Gestion des tâches Appian avec Ollama Qwen LLM et gestion mémoire Postgres
Ceci est unAI Chatbot, Multimodal AIworkflow d'automatisation du domainecontenant 13 nœuds.Utilise principalement des nœuds comme Set, Webhook, Agent, HttpRequestTool, RespondToWebhook. utilisationOllama Qwen LLMetPostgres内存gestionAppian任务
- •Point de terminaison HTTP Webhook (généré automatiquement par n8n)
- •Peut nécessiter les informations d'identification d'authentification de l'API cible
- •Informations de connexion à la base de données PostgreSQL
Nœuds utilisés (13)
Catégorie
{
"meta": {
"templateCredsSetupCompleted": false
},
"nodes": [
{
"id": "template-vars-0001",
"name": "Variables de modèle",
"type": "n8n-nodes-base.set",
"position": [
480,
704
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "a1",
"name": "baseUrl",
"type": "string",
"value": "https://YOUR-APP-BASE/suite/webapi"
},
{
"id": "a2",
"name": "defaultBatchSize",
"type": "number",
"value": "10"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "chat-trigger-0001",
"name": "À réception d'un message de chat",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
672,
624
],
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "webhook-0001",
"name": "Webhook",
"type": "n8n-nodes-base.webhook",
"position": [
672,
832
],
"parameters": {
"path": "your-webhook-path",
"options": {},
"httpMethod": "POST",
"responseMode": "responseNode",
"authentication": "headerAuth"
},
"typeVersion": 2
},
{
"id": "set-normalize-0001",
"name": "Normaliser l'entrée du chat",
"type": "n8n-nodes-base.set",
"position": [
976,
704
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "set-chatInput",
"name": "chatInput",
"type": "string",
"value": "={{ $json?.body?.text || $json?.chatInput || $json.body?.chatInput }}"
},
{
"id": "set-sessionId",
"name": "sessionId",
"type": "string",
"value": "={{ $json?.body?.conversation?.id || $json?.sessionId || $json.body?.sessionId}}"
},
{
"id": "set-username",
"name": "username",
"type": "string",
"value": "={{ $json?.body?.user || $json?.username || 'user@example.com' }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "agent-0001",
"name": "Agent IA",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1360,
704
],
"parameters": {
"options": {
"maxIterations": 15,
"systemMessage": "You are a helpful assistant that can list and create Appian tasks using the provided tools. Keep responses concise and format dates as 'mmmm d, yyyy'.",
"returnIntermediateSteps": true
}
},
"typeVersion": 1.6
},
{
"id": "ollama-llm-0001",
"name": "Ollama Modèle de chat",
"type": "@n8n/n8n-nodes-langchain.lmChatOllama",
"position": [
1152,
928
],
"parameters": {
"model": "qwen2.5:7b",
"options": {
"numCtx": 8147
}
},
"typeVersion": 1
},
{
"id": "pg-memory-0001",
"name": "Mémoire de chat Postgres",
"type": "@n8n/n8n-nodes-langchain.memoryPostgresChat",
"position": [
1360,
928
],
"parameters": {},
"typeVersion": 1.1
},
{
"id": "tool-list-tasks-0001",
"name": "Lister les tâches (Appian)",
"type": "n8n-nodes-base.httpRequestTool",
"position": [
1600,
928
],
"parameters": {
"url": "={{ $('Template Vars').item.json.baseUrl }}/tasks",
"options": {},
"sendQuery": true,
"authentication": "genericCredentialType",
"genericAuthType": "oAuth2Api",
"queryParameters": {
"parameters": [
{
"name": "username",
"value": "={{ $('Normalize Chat Input').item.json.username }}"
},
{
"name": "startIndex",
"value": "={{ parseInt($fromAI('parameters1_Value', 'First result index, default 1', 'string')) || 1 }}"
},
{
"name": "batchSize",
"value": "={{ parseInt($('Template Vars').item.json.defaultBatchSize) || 10 }}"
}
]
},
"toolDescription": "List all user tasks. Use startIndex and batchSize to page the results."
},
"typeVersion": 4.2
},
{
"id": "tool-list-types-0001",
"name": "Lister les types de tâches (Appian)",
"type": "n8n-nodes-base.httpRequestTool",
"position": [
1808,
928
],
"parameters": {
"url": "={{ $('Template Vars').item.json.baseUrl }}/tasktypes",
"options": {},
"authentication": "genericCredentialType",
"genericAuthType": "oAuth2Api",
"toolDescription": "Lists all of the available task types."
},
"typeVersion": 4.2
},
{
"id": "tool-create-task-0001",
"name": "Créer une tâche (Appian)",
"type": "n8n-nodes-base.httpRequestTool",
"position": [
2032,
928
],
"parameters": {
"url": "={{ $('Template Vars').item.json.baseUrl }}/tasks",
"method": "POST",
"options": {},
"sendBody": true,
"authentication": "genericCredentialType",
"bodyParameters": {
"parameters": [
{
"name": "username",
"value": "={{ $('Normalize Chat Input').item.json.username }}"
},
{
"name": "title",
"value": "={{ $fromAI('parameters1_Value', 'Short task title', 'string') }}"
},
{
"name": "description",
"value": "={{ $fromAI('parameters2_Value', 'Detailed task description', 'string') }}"
},
{
"name": "estimatedHours",
"value": "={{ $fromAI('parameters3_Value', 'Estimated hours (optional)', 'string') }}"
},
{
"name": "estimatedCost",
"value": "={{ $fromAI('parameters4_Value', 'Estimated cost (optional)', 'string') }}"
}
]
},
"genericAuthType": "oAuth2Api",
"toolDescription": "Creates a new task. Execute only once per task."
},
"typeVersion": 4.2
},
{
"id": "set-output-0001",
"name": "Préparer la réponse",
"type": "n8n-nodes-base.set",
"position": [
1808,
704
],
"parameters": {
"options": {
"dotNotation": true
},
"assignments": {
"assignments": [
{
"id": "set-output",
"name": "output",
"type": "string",
"value": "={{ $json.output }}"
},
{
"id": "set-sessionId-out",
"name": "sessionId",
"type": "string",
"value": "={{ $('Normalize Chat Input').item.json.sessionId }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "respond-0001",
"name": "Répondre à Webhook",
"type": "n8n-nodes-base.respondToWebhook",
"position": [
2048,
704
],
"parameters": {
"options": {}
},
"typeVersion": 1.3
},
{
"id": "note-0001",
"name": "Notes",
"type": "n8n-nodes-base.stickyNote",
"position": [
560,
520
],
"parameters": {
"width": 900,
"height": 420,
"content": "Appian Tasks Chat Agent\nThis template shows a local AI chat agent that lists and creates tasks via an Appian-compatible API. Configure Template Vars and attach your own credentials after import."
},
"typeVersion": 1
}
],
"connections": {
"webhook-0001": {
"main": [
[
{
"node": "set-normalize-0001",
"type": "main",
"index": 0
}
]
]
},
"agent-0001": {
"main": [
[
{
"node": "set-output-0001",
"type": "main",
"index": 0
}
]
]
},
"set-output-0001": {
"main": [
[
{
"node": "respond-0001",
"type": "main",
"index": 0
}
]
]
},
"ollama-llm-0001": {
"ai_languageModel": [
[
{
"node": "agent-0001",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"tool-list-tasks-0001": {
"ai_tool": [
[
{
"node": "agent-0001",
"type": "ai_tool",
"index": 0
}
]
]
},
"tool-create-task-0001": {
"ai_tool": [
[
{
"node": "agent-0001",
"type": "ai_tool",
"index": 0
}
]
]
},
"set-normalize-0001": {
"main": [
[
{
"node": "agent-0001",
"type": "main",
"index": 0
}
]
]
},
"pg-memory-0001": {
"ai_memory": [
[
{
"node": "agent-0001",
"type": "ai_memory",
"index": 0
}
]
]
},
"tool-list-types-0001": {
"ai_tool": [
[
{
"node": "agent-0001",
"type": "ai_tool",
"index": 0
}
]
]
},
"chat-trigger-0001": {
"main": [
[
{
"node": "set-normalize-0001",
"type": "main",
"index": 0
}
]
]
}
}
}Comment utiliser ce workflow ?
Copiez le code de configuration JSON ci-dessus, créez un nouveau workflow dans votre instance n8n et sélectionnez "Importer depuis le JSON", collez la configuration et modifiez les paramètres d'authentification selon vos besoins.
Dans quelles scénarios ce workflow est-il adapté ?
Intermédiaire - Chatbot IA, IA Multimodale
Est-ce payant ?
Ce workflow est entièrement gratuit et peut être utilisé directement. Veuillez noter que les services tiers utilisés dans le workflow (comme l'API OpenAI) peuvent nécessiter un paiement de votre part.
Workflows recommandés
Joe Swink
@dhawkPartager ce workflow