> ## Documentation Index
> Fetch the complete documentation index at: https://api.aodocs.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Chat
> Answers a chat message based on information inside AODocs
## OpenAPI
````yaml https://document-assistant.us.aodocs.app/openapi.json post /assistant/api/v1/tenants/{tenant}/chat
openapi: 3.1.0
info:
title: Document Assistant API
description: |
The Document Assistant API enables developers to integrate document-based assistant
functionalities into their applications using AODocs.
The first step is to enable AIDA (AODocs Intelligent Document Assistant) in your tenant.
The support team will provide you with the necessary information on how to get started.
The second step is to enable AIDA on libraries. You need to be an administrator of the
library to do this.
AIDA can answer questions only from those documents that are in an AIDA enabled
library.
We create a vector store index for these documents. This can take some time. The get
library API provides the status of the indexation and an estimate of the time
remaining.
The content of the index is automatically kept up-to-date near real time with the
content changes.
The third step is to ask questions based on the AODocs documents.
AIDA automatically filters the results based on the user's permissions.
Authentication: All API endpoints require a valid OAuth2 token in the
Authorization header. Ensure the client ID of the OAuth2 token is whitelisted in AODocs.
version: 1.1.0
servers:
- url: https://document-assistant.us.aodocs.app
description: Production US
- url: https://document-assistant.eu.aodocs.app
description: Production EU
security: []
paths:
/assistant/api/v1/tenants/{tenant}/chat:
post:
tags:
- chat
summary: Chat
description: Answers a chat message based on information inside AODocs
operationId: chat_assistant_api_v1_tenants__tenant__chat_post
parameters:
- name: tenant
in: path
required: true
schema:
anyOf:
- type: string
- type: 'null'
description: The domain of the customer
examples:
- example.com
title: Tenant
description: The domain of the customer
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/SyncChatRequest'
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/ChatResponse'
'400':
description: The request contains conflicting document filters
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
'500':
description: No answer was generated
security:
- HTTPBearer: []
components:
schemas:
SyncChatRequest:
properties:
message:
type: string
title: Message
description: The message to be sent to the assistant
agent_id:
anyOf:
- type: string
- type: 'null'
title: Agent Id
description: The id of the agent to scope this chat request
conversation_id:
anyOf:
- type: string
- type: 'null'
title: Conversation Id
description: |-
The conversation ID of the chat message.
If not provided a new conversation will be created.
library_id:
anyOf:
- type: string
- type: 'null'
title: Library Id
description: >-
Use library_ids field, answer the question in the context of the
library
deprecated: true
library_ids:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Library Ids
description: Answer the question in the context of these libraries
document_id:
anyOf:
- type: string
- type: 'null'
title: Document Id
description: >-
DEPRECATED: use document_ids field, answer the question in the
context of the document
deprecated: true
document_ids:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Document Ids
description: Answer the question in the context of these documents
view_id:
anyOf:
- type: string
- type: 'null'
title: View Id
description: Answer the question in the context of the view
filters:
additionalProperties: true
type: object
title: Filters
description: >-
These filters limit which documents are considered as sources during
the answer generation.
timezone:
type: integer
title: Timezone
description: >-
Timezone of the user. If is not provided we use UTC timezone.
We
use this information to accurately interpret time-related
queries.
Format: offset from UTC, in minutes
default: 0
read_only:
type: boolean
title: Read Only
description: Disable tools that can modify documents for this request
default: false
include_quotes:
anyOf:
- type: boolean
- type: 'null'
title: Include Quotes
description: Include quotes that the answer is based on in the response
default: false
type: object
required:
- message
title: SyncChatRequest
ChatResponse:
properties:
metadata:
$ref: '#/components/schemas/ChatResponseMetadata'
response:
type: string
title: Response
type: object
required:
- metadata
- response
title: ChatResponse
HTTPValidationError:
properties:
detail:
items:
$ref: '#/components/schemas/ValidationError'
type: array
title: Detail
type: object
title: HTTPValidationError
ChatResponseMetadata:
properties:
conversation_id:
anyOf:
- type: string
- type: 'null'
title: Conversation Id
description: The conversation ID of the chat message
message_id:
type: string
title: Message Id
description: The message ID of the chat message
response_id:
type: string
title: Response Id
description: The response ID of the chat message
sources:
items:
$ref: '#/components/schemas/Reference'
type: array
title: Sources
description: Document information used to generate the response
default: []
links:
items:
$ref: '#/components/schemas/ChatLink'
type: array
title: Links
description: Links to be displayed in the response
default: []
type: object
required:
- conversation_id
- message_id
- response_id
title: ChatResponseMetadata
ValidationError:
properties:
loc:
items:
anyOf:
- type: string
- type: integer
type: array
title: Location
msg:
type: string
title: Message
type:
type: string
title: Error Type
input:
title: Input
ctx:
type: object
title: Context
type: object
required:
- loc
- msg
- type
title: ValidationError
Reference:
properties:
id:
type: string
title: Id
description: Unique identifier for the reference
library_id:
type: string
title: Library Id
description: The library ID of the node
document_id:
type: string
title: Document Id
description: The document ID of the node
document_title:
type: string
title: Document Title
description: Title of document
document_link:
type: string
title: Document Link
description: Link to the document
quoted_text:
anyOf:
- type: string
- type: 'null'
title: Quoted Text
description: >-
Quoted text from the document. A short excerpt that verifies
verbatim against the source where the answering flow narrowed it —
the default for content-search answers — and the full retrieved
source chunk otherwise. quote_narrowed tells the two apart.
attachment_id:
anyOf:
- type: string
- type: 'null'
title: Attachment Id
description: The attachment ID of the node
attachment_name:
anyOf:
- type: string
- type: 'null'
title: Attachment Name
description: The attachment name of the node
attachment_mime_type:
anyOf:
- type: string
- type: 'null'
title: Attachment Mime Type
description: The attachment mime type of the node
attachment_link:
anyOf:
- type: string
- type: 'null'
title: Attachment Link
description: The attachment link of the node
location_info:
anyOf:
- type: string
- type: 'null'
title: Location Info
description: Location of the quoted text on the document (optional
location_type:
anyOf:
- type: string
- type: 'null'
title: Location Type
description: Type of the location of the quoted text
revision_id:
anyOf:
- type: string
- type: 'null'
title: Revision Id
description: The revision ID of the attachment (optional)
external_source_url:
anyOf:
- type: string
- type: 'null'
title: External Source Url
description: URL of the external source
external_source_title:
anyOf:
- type: string
- type: 'null'
title: External Source Title
description: Display name of the external source
quote_narrowed:
type: boolean
title: Quote Narrowed
description: >-
True when quoted_text has already been narrowed to a short, verified
supporting quote (or nulled after failing verification) instead of
holding the full raw retrieved chunk. Set only where that narrowing
actually happens; callers deciding whether to strip quoted_text
should check this field rather than the request's feature flags,
since a flag being on doesn't mean the citation's own flow acted on
it.
default: false
bounding_boxes_available:
type: boolean
title: Bounding Boxes Available
description: >-
Whether this citation can be submitted to the bounding-box lookup
endpoint.
readOnly: true
type: object
required:
- id
- library_id
- document_id
- document_title
- document_link
- bounding_boxes_available
title: Reference
ChatLink:
properties:
title:
type: string
title: Title
url:
type: string
title: Url
type: object
required:
- title
- url
title: ChatLink
securitySchemes:
HTTPBearer:
type: http
scheme: bearer
````
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.