

Response samples

Content type
application/json
{
  • "id": "string",
  • "type": "string",
  • "status": "pending",
  • "download_url": "string",
  • "query": { }
}

List Download Requests

List all download requests for the account

path Parameters
agent_id
required
string (Agent Id)

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Retrieval Agent

Request Interactions Audit Download

Request a download for the audit log of an agent's interactions

path Parameters
agent_id
required
string (Agent Id)
header Parameters
accept
string (Accept)
Default: text/csv
Enum: "application/x-ndjson" "text/csv"
Request Body schema: application/json
required
Session Id (string) or Session Id (null) (Session Id)

Filter by session ID

Year (integer) or Year (null) (Year)

Filter by year (e.g., 2024). If not specified, defaults to the current year.

Month (integer) or Month (null) (Month)

Filter by month (1-12). If not specified, defaults to the past month.

Responses

Request samples

Content type
application/json
{
  • "session_id": "string",
  • "year": 0,
  • "month": 0
}

Response samples

Content type
application/json
{
  • "id": "string",
  • "type": "string",
  • "status": "pending",
  • "download_url": "string",
  • "query": { }
}

Patch Driver

Set Agent Configuration

path Parameters
agent_id
required
string (Agent Id)
driver
required
string (Driver)
Request Body schema: application/json
required
Id (string) or Id (null) (Id)
identifier
required
string (Identifier)
name
required
string (Name)
provider
required
string (Provider)
Value: "alinia"
required
object (AliniaInnerConfig)

Responses

Request samples

Content type
application/json
Example
{
  • "id": "string",
  • "identifier": "string",
  • "name": "string",
  • "provider": "alinia",
  • "config": {
    }
}

Response samples

Content type
application/json
null

Delete Driver

Set Agent Configuration

path Parameters
agent_id
required
string (Agent Id)
driver
required
string (Driver)

Responses

Response samples

Content type
application/json
null

Add Driver

Set Agent Configuration

path Parameters
agent_id
required
string (Agent Id)
Request Body schema: application/json
required
Id (string) or Id (null) (Id)
identifier
required
string (Identifier)
name
required
string (Name)
provider
required
string (Provider)
Value: "alinia"
required
object (AliniaInnerConfig)

Responses

Request samples

Content type
application/json
Example
{
  • "id": "string",
  • "identifier": "string",
  • "name": "string",
  • "provider": "alinia",
  • "config": {
    }
}

Response samples

Content type
application/json
{
  • "id": "string"
}

Get Driver

Get Agent Configuration

path Parameters
agent_id
required
string (Agent Id)

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Request Export Retrieval Agent

Request the export of a Retrieval Agent. This will send an email with a download link to the email associated with the account.

path Parameters
agent_id
required
string (Agent Id)
Request Body schema: application/json
required
passphrase
required
string (Passphrase) >= 16 characters

Passphrase to encrypt the exported configuration. Will be required for import.

Responses

Request samples

Content type
application/json
{
  • "passphrase": "stringstringstri"
}

Response samples

Content type
application/json
null

Get Full Schema

Get Agent Schema (NEW)

path Parameters
agent_id
required
string (Agent Id)

Responses

Response samples

Content type
application/json
null

Add Generation

Add Generation Agent Configuration

path Parameters
agent_id
required
string (Agent Id)
Request Body schema: application/json
required
Id (string) or Id (null) (Id)
title
string (Title)
Default: "agent"
Array of Rules (strings) or Rules (null) (Rules)
max_retries
integer (Max Retries)
Default: 1
module
string (Module)
Default: "summarize"
Value: "summarize"
Prompt (string) or Prompt (null) (Prompt)
model
string (Generative model)
Default: "chatgpt-azure-4o-mini"

Model used to generate the response

images
boolean (Images)
Default: false
conversational
boolean (Conversational)
Default: false
include_mcp_prompts
boolean (If MCP prompts were used during the context steps, include them in the prompt to generate the final answer)
Default: false
citations
boolean (Whether to include markdown citations in the generated answer.)
Default: false
force_chunk_level_citations
boolean (Whether to always use chunk-level citations instead of context-level citations.)
Default: false

Responses

Request samples

Content type
application/json
Example
{
  • "id": "string",
  • "title": "agent",
  • "rules": [
    ],
  • "max_retries": 1,
  • "module": "summarize",
  • "prompt": "string",
  • "model": "chatgpt-azure-4o-mini",
  • "images": false,
  • "conversational": false,
  • "include_mcp_prompts": false,
  • "citations": false,
  • "force_chunk_level_citations": false
}

Response samples

Content type
application/json
{
  • "id": "string"
}

Get Generation

Set Agent Configuration

path Parameters
agent_id
required
string (Agent Id)

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Patch Generation

Set PreProcess Agent Configuration

path Parameters
agent_id
required
string (Agent Id)
generation
required
string (Generation)
Request Body schema: application/json
required
Id (string) or Id (null) (Id)
title
string (Title)
Default: "agent"
Array of Rules (strings) or Rules (null) (Rules)
max_retries
integer (Max Retries)
Default: 1
module
string (Module)
Default: "summarize"
Value: "summarize"
Prompt (string) or Prompt (null) (Prompt)
model
string (Generative model)
Default: "chatgpt-azure-4o-mini"

Model used to generate the response

images
boolean (Images)
Default: false
conversational
boolean (Conversational)
Default: false
include_mcp_prompts
boolean (If MCP prompts were used during the context steps, include them in the prompt to generate the final answer)
Default: false
citations
boolean (Whether to include markdown citations in the generated answer.)
Default: false
force_chunk_level_citations
boolean (Whether to always use chunk-level citations instead of context-level citations.)
Default: false

Responses

Request samples

Content type
application/json
Example
{
  • "id": "string",
  • "title": "agent",
  • "rules": [
    ],
  • "max_retries": 1,
  • "module": "summarize",
  • "prompt": "string",
  • "model": "chatgpt-azure-4o-mini",
  • "images": false,
  • "conversational": false,
  • "include_mcp_prompts": false,
  • "citations": false,
  • "force_chunk_level_citations": false
}

Response samples

Content type
application/json
null

Delete Generation

Delete Generation Agent Configuration

path Parameters
agent_id
required
string (Agent Id)
generation
required
string (Generation)

Responses

Response samples

Content type
application/json
null

Import Retrieval Agent

Import Retrieval Agent Configuration

path Parameters
agent_id
required
string (Agent Id)
Request Body schema: multipart/form-data
required
file
required
string <binary> (File)
passphrase
required
string (Passphrase)

Passphrase for the encrypted export file

overwrite
boolean (Overwrite)
Default: false

Whether to overwrite existing agent configuration. If false and the agent configuration is not empty, the import will fail.

Responses

Response samples

Content type
application/json
null

Add Postprocess

Add PostProcess Agent Configuration

path Parameters
agent_id
required
string (Agent Id)
Request Body schema: application/json
required
Id (string) or Id (null) (Id)
title
string (Title)
Default: "agent"
Array of Rules (strings) or Rules (null) (Rules)
max_retries
integer (Max Retries)
Default: 1
module
string (Module)
Default: "remi"
Value: "remi"
context_granularity
string (Granularity of the contexts pieces)
Default: "full"
Enum: "full" "partial_answers"

Granularity of the context pieces sent to REMi for groundedness evaluation. If 'partial_answers', the evaluation will use agent-level answer attempts to the question when available for a speedier analysis. If 'full', the evaluation will use all individual text chunks that each agent generated for a more detailed analysis.

Responses

Request samples

Content type
application/json
Example
{
  • "id": "string",
  • "title": "agent",
  • "rules": [
    ],
  • "max_retries": 1,
  • "module": "remi",
  • "context_granularity": "full"
}

Response samples

Content type
application/json
{
  • "id": "string"
}

Get Postprocess

Set Agent Configuration

path Parameters
agent_id
required
string (Agent Id)

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Patch Postprocess

Set PostProcess Agent Configuration

path Parameters
agent_id
required
string (Agent Id)
postprocess
required
string (Postprocess)
Request Body schema: application/json
required
Id (string) or Id (null) (Id)
title
string (Title)
Default: "agent"
Array of Rules (strings) or Rules (null) (Rules)
max_retries
integer (Max Retries)
Default: 1
module
string (Module)
Default: "remi"
Value: "remi"
context_granularity
string (Granularity of the contexts pieces)
Default: "full"
Enum: "full" "partial_answers"

Granularity of the context pieces sent to REMi for groundedness evaluation. If 'partial_answers', the evaluation will use agent-level answer attempts to the question when available for a speedier analysis. If 'full', the evaluation will use all individual text chunks that each agent generated for a more detailed analysis.

Responses

Request samples

Content type
application/json
Example
{
  • "id": "string",
  • "title": "agent",
  • "rules": [
    ],
  • "max_retries": 1,
  • "module": "remi",
  • "context_granularity": "full"
}

Response samples

Content type
application/json
null

Delete Postprocess

Delete PreProcess Agent Configuration

path Parameters
agent_id
required
string (Agent Id)
postprocess
required
string (Postprocess)

Responses

Response samples

Content type
application/json
null

Add Preprocess

Add PreProcess Agent Configuration

path Parameters
agent_id
required
string (Agent Id)
Request Body schema: application/json
required
Id (string) or Id (null) (Id)
title
string (Title)
Default: "agent"
Array of Rules (strings) or Rules (null) (Rules)
max_retries
integer (Max Retries)
Default: 1
module
string (Module)
Default: "historical"
Value: "historical"
all
required
boolean (All)

Responses

Request samples

Content type
application/json
Example
{
  • "id": "string",
  • "title": "agent",
  • "rules": [
    ],
  • "max_retries": 1,
  • "module": "historical",
  • "all": true
}

Response samples

Content type
application/json
{
  • "id": "string"
}

Get Preprocess

Set Agent Configuration

path Parameters
agent_id
required
string (Agent Id)

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Patch Preprocess

Set PreProcess Agent Configuration

path Parameters
agent_id
required
string (Agent Id)
preprocess
required
string (Preprocess)
Request Body schema: application/json
required
Id (string) or Id (null) (Id)
title
string (Title)
Default: "agent"
Array of Rules (strings) or Rules (null) (Rules)
max_retries
integer (Max Retries)
Default: 1
module
string (Module)
Default: "historical"
Value: "historical"
all
required
boolean (All)

Responses

Request samples

Content type
application/json
Example
{
  • "id": "string",
  • "title": "agent",
  • "rules": [
    ],
  • "max_retries": 1,
  • "module": "historical",
  • "all": true
}

Response samples

Content type
application/json
null

Delete Preprocess

Delete PreProcess Agent Configuration

path Parameters
agent_id
required
string (Agent Id)
preprocess
required
string (Preprocess)

Responses

Response samples

Content type
application/json
null

Set Rules

Set Agent Configuration

path Parameters
agent_id
required
string (Agent Id)
Request Body schema: application/json
required
Array of Rule (object) or strings (Rules)

List of rules that the workflow should follow. Each rule can be a string or a Rule object with a prompt.

Array
Any of
Prompt (string) or Prompt (null) (Prompt)
Any of
string (Prompt)

Responses

Request samples

Content type
application/json
{
  • "rules": [
    ]
}

Response samples

Content type
application/json
null

Get Rules

Set Agent Configuration

path Parameters
agent_id
required
string (Agent Id)

Responses

Response samples

Content type
application/json
null

Interaction

Interact session

path Parameters
agent_id
required
string (Agent Id)
session
required
string (Session)
query Parameters
workflow_id
string (Workflow Id)
Default: "default"
From Cursor (integer) or From Cursor (null) (From Cursor)
Request Body schema: application/json
required
question
required
string (Question)
object (Headers)
Default: {}
object (Arguments)
Default: {}
operation
integer (InteractionOperation)
Default: 0
Enum: 0 1

Responses

Request samples

Content type
application/json
{
  • "question": "string",
  • "headers": { },
  • "arguments": { },
  • "operation": 0
}

Response samples

Content type
application/json
null

Patch Session

Create session

path Parameters
agent_id
required
string (Agent Id)
session
required
string (Session)
Request Body schema: application/json
required
slug
required
string (Slug)
name
required
string (Name)
summary
required
string (Summary)
data
required
string (Data)
format
required
string (TextFormat)
Enum: "PLAIN" "HTML" "RST" "MARKDOWN" "JSON" "KEEP_MARKDOWN" "JSONL" "PLAIN_BLANKLINE_SPLIT"

Responses

Request samples

Content type
application/json
{
  • "slug": "string",
  • "name": "string",
  • "summary": "string",
  • "data": "string",
  • "format": "PLAIN"
}

Response samples

Content type
application/json
null

Delete Session

Delete session

path Parameters
agent_id
required
string (Agent Id)
session
required
string (Session)

Responses

Response samples

Content type
application/json
null

Get Session

Create session

path Parameters
agent_id
required
string (Agent Id)
session
required
string (Session)

Responses

Response samples

Content type
application/json
{
  • "id": "string",
  • "slug": "string",
  • "title": "string",
  • "summary": "string",
  • "icon": "string",
  • "thumbnail": "string",
  • "metadata": {
    },
  • "usermetadata": {
    },
  • "fieldmetadata": [
    ],
  • "computedmetadata": {
    },
  • "created": "2019-08-24T14:15:22Z",
  • "modified": "2019-08-24T14:15:22Z",
  • "last_seqid": 0,
  • "last_account_seq": 0,
  • "queue": "private",
  • "hidden": true,
  • "origin": {
    },
  • "extra": {
    },
  • "relations": [
    ],
  • "data": {
    },
  • "security": {
    }
}

Create Session

Create session

path Parameters
agent_id
required
string (Agent Id)
Request Body schema: application/json
required
slug
required
string (Slug)
name
required
string (Name)
summary
required
string (Summary)
data
required
string (Data)
format
required
string (TextFormat)
Enum: "PLAIN" "HTML" "RST" "MARKDOWN" "JSON" "KEEP_MARKDOWN" "JSONL" "PLAIN_BLANKLINE_SPLIT"

Responses

Request samples

Content type
application/json
{
  • "slug": "string",
  • "name": "string",
  • "summary": "string",
  • "data": "string",
  • "format": "PLAIN"
}

Response samples

Content type
application/json
{
  • "uuid": "string",
  • "elapsed": 0,
  • "seqid": 0
}

Get Sessions

Create session

path Parameters
agent_id
required
string (Agent Id)
query Parameters
page
integer (Page)
Default: 0

Requested page number (0-based)

size
integer (Size)
Default: 20

Page size

Responses

Response samples

Content type
application/json
{
  • "resources": [
    ],
  • "pagination": {
    }
}

Interaction

Interact session

path Parameters
agent_id
required
string (Agent Id)
session
required
string (Session)
workflow_id
required
string (Workflow Id)
query Parameters
From Cursor (integer) or From Cursor (null) (From Cursor)
Request Body schema: application/json
required
question
required
string (Question)
object (Headers)
Default: {}
object (Arguments)
Default: {}
operation
integer (InteractionOperation)
Default: 0
Enum: 0 1

Responses

Request samples

Content type
application/json
{
  • "question": "string",
  • "headers": { },
  • "arguments": { },
  • "operation": 0
}

Response samples

Content type
application/json
null

Prompt Management

Patch Prompt

Update Prompt of Agent

path Parameters
agent_id
required
string (Agent Id)
prompt_id
required
string (Prompt Id)
Request Body schema: application/json
required
name
required
string (Name)
description
required
string (Description)
prompt
required
string (Prompt)
Array of Arguments (objects) or Arguments (null) (Arguments)
Icons (object) or Icons (null) (Icons)
Meta (object) or Meta (null) (Meta)
Prompt Id (string) or Prompt Id (null) (Prompt Id)

Responses

Request samples

Content type
application/json
{
  • "name": "string",
  • "description": "string",
  • "prompt": "string",
  • "arguments": [
    ],
  • "icons": {
    },
  • "meta": {
    },
  • "prompt_id": "string"
}

Response samples

Content type
application/json
null

Delete Prompt

Delete prompt id

path Parameters
agent_id
required
string (Agent Id)
prompt_id
required
string (Prompt Id)

Responses

Response samples

Content type
application/json
null

Get Prompt

Get Agent Configuration

path Parameters
agent_id
required
string (Agent Id)
prompt_id
required
string (Prompt Id)

Responses

Response samples

Content type
application/json
{
  • "name": "string",
  • "description": "string",
  • "prompt": "string",
  • "arguments": [
    ],
  • "icons": {
    },
  • "meta": {
    },
  • "prompt_id": "string"
}

Add Prompt

Add Prompt to Agent

path Parameters
agent_id
required
string (Agent Id)
Request Body schema: application/json
required
name
required
string (Name)
description
required
string (Description)
prompt
required
string (Prompt)
Array of Arguments (objects) or Arguments (null) (Arguments)
Icons (object) or Icons (null) (Icons)
Meta (object) or Meta (null) (Meta)
Prompt Id (string) or Prompt Id (null) (Prompt Id)

Responses

Request samples

Content type
application/json
{
  • "name": "string",
  • "description": "string",
  • "prompt": "string",
  • "arguments": [
    ],
  • "icons": {
    },
  • "meta": {
    },
  • "prompt_id": "string"
}

Response samples

Content type
application/json
{
  • "id": "string"
}

Get Prompts

Get Agent Configuration

path Parameters
agent_id
required
string (Agent Id)

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Mcp Handler Delete

path Parameters
agent_id
required
string (Agent Id)
session
required
string (Session)

Responses

Response samples

Content type
application/json
null

Mcp Handler

path Parameters
agent_id
required
string (Agent Id)
session
required
string (Session)

Responses

Response samples

Content type
application/json
null

Mcp Handler

path Parameters
agent_id
required
string (Agent Id)
session
required
string (Session)

Responses

Response samples

Content type
application/json
null

Mcp Handler

path Parameters
kbid
required
string (Kbid)
header Parameters
x-ndb-client
string (NucliaDBClientType)
Default: api
Enum: "api" "widget" "web" "dashboard" "desktop" "chrome_extension"
x-nucliadb-user
string (X-Nucliadb-User)
Default:
x-forwarded-for
string (X-Forwarded-For)
Default:

Responses

Response samples

Content type
application/json
null

Mcp Handler

path Parameters
kbid
required
string (Kbid)
header Parameters
x-ndb-client
string (NucliaDBClientType)
Default: api
Enum: "api" "widget" "web" "dashboard" "desktop" "chrome_extension"
x-nucliadb-user
string (X-Nucliadb-User)
Default:
x-forwarded-for
string (X-Forwarded-For)
Default:

Responses

Response samples

Content type
application/json
null

Workflows

Set Workflow

Set Workflow Configuration

path Parameters
agent_id
required
string (Agent Id)
workflow_id
required
string (Workflow Id)
Request Body schema: application/json
required
name
required
string (Name)
description
required
string (Description)
required
object (Parameters)
required
Array of strings (Required)
Rules (object) or null

Responses

Request samples

Content type
application/json
{
  • "name": "string",
  • "description": "string",
  • "parameters": { },
  • "required": [
    ],
  • "rules": {
    }
}

Response samples

Content type
application/json
null

Add Generation

Add Generation Workflows Configuration

path Parameters
agent_id
required
string (Agent Id)
workflow_id
required
string (Workflow Id)
Request Body schema: application/json
required
Id (string) or Id (null) (Id)
title
string (Title)
Default: "agent"
Array of Rules (strings) or Rules (null) (Rules)
max_retries
integer (Max Retries)
Default: 1
module
string (Module)
Default: "summarize"
Value: "summarize"
Prompt (string) or Prompt (null) (Prompt)
model
string (Generative model)
Default: "chatgpt-azure-4o-mini"

Model used to generate the response

images
boolean (Images)
Default: false
conversational
boolean (Conversational)
Default: false
include_mcp_prompts
boolean (If MCP prompts were used during the context steps, include them in the prompt to generate the final answer)
Default: false
citations
boolean (Whether to include markdown citations in the generated answer.)
Default: false
force_chunk_level_citations
boolean (Whether to always use chunk-level citations instead of context-level citations.)
Default: false

Responses

Request samples

Content type
application/json
Example
{
  • "id": "string",
  • "title": "agent",
  • "rules": [
    ],
  • "max_retries": 1,
  • "module": "summarize",
  • "prompt": "string",
  • "model": "chatgpt-azure-4o-mini",
  • "images": false,
  • "conversational": false,
  • "include_mcp_prompts": false,
  • "citations": false,
  • "force_chunk_level_citations": false
}

Response samples

Content type
application/json
{
  • "id": "string"
}

Get Generation

Get Generation Workflows Configuration

path Parameters
agent_id
required
string (Agent Id)
workflow_id
required
string (Workflow Id)

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Patch Generation

Set Generation Workflows Configuration

path Parameters
agent_id
required
string (Agent Id)
workflow_id
required
string (Workflow Id)
generation
required
string (Generation)
Request Body schema: application/json
required
Id (string) or Id (null) (Id)
title
string (Title)
Default: "agent"
Array of Rules (strings) or Rules (null) (Rules)
max_retries
integer (Max Retries)
Default: 1
module
string (Module)
Default: "summarize"
Value: "summarize"
Prompt (string) or Prompt (null) (Prompt)
model
string (Generative model)
Default: "chatgpt-azure-4o-mini"

Model used to generate the response

images
boolean (Images)
Default: false
conversational
boolean (Conversational)
Default: false
include_mcp_prompts
boolean (If MCP prompts were used during the context steps, include them in the prompt to generate the final answer)
Default: false
citations
boolean (Whether to include markdown citations in the generated answer.)
Default: false
force_chunk_level_citations
boolean (Whether to always use chunk-level citations instead of context-level citations.)
Default: false

Responses

Request samples

Content type
application/json
Example
{
  • "id": "string",
  • "title": "agent",
  • "rules": [
    ],
  • "max_retries": 1,
  • "module": "summarize",
  • "prompt": "string",
  • "model": "chatgpt-azure-4o-mini",
  • "images": false,
  • "conversational": false,
  • "include_mcp_prompts": false,
  • "citations": false,
  • "force_chunk_level_citations": false
}

Response samples

Content type
application/json
null

Delete Generation

Delete Generation Workflows Configuration

path Parameters
agent_id
required
string (Agent Id)
workflow_id
required
string (Workflow Id)
generation
required
string (Generation)

Responses

Response samples

Content type
application/json
null

Add Postprocess

Add PostProcess Workflows Configuration

path Parameters
agent_id
required
string (Agent Id)
workflow_id
required
string (Workflow Id)
Request Body schema: application/json
required
Id (string) or Id (null) (Id)
title
string (Title)
Default: "agent"
Array of Rules (strings) or Rules (null) (Rules)
max_retries
integer (Max Retries)
Default: 1
module
string (Module)
Default: "remi"
Value: "remi"
context_granularity
string (Granularity of the contexts pieces)
Default: "full"
Enum: "full" "partial_answers"

Granularity of the context pieces sent to REMi for groundedness evaluation. If 'partial_answers', the evaluation will use agent-level answer attempts to the question when available for a speedier analysis. If 'full', the evaluation will use all individual text chunks that each agent generated for a more detailed analysis.

Responses

Request samples

Content type
application/json
Example
{
  • "id": "string",
  • "title": "agent",
  • "rules": [
    ],
  • "max_retries": 1,
  • "module": "remi",
  • "context_granularity": "full"
}

Response samples

Content type
application/json
{
  • "id": "string"
}

Get Postprocess

Get PostProcess Workflows Configuration

path Parameters
agent_id
required
string (Agent Id)
workflow_id
required
string (Workflow Id)

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Patch Postprocess

Set PostProcess Workflows Configuration

path Parameters
agent_id
required
string (Agent Id)
workflow_id
required
string (Workflow Id)
postprocess
required
string (Postprocess)
Request Body schema: application/json
required
Id (string) or Id (null) (Id)
title
string (Title)
Default: "agent"
Array of Rules (strings) or Rules (null) (Rules)
max_retries
integer (Max Retries)
Default: 1
module
string (Module)
Default: "remi"
Value: "remi"
context_granularity
string (Granularity of the contexts pieces)
Default: "full"
Enum: "full" "partial_answers"

Granularity of the context pieces sent to REMi for groundedness evaluation. If 'partial_answers', the evaluation will use agent-level answer attempts to the question when available for a speedier analysis. If 'full', the evaluation will use all individual text chunks that each agent generated for a more detailed analysis.

Responses

Request samples

Content type
application/json
Example
{
  • "id": "string",
  • "title": "agent",
  • "rules": [
    ],
  • "max_retries": 1,
  • "module": "remi",
  • "context_granularity": "full"
}

Response samples

Content type
application/json
null

Delete Postprocess

Delete PostProcess Workflows Configuration

path Parameters
agent_id
required
string (Agent Id)
workflow_id
required
string (Workflow Id)
postprocess
required
string (Postprocess)

Responses

Response samples

Content type
application/json
null

Add Preprocess

Add PreProcess Workflows Configuration

path Parameters
agent_id
required
string (Agent Id)
workflow_id
required
string (Workflow Id)
Request Body schema: application/json
required
Id (string) or Id (null) (Id)
title
string (Title)
Default: "agent"
Array of Rules (strings) or Rules (null) (Rules)
max_retries
integer (Max Retries)
Default: 1
module
string (Module)
Default: "historical"
Value: "historical"
all
required
boolean (All)

Responses

Request samples

Content type
application/json
Example
{
  • "id": "string",
  • "title": "agent",
  • "rules": [
    ],
  • "max_retries": 1,
  • "module": "historical",
  • "all": true
}

Response samples

Content type
application/json
{
  • "id": "string"
}

Get Preprocess

Set Workflow Configuration

path Parameters
agent_id
required
string (Agent Id)
workflow_id
required
string (Workflow Id)

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Patch Preprocess

Set PreProcess Workflows Configuration

path Parameters
agent_id
required
string (Agent Id)
workflow_id
required
string (Workflow Id)
preprocess
required
string (Preprocess)
Request Body schema: application/json
required
Id (string) or Id (null) (Id)
title
string (Title)
Default: "agent"
Array of Rules (strings) or Rules (null) (Rules)
max_retries
integer (Max Retries)
Default: 1
module
string (Module)
Default: "historical"
Value: "historical"
all
required
boolean (All)

Responses

Request samples

Content type
application/json
Example
{
  • "id": "string",
  • "title": "agent",
  • "rules": [
    ],
  • "max_retries": 1,
  • "module": "historical",
  • "all": true
}

Response samples

Content type
application/json
null

Delete Preprocess

Delete PreProcess Workflows Configuration

path Parameters
agent_id
required
string (Agent Id)
preprocess
required
string (Preprocess)
workflow_id
required
string (Workflow Id)

Responses

Response samples

Content type
application/json
null

Set Rules

Set Workflow Rules Configuration

path Parameters
agent_id
required
string (Agent Id)
workflow_id
required
string (Workflow Id)
Request Body schema: application/json
required
Array of Rule (object) or strings (Rules)

List of rules that the workflow should follow. Each rule can be a string or a Rule object with a prompt.

Array
Any of
Prompt (string) or Prompt (null) (Prompt)
Any of
string (Prompt)

Responses

Request samples

Content type
application/json
{
  • "rules": [
    ]
}

Response samples

Content type
application/json
null

Get Rules

Get Workflow Rules Configuration

path Parameters
agent_id
required
string (Agent Id)
workflow_id
required
string (Workflow Id)

Responses

Response samples

Content type
application/json
null

Add Workflow

Add Workflow Configuration

path Parameters
agent_id
required
string (Agent Id)
Request Body schema: application/json
required
id
required
string (Id)
name
required
string (Name)
Description (string) or Description (null) (Description)
Parameters (object) or Parameters (null) (Parameters)
object (Rules)
required
Array of strings (Required)

Responses

Request samples

Content type
application/json
{
  • "id": "string",
  • "name": "string",
  • "description": "string",
  • "parameters": { },
  • "rules": {
    },
  • "required": [
    ]
}

Response samples

Content type
application/json
null

Get Workflows

Get Workflow Configuration

path Parameters
agent_id
required
string (Agent Id)

Responses

Response samples

Content type
application/json
[
  • {
    }
]

Ingestion Agents and Tasks

Start Dataset Task

Start an Ingestion Agent or a Task on a Dataset

path Parameters
dataset_id
required
string (Dataset Id)
Request Body schema: application/json
required
name
required
string (TaskName)
Enum: "dummy" "env" "demo-dataset" "labeler" "llm-graph" "synthetic-questions" "ask" "llm-align" "semantic-model-migrator" "llama-guard" "prompt-guard"
DataAugmentation (object) or SemanticModelMigrationParams (object) or Parameters (null) (Parameters)

Parameters to be passed to the task. These must match the validation field for the Task definition class

Uuid Task (string) or Uuid Task (null) (Uuid Task)

UUID of an already configured task. This is used to start a task that was already configured

Responses

Request samples

Content type
application/json
{
  • "name": "dummy",
  • "parameters": {
    },
  • "uuid_task": "string"
}

Response samples

Content type
application/json
{
  • "name": "dummy",
  • "status": "not_running",
  • "id": "string"
}

Delete Dataset Task

Delete an Ingestion Agent or a Task of a Dataset

path Parameters
dataset_id
required
string (Dataset Id)
task_id
required
string (Task Id)

Responses

Response samples

Content type
application/json
null

Inspect Dataset Task

Get the status of an Ingestion Agent or a Task of a Dataset

path Parameters
dataset_id
required
string (Dataset Id)
task_id
required
string (Task Id)

Responses

Response samples

Content type
application/json
{
  • "task": {
    },
  • "source": "nucliadb",
  • "kbid": "string",
  • "dataset_id": "string",
  • "account_id": "string",
  • "nua_client_id": "string",
  • "user_id": "string",
  • "id": "string",
  • "task_config_id": "string",
  • "timestamp": "2019-08-24T14:15:22Z",
  • "scheduled": false,
  • "completed": false,
  • "stopped": false,
  • "scheduled_at": "2019-08-24T14:15:22Z",
  • "completed_at": "2019-08-24T14:15:22Z",
  • "stopped_at": "2019-08-24T14:15:22Z",
  • "failed": false,
  • "retries": 0,
  • "parameters": {
    },
  • "log": "string",
  • "cleanup_parent_task_id": "string"
}

Stop Dataset Task

Stop an Ingestion Agent or a Task of a Dataset

path Parameters
dataset_id
required
string (Dataset Id)
task_id
required
string (Task Id)

Responses

Response samples

Content type
application/json
{
  • "name": "dummy",
  • "status": "not_running",
  • "id": "string"
}

List Account Available Tasks

Get the available tasks for a Dataset

path Parameters
dataset_id
required
string (Dataset Id)
query Parameters
count
integer (Count)
Default: 10

How many finished tasks to return

Responses

Response samples

Content type
application/json
{
  • "tasks": [
    ],
  • "running": [
    ],
  • "configs": [
    ],
  • "done": [
    ]
}

Start Knowledge Box Task

Start an Ingestion Agent or a Task on a Knowledge Box

path Parameters
kb_uuid
required
string (Kb Uuid)
Request Body schema: application/json
required
name
required
string (TaskName)
Enum: "dummy" "env" "demo-dataset" "labeler" "llm-graph" "synthetic-questions" "ask" "llm-align" "semantic-model-migrator" "llama-guard" "prompt-guard"
DataAugmentation (object) or SemanticModelMigrationParams (object) or Parameters (null) (Parameters)

Parameters to be passed to the task. These must match the validation field for the Task definition class

Uuid Task (string) or Uuid Task (null) (Uuid Task)

UUID of an already configured task. This is used to start a task that was already configured

apply
string (ApplyOptions)
Default: "ALL"
Enum: "EXISTING" "NEW" "ALL" 
Defines how the tasks should be applied to the existing data.
- EXSITING: Only apply to existing data (starts a worker that executes the task)
- NEW: Only apply to new data (enables the task at processing time)
- ALL: Apply to all data (both of the above)
enabled
boolean (Enabled)
Default: true

Whether the task should be enabled at the time of creation. This only applies to tasks involving 'NEW' apply options, as 'EXISTING' tasks start immediately

Responses

Request samples

Content type
application/json
{
  • "name": "dummy",
  • "parameters": {
    },
  • "uuid_task": "string",
  • "apply": "EXISTING",
  • "enabled": true
}

Response samples

Content type
application/json
{
  • "name": "dummy",
  • "status": "not_running",
  • "id": "string"
}

Patch Knowledge Box Task

Modify the parameters of a task. This is only available for tasks that run on NEW resources, tasks that run on EXISTING resources cannot be modified.

path Parameters
kb_uuid
required
string (Kb Uuid)
task_id
required
string (Task Id)
Request Body schema: application/json
required
required
DataAugmentation (object) or SemanticModelMigrationParams (object) or Parameters (null) (Parameters)

Parameters to be passed to the task. These must match the validation field for the Task definition class

Any of
name
string (Name)
Default: ""
on
integer (ApplyTo)
Default: 0
Enum: 0 1

Defines if the task should be applied to paragraphs (0) or whole fields (1)

Filter (object) or null

Filter to apply the data augmentation

Array of objects (Operations)
object (LLMConfig-Input)
Filter Expression Json (string) or Filter Expression Json (null) (Filter Expression Json)
Default: ""

JSON representation of the filter expression, used to filter the data augmentation in the UI. If set, it takes precedence over the filter field

Responses

Request samples

Content type
application/json
{
  • "parameters": {
    }
}

Response samples

Content type
application/json
{
  • "task": {
    },
  • "source": "nucliadb",
  • "kbid": "string",
  • "dataset_id": "string",
  • "dataset_path": "string",
  • "account_id": "string",
  • "account_type": "string",
  • "nua_client_id": "string",
  • "user_id": "string",
  • "parameters": {
    },
  • "id": "string",
  • "task_config_id": "string",
  • "timestamp": "2019-08-24T14:15:22Z",
  • "scheduled": false,
  • "completed": false,
  • "stopped": false,
  • "scheduled_at": "2019-08-24T14:15:22Z",
  • "completed_at": "2019-08-24T14:15:22Z",
  • "stopped_at": "2019-08-24T14:15:22Z",
  • "failed": false,
  • "retries": 0,
  • "token": "string",
  • "key_id": "string",
  • "ndb_token": "string",
  • "log": "string",
  • "cleanup_parent_task_id": "string"
}

Delete Knowledge Box Task

Delete an Ingestion Agent or a Task of a Knowledge Box

path Parameters
kb_uuid
required
string (Kb Uuid)
task_id
required
string (Task Id)
query Parameters
cleanup
boolean (Cleanup)
Default: false

Cleanup all data associated with the task

Responses

Response samples

Content type
application/json
null

Cleanup Knowledge Box Task

Start a cleanup process for an Ingestion Agent or a Task of a Knowledge Box

path Parameters
kb_uuid
required
string (Kb Uuid)
task_id
required
string (Task Id)

Responses

Response samples

Content type
application/json
{
  • "request": {
    },
  • "config": {
    }
}

Enable Knowledge Box Task

Enable or disable a task. This is only available for tasks that run on NEW resources. To disable a task that runs on EXISTING resources, use the stop endpoint.

path Parameters
task_id
required
string (Task Id)
kb_uuid
required
string (Kb Uuid)
Request Body schema: application/json
required
enabled
required
boolean (Enabled)

Responses

Request samples

Content type
application/json
{
  • "enabled": true
}

Response samples

Content type
application/json
null

Inspect Knowledge Box Task

Get the details of an Ingestion Agent or a Task of a Knowledge Box

path Parameters
kb_uuid
required
string (Kb Uuid)
task_id
required
string (Task Id)

Responses

Response samples

Content type
application/json
{
  • "request": {
    },
  • "config": {
    }
}

Restart Knowledge Box Task

Restart an Ingestion Agent or a Task of a Knowledge Box. This only affects tasks that are configured to run on EXISTING resources, for tasks that run on NEW resources, use the enable endpoint.

path Parameters
kb_uuid
required
string (Kb Uuid)
task_id
required
string (Task Id)

Responses

Response samples

Content type
application/json
{
  • "name": "dummy",
  • "status": "not_running",
  • "id": "string"
}

Stop Knowledge Box Task

Stop an Ingestion Agent or a Task of a Knowledge Box. This only affects tasks that are currently running on EXISTING resources, for disabling tasks that run on NEW resources, use the enable endpoint.

path Parameters
kb_uuid
required
string (Kb Uuid)
task_id
required
string (Task Id)

Responses

Response samples

Content type
application/json
{
  • "name": "dummy",
  • "status": "not_running",
  • "id": "string"
}

Inspect Knowledge Box Task Worker

Get the worker config of a task on a knowledge box

path Parameters
task_id
required
string (Task Id)

Responses

Response samples

Content type
application/json
{
  • "task": {
    },
  • "source": "nucliadb",
  • "kbid": "string",
  • "dataset_id": "string",
  • "dataset_path": "string",
  • "account_id": "string",
  • "account_type": "string",
  • "nua_client_id": "string",
  • "user_id": "string",
  • "parameters": {
    },
  • "id": "string",
  • "task_config_id": "string",
  • "timestamp": "2019-08-24T14:15:22Z",
  • "scheduled": false,
  • "completed": false,
  • "stopped": false,
  • "scheduled_at": "2019-08-24T14:15:22Z",
  • "completed_at": "2019-08-24T14:15:22Z",
  • "stopped_at": "2019-08-24T14:15:22Z",
  • "failed": false,
  • "retries": 0,
  • "token": "string",
  • "key_id": "string",
  • "ndb_token": "string",
  • "log": "string",
  • "cleanup_parent_task_id": "string"
}

List Knowledge Box Available Tasks

Get the available Ingestion Agents and Tasks of a Knowledge Box

path Parameters
kb_uuid
required
string (Kb Uuid)
query Parameters
count
integer (Count)
Default: 10

How many finished tasks to return

Responses

Response samples

Content type
application/json
{
  • "tasks": [
    ],
  • "running": [
    ],
  • "configs": [
    ],
  • "done": [
    ]
}

Extract Strategies

Learning Extract Strategies

Get available extract strategies onprem

path Parameters
kbid
required
string (Kbid)

Responses

Response samples

Content type
application/json
{
  • "property1": {
    },
  • "property2": {
    }
}

Add A Extract Strategy To A Kb Onprem

Add a extract strategy to a KB to be used

path Parameters
kbid
required
string (Kbid)
Request Body schema: application/json
required
name
string (Name)
Default: ""
VLLMExtractionConfig (object) or null
AITables (object) or null
SplitConfig (object) or null

Responses

Request samples

Content type
application/json
{
  • "name": "",
  • "vllm_config": {
    },
  • "ai_tables": {
    },
  • "split": {
    }
}

Response samples

Content type
application/json
"string"

Extract Strategy Configuration

Get extract strategy for a given id

path Parameters
kbid
required
string (Kbid)
strategy_id
required
string (Strategy Id)

Responses

Response samples

Content type
application/json
{
  • "name": "",
  • "vllm_config": {
    },
  • "ai_tables": {
    },
  • "split": {
    }
}

Disable Extract Strategy Onprem

Disable a extract strategy from a Knowledge Box

path Parameters
kbid
required
string (Kbid)
strategy_id
required
string (Strategy Id)

Responses

Response samples

Content type
application/json
null

Search

Ask Knowledge Box

Ask questions on a Knowledge Box

path Parameters
kbid
required
string (Kbid)
header Parameters
x-ndb-client
string (NucliaDBClientType)
Default: api
Enum: "api" "widget" "web" "dashboard" "desktop" "chrome_extension"
x-show-consumption
boolean (X-Show-Consumption)
Default: false
x-nucliadb-user
string (X-Nucliadb-User)
Default:
x-forwarded-for
string (X-Forwarded-For)
Default:
x-synchronous
boolean (X-Synchronous)
Default: false

When set to true, outputs response as JSON in a non-streaming way. This is slower and requires waiting for entire answer to be ready.

Request Body schema: application/json
required
Audit metadata (object) or Audit metadata (null) (Audit metadata)

A dictionary containing optional audit-specific metadata, such as user_id, environment, or other contextual information. This metadata can be leveraged for filtering and analyzing activity logs in future operations. Each key-value pair represents a piece of metadata relevant to the user's request.

query
required
string (Query) <= 20000 characters

The query to get a generative answer for

top_k
integer (Top k) [ 1 .. 200 ]
Default: 20

The top most relevant results to fetch at the retrieval step. The maximum number of results allowed is 200.

FilterExpression (object) or Filter resource by an expression (null) (Filter resource by an expression)

Returns only documents that match this filter expression.Filtering examples can be found here: https://docs.nuclia.dev/docs/rag/advanced/search-filters This allows building complex filtering expressions and replaces the following parameters:fields, filters, range_*, resource_filters, keyword_filters.

fields
Array of strings (Fields)
Default: []

The list of fields to search in. For instance: a/title to search only on title field. For more details on filtering by field, see: https://docs.nuclia.dev/docs/rag/advanced/search/#search-in-a-specific-field.

Array of Search Filters (strings) or Array of Search Filters (objects) (Search Filters)
Default: []

The list of filters to apply. Filtering examples can be found here: https://docs.nuclia.dev/docs/rag/advanced/search-filters

Array of Keyword filters (strings) or Array of Keyword filters (objects) (Keyword filters)
Default: []

List of keyword filter expressions to apply to the retrieval step. The text block search will only be performed on the documents that contain the specified keywords. The filters are case-insensitive, and only alphanumeric characters and spaces are allowed. Filtering examples can be found here: https://docs.nuclia.dev/docs/rag/advanced/search-filters

Vectorset (string) or Vectorset (null) (Vectorset)

Vectors index to perform the search in. If not provided, NucliaDB will use the default one

Minimum score (number) or MinScore (object) or Minimum score (null) (Minimum score)

Minimum score to filter search results. Results with a lower score will be ignored. Accepts either a float or a dictionary with the minimum scores for the bm25 and vector indexes. If a float is provided, it is interpreted as the minimum score for vector index search.

features
Array of strings (Chat features)
Default: ["semantic","keyword"]
Items Enum: "keyword" "relations" "semantic"

Features enabled for the chat endpoint. Semantic search is done if semantic is included. If keyword is included, the results will include matching paragraphs from the bm25 index. If relations is included, a graph of entities related to the answer is returned. paragraphs and vectors are deprecated, please use keyword and semantic instead

Resource creation range start (string) or Resource creation range start (null) (Resource creation range start)

Resources created before this date will be filtered out of search results. Datetime are represented as a str in ISO 8601 format, like: 2008-09-15T15:53:00+05:00.

Resource creation range end (string) or Resource creation range end (null) (Resource creation range end)

Resources created after this date will be filtered out of search results. Datetime are represented as a str in ISO 8601 format, like: 2008-09-15T15:53:00+05:00.

Resource modification range start (string) or Resource modification range start (null) (Resource modification range start)

Resources modified before this date will be filtered out of search results. Datetime are represented as a str in ISO 8601 format, like: 2008-09-15T15:53:00+05:00.

Resource modification range end (string) or Resource modification range end (null) (Resource modification range end)

Resources modified after this date will be filtered out of search results. Datetime are represented as a str in ISO 8601 format, like: 2008-09-15T15:53:00+05:00.

show
Array of strings (Show metadata)
Default: ["basic"]
Items Enum: "basic" "origin" "extra" "relations" "values" "extracted" "errors" "security"

Controls which types of metadata are serialized on resources of search results

field_type_filter
Array of strings (Field type filter)
Default: ["text","file","link","conversation","generic"]
Items Enum: "text" "file" "link" "conversation" "generic"

Define which field types are serialized on resources of search results

extracted
Array of strings (Extracted metadata)
Deprecated
Default: []
Items Enum: "text" "metadata" "shortened_metadata" "large_metadata" "vectors" "link" "file" "question_answers" "relation_vectors"

[Deprecated] Please use GET resource endpoint instead to get extracted metadata

Array of Chat context (deprecated) (objects) or Chat context (deprecated) (null) (Chat context (deprecated))
Deprecated

DEPRECATED! Please, use chat_history instead.

Array of Chat history (objects) or Chat history (null) (Chat history)

Use to rephrase the new LLM query by taking into account the chat conversation history. This will be passed to the LLM so that it is aware of the previous conversation.

Array of Extra query context (strings) or Extra query context (null) (Extra query context)

Additional context that is added to the retrieval context sent to the LLM. It allows extending the chat feature with content that may not be in the Knowledge Box.

Array of Extra query context images (objects) or Extra query context images (null) (Extra query context images)

Additional images added to the retrieval context sent to the LLM." It allows extending the chat feature with content that may not be in the Knowledge Box.

Image (object) or Query image (null) (Query image)

Image that will be used together with the query text for retrieval and then sent to the LLM as part of the context. If a query image is provided, the extra_context_images and rag_images_strategies will be disabled.

highlight
boolean (Highlight)
Default: false

If set to true, the query terms will be highlighted in the results between ... tags

resource_filters
Array of strings (Resources filter)
Default: []

List of resource ids to filter search results for. Only paragraphs from the specified resources will be returned.

Prompts (string) or CustomPrompt (object) or Prompts (null) (Prompts)

Use to customize the prompts given to the generative model. Both system and user prompts can be customized. If a string is provided, it is interpreted as the user prompt.

RankFusionName (string) or Rank fusion (any) (Rank fusion)
Default: "rrf"

Rank fusion algorithm to use to merge results from multiple retrievers (keyword, semantic)

RerankerName (string) or Reranker (any) (Reranker)
Default: "predict"

Reranker let you specify which method you want to use to rerank your results at the end of retrieval

Citations (boolean) or CitationsType (string) or Citations (null) (Citations)

Whether to include citations in the response. If set to None or False, no citations will be computed. If set to True or 'default', citations will be computed after answer generation and send as a separate CitationsGenerativeResponse chunk. If set to 'llm_footnotes', citations will be included in the LLM's response as markdown-styled footnotes. A FootnoteCitationsGenerativeResponse chunk will also be sent to map footnote ids to context keys in the query_context.

Citation Threshold (number) or Citation Threshold (null) (Citation Threshold)

If citations is set to True or 'default', this will be the similarity threshold. Value between 0 and 1, lower values will produce more citations. If not set, it will be set to the optimized threshold found by Nuclia.

RequestSecurity (object) or Security (null) (Security)

Security metadata for the request. If not provided, the search request is done without the security lookup phase.

show_hidden
boolean (Show hidden resources)
Default: false

If set to false (default), excludes hidden resources from search

Array of any (RAG context building strategies)
Default: []

Options for tweaking how the context for the LLM model is crafted:

  • full_resource will add the full text of the matching resources to the context. This strategy cannot be combined with hierarchy, neighbouring_paragraphs, or field_extension.
  • field_extension will add the text of the matching resource's specified fields to the context.
  • hierarchy will add the title and summary text of the parent resource to the context for each matching paragraph.
  • neighbouring_paragraphs will add the sorrounding paragraphs to the context for each matching paragraph.
  • metadata_extension will add the metadata of the matching paragraphs or its resources to the context.
  • prequeries allows to run multiple retrieval queries before the main query and add the results to the context. The results of specific queries can be boosted by the specifying weights.

If empty, the default strategy is used, which simply adds the text of the matching paragraphs to the context.

Array of any (RAG image context building strategies)
Default: []

Options for tweaking how the image based context for the LLM model is crafted:

  • page_image will add the full page image of the matching resources to the context.
  • tables will send the table images for the paragraphs that contain tables and matched the retrieval query.
  • paragraph_image will add the images of the paragraphs that contain images (images for tables are not included). No image strategy is used by default. Note that this is only available for LLM models that support visual inputs. If the model does not support visual inputs, the image strategies will be ignored.
debug
boolean (Debug mode)
Default: false

If set, the response will include some extra metadata for debugging purposes, like the list of queried nodes.

Generative model (string) or Generative model (null) (Generative model)

The generative model to use for the chat endpoint. If not provided, the model configured for the Knowledge Box is used.

Seed for the generative model (integer) or Seed for the generative model (null) (Seed for the generative model)

The seed to use for the generative model for deterministic generation. Only supported by some models.

Maximum LLM tokens to use for the request (integer) or MaxTokens (object) or Maximum LLM tokens to use for the request (null) (Maximum LLM tokens to use for the request)

Use to limit the amount of tokens used in the LLM context and/or for generating the answer. If not provided, the default maximum tokens of the generative model will be used. If an integer is provided, it is interpreted as the maximum tokens for the answer.

rephrase
boolean (Rephrase)
Default: false

Rephrase the query for a more efficient retrieval. This will consume LLM tokens and make the request slower.

Chat History Relevance Threshold (number) or Chat History Relevance Threshold (null) (Chat History Relevance Threshold)

Threshold to determine if the past chat history is relevant to rephrase the user's question. 0 - Always treat previous messages as relevant (always rephrase).1 - Always treat previous messages as irrelevant (never rephrase).Values in between adjust the sensitivity.

prefer_markdown
boolean (Prefer markdown)
Default: false

If set to true, the response will be in markdown format

Answer JSON schema (object) or Answer JSON schema (null) (Answer JSON schema)

Desired JSON schema for the LLM answer. This schema is passed to the LLM so that it answers in a scructured format following the schema. If not provided, textual response is returned. Note that when using this parameter, the answer in the generative response will not be returned in chunks, the whole response text will be returned instead. Using this feature also disables the citations parameter. For maximal accuracy, please include a description for each field of the schema.

generate_answer
boolean (Generate Answer)
Default: true

Whether to generate an answer using the generative model. If set to false, the response will only contain the retrieval results.

Search Configuration (string) or Search Configuration (null) (Search Configuration)

Load ask parameters from this configuration. Parameters in the request override parameters from the configuration.

Reasoning (object) or Reasoning options (boolean) (Reasoning options)
Default: false

Reasoning options for the generative model. Set to True to enable default reasoning, False to disable, or provide a Reasoning object for custom options.

Responses

Request samples

Content type
application/json
{
  • "audit_metadata": {
    },
  • "query": "string",
  • "top_k": 20,
  • "filter_expression": {
    },
  • "fields": [ ],
  • "filters": [ ],
  • "keyword_filters": [
    ],
  • "vectorset": "string",
  • "min_score": 0,
  • "features": [
    ],
  • "range_creation_start": "2019-08-24T14:15:22Z",
  • "range_creation_end": "2019-08-24T14:15:22Z",
  • "range_modification_start": "2019-08-24T14:15:22Z",
  • "range_modification_end": "2019-08-24T14:15:22Z",
  • "show": [
    ],
  • "field_type_filter": [
    ],
  • "extracted": [ ],
  • "context": [
    ],
  • "chat_history": [
    ],
  • "extra_context": [
    ],
  • "extra_context_images": [
    ],
  • "query_image": {
    },
  • "highlight": false,
  • "resource_filters": [ ],
  • "prompt": "string",
  • "rank_fusion": "rrf",
  • "reranker": "predict",
  • "citations": true,
  • "citation_threshold": 1,
  • "security": {
    },
  • "show_hidden": false,
  • "rag_strategies": [
    ],
  • "rag_images_strategies": [ ],
  • "debug": false,
  • "generative_model": "string",
  • "generative_model_seed": 0,
  • "max_tokens": 0,
  • "rephrase": false,
  • "chat_history_relevance_threshold": 1,
  • "prefer_markdown": false,
  • "answer_json_schema": {
    },
  • "generate_answer": true,
  • "search_configuration": "string",
  • "reasoning": false
}

Response samples

Content type
application/json
{
  • "answer": "string",
  • "reasoning": "string",
  • "answer_json": { },
  • "status": "string",
  • "retrieval_results": {
    },
  • "retrieval_best_matches": [ ],
  • "prequeries": {
    },
  • "learning_id": "",
  • "relations": {
    },
  • "citations": { },
  • "citation_footnote_to_context": {
    },
  • "augmented_context": {
    },
  • "prompt_context": [
    ],
  • "predict_request": { },
  • "metadata": {
    },
  • "consumption": {
    },
  • "error_details": "string",
  • "debug": { }
}

Ask a resource (by id)

Ask questions to a resource

path Parameters
kbid
required
string (Kbid)
rid
required
string <uuid> (Rid)
header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false
x-ndb-client
string (NucliaDBClientType)
Default: api
Enum: "api" "widget" "web" "dashboard" "desktop" "chrome_extension"
x-nucliadb-user
string (X-Nucliadb-User)
Default:
x-forwarded-for
string (X-Forwarded-For)
Default:
x-synchronous
boolean (X-Synchronous)
Default: false

When set to true, outputs response as JSON in a non-streaming way. This is slower and requires waiting for entire answer to be ready.

Request Body schema: application/json
required
Audit metadata (object) or Audit metadata (null) (Audit metadata)

A dictionary containing optional audit-specific metadata, such as user_id, environment, or other contextual information. This metadata can be leveraged for filtering and analyzing activity logs in future operations. Each key-value pair represents a piece of metadata relevant to the user's request.

query
required
string (Query) <= 20000 characters

The query to get a generative answer for

top_k
integer (Top k) [ 1 .. 200 ]
Default: 20

The top most relevant results to fetch at the retrieval step. The maximum number of results allowed is 200.

FilterExpression (object) or Filter resource by an expression (null) (Filter resource by an expression)

Returns only documents that match this filter expression.Filtering examples can be found here: https://docs.nuclia.dev/docs/rag/advanced/search-filters This allows building complex filtering expressions and replaces the following parameters:fields, filters, range_*, resource_filters, keyword_filters.

fields
Array of strings (Fields)
Default: []

The list of fields to search in. For instance: a/title to search only on title field. For more details on filtering by field, see: https://docs.nuclia.dev/docs/rag/advanced/search/#search-in-a-specific-field.

Array of Search Filters (strings) or Array of Search Filters (objects) (Search Filters)
Default: []

The list of filters to apply. Filtering examples can be found here: https://docs.nuclia.dev/docs/rag/advanced/search-filters

Array of Keyword filters (strings) or Array of Keyword filters (objects) (Keyword filters)
Default: []

List of keyword filter expressions to apply to the retrieval step. The text block search will only be performed on the documents that contain the specified keywords. The filters are case-insensitive, and only alphanumeric characters and spaces are allowed. Filtering examples can be found here: https://docs.nuclia.dev/docs/rag/advanced/search-filters

Vectorset (string) or Vectorset (null) (Vectorset)

Vectors index to perform the search in. If not provided, NucliaDB will use the default one

Minimum score (number) or MinScore (object) or Minimum score (null) (Minimum score)

Minimum score to filter search results. Results with a lower score will be ignored. Accepts either a float or a dictionary with the minimum scores for the bm25 and vector indexes. If a float is provided, it is interpreted as the minimum score for vector index search.

features
Array of strings (Chat features)
Default: ["semantic","keyword"]
Items Enum: "keyword" "relations" "semantic"

Features enabled for the chat endpoint. Semantic search is done if semantic is included. If keyword is included, the results will include matching paragraphs from the bm25 index. If relations is included, a graph of entities related to the answer is returned. paragraphs and vectors are deprecated, please use keyword and semantic instead

Resource creation range start (string) or Resource creation range start (null) (Resource creation range start)

Resources created before this date will be filtered out of search results. Datetime are represented as a str in ISO 8601 format, like: 2008-09-15T15:53:00+05:00.

Resource creation range end (string) or Resource creation range end (null) (Resource creation range end)

Resources created after this date will be filtered out of search results. Datetime are represented as a str in ISO 8601 format, like: 2008-09-15T15:53:00+05:00.

Resource modification range start (string) or Resource modification range start (null) (Resource modification range start)

Resources modified before this date will be filtered out of search results. Datetime are represented as a str in ISO 8601 format, like: 2008-09-15T15:53:00+05:00.

Resource modification range end (string) or Resource modification range end (null) (Resource modification range end)

Resources modified after this date will be filtered out of search results. Datetime are represented as a str in ISO 8601 format, like: 2008-09-15T15:53:00+05:00.

show
Array of strings (Show metadata)
Default: ["basic"]
Items Enum: "basic" "origin" "extra" "relations" "values" "extracted" "errors" "security"

Controls which types of metadata are serialized on resources of search results

field_type_filter
Array of strings (Field type filter)
Default: ["text","file","link","conversation","generic"]
Items Enum: "text" "file" "link" "conversation" "generic"

Define which field types are serialized on resources of search results

extracted
Array of strings (Extracted metadata)
Deprecated
Default: []
Items Enum: "text" "metadata" "shortened_metadata" "large_metadata" "vectors" "link" "file" "question_answers" "relation_vectors"

[Deprecated] Please use GET resource endpoint instead to get extracted metadata

Array of Chat context (deprecated) (objects) or Chat context (deprecated) (null) (Chat context (deprecated))
Deprecated

DEPRECATED! Please, use chat_history instead.

Array of Chat history (objects) or Chat history (null) (Chat history)

Use to rephrase the new LLM query by taking into account the chat conversation history. This will be passed to the LLM so that it is aware of the previous conversation.

Array of Extra query context (strings) or Extra query context (null) (Extra query context)

Additional context that is added to the retrieval context sent to the LLM. It allows extending the chat feature with content that may not be in the Knowledge Box.

Array of Extra query context images (objects) or Extra query context images (null) (Extra query context images)

Additional images added to the retrieval context sent to the LLM." It allows extending the chat feature with content that may not be in the Knowledge Box.

Image (object) or Query image (null) (Query image)

Image that will be used together with the query text for retrieval and then sent to the LLM as part of the context. If a query image is provided, the extra_context_images and rag_images_strategies will be disabled.

highlight
boolean (Highlight)
Default: false

If set to true, the query terms will be highlighted in the results between ... tags

resource_filters
Array of strings (Resources filter)
Default: []

List of resource ids to filter search results for. Only paragraphs from the specified resources will be returned.

Prompts (string) or CustomPrompt (object) or Prompts (null) (Prompts)

Use to customize the prompts given to the generative model. Both system and user prompts can be customized. If a string is provided, it is interpreted as the user prompt.

RankFusionName (string) or Rank fusion (any) (Rank fusion)
Default: "rrf"

Rank fusion algorithm to use to merge results from multiple retrievers (keyword, semantic)

RerankerName (string) or Reranker (any) (Reranker)
Default: "predict"

Reranker let you specify which method you want to use to rerank your results at the end of retrieval

Citations (boolean) or CitationsType (string) or Citations (null) (Citations)

Whether to include citations in the response. If set to None or False, no citations will be computed. If set to True or 'default', citations will be computed after answer generation and send as a separate CitationsGenerativeResponse chunk. If set to 'llm_footnotes', citations will be included in the LLM's response as markdown-styled footnotes. A FootnoteCitationsGenerativeResponse chunk will also be sent to map footnote ids to context keys in the query_context.

Citation Threshold (number) or Citation Threshold (null) (Citation Threshold)

If citations is set to True or 'default', this will be the similarity threshold. Value between 0 and 1, lower values will produce more citations. If not set, it will be set to the optimized threshold found by Nuclia.

RequestSecurity (object) or Security (null) (Security)

Security metadata for the request. If not provided, the search request is done without the security lookup phase.

show_hidden
boolean (Show hidden resources)
Default: false

If set to false (default), excludes hidden resources from search

Array of any (RAG context building strategies)
Default: []

Options for tweaking how the context for the LLM model is crafted:

  • full_resource will add the full text of the matching resources to the context. This strategy cannot be combined with hierarchy, neighbouring_paragraphs, or field_extension.
  • field_extension will add the text of the matching resource's specified fields to the context.
  • hierarchy will add the title and summary text of the parent resource to the context for each matching paragraph.
  • neighbouring_paragraphs will add the sorrounding paragraphs to the context for each matching paragraph.
  • metadata_extension will add the metadata of the matching paragraphs or its resources to the context.
  • prequeries allows to run multiple retrieval queries before the main query and add the results to the context. The results of specific queries can be boosted by the specifying weights.

If empty, the default strategy is used, which simply adds the text of the matching paragraphs to the context.

Array of any (RAG image context building strategies)
Default: []

Options for tweaking how the image based context for the LLM model is crafted:

  • page_image will add the full page image of the matching resources to the context.
  • tables will send the table images for the paragraphs that contain tables and matched the retrieval query.
  • paragraph_image will add the images of the paragraphs that contain images (images for tables are not included). No image strategy is used by default. Note that this is only available for LLM models that support visual inputs. If the model does not support visual inputs, the image strategies will be ignored.
debug
boolean (Debug mode)
Default: false

If set, the response will include some extra metadata for debugging purposes, like the list of queried nodes.

Generative model (string) or Generative model (null) (Generative model)

The generative model to use for the chat endpoint. If not provided, the model configured for the Knowledge Box is used.

Seed for the generative model (integer) or Seed for the generative model (null) (Seed for the generative model)

The seed to use for the generative model for deterministic generation. Only supported by some models.

Maximum LLM tokens to use for the request (integer) or MaxTokens (object) or Maximum LLM tokens to use for the request (null) (Maximum LLM tokens to use for the request)

Use to limit the amount of tokens used in the LLM context and/or for generating the answer. If not provided, the default maximum tokens of the generative model will be used. If an integer is provided, it is interpreted as the maximum tokens for the answer.

rephrase
boolean (Rephrase)
Default: false

Rephrase the query for a more efficient retrieval. This will consume LLM tokens and make the request slower.

Chat History Relevance Threshold (number) or Chat History Relevance Threshold (null) (Chat History Relevance Threshold)

Threshold to determine if the past chat history is relevant to rephrase the user's question. 0 - Always treat previous messages as relevant (always rephrase).1 - Always treat previous messages as irrelevant (never rephrase).Values in between adjust the sensitivity.

prefer_markdown
boolean (Prefer markdown)
Default: false

If set to true, the response will be in markdown format

Answer JSON schema (object) or Answer JSON schema (null) (Answer JSON schema)

Desired JSON schema for the LLM answer. This schema is passed to the LLM so that it answers in a scructured format following the schema. If not provided, textual response is returned. Note that when using this parameter, the answer in the generative response will not be returned in chunks, the whole response text will be returned instead. Using this feature also disables the citations parameter. For maximal accuracy, please include a description for each field of the schema.

generate_answer
boolean (Generate Answer)
Default: true

Whether to generate an answer using the generative model. If set to false, the response will only contain the retrieval results.

Search Configuration (string) or Search Configuration (null) (Search Configuration)

Load ask parameters from this configuration. Parameters in the request override parameters from the configuration.

Reasoning (object) or Reasoning options (boolean) (Reasoning options)
Default: false

Reasoning options for the generative model. Set to True to enable default reasoning, False to disable, or provide a Reasoning object for custom options.

Responses

Request samples

Content type
application/json
{
  • "audit_metadata": {
    },
  • "query": "string",
  • "top_k": 20,
  • "filter_expression": {
    },
  • "fields": [ ],
  • "filters": [ ],
  • "keyword_filters": [
    ],
  • "vectorset": "string",
  • "min_score": 0,
  • "features": [
    ],
  • "range_creation_start": "2019-08-24T14:15:22Z",
  • "range_creation_end": "2019-08-24T14:15:22Z",
  • "range_modification_start": "2019-08-24T14:15:22Z",
  • "range_modification_end": "2019-08-24T14:15:22Z",
  • "show": [
    ],
  • "field_type_filter": [
    ],
  • "extracted": [ ],
  • "context": [
    ],
  • "chat_history": [
    ],
  • "extra_context": [
    ],
  • "extra_context_images": [
    ],
  • "query_image": {
    },
  • "highlight": false,
  • "resource_filters": [ ],
  • "prompt": "string",
  • "rank_fusion": "rrf",
  • "reranker": "predict",
  • "citations": true,
  • "citation_threshold": 1,
  • "security": {
    },
  • "show_hidden": false,
  • "rag_strategies": [
    ],
  • "rag_images_strategies": [ ],
  • "debug": false,
  • "generative_model": "string",
  • "generative_model_seed": 0,
  • "max_tokens": 0,
  • "rephrase": false,
  • "chat_history_relevance_threshold": 1,
  • "prefer_markdown": false,
  • "answer_json_schema": {
    },
  • "generate_answer": true,
  • "search_configuration": "string",
  • "reasoning": false
}

Response samples

Content type
application/json
{
  • "answer": "string",
  • "reasoning": "string",
  • "answer_json": { },
  • "status": "string",
  • "retrieval_results": {
    },
  • "retrieval_best_matches": [ ],
  • "prequeries": {
    },
  • "learning_id": "",
  • "relations": {
    },
  • "citations": { },
  • "citation_footnote_to_context": {
    },
  • "augmented_context": {
    },
  • "prompt_context": [
    ],
  • "predict_request": { },
  • "metadata": {
    },
  • "consumption": {
    },
  • "error_details": "string",
  • "debug": { }
}

Ask a resource (by slug)

Ask questions to a resource

path Parameters
kbid
required
string (Kbid)
slug
required
string (Slug)
header Parameters
x-show-consumption
boolean (X-Show-Consumption)
Default: false
x-ndb-client
string (NucliaDBClientType)
Default: api
Enum: "api" "widget" "web" "dashboard" "desktop" "chrome_extension"
x-nucliadb-user
string (X-Nucliadb-User)
Default:
x-forwarded-for
string (X-Forwarded-For)
Default:
x-synchronous
boolean (X-Synchronous)
Default: false

When set to true, outputs response as JSON in a non-streaming way. This is slower and requires waiting for entire answer to be ready.

Request Body schema: application/json
required
Audit metadata (object) or Audit metadata (null) (Audit metadata)

A dictionary containing optional audit-specific metadata, such as user_id, environment, or other contextual information. This metadata can be leveraged for filtering and analyzing activity logs in future operations. Each key-value pair represents a piece of metadata relevant to the user's request.

query
required
string (Query) <= 20000 characters

The query to get a generative answer for

top_k
integer (Top k) [ 1 .. 200 ]
Default: 20

The top most relevant results to fetch at the retrieval step. The maximum number of results allowed is 200.

FilterExpression (object) or Filter resource by an expression (null) (Filter resource by an expression)

Returns only documents that match this filter expression.Filtering examples can be found here: https://docs.nuclia.dev/docs/rag/advanced/search-filters This allows building complex filtering expressions and replaces the following parameters:fields, filters, range_*, resource_filters, keyword_filters.

fields
Array of strings (Fields)
Default: []

The list of fields to search in. For instance: a/title to search only on title field. For more details on filtering by field, see: https://docs.nuclia.dev/docs/rag/advanced/search/#search-in-a-specific-field.

Array of Search Filters (strings) or Array of Search Filters (objects) (Search Filters)
Default: []

The list of filters to apply. Filtering examples can be found here: https://docs.nuclia.dev/docs/rag/advanced/search-filters

Array of Keyword filters (strings) or Array of Keyword filters (objects) (Keyword filters)
Default: []

List of keyword filter expressions to apply to the retrieval step. The text block search will only be performed on the documents that contain the specified keywords. The filters are case-insensitive, and only alphanumeric characters and spaces are allowed. Filtering examples can be found here: https://docs.nuclia.dev/docs/rag/advanced/search-filters

Vectorset (string) or Vectorset (null) (Vectorset)

Vectors index to perform the search in. If not provided, NucliaDB will use the default one

Minimum score (number) or MinScore (object) or Minimum score (null) (Minimum score)

Minimum score to filter search results. Results with a lower score will be ignored. Accepts either a float or a dictionary with the minimum scores for the bm25 and vector indexes. If a float is provided, it is interpreted as the minimum score for vector index search.

features
Array of strings (Chat features)
Default: ["semantic","keyword"]
Items Enum: "keyword" "relations" "semantic"

Features enabled for the chat endpoint. Semantic search is done if semantic is included. If keyword is included, the results will include matching paragraphs from the bm25 index. If relations is included, a graph of entities related to the answer is returned. paragraphs and vectors are deprecated, please use keyword and semantic instead

Resource creation range start (string) or Resource creation range start (null) (Resource creation range start)

Resources created before this date will be filtered out of search results. Datetime are represented as a str in ISO 8601 format, like: 2008-09-15T15:53:00+05:00.

Resource creation range end (string) or Resource creation range end (null) (Resource creation range end)

Resources created after this date will be filtered out of search results. Datetime are represented as a str in ISO 8601 format, like: 2008-09-15T15:53:00+05:00.

Resource modification range start (string) or Resource modification range start (null) (Resource modification range start)

Resources modified before this date will be filtered out of search results. Datetime are represented as a str in ISO 8601 format, like: 2008-09-15T15:53:00+05:00.

Resource modification range end (string) or Resource modification range end (null) (Resource modification range end)

Resources modified after this date will be filtered out of search results. Datetime are represented as a str in ISO 8601 format, like: 2008-09-15T15:53:00+05:00.

show
Array of strings (Show metadata)
Default: ["basic"]
Items Enum: "basic" "origin" "extra" "relations" "values" "extracted" "errors" "security"

Controls which types of metadata are serialized on resources of search results

field_type_filter
Array of strings (Field type filter)
Default: ["text","file","link","conversation","generic"]
Items Enum: "text" "file" "link" "conversation" "generic"

Define which field types are serialized on resources of search results

extracted
Array of strings (Extracted metadata)
Deprecated
Default: []
Items Enum: "text" "metadata" "shortened_metadata" "large_metadata" "vectors" "link" "file" "question_answers" "relation_vectors"

[Deprecated] Please use GET resource endpoint instead to get extracted metadata

Array of Chat context (deprecated) (objects) or Chat context (deprecated) (null) (Chat context (deprecated))
Deprecated

DEPRECATED! Please, use chat_history instead.

Array of Chat history (objects) or Chat history (null) (Chat history)

Use to rephrase the new LLM query by taking into account the chat conversation history. This will be passed to the LLM so that it is aware of the previous conversation.

Array of Extra query context (strings) or Extra query context (null) (Extra query context)

Additional context that is added to the retrieval context sent to the LLM. It allows extending the chat feature with content that may not be in the Knowledge Box.

Array of Extra query context images (objects) or Extra query context images (null) (Extra query context images)

Additional images added to the retrieval context sent to the LLM." It allows extending the chat feature with content that may not be in the Knowledge Box.

Image (object) or Query image (null) (Query image)

Image that will be used together with the query text for retrieval and then sent to the LLM as part of the context. If a query image is provided, the extra_context_images and rag_images_strategies will be disabled.

highlight
boolean (Highlight)
Default: false

If set to true, the query terms will be highlighted in the results between ... tags

resource_filters
Array of strings (Resources filter)
Default: []

List of resource ids to filter search results for. Only paragraphs from the specified resources will be returned.

Prompts (string) or CustomPrompt (object) or Prompts (null) (Prompts)

Use to customize the prompts given to the generative model. Both system and user prompts can be customized. If a string is provided, it is interpreted as the user prompt.

RankFusionName (string) or Rank fusion (any) (Rank fusion)
Default: "rrf"

Rank fusion algorithm to use to merge results from multiple retrievers (keyword, semantic)

RerankerName (string) or Reranker (any) (Reranker)
Default: "predict"

Reranker let you specify which method you want to use to rerank your results at the end of retrieval

Citations (boolean) or CitationsType (string) or Citations (null) (Citations)

Whether to include citations in the response. If set to None or False, no citations will be computed. If set to True or 'default', citations will be computed after answer generation and send as a separate CitationsGenerativeResponse chunk. If set to 'llm_footnotes', citations will be included in the LLM's response as markdown-styled footnotes. A FootnoteCitationsGenerativeResponse chunk will also be sent to map footnote ids to context keys in the query_context.

Citation Threshold (number) or Citation Threshold (null) (Citation Threshold)

If citations is set to True or 'default', this will be the similarity threshold. Value between 0 and 1, lower values will produce more citations. If not set, it will be set to the optimized threshold found by Nuclia.

RequestSecurity (object) or Security (null) (Security)

Security metadata for the request. If not provided, the search request is done without the security lookup phase.

show_hidden
boolean (Show hidden resources)
Default: false

If set to false (default), excludes hidden resources from search

Array of any (RAG context building strategies)
Default: []

Options for tweaking how the context for the LLM model is crafted:

  • full_resource will add the full text of the matching resources to the context. This strategy cannot be combined with hierarchy, neighbouring_paragraphs, or field_extension.
  • field_extension will add the text of the matching resource's specified fields to the context.
  • hierarchy will add the title and summary text of the parent resource to the context for each matching paragraph.
  • neighbouring_paragraphs will add the sorrounding paragraphs to the context for each matching paragraph.
  • metadata_extension will add the metadata of the matching paragraphs or its resources to the context.
  • prequeries allows to run multiple retrieval queries before the main query and add the results to the context. The results of specific queries can be boosted by the specifying weights.

If empty, the default strategy is used, which simply adds the text of the matching paragraphs to the context.

Array of any (RAG image context building strategies)
Default: []

Options for tweaking how the image based context for the LLM model is crafted:

  • page_image will add the full page image of the matching resources to the context.
  • tables will send the table images for the paragraphs that contain tables and matched the retrieval query.
  • paragraph_image will add the images of the paragraphs that contain images (images for tables are not included). No image strategy is used by default. Note that this is only available for LLM models that support visual inputs. If the model does not support visual inputs, the image strategies will be ignored.
debug
boolean (Debug mode)
Default: false

If set, the response will include some extra metadata for debugging purposes, like the list of queried nodes.

Generative model (string) or Generative model (null) (Generative model)

The generative model to use for the chat endpoint. If not provided, the model configured for the Knowledge Box is used.

Seed for the generative model (integer) or Seed for the generative model (null) (Seed for the generative model)

The seed to use for the generative model for deterministic generation. Only supported by some models.

Maximum LLM tokens to use for the request (integer) or MaxTokens (object) or Maximum LLM tokens to use for the request (null) (Maximum LLM tokens to use for the request)

Use to limit the amount of tokens used in the LLM context and/or for generating the answer. If not provided, the default maximum tokens of the generative model will be used. If an integer is provided, it is interpreted as the maximum tokens for the answer.

rephrase
boolean (Rephrase)
Default: false

Rephrase the query for a more efficient retrieval. This will consume LLM tokens and make the request slower.

Chat History Relevance Threshold (number) or Chat History Relevance Threshold (null) (Chat History Relevance Threshold)

Threshold to determine if the past chat history is relevant to rephrase the user's question. 0 - Always treat previous messages as relevant (always rephrase).1 - Always treat previous messages as irrelevant (never rephrase).Values in between adjust the sensitivity.

prefer_markdown
boolean (Prefer markdown)
Default: false

If set to true, the response will be in markdown format

Answer JSON schema (object) or Answer JSON schema (null) (Answer JSON schema)

Desired JSON schema for the LLM answer. This schema is passed to the LLM so that it answers in a scructured format following the schema. If not provided, textual response is returned. Note that when using this parameter, the answer in the generative response will not be returned in chunks, the whole response text will be returned instead. Using this feature also disables the citations parameter. For maximal accuracy, please include a description for each field of the schema.

generate_answer
boolean (Generate Answer)
Default: true

Whether to generate an answer using the generative model. If set to false, the response will only contain the retrieval results.

Search Configuration (string) or Search Configuration (null) (Search Configuration)

Load ask parameters from this configuration. Parameters in the request override parameters from the configuration.

Reasoning (object) or Reasoning options (boolean) (Reasoning options)
Default: false

Reasoning options for the generative model. Set to True to enable default reasoning, False to disable, or provide a Reasoning object for custom options.

Responses

Request samples

Content type
application/json
{
  • "audit_metadata": {
    },
  • "query": "string",
  • "top_k": 20,
  • "filter_expression": {
    },
  • "fields": [ ],
  • "filters": [ ],
  • "keyword_filters": [
    ],
  • "vectorset": "string",
  • "min_score": 0,
  • "features": [
    ],
  • "range_creation_start": "2019-08-24T14:15:22Z",
  • "range_creation_end": "2019-08-24T14:15:22Z",
  • "range_modification_start": "2019-08-24T14:15:22Z",
  • "range_modification_end": "2019-08-24T14:15:22Z",
  • "show": [
    ],
  • "field_type_filter": [
    ],
  • "extracted": [ ],
  • "context": [
    ],
  • "chat_history": [
    ],
  • "extra_context": [
    ],
  • "extra_context_images": [
    ],
  • "query_image": {
    },
  • "highlight": false,
  • "resource_filters": [ ],
  • "prompt": "string",
  • "rank_fusion": "rrf",
  • "reranker": "predict",
  • "citations": true,
  • "citation_threshold": 1,
  • "security": {
    },
  • "show_hidden": false,
  • "rag_strategies": [
    ],
  • "rag_images_strategies": [ ],
  • "debug": false,
  • "generative_model": "string",
  • "generative_model_seed": 0,
  • "max_tokens": 0,
  • "rephrase": false,
  • "chat_history_relevance_threshold": 1,
  • "prefer_markdown": false,
  • "answer_json_schema": {
    },
  • "generate_answer": true,
  • "search_configuration": "string",
  • "reasoning": false
}

Response samples

Content type
application/json
{
  • "answer": "string",
  • "reasoning": "string",
  • "answer_json": { },
  • "status": "string",
  • "retrieval_results": {
    },
  • "retrieval_best_matches": [ ],
  • "prequeries": {
    },
  • "learning_id": "",
  • "relations": {
    },
  • "citations": { },
  • "citation_footnote_to_context": {
    },
  • "augmented_context": {
    },
  • "prompt_context": [
    ],
  • "predict_request": { },
  • "metadata": {
    },
  • "consumption": {
    },
  • "error_details": "string",
  • "debug": { }
}

split Strategies

Learning Split Strategies

Get available split strategies onprem

path Parameters
kbid
required
string (Kbid)

Responses

Response samples

Content type
application/json
{
  • "property1": {
    },
  • "property2": {
    }
}

Add A Split Strategy To A Kb Onprem

Add a split strategy to a KB to be used

path Parameters
kbid
required
string (Kbid)
Request Body schema: application/json
required
name
string (Name)
Default: ""
max_paragraph
integer (Max Paragraph)
Default: 0
CustomSplitStrategy (integer) or null
Default: 0
LLMSplitConfig (object) or null
ManualSplitConfig (object) or null

Responses

Request samples

Content type
application/json
{
  • "name": "",
  • "max_paragraph": 0,
  • "custom_split": 0,
  • "llm_split": {
    },
  • "manual_split": {
    }
}

Response samples

Content type
application/json
"string"

Split Strategy Configuration

Get split strategy for a given id

path Parameters
kbid
required
string (Kbid)
strategy_id
required
string (Strategy Id)

Responses

Response samples

Content type
application/json
{
  • "name": "",
  • "max_paragraph": 0,
  • "custom_split": 0,
  • "llm_split": {
    },
  • "manual_split": {
    }
}

Disable Split Strategy Onprem

Disable a split strategy from a Knowledge Box

path Parameters
kbid
required
string (Kbid)
strategy_id
required
string (Strategy Id)

Responses

Response samples

Content type
application/json
null