API

Quickchat AI fournit une API REST pour acceder de maniere programmatique a la Base de connaissances, aux Conversations, aux Actions IA et bien plus de votre Assistant IA.

Authentification

Tous les endpoints de l’API utilisent l’authentification par jeton Bearer. Incluez votre jeton API dans l’en-tete Authorization de chaque requete :

Authorization: Bearer <API_TOKEN>

Les jetons sont crees dans le Tableau de bord Quickchat sous Integrations > API. Chaque jeton est un JWT qui contient votre scenario_id, aucun identifiant supplementaire n’est donc necessaire.

• Validite du jeton : 52 semaines a compter de la creation
• Les jetons peuvent etre revoques a tout moment depuis le Tableau de bord
• Chaque jeton est lie a un seul Assistant IA (scenario)

Note

L’endpoint Chat utilise une methode d’authentification differente et heritee (api_key + scenario_id dans le corps de la requete). Voir Chat (authentification heritee) ci-dessous, ou la documentation heritee complete.

URL de base

Endpoint Group	Base URL
Base de connaissances, Actions IA, Upload de fichiers, Import	https://app.quickchat.ai/v1/api/
Conversations	https://app.quickchat.ai/v1/api_core/
Chat (herite)	https://chat.quickchat.ai/

Limites de debit

Les limites de debit sont appliquees par jeton et par endpoint.

Tier	Limit	Applies To
READ	120 requetes/min	Operations GET et listes
WRITE	60 requetes/min	POST, PATCH, PUT, DELETE
HEAVY	20 requetes/min	Uploads de fichiers, imports, scraping

Lorsqu’une limite de debit est depassee, l’API retourne HTTP 429 Too Many Requests.

Pagination

Les endpoints de liste prennent en charge la pagination via des parametres de requete :

Parameter	Type	Description
limit	integer	Nombre d’elements par page
offset	integer	Nombre d’elements a ignorer

Les reponses paginatees suivent cette structure :

{
  "items": [],
  "offset": 0,
  "count": 100
}

Gestion des erreurs

Toutes les erreurs sont retournees en JSON au format suivant :

{
  "errors": {
    "root": [
      {
        "message": "Description of the error",
        "code": "ERROR_CODE"
      }
    ]
  }
}

Status	Code	Description
400	BAD_REQUEST	Saisie invalide ou champs requis manquants
401	PERMISSION_DENIED	Jeton invalide, expire ou revoque
402	PAYMENT_REQUIRED	Un abonnement actif est requis
404	NOT_FOUND	Ressource introuvable
409	CONFLICT	Operation en conflit (p. ex. modification concurrente)
422	VALIDATION_ERROR	Le corps de la requete n’a pas passe la validation du schema
429	TOO_MANY_REQUESTS	Limite de debit depassee
500	UNKNOWN	Erreur interne du serveur
503	SERVICE_UNAVAILABLE	Indisponibilite temporaire

---

Chat (authentification heritee)

L’endpoint Chat utilise une authentification heritee avec api_key et scenario_id dans le corps de la requete. Il n’utilise pas de jetons Bearer.

Envoyer un message

POST https://chat.quickchat.ai/chat

Corps de la requete

Parameter	Type	Required	Description
api_key	string	Yes	Votre cle API depuis le Tableau de bord
scenario_id	string	Yes	ID de votre Assistant IA
text	string	Yes	Message de l’utilisateur
conv_id	string	No	ID de conversation. Omettez pour demarrer une nouvelle conversation
message_context	string	No	Contexte supplementaire par message transmis a l’IA
client_metadata	object	No	Paires cle-valeur personnalisees (max 5 cles) attachees aux messages

Shell

curl -X POST https://chat.quickchat.ai/chat \
  -H 'Content-Type: application/json' \
  -d '{
  "api_key": "<API_KEY>",
  "scenario_id": "<SCENARIO_ID>",
  "text": "Hello!",
  "conv_id": "abcd1234"
}'

Python

import requests

response = requests.post(
    url="https://chat.quickchat.ai/chat",
    json={
        "api_key": "<API_KEY>",
        "scenario_id": "<SCENARIO_ID>",
        "text": "Hello!",
        "conv_id": "abcd1234",
    },
)
data = response.json()

Reponse 200 OK

{
  "ord_number": 236,
  "conv_id": "abcd1234",
  "reply": "Hey there!"
}

Field	Type	Description
ord_number	integer	Numero sequentiel du message dans la conversation
conv_id	string	Identifiant de conversation (utilisez-le pour poursuivre la conversation)
reply	string	Reponse de l’Assistant IA

---

Base de connaissances

Obtenir les parametres

Recuperer la configuration de votre Base de connaissances.

GET https://app.quickchat.ai/v1/api/knowledge_base/

Shell

curl https://app.quickchat.ai/v1/api/knowledge_base/ \
  -H 'Authorization: Bearer <API_TOKEN>'

Python

import requests

response = requests.get(
    url="https://app.quickchat.ai/v1/api/knowledge_base/",
    headers={"Authorization": "Bearer <API_TOKEN>"},
)
data = response.json()

Reponse 200 OK

{
  "one_word_description": "Support Agent",
  "short_description": "A helpful customer support assistant.",
  "ai_commands": ["Be polite", "Stay on topic"],
  "retrain_state": null
}

Field	Type	Description
one_word_description	string	Libelle court de la Base de connaissances
short_description	string	Description de l’objectif de l’Assistant IA
ai_commands	array of strings	Instructions personnalisees pour l’IA
retrain_state	string or null	Etat actuel de l’entrainement

Modifier les parametres

PATCH https://app.quickchat.ai/v1/api/knowledge_base/

Corps de la requete

Parameter	Type	Required	Description
one_word_description	string	No	Libelle court de la Base de connaissances
short_description	string	No	Description de l’objectif de l’Assistant IA
ai_commands	array of strings	No	Instructions personnalisees pour l’IA

Shell

curl -X PATCH https://app.quickchat.ai/v1/api/knowledge_base/ \
  -H 'Authorization: Bearer <API_TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '{
  "one_word_description": "Sales Bot"
}'

Python

import requests

response = requests.patch(
    url="https://app.quickchat.ai/v1/api/knowledge_base/",
    headers={"Authorization": "Bearer <API_TOKEN>"},
    json={"one_word_description": "Sales Bot"},
)
data = response.json()

Reponse 200 OK — Retourne les parametres mis a jour de la Base de connaissances (meme schema que Obtenir les parametres).

---

Articles

Creer un article

POST https://app.quickchat.ai/v1/api/knowledge_base/articles/

Corps de la requete

Parameter	Type	Required	Description
content	string	Yes	Contenu de l’article
type	string	No	"Article" (par defaut) ou "Paragraph"
title	string	No	Titre de l’article

Shell

curl -X POST https://app.quickchat.ai/v1/api/knowledge_base/articles/ \
  -H 'Authorization: Bearer <API_TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '{
  "content": "Our return policy allows returns within 30 days.",
  "title": "Return Policy"
}'

Python

import requests

response = requests.post(
    url="https://app.quickchat.ai/v1/api/knowledge_base/articles/",
    headers={"Authorization": "Bearer <API_TOKEN>"},
    json={
        "content": "Our return policy allows returns within 30 days.",
        "title": "Return Policy",
    },
)
data = response.json()

Reponse 201 Created

{
  "id": 1234,
  "article_id": "abc-123",
  "type": "Article",
  "title": "Return Policy",
  "description": "",
  "content": "Our return policy allows returns within 30 days.",
  "state": "draft",
  "url": null,
  "parent_id": null,
  "parent_type": null,
  "shortened": false,
  "tags": [],
  "created_timestamp": "2026-01-15",
  "last_modified_timestamp": "2026-01-15"
}

Lister les articles

GET https://app.quickchat.ai/v1/api/knowledge_base/articles/

Parametres de requete

Parameter	Type	Required	Description
limit	integer	No	Elements par page
offset	integer	No	Elements a ignorer
types	string	No	Filtrer par type : Article, Paragraph
tags	string	No	Filtrer par tag
url	string	No	Filtrer par URL
title	string	No	Filtrer par titre
query	string	No	Rechercher par contenu

Shell

curl 'https://app.quickchat.ai/v1/api/knowledge_base/articles/?limit=10&offset=0' \
  -H 'Authorization: Bearer <API_TOKEN>'

Python

import requests

response = requests.get(
    url="https://app.quickchat.ai/v1/api/knowledge_base/articles/",
    headers={"Authorization": "Bearer <API_TOKEN>"},
    params={"limit": 10, "offset": 0},
)
data = response.json()

Reponse 200 OK

{
  "items": [
    {
      "id": 1234,
      "article_id": "abc-123",
      "type": "Article",
      "title": "Return Policy",
      "description": "",
      "state": "published",
      "url": null,
      "parent_id": null,
      "parent_type": null,
      "shortened": false,
      "tags": ["policies"],
      "created_timestamp": "2026-01-15",
      "last_modified_timestamp": "2026-01-15"
    }
  ],
  "offset": 0,
  "count": 1
}

Obtenir un article

GET https://app.quickchat.ai/v1/api/knowledge_base/articles/{article_id}

Shell

curl https://app.quickchat.ai/v1/api/knowledge_base/articles/1234 \
  -H 'Authorization: Bearer <API_TOKEN>'

Python

import requests

response = requests.get(
    url="https://app.quickchat.ai/v1/api/knowledge_base/articles/1234",
    headers={"Authorization": "Bearer <API_TOKEN>"},
)
data = response.json()

Reponse 200 OK — Retourne l’objet article complet (meme schema que la reponse de Creer un article).

Modifier un article

PATCH https://app.quickchat.ai/v1/api/knowledge_base/articles/{article_id}

Corps de la requete

Parameter	Type	Required	Description
content	string	No	Contenu mis a jour de l’article
title	string	No	Titre mis a jour
tags	array of strings	No	Tags mis a jour
save_mode	string	No	"draft" (par defaut) ou "publish"

Shell

curl -X PATCH https://app.quickchat.ai/v1/api/knowledge_base/articles/1234 \
  -H 'Authorization: Bearer <API_TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '{
  "title": "Updated Return Policy",
  "content": "Returns accepted within 60 days.",
  "save_mode": "publish"
}'

Python

import requests

response = requests.patch(
    url="https://app.quickchat.ai/v1/api/knowledge_base/articles/1234",
    headers={"Authorization": "Bearer <API_TOKEN>"},
    json={
        "title": "Updated Return Policy",
        "content": "Returns accepted within 60 days.",
        "save_mode": "publish",
    },
)
data = response.json()

Reponse 200 OK — Retourne l’objet article mis a jour.

Supprimer des articles

Supprimer un ou plusieurs articles par ID.

DELETE https://app.quickchat.ai/v1/api/knowledge_base/articles/

Corps de la requete — Tableau JSON d’identifiants d’articles.

Shell

curl -X DELETE https://app.quickchat.ai/v1/api/knowledge_base/articles/ \
  -H 'Authorization: Bearer <API_TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '[1234, 5678]'

Python

import requests

response = requests.delete(
    url="https://app.quickchat.ai/v1/api/knowledge_base/articles/",
    headers={"Authorization": "Bearer <API_TOKEN>"},
    json=[1234, 5678],
)

Reponse 200 OK

Rechercher des articles

Rechercher dans le contenu des articles par correspondance de texte.

GET https://app.quickchat.ai/v1/api/knowledge_base/articles/search

Parametres de requete

Parameter	Type	Required	Description
query	string	Yes	Requete de recherche
is_case_insensitive	boolean	No	Recherche insensible a la casse (par defaut : true)
with_title_url_and_tags	boolean	No	Inclure titre/URL/tags dans la recherche (par defaut : true)
strict_search	boolean	No	Exiger une correspondance exacte (par defaut : false)
num_of_display_articles	integer	No	Nombre d’articles a afficher (par defaut : 5)
num_of_data_articles	integer	No	Nombre d’articles a rechercher (par defaut : 15)

Shell

curl 'https://app.quickchat.ai/v1/api/knowledge_base/articles/search?query=return%20policy' \
  -H 'Authorization: Bearer <API_TOKEN>'

Python

import requests

response = requests.get(
    url="https://app.quickchat.ai/v1/api/knowledge_base/articles/search",
    headers={"Authorization": "Bearer <API_TOKEN>"},
    params={"query": "return policy"},
)
data = response.json()

Reponse 200 OK

{
  "article_snippets": [
    {
      "article_id": 1234,
      "expository_sentence": "Our return policy allows returns within 30 days.",
      "query_words_ids": [
        {"start_char": 4, "end_char": 10, "text": "return"}
      ]
    }
  ],
  "article_snapshots": {
    "items": [],
    "offset": 0,
    "count": 1
  }
}

Lister les paragraphes

Lister tous les paragraphes (contenu decoupe) de la Base de connaissances.

GET https://app.quickchat.ai/v1/api/knowledge_base/articles/paragraphs

Parametres de requete

Parameter	Type	Required	Description
limit	integer	No	Elements par page
offset	integer	No	Elements a ignorer
query	string	No	Filtrer par contenu

Shell

curl 'https://app.quickchat.ai/v1/api/knowledge_base/articles/paragraphs?limit=10' \
  -H 'Authorization: Bearer <API_TOKEN>'

Python

import requests

response = requests.get(
    url="https://app.quickchat.ai/v1/api/knowledge_base/articles/paragraphs",
    headers={"Authorization": "Bearer <API_TOKEN>"},
    params={"limit": 10},
)
data = response.json()

Reponse 200 OK

{
  "items": [
    {
      "id": 1,
      "content": "Our return policy allows returns within 30 days."
    }
  ],
  "offset": 0,
  "count": 1
}

---

URLs linguistiques des articles

Gerer les URLs specifiques a une langue pour les articles. Ces URLs permettent de relier les articles a des versions localisees du contenu.

Obtenir l’URL linguistique

GET https://app.quickchat.ai/v1/api/knowledge_base/articles/{article_id}/lang_urls/{language}

Shell

curl https://app.quickchat.ai/v1/api/knowledge_base/articles/1234/lang_urls/en \
  -H 'Authorization: Bearer <API_TOKEN>'

Python

import requests

response = requests.get(
    url="https://app.quickchat.ai/v1/api/knowledge_base/articles/1234/lang_urls/en",
    headers={"Authorization": "Bearer <API_TOKEN>"},
)
data = response.json()

Reponse 200 OK

{
  "url": "https://example.com/en/return-policy"
}

Creer une URL linguistique

POST https://app.quickchat.ai/v1/api/knowledge_base/articles/{article_id}/lang_urls/{language}

Corps de la requete

Parameter	Type	Required	Description
url	string	Yes	URL de la version dans la langue concernee

Shell

curl -X POST https://app.quickchat.ai/v1/api/knowledge_base/articles/1234/lang_urls/en \
  -H 'Authorization: Bearer <API_TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '{"url": "https://example.com/en/return-policy"}'

Python

import requests

response = requests.post(
    url="https://app.quickchat.ai/v1/api/knowledge_base/articles/1234/lang_urls/en",
    headers={"Authorization": "Bearer <API_TOKEN>"},
    json={"url": "https://example.com/en/return-policy"},
)
data = response.json()

Reponse 200 OK

{
  "url": "https://example.com/en/return-policy"
}

Modifier l’URL linguistique

PATCH https://app.quickchat.ai/v1/api/knowledge_base/articles/{article_id}/lang_urls/{language}

Corps de la requete

Parameter	Type	Required	Description
url	string	Yes	URL mise a jour

Reponse 200 OK — Retourne l’objet URL mis a jour.

Supprimer l’URL linguistique

DELETE https://app.quickchat.ai/v1/api/knowledge_base/articles/{article_id}/lang_urls/{language}

Shell

curl -X DELETE https://app.quickchat.ai/v1/api/knowledge_base/articles/1234/lang_urls/en \
  -H 'Authorization: Bearer <API_TOKEN>'

Python

import requests

response = requests.delete(
    url="https://app.quickchat.ai/v1/api/knowledge_base/articles/1234/lang_urls/en",
    headers={"Authorization": "Bearer <API_TOKEN>"},
)

Reponse 200 OK

---

Tags

Lister les tags

Recuperer tous les tags utilises dans les articles de la Base de connaissances.

GET https://app.quickchat.ai/v1/api/knowledge_base/tags/

Shell

curl https://app.quickchat.ai/v1/api/knowledge_base/tags/ \
  -H 'Authorization: Bearer <API_TOKEN>'

Python

import requests

response = requests.get(
    url="https://app.quickchat.ai/v1/api/knowledge_base/tags/",
    headers={"Authorization": "Bearer <API_TOKEN>"},
)
tags = response.json()

Reponse 200 OK

["policies", "faq", "product-info"]

---

Upload de fichiers

Uploader des fichiers pour qu’ils soient traites et ajoutes a la Base de connaissances sous forme d’articles.

Uploader un PDF

POST https://app.quickchat.ai/v1/api/knowledge_base/file_upload_api/pdf

Uploader un fichier PDF. Le contenu est extrait et ajoute en tant qu’article.

Shell

curl -X POST https://app.quickchat.ai/v1/api/knowledge_base/file_upload_api/pdf \
  -H 'Authorization: Bearer <API_TOKEN>' \
  -F 'pdf_file=@document.pdf'

Python

import requests

with open("document.pdf", "rb") as f:
    response = requests.post(
        url="https://app.quickchat.ai/v1/api/knowledge_base/file_upload_api/pdf",
        headers={"Authorization": "Bearer <API_TOKEN>"},
        files={"pdf_file": f},
    )
data = response.json()

Reponse 200 OK

{
  "status": "success",
  "message": "File processed successfully.",
  "article": {
    "id": 1234,
    "title": "document.pdf"
  }
}

Field	Type	Description
status	string	Etat du traitement
message	string	Message de resultat lisible
article	object	L’article cree

Uploader un fichier

POST https://app.quickchat.ai/v1/api/knowledge_base/file_upload_api/

Uploader un fichier pris en charge (PDF, DOCX). Le contenu est extrait et ajoute en tant qu’article.

Shell

curl -X POST https://app.quickchat.ai/v1/api/knowledge_base/file_upload_api/ \
  -H 'Authorization: Bearer <API_TOKEN>' \
  -F 'file=@document.docx'

Python

import requests

with open("document.docx", "rb") as f:
    response = requests.post(
        url="https://app.quickchat.ai/v1/api/knowledge_base/file_upload_api/",
        headers={"Authorization": "Bearer <API_TOKEN>"},
        files={"file": f},
    )
data = response.json()

Reponse 200 OK — Meme schema que Uploader un PDF.

---

Importer du contenu externe

Importer du contenu provenant de sources externes dans la Base de connaissances. Ces endpoints traitent le contenu de maniere asynchrone.

Scraper un site web

Scraper une page web unique ou un site entier et importer le contenu.

POST https://app.quickchat.ai/v1/api/knowledge_base/import_external/website

Corps de la requete

Parameter	Type	Required	Description
url	string	Yes	URL a scraper
mode	string	No	"individual" (par defaut), "site_wide" ou "individual_with_summary"
phrases	array of strings	No	Expressions cles a extraire
html_selector	string	No	Selecteur CSS pour cibler un contenu specifique

Shell

curl -X POST https://app.quickchat.ai/v1/api/knowledge_base/import_external/website \
  -H 'Authorization: Bearer <API_TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '{
  "url": "https://example.com/docs",
  "mode": "individual"
}'

Python

import requests

response = requests.post(
    url="https://app.quickchat.ai/v1/api/knowledge_base/import_external/website",
    headers={"Authorization": "Bearer <API_TOKEN>"},
    json={"url": "https://example.com/docs", "mode": "individual"},
)
data = response.json()

Reponse 200 OK

{
  "status": "success",
  "url": "https://example.com/docs",
  "article": {}
}

Importer une transcription YouTube

Importer la transcription d’une video YouTube.

POST https://app.quickchat.ai/v1/api/knowledge_base/import_external/youtube

Corps de la requete

Parameter	Type	Required	Description
url	string	Yes	URL de la video YouTube
toast_process_uuid	string	Yes	UUID v4 pour le suivi du processus d’import

Shell

curl -X POST https://app.quickchat.ai/v1/api/knowledge_base/import_external/youtube \
  -H 'Authorization: Bearer <API_TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '{
  "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
  "toast_process_uuid": "550e8400-e29b-41d4-a716-446655440000"
}'

Python

import uuid
import requests

response = requests.post(
    url="https://app.quickchat.ai/v1/api/knowledge_base/import_external/youtube",
    headers={"Authorization": "Bearer <API_TOKEN>"},
    json={
        "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
        "toast_process_uuid": str(uuid.uuid4()),
    },
)

Reponse 202 Accepted — La transcription est traitee de maniere asynchrone.

Importer un sitemap

Importer le contenu de tous les liens d’un sitemap XML.

POST https://app.quickchat.ai/v1/api/knowledge_base/import_external/site-map

Corps de la requete

Parameter	Type	Required	Description
site_map	string	Yes	URL d’un sitemap XML
link_filter_regex	string	No	Regex pour filtrer les liens a importer (par defaut : ".*")
html_selector	string	No	Selecteur CSS pour cibler un contenu specifique
summarize	boolean	No	Resumer le contenu importe (par defaut : false)

Shell

curl -X POST https://app.quickchat.ai/v1/api/knowledge_base/import_external/site-map \
  -H 'Authorization: Bearer <API_TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '{
  "site_map": "https://example.com/sitemap.xml"
}'

Python

import requests

response = requests.post(
    url="https://app.quickchat.ai/v1/api/knowledge_base/import_external/site-map",
    headers={"Authorization": "Bearer <API_TOKEN>"},
    json={"site_map": "https://example.com/sitemap.xml"},
)
data = response.json()

Reponse 200 OK

{
  "status": "success",
  "links": ["https://example.com/page1", "https://example.com/page2"]
}

Scraper une liste de liens

Importer le contenu d’une liste specifique d’URLs.

POST https://app.quickchat.ai/v1/api/knowledge_base/import_external/scrape-list

Corps de la requete

Parameter	Type	Required	Description
links	array of strings	Yes	Liste d’URLs a scraper (non vide)
tags	array of strings	No	Tags a appliquer aux articles importes
html_selector	string	No	Selecteur CSS pour cibler un contenu specifique
summarize	boolean	No	Resumer le contenu importe (par defaut : false)

Shell

curl -X POST https://app.quickchat.ai/v1/api/knowledge_base/import_external/scrape-list \
  -H 'Authorization: Bearer <API_TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '{
  "links": ["https://example.com/page1", "https://example.com/page2"],
  "tags": ["imported"]
}'

Python

import requests

response = requests.post(
    url="https://app.quickchat.ai/v1/api/knowledge_base/import_external/scrape-list",
    headers={"Authorization": "Bearer <API_TOKEN>"},
    json={
        "links": ["https://example.com/page1", "https://example.com/page2"],
        "tags": ["imported"],
    },
)
data = response.json()

Reponse 200 OK

{
  "status": "success",
  "links": ["https://example.com/page1", "https://example.com/page2"]
}

---

Sources

Gerer les sources de contenu externes (p. ex. Intercom, Shopify) qui synchronisent des articles vers votre Base de connaissances.

Le parametre de chemin {source} accepte des valeurs telles que "intercom", "shopify", etc.

Importer les articles d’une source

POST https://app.quickchat.ai/v1/api/knowledge_base/sources/{source}/import

Shell

curl -X POST https://app.quickchat.ai/v1/api/knowledge_base/sources/intercom/import \
  -H 'Authorization: Bearer <API_TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '{}'

Python

import requests

response = requests.post(
    url="https://app.quickchat.ai/v1/api/knowledge_base/sources/intercom/import",
    headers={"Authorization": "Bearer <API_TOKEN>"},
    json={},
)
data = response.json()

Reponse 200 OK — Retourne une liste d’aperçus d’articles importes.

Supprimer les articles d’une source

POST https://app.quickchat.ai/v1/api/knowledge_base/sources/{source}/delete

Supprime tous les articles importes depuis la source specifiee.

Reponse 204 No Content

Comparer les articles d’une source

Comparer les articles locaux avec la source externe pour detecter les modifications.

POST https://app.quickchat.ai/v1/api/knowledge_base/sources/{source}/articles_diff

Reponse 200 OK

[
  {
    "internal_article_diff": "CHANGED",
    "external_article_diff": "UNCHANGED",
    "article_snapshot": {}
  }
]

Field	Type	Description
internal_article_diff	string	"CHANGED" ou "UNCHANGED"
external_article_diff	string	"CHANGED", "UNCHANGED" ou "REMOVED"
article_snapshot	object	Donnees de l’aperçu de l’article

---

Base de connaissances Intercom

Endpoints dedies a la gestion de l’integration de la Base de connaissances Intercom.

Rafraichir les articles Intercom

Re-recuperer le contenu depuis Intercom pour les articles existants.

POST https://app.quickchat.ai/v1/api/knowledge_base/intercom/refresh_articles

Corps de la requete

Parameter	Type	Required	Description
article_ids	array of integers	No	IDs d’articles specifiques a rafraichir (par defaut : tous)
fetch_new_articles	boolean	No	Recuperer les nouveaux articles (par defaut : true)

Reponse 204 No Content

Importer les articles Intercom

Importer tous les articles depuis Intercom.

POST https://app.quickchat.ai/v1/api/knowledge_base/intercom/import

Reponse 200 OK — Retourne une liste d’aperçus d’articles importes.

Supprimer les articles Intercom

Supprimer tous les articles provenant d’Intercom de la Base de connaissances.

POST https://app.quickchat.ai/v1/api/knowledge_base/intercom/delete

Reponse 204 No Content

Comparer les articles Intercom

Comparer les articles locaux avec Intercom pour detecter les modifications.

GET https://app.quickchat.ai/v1/api/knowledge_base/intercom/articles_diff

Shell

curl https://app.quickchat.ai/v1/api/knowledge_base/intercom/articles_diff \
  -H 'Authorization: Bearer <API_TOKEN>'

Python

import requests

response = requests.get(
    url="https://app.quickchat.ai/v1/api/knowledge_base/intercom/articles_diff",
    headers={"Authorization": "Bearer <API_TOKEN>"},
)
data = response.json()

Reponse 200 OK — Retourne une liste d’objets de comparaison d’articles (meme schema que Comparer les articles d’une source).

---

Conversations

Lister les conversations

GET https://app.quickchat.ai/v1/api_core/conversations

Parametres de requete

Parameter	Type	Required	Description
limit	integer	No	Elements par page
offset	integer	No	Elements a ignorer
query	string	No	Rechercher par numero d’ordre, UUID ou texte de message
assignee_type	string	No	"ai_assistant", "human_operator" ou "unassigned"
source	string	No	"widget", "slack", "telegram", "whatsapp", etc.
resolution_status	string	No	"open" ou "resolved"
created_timestamp_start_date	datetime	No	Filtrer par date de creation (debut)
created_timestamp_end_date	datetime	No	Filtrer par date de creation (fin)
last_message_at_start_date	datetime	No	Filtrer par date du dernier message (debut)
last_message_at_end_date	datetime	No	Filtrer par date du dernier message (fin)
most_frequent_language	string	No	Filtrer par langue detectee

Shell

curl 'https://app.quickchat.ai/v1/api_core/conversations?limit=10&resolution_status=open' \
  -H 'Authorization: Bearer <API_TOKEN>'

Python

import requests

response = requests.get(
    url="https://app.quickchat.ai/v1/api_core/conversations",
    headers={"Authorization": "Bearer <API_TOKEN>"},
    params={"limit": 10, "resolution_status": "open"},
)
data = response.json()

Reponse 200 OK

{
  "items": [
    {
      "id": "conv-uuid-1234",
      "ord": 42,
      "created_at": "2026-01-15T10:30:00Z",
      "last_message_at": "2026-01-15T10:35:00Z",
      "title": "Return policy question",
      "source": "widget",
      "terminated": false,
      "resolution_status": "open",
      "has_unread_messages": true,
      "assignee": {
        "type": "ai_assistant"
      },
      "visitor_name": "John",
      "visitor_email": "john@example.com",
      "visitor_phone_number": null,
      "visitor_label": null
    }
  ],
  "offset": 0,
  "count": 42
}

Obtenir les details d’une conversation

GET https://app.quickchat.ai/v1/api_core/conversations/{conversation_id}/

Shell

curl https://app.quickchat.ai/v1/api_core/conversations/conv-uuid-1234/ \
  -H 'Authorization: Bearer <API_TOKEN>'

Python

import requests

response = requests.get(
    url="https://app.quickchat.ai/v1/api_core/conversations/conv-uuid-1234/",
    headers={"Authorization": "Bearer <API_TOKEN>"},
)
data = response.json()

Reponse 200 OK

{
  "id": "conv-uuid-1234",
  "ord": 42,
  "created_at": "2026-01-15T10:30:00Z",
  "last_message_at": "2026-01-15T10:35:00Z",
  "title": "Return policy question",
  "source": "widget",
  "terminated": false,
  "resolution_status": "open",
  "has_unread_messages": true,
  "assignee": {
    "type": "ai_assistant"
  },
  "url": null,
  "client_metadata": {"userId": 12},
  "data_gathering": null,
  "last_visitor_message_at": "2026-01-15T10:34:00Z",
  "visitor_name": "John",
  "visitor_email": "john@example.com",
  "visitor_phone_number": null,
  "visitor_label": null
}

---

Metadonnees de conversation

Stocker et recuperer des metadonnees personnalisees pour les conversations. Les metadonnees sont validees par rapport a un schema JSON si un schema est configure dans le Tableau de bord.

Obtenir les metadonnees

GET https://app.quickchat.ai/v1/api_core/conversations/{conv_id}/metadata

Shell

curl https://app.quickchat.ai/v1/api_core/conversations/conv-uuid-1234/metadata \
  -H 'Authorization: Bearer <API_TOKEN>'

Python

import requests

response = requests.get(
    url="https://app.quickchat.ai/v1/api_core/conversations/conv-uuid-1234/metadata",
    headers={"Authorization": "Bearer <API_TOKEN>"},
)
data = response.json()

Reponse 200 OK

{
  "metadata": {
    "ticket_id": "T-1234",
    "priority": "high"
  }
}

Definir les metadonnees

Creer ou mettre a jour les metadonnees d’une conversation.

POST https://app.quickchat.ai/v1/api_core/conversations/{conv_id}/metadata

Corps de la requete

Parameter	Type	Required	Description
metadata	object	Yes	Metadonnees cle-valeur a stocker

Shell

curl -X POST https://app.quickchat.ai/v1/api_core/conversations/conv-uuid-1234/metadata \
  -H 'Authorization: Bearer <API_TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '{
  "metadata": {
    "ticket_id": "T-1234",
    "priority": "high"
  }
}'

Python

import requests

response = requests.post(
    url="https://app.quickchat.ai/v1/api_core/conversations/conv-uuid-1234/metadata",
    headers={"Authorization": "Bearer <API_TOKEN>"},
    json={
        "metadata": {"ticket_id": "T-1234", "priority": "high"}
    },
)
data = response.json()

Reponse 200 OK

{
  "metadata": {
    "ticket_id": "T-1234",
    "priority": "high"
  }
}

---

Actions IA

Creer une Action IA Base de connaissances

Creer une nouvelle Action IA de type Base de connaissances. Les Actions IA Base de connaissances permettent a l’IA de rechercher dans des sous-ensembles d’articles filtres par tag lorsqu’elles sont declenchees.

POST https://app.quickchat.ai/v1/api/ai_actions/knowledge_base

Shell

curl -X POST https://app.quickchat.ai/v1/api/ai_actions/knowledge_base \
  -H 'Authorization: Bearer <API_TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '{}'

Python

import requests

response = requests.post(
    url="https://app.quickchat.ai/v1/api/ai_actions/knowledge_base",
    headers={"Authorization": "Bearer <API_TOKEN>"},
    json={},
)
data = response.json()

Reponse 201 Created

{
  "id": 1,
  "name": "",
  "description": "",
  "icon": null,
  "icon_color": null,
  "is_active": false,
  "is_valid": false,
  "tag": null,
  "parameter_description": "",
  "type": "knowledge_base"
}

Field	Type	Description
id	integer	Identifiant de l’Action IA
name	string	Nom d’affichage (max 100 caracteres)
description	string	Description du moment ou l’action doit se declencher (max 1000 caracteres)
icon	string or null	Identifiant d’icone
icon_color	string or null	Couleur de l’icone
is_active	boolean	Indique si l’action est activee
is_valid	boolean	Indique si l’action est correctement configuree
tag	string or null	Tag de la Base de connaissances pour filtrer les articles (max 255 caracteres)
parameter_description	string	Description du parametre que l’IA extrait (max 500 caracteres)
type	string	Toujours "knowledge_base"

Obtenir une Action IA Base de connaissances

GET https://app.quickchat.ai/v1/api/ai_actions/{action_id}/knowledge_base

Shell

curl https://app.quickchat.ai/v1/api/ai_actions/1/knowledge_base \
  -H 'Authorization: Bearer <API_TOKEN>'

Python

import requests

response = requests.get(
    url="https://app.quickchat.ai/v1/api/ai_actions/1/knowledge_base",
    headers={"Authorization": "Bearer <API_TOKEN>"},
)
data = response.json()

Reponse 200 OK — Retourne l’objet Action IA (meme schema que la reponse de Creer une Action IA Base de connaissances).

Modifier une Action IA Base de connaissances

PUT https://app.quickchat.ai/v1/api/ai_actions/{action_id}/knowledge_base

Corps de la requete

Parameter	Type	Required	Description
name	string	Yes	Nom d’affichage (max 100 caracteres)
description	string	Yes	Moment ou l’action doit se declencher (max 1000 caracteres)
parameter_description	string	Yes	Description du parametre (max 500 caracteres)
tag	string	Yes	Tag de la Base de connaissances pour filtrer (max 255 caracteres)

Shell

curl -X PUT https://app.quickchat.ai/v1/api/ai_actions/1/knowledge_base \
  -H 'Authorization: Bearer <API_TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '{
  "name": "Search Returns",
  "description": "Search the return policy articles when customer asks about returns.",
  "parameter_description": "The return-related query from the customer",
  "tag": "returns"
}'

Python

import requests

response = requests.put(
    url="https://app.quickchat.ai/v1/api/ai_actions/1/knowledge_base",
    headers={"Authorization": "Bearer <API_TOKEN>"},
    json={
        "name": "Search Returns",
        "description": "Search the return policy articles when customer asks about returns.",
        "parameter_description": "The return-related query from the customer",
        "tag": "returns",
    },
)
data = response.json()

Reponse 200 OK — Retourne l’objet Action IA mis a jour.