Nuclia Understanding API (v1)
API reference for the Nuclia Understanding API.
Get Processed Activity Log
Get latest events related to activity of a Nuclia Understanding API client
query Parameters
page | integer (Page) Default: 0 |
size | integer (Size) Default: 50 |
Responses
Response samples
- 200
- 422
{- "events": [
- { }
], - "pagination": {
- "page": 0,
- "size": 0,
- "last": true
}
}
Pull
Pull internal message on a partition
query Parameters
timeout | integer (Timeout) Default: 5 |
partition | integer (Partition) Default: 1 |
from_cursor | integer (From Cursor) |
limit | integer (Limit) Default: 5 |
Responses
Response samples
- 200
- 422
{- "status": "ok",
- "payload": "string",
- "payloads": [ ],
- "msgid": "string",
- "cursor": 0
}
Send Data To Process
Push data to process
Request Body schema: application/jsonrequired
kbid | string (Kbid) |
uuid | string (Uuid) |
title | string (Title) |
labels | Array of strings (Labels) Default: [] |
slug | string (Slug) |
source | integer (Source) Enum: 0 1 An enumeration. |
userid | string (Userid) |
object (Genericfield) Default: {} | |
object (Filefield) Default: {} | |
object (Linkfield) Default: {} | |
object (Textfield) Default: {} | |
object (Layoutfield) Default: {} | |
object (Conversationfield) Default: {} | |
object (PushProcessingOptions) | |
object (LearningConfig) | |
object (WebhookConfig) |
Responses
Request samples
- Payload
{- "kbid": "string",
- "uuid": "string",
- "title": "string",
- "labels": [ ],
- "slug": "string",
- "source": 0,
- "userid": "string",
- "genericfield": { },
- "filefield": { },
- "linkfield": { },
- "textfield": { },
- "layoutfield": { },
- "conversationfield": { },
- "processing_options": {
- "ml_text": true
}, - "learning_config": {
- "semantic_model": "string",
- "generative_model": "string",
- "ner_model": "string",
- "anonymization_model": "string",
- "visual_labeling": "string"
}, - "webhook_config": {
- "uri": "string",
- "headers": { }
}
}
Response samples
- 200
- 422
{- "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 (Cursor) |
limit | integer (Limit) Default: 20 |
scheduled | boolean (Scheduled) |
kbid | string (Kbid) |
sort_on | string (SortFields) Default: "timestamp" Enum: "timestamp" "scheduled_at" "completed_at" An enumeration. |
sort_order | string (SortOrder) Default: "asc" Enum: "asc" "desc" An enumeration. |
Responses
Response samples
- 200
- 422
{- "results": [
- {
- "processing_id": "string",
- "resource_id": "string",
- "kbid": "string",
- "title": "string",
- "labels": [
- "string"
], - "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"
}
], - "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
- 200
- 422
{- "processing_id": "string",
- "resource_id": "string",
- "kbid": "string",
- "title": "string",
- "labels": [
- "string"
], - "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"
}
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
- 200
- 422
null
Add A Model To A Kb
Add a model to a KB to be used
path Parameters
account_id required | string (Account Id) |
kbid required | string (Kbid) |
Request Body schema: application/jsonrequired
id required | string (Id) |
Responses
Request samples
- Payload
{- "id": "string"
}
Response samples
- 200
- 422
null
Knowledgebox Models Configuration
Current configuration of models assigned to a knowledgebox
path Parameters
kbid required | string (Kbid) |
Responses
Response samples
- 200
- 422
{- "resource_labelers_models": [
- "string"
], - "paragraph_labelers_models": [
- "string"
], - "intent_models": [
- "string"
], - "semantic_model": "multilingual-2023-02-21",
- "anonymization_model": "disabled",
- "generative_model": "chatgpt-azure-3",
- "ner_model": "multilingual",
- "relation_model": "base",
- "visual_labeling": "disabled",
- "user_keys": {
- "openai": {
- "key": "string",
- "org": "string"
}, - "azure_openai": {
- "key": "string",
- "url": "string",
- "deployment": "string",
- "model": "string"
}, - "mistral": {
- "key": "string"
}, - "palm": {
- "credentials": "string",
- "location": "string"
}, - "anthropic": {
- "key": "string"
}, - "azure_mistral": {
- "key": "string"
}
}, - "user_prompts": {
- "openai": {
- "system": "You are a medical assistant, use medical terminology",
- "prompt": "Taking into account our previous conversation, and this context: {context} answer this {question}"
}, - "azure_openai": {
- "system": "You are a medical assistant, use medical terminology",
- "prompt": "Taking into account our previous conversation, and this context: {context} answer this {question}"
}, - "palm": {
- "prompt": "Answer my question in an informal tone, based only in this context: {context}. Question: {question}"
}, - "anthropic": {
- "prompt": "Taking into account our chat history: {chat_history} and this provided context: <Context> {context} </Context>\n Can you answer this question in a clear, concise way: <Question> {question} </Question>"
}, - "claude3": {
- "system": "You are a medical assistant, use medical terminology",
- "prompt": "Taking into account our previous conversation, and this context: {context} answer this {question}"
}, - "text_generation": {
- "prompt": "Taking into account our chat history: {chat_history} and this provided context: {context}, answer this question: \"{question}\" :"
}, - "mistral": {
- "prompt": "Taking into account our chat history: {chat_history} and this provided context: <Context> {context} </Context>\n Can you answer this question in a clear, concise way: <Question> {question} </Question>"
}, - "azure_mistral": {
- "prompt": "Taking into account this provided context: <Context> {context} </Context>\n Can you answer this question in a clear, concise way: <Question> {question} </Question>"
}
}, - "semantic_vector_similarity": "dot",
- "semantic_vector_size": 768,
- "semantic_matryoshka_dims": [ ],
- "semantic_threshold": 1.5,
- "summary": "simple",
- "summary_model": "chatgpt-azure-3",
- "summary_prompt": {
- "prompt": "Make a bullet point summary of the following content: {text}"
}
}
Knowledgebox Models Add Configuration
Current configuration of models assigned to a knowledgebox
path Parameters
kbid required | string (Kbid) |
Request Body schema: application/jsonrequired
AnonymizationModel (string) or Anonymization Model (string) (Anonymization Model) Default: "disabled" | |
VisualLabeling (string) or Visual Labeling (string) (Visual Labeling) Default: "disabled" | |
GenerativeModel (string) or Generative Model (string) (Generative Model) Default: "chatgpt-azure-3" | |
NERModel (string) or Ner Model (string) (Ner Model) Default: "multilingual" | |
RelationModel (string) or Relation Model (string) (Relation Model) Default: "base" | |
object (UserLearningKeys) | |
object (UserPrompts) | |
summary | string (Summary) Default: "simple" Enum: "extended" "simple" An enumeration. |
GenerativeModel (string) or Summary Model (string) (Summary Model) Default: "anthropic" | |
object (SummaryPrompt) | |
resource_labelers_models | Array of strings (Resource Labelers Models) |
paragraph_labelers_models | Array of strings (Paragraph Labelers Models) |
intent_models | Array of strings (Intent Models) |
semantic_model | string (SemanticModel) Default: "multilingual-2023-02-21" Enum: "en" "bge-large-en-v1-5" "multilingual-2023-02-21" "multilingual-2023-08-16" "text-embedding-3-small" "text-embedding-3-large" "gecko-embeddings-multi" An enumeration. |
Responses
Request samples
- Payload
{- "anonymization_model": "disabled",
- "visual_labeling": "disabled",
- "generative_model": "chatgpt-azure-3",
- "ner_model": "multilingual",
- "relation_model": "base",
- "user_keys": {
- "openai": {
- "key": "string",
- "org": "string"
}, - "azure_openai": {
- "key": "string",
- "url": "string",
- "deployment": "string",
- "model": "string"
}, - "mistral": {
- "key": "string"
}, - "palm": {
- "credentials": "string",
- "location": "string"
}, - "anthropic": {
- "key": "string"
}, - "azure_mistral": {
- "key": "string"
}
}, - "user_prompts": {
- "openai": {
- "system": "You are a medical assistant, use medical terminology",
- "prompt": "Taking into account our previous conversation, and this context: {context} answer this {question}"
}, - "azure_openai": {
- "system": "You are a medical assistant, use medical terminology",
- "prompt": "Taking into account our previous conversation, and this context: {context} answer this {question}"
}, - "palm": {
- "prompt": "Answer my question in an informal tone, based only in this context: {context}. Question: {question}"
}, - "anthropic": {
- "prompt": "Taking into account our chat history: {chat_history} and this provided context: <Context> {context} </Context>\n Can you answer this question in a clear, concise way: <Question> {question} </Question>"
}, - "claude3": {
- "system": "You are a medical assistant, use medical terminology",
- "prompt": "Taking into account our previous conversation, and this context: {context} answer this {question}"
}, - "text_generation": {
- "prompt": "Taking into account our chat history: {chat_history} and this provided context: {context}, answer this question: \"{question}\" :"
}, - "mistral": {
- "prompt": "Taking into account our chat history: {chat_history} and this provided context: <Context> {context} </Context>\n Can you answer this question in a clear, concise way: <Question> {question} </Question>"
}, - "azure_mistral": {
- "prompt": "Taking into account this provided context: <Context> {context} </Context>\n Can you answer this question in a clear, concise way: <Question> {question} </Question>"
}
}, - "summary": "simple",
- "summary_model": "anthropic",
- "summary_prompt": {
- "prompt": "Make a bullet point summary of the following content: {text}"
}, - "resource_labelers_models": [
- "string"
], - "paragraph_labelers_models": [
- "string"
], - "intent_models": [
- "string"
], - "semantic_model": "multilingual-2023-02-21"
}
Response samples
- 200
- 422
{- "resource_labelers_models": [
- "string"
], - "paragraph_labelers_models": [
- "string"
], - "intent_models": [
- "string"
], - "semantic_model": "multilingual-2023-02-21",
- "anonymization_model": "disabled",
- "generative_model": "chatgpt-azure-3",
- "ner_model": "multilingual",
- "relation_model": "base",
- "visual_labeling": "disabled",
- "user_keys": {
- "openai": {
- "key": "string",
- "org": "string"
}, - "azure_openai": {
- "key": "string",
- "url": "string",
- "deployment": "string",
- "model": "string"
}, - "mistral": {
- "key": "string"
}, - "palm": {
- "credentials": "string",
- "location": "string"
}, - "anthropic": {
- "key": "string"
}, - "azure_mistral": {
- "key": "string"
}
}, - "user_prompts": {
- "openai": {
- "system": "You are a medical assistant, use medical terminology",
- "prompt": "Taking into account our previous conversation, and this context: {context} answer this {question}"
}, - "azure_openai": {
- "system": "You are a medical assistant, use medical terminology",
- "prompt": "Taking into account our previous conversation, and this context: {context} answer this {question}"
}, - "palm": {
- "prompt": "Answer my question in an informal tone, based only in this context: {context}. Question: {question}"
}, - "anthropic": {
- "prompt": "Taking into account our chat history: {chat_history} and this provided context: <Context> {context} </Context>\n Can you answer this question in a clear, concise way: <Question> {question} </Question>"
}, - "claude3": {
- "system": "You are a medical assistant, use medical terminology",
- "prompt": "Taking into account our previous conversation, and this context: {context} answer this {question}"
}, - "text_generation": {
- "prompt": "Taking into account our chat history: {chat_history} and this provided context: {context}, answer this question: \"{question}\" :"
}, - "mistral": {
- "prompt": "Taking into account our chat history: {chat_history} and this provided context: <Context> {context} </Context>\n Can you answer this question in a clear, concise way: <Question> {question} </Question>"
}, - "azure_mistral": {
- "prompt": "Taking into account this provided context: <Context> {context} </Context>\n Can you answer this question in a clear, concise way: <Question> {question} </Question>"
}
}, - "semantic_vector_similarity": "dot",
- "semantic_vector_size": 768,
- "semantic_matryoshka_dims": [ ],
- "semantic_threshold": 1.5,
- "summary": "simple",
- "summary_model": "chatgpt-azure-3",
- "summary_prompt": {
- "prompt": "Make a bullet point summary of the following content: {text}"
}
}
Knowledgebox Models Update Configuration
Current configuration of models assigned to a knowledgebox
path Parameters
kbid required | string (Kbid) |
Request Body schema: application/jsonrequired
AnonymizationModel (string) or Anonymization Model (string) (Anonymization Model) Default: "disabled" | |
VisualLabeling (string) or Visual Labeling (string) (Visual Labeling) Default: "disabled" | |
GenerativeModel (string) or Generative Model (string) (Generative Model) Default: "chatgpt-azure-3" | |
NERModel (string) or Ner Model (string) (Ner Model) Default: "multilingual" | |
RelationModel (string) or Relation Model (string) (Relation Model) Default: "base" | |
object (UserLearningKeys) | |
object (UserPrompts) | |
summary | string (Summary) Default: "simple" Enum: "extended" "simple" An enumeration. |
GenerativeModel (string) or Summary Model (string) (Summary Model) Default: "anthropic" | |
object (SummaryPrompt) | |
resource_labelers_models | Array of strings (Resource Labelers Models) |
paragraph_labelers_models | Array of strings (Paragraph Labelers Models) |
intent_models | Array of strings (Intent Models) |
Responses
Request samples
- Payload
{- "anonymization_model": "disabled",
- "visual_labeling": "disabled",
- "generative_model": "chatgpt-azure-3",
- "ner_model": "multilingual",
- "relation_model": "base",
- "user_keys": {
- "openai": {
- "key": "string",
- "org": "string"
}, - "azure_openai": {
- "key": "string",
- "url": "string",
- "deployment": "string",
- "model": "string"
}, - "mistral": {
- "key": "string"
}, - "palm": {
- "credentials": "string",
- "location": "string"
}, - "anthropic": {
- "key": "string"
}, - "azure_mistral": {
- "key": "string"
}
}, - "user_prompts": {
- "openai": {
- "system": "You are a medical assistant, use medical terminology",
- "prompt": "Taking into account our previous conversation, and this context: {context} answer this {question}"
}, - "azure_openai": {
- "system": "You are a medical assistant, use medical terminology",
- "prompt": "Taking into account our previous conversation, and this context: {context} answer this {question}"
}, - "palm": {
- "prompt": "Answer my question in an informal tone, based only in this context: {context}. Question: {question}"
}, - "anthropic": {
- "prompt": "Taking into account our chat history: {chat_history} and this provided context: <Context> {context} </Context>\n Can you answer this question in a clear, concise way: <Question> {question} </Question>"
}, - "claude3": {
- "system": "You are a medical assistant, use medical terminology",
- "prompt": "Taking into account our previous conversation, and this context: {context} answer this {question}"
}, - "text_generation": {
- "prompt": "Taking into account our chat history: {chat_history} and this provided context: {context}, answer this question: \"{question}\" :"
}, - "mistral": {
- "prompt": "Taking into account our chat history: {chat_history} and this provided context: <Context> {context} </Context>\n Can you answer this question in a clear, concise way: <Question> {question} </Question>"
}, - "azure_mistral": {
- "prompt": "Taking into account this provided context: <Context> {context} </Context>\n Can you answer this question in a clear, concise way: <Question> {question} </Question>"
}
}, - "summary": "simple",
- "summary_model": "anthropic",
- "summary_prompt": {
- "prompt": "Make a bullet point summary of the following content: {text}"
}, - "resource_labelers_models": [
- "string"
], - "paragraph_labelers_models": [
- "string"
], - "intent_models": [
- "string"
]
}
Response samples
- 200
- 422
{- "resource_labelers_models": [
- "string"
], - "paragraph_labelers_models": [
- "string"
], - "intent_models": [
- "string"
], - "semantic_model": "multilingual-2023-02-21",
- "anonymization_model": "disabled",
- "generative_model": "chatgpt-azure-3",
- "ner_model": "multilingual",
- "relation_model": "base",
- "visual_labeling": "disabled",
- "user_keys": {
- "openai": {
- "key": "string",
- "org": "string"
}, - "azure_openai": {
- "key": "string",
- "url": "string",
- "deployment": "string",
- "model": "string"
}, - "mistral": {
- "key": "string"
}, - "palm": {
- "credentials": "string",
- "location": "string"
}, - "anthropic": {
- "key": "string"
}, - "azure_mistral": {
- "key": "string"
}
}, - "user_prompts": {
- "openai": {
- "system": "You are a medical assistant, use medical terminology",
- "prompt": "Taking into account our previous conversation, and this context: {context} answer this {question}"
}, - "azure_openai": {
- "system": "You are a medical assistant, use medical terminology",
- "prompt": "Taking into account our previous conversation, and this context: {context} answer this {question}"
}, - "palm": {
- "prompt": "Answer my question in an informal tone, based only in this context: {context}. Question: {question}"
}, - "anthropic": {
- "prompt": "Taking into account our chat history: {chat_history} and this provided context: <Context> {context} </Context>\n Can you answer this question in a clear, concise way: <Question> {question} </Question>"
}, - "claude3": {
- "system": "You are a medical assistant, use medical terminology",
- "prompt": "Taking into account our previous conversation, and this context: {context} answer this {question}"
}, - "text_generation": {
- "prompt": "Taking into account our chat history: {chat_history} and this provided context: {context}, answer this question: \"{question}\" :"
}, - "mistral": {
- "prompt": "Taking into account our chat history: {chat_history} and this provided context: <Context> {context} </Context>\n Can you answer this question in a clear, concise way: <Question> {question} </Question>"
}, - "azure_mistral": {
- "prompt": "Taking into account this provided context: <Context> {context} </Context>\n Can you answer this question in a clear, concise way: <Question> {question} </Question>"
}
}, - "semantic_vector_similarity": "dot",
- "semantic_vector_size": 768,
- "semantic_matryoshka_dims": [ ],
- "semantic_threshold": 1.5,
- "summary": "simple",
- "summary_model": "chatgpt-azure-3",
- "summary_prompt": {
- "prompt": "Make a bullet point summary of the following content: {text}"
}
}
Learning Configuration Schema
Get jsonschema definition for learning_configuration
field of knowledgebox creation payload
Responses
Response samples
- 200
- 422
{- "resource_labelers_models": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "paragraph_labelers_models": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "intent_models": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "semantic_model": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "anonymization_model": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "visual_labeling": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "generative_model": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "ner_model": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "relation_model": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "summary_model": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "summary": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "user_keys": {
- "schemas": { },
- "create": false,
- "update": false
}, - "user_prompts": {
- "schemas": { },
- "create": false,
- "update": false
}, - "summary_prompt": {
- "schemas": { },
- "create": false,
- "update": false
}
}
Learning Configuration Schema
Get jsonschema definition for learning_configuration
field of knowledgebox creation payload
Responses
Response samples
- 200
- 422
{- "resource_labelers_models": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "paragraph_labelers_models": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "intent_models": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "semantic_model": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "anonymization_model": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "visual_labeling": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "generative_model": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "ner_model": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "relation_model": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "summary_model": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "summary": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "user_keys": {
- "schemas": { },
- "create": false,
- "update": false
}, - "user_prompts": {
- "schemas": { },
- "create": false,
- "update": false
}, - "summary_prompt": {
- "schemas": { },
- "create": false,
- "update": false
}
}
Learning Configuration Schema
Get jsonschema definition for learning_configuration
field of knowledgebox update payload
path Parameters
kbid required | string (Kbid) |
Responses
Response samples
- 200
- 422
{- "resource_labelers_models": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "paragraph_labelers_models": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "intent_models": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "semantic_model": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "anonymization_model": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "visual_labeling": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "generative_model": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "ner_model": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "relation_model": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "summary_model": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "summary": {
- "options": [
- {
- "name": "string",
- "value": "string",
- "user_prompt": "string",
- "user_key": "string"
}
], - "default": "string",
- "create": false,
- "update": false,
- "multiple": false
}, - "user_keys": {
- "schemas": { },
- "create": false,
- "update": false
}, - "user_prompts": {
- "schemas": { },
- "create": false,
- "update": false
}, - "summary_prompt": {
- "schemas": { },
- "create": false,
- "update": false
}
}
Predict Chat
Chat interface for your NucliaDB
query Parameters
model | string (Model) Default: "chatgpt-azure-3" |
Request Body schema: application/jsonrequired
question required | string (Question) |
retrieval | boolean (Retrieval) Default: true |
user_id required | string (User Id) |
system | string (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 (Truncate) Default: false |
object (UserPrompt) | |
citations | boolean (Citations) Default: false |
generative_model | string (Generative Model) |
max_tokens | integer (Max Tokens) |
Array of Query Context Images (objects) or Query Context Images (object) (Query Context Images) Default: {} |
Responses
Request samples
- Payload
{- "question": "string",
- "retrieval": true,
- "user_id": "string",
- "system": "string",
- "chat_history": [ ],
- "context": [ ],
- "query_context": { },
- "query_context_order": { },
- "truncate": false,
- "user_prompt": {
- "prompt": "string"
}, - "citations": false,
- "generative_model": "string",
- "max_tokens": 0,
- "query_context_images": { }
}
Response samples
- 200
- 422
null
Predict Chat Kbid
Chat interface for your NucliaDB
path Parameters
kbid required | string (Kbid) |
Request Body schema: application/jsonrequired
question required | string (Question) |
retrieval | boolean (Retrieval) Default: true |
user_id required | string (User Id) |
system | string (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 (Truncate) Default: false |
object (UserPrompt) | |
citations | boolean (Citations) Default: false |
generative_model | string (Generative Model) |
max_tokens | integer (Max Tokens) |
Array of Query Context Images (objects) or Query Context Images (object) (Query Context Images) Default: {} |
Responses
Request samples
- Payload
{- "question": "string",
- "retrieval": true,
- "user_id": "string",
- "system": "string",
- "chat_history": [ ],
- "context": [ ],
- "query_context": { },
- "query_context_order": { },
- "truncate": false,
- "user_prompt": {
- "prompt": "string"
}, - "citations": false,
- "generative_model": "string",
- "max_tokens": 0,
- "query_context_images": { }
}
Response samples
- 200
- 422
null
Predict Feedback
Get feedback
query Parameters
model required | string (Model) |
Request Body schema: application/jsonrequired
ident required | string (Ident) |
good required | boolean (Good) |
task required | string (FeedbackTasks) Enum: "CHAT" "SUMMARY" An enumeration. |
feedback | string (Feedback) |
user_id | string (User Id) |
client | string (Client) |
forwarded | string (Forwarded) |
Responses
Request samples
- Payload
{- "ident": "string",
- "good": true,
- "task": "CHAT",
- "feedback": "string",
- "user_id": "string",
- "client": "string",
- "forwarded": "string"
}
Response samples
- 422
{- "detail": [
- {
- "loc": [
- "string"
], - "msg": "string",
- "type": "string"
}
]
}
Predict Feedback Kbid
Get feedback
path Parameters
kbid required | string (Kbid) |
Request Body schema: application/jsonrequired
ident required | string (Ident) |
good required | boolean (Good) |
task required | string (FeedbackTasks) Enum: "CHAT" "SUMMARY" An enumeration. |
feedback | string (Feedback) |
user_id | string (User Id) |
client | string (Client) |
forwarded | string (Forwarded) |
Responses
Request samples
- Payload
{- "ident": "string",
- "good": true,
- "task": "CHAT",
- "feedback": "string",
- "user_id": "string",
- "client": "string",
- "forwarded": "string"
}
Response samples
- 422
{- "detail": [
- {
- "loc": [
- "string"
], - "msg": "string",
- "type": "string"
}
]
}
Predict Query
Get the vector of a sentence
query Parameters
text required | string (Text) |
semantic_model | string (Semantic Model) Default: "multilingual-2023-02-21" |
token_model | string (Token Model) Default: "multilingual" |
generative_model | string (Generative Model) Default: "chatgpt-azure-3" |
rephrase | boolean (Rephrase) Default: false |
Responses
Response samples
- 200
- 422
{- "language": "string",
- "stop_words": [
- "string"
], - "semantic_threshold": 0,
- "visual_llm": true,
- "max_context": 0,
- "entities": {
- "tokens": [ ],
- "time": 0
}, - "sentence": {
- "data": [ ],
- "time": 0
}, - "query": "string"
}
Predict Query Kbid
Get the vector of a sentence
path Parameters
kbid required | string (Kbid) |
query Parameters
text required | string (Text) |
generative_model | string (Generative Model) Default: "chatgpt-azure-3" |
rephrase | boolean (Rephrase) Default: false |
Responses
Response samples
- 200
- 422
{- "language": "string",
- "stop_words": [
- "string"
], - "semantic_threshold": 0,
- "visual_llm": true,
- "max_context": 0,
- "entities": {
- "tokens": [ ],
- "time": 0
}, - "sentence": {
- "data": [ ],
- "time": 0
}, - "query": "string"
}
Predict Rephrase
Rephrase interface for your NucliaDB
query Parameters
model | string (Model) Default: "chatgpt-azure-3" |
Request Body schema: application/jsonrequired
question required | string (Question) |
Array of objects (Chat History) Default: [] | |
Array of objects (Context) Default: [] | |
user_context | Array of strings (User Context) Default: [] |
user_id required | string (User Id) |
generative_model | string (Generative Model) |
Responses
Request samples
- Payload
{- "question": "string",
- "chat_history": [ ],
- "context": [ ],
- "user_context": [ ],
- "user_id": "string",
- "generative_model": "string"
}
Response samples
- 200
- 422
"string"
Predict Rephrase Kbid
Rephrase interface for your NucliaDB with Container
path Parameters
kbid required | string (Kbid) |
Request Body schema: application/jsonrequired
question required | string (Question) |
Array of objects (Chat History) Default: [] | |
Array of objects (Context) Default: [] | |
user_context | Array of strings (User Context) Default: [] |
user_id required | string (User Id) |
generative_model | string (Generative Model) |
Responses
Request samples
- Payload
{- "question": "string",
- "chat_history": [ ],
- "context": [ ],
- "user_context": [ ],
- "user_id": "string",
- "generative_model": "string"
}
Response samples
- 200
- 422
null
Predict Summarize
Get summarized answers via NUA
query Parameters
model | string (Model) Default: "anthropic" |
Request Body schema: application/jsonrequired
required | object (Resources) |
summary_kind | string (SummaryKind) Default: "simple" Enum: "simple" "extended" An enumeration. |
user_prompt | string (User Prompt) Default: "" |
generative_model | string (Generative Model) |
Responses
Request samples
- Payload
{- "resources": {
- "property1": {
- "fields": {
- "property1": "string",
- "property2": "string"
}
}, - "property2": {
- "fields": {
- "property1": "string",
- "property2": "string"
}
}
}, - "summary_kind": "simple",
- "user_prompt": "",
- "generative_model": "string"
}
Response samples
- 200
- 422
null
Predict Summarize Kbid
Get summarized answers via NUA with Container
path Parameters
kbid required | string (Kbid) |
Request Body schema: application/jsonrequired
required | object (Resources) |
summary_kind | string (SummaryKind) Default: "simple" Enum: "simple" "extended" An enumeration. |
user_prompt | string (User Prompt) Default: "" |
generative_model | string (Generative Model) |
Responses
Request samples
- Payload
{- "resources": {
- "property1": {
- "fields": {
- "property1": "string",
- "property2": "string"
}
}, - "property2": {
- "fields": {
- "property1": "string",
- "property2": "string"
}
}
}, - "summary_kind": "simple",
- "user_prompt": "",
- "generative_model": "string"
}
Response samples
- 200
- 422
null
Download Knowledgebox Activity
Download the csv file for the activity audit for a given month
path Parameters
kb_uuid required | string (Kb Uuid) |
query Parameters
type required | string (EventType) Enum: "VISITED" "MODIFIED" "DELETED" "NEW" "STARTED" "STOPPED" "SEARCH" "PROCESSED" "SUGGEST" "CHAT" Audit event type |
month required | string (Month) ^\d+-(0[1-9]|1[012])$ Month in YYYY-MM format |
Responses
Response samples
- 200
- 422
null
Get Knowledgebox Activity Downloads List
Get the list of monthly activity audit files available to download
path Parameters
kb_uuid required | string (Kb Uuid) |
query Parameters
type required | string (EventType) Enum: "VISITED" "MODIFIED" "DELETED" "NEW" "STARTED" "STOPPED" "SEARCH" "PROCESSED" "SUGGEST" "CHAT" Audit event type |
Responses
Response samples
- 200
- 422
{- "downloads": [
- "string"
]
}
Get Processed Activity Log
Get latest events related to activity of a Nuclia Understanding API client
path Parameters
account_slug required | string (Account Slug) |
client_id required | string (Client Id) |
query Parameters
page | integer (Page) Default: 0 |
size | integer (Size) Default: 50 |
Responses
Response samples
- 200
- 422
{- "events": [
- { }
], - "pagination": {
- "page": 0,
- "size": 0,
- "last": true
}
}
Get Knowledgebox Activity Deprecated
Get latest events related to activity of a knowledgebox
path Parameters
kb_uuid required | string (Kb Uuid) |
query Parameters
type | string (EventType) Default: "PROCESSED" Enum: "VISITED" "MODIFIED" "DELETED" "NEW" "STARTED" "STOPPED" "SEARCH" "PROCESSED" "SUGGEST" "CHAT" An enumeration. |
page | integer (Page) Default: 0 |
size | integer (Size) Default: 50 |
Responses
Response samples
- 200
- 422
{- "events": [
- { }
], - "pagination": {
- "page": 0,
- "size": 0,
- "last": true
}
}