Automatisation du processus RFP avec l'assistant OpenAI
Ceci est unAIworkflow d'automatisation du domainecontenant 23 nœuds.Utilise principalement des nœuds comme Set, Gmail, Slack, Webhook, GoogleDocs, combinant la technologie d'intelligence artificielle pour une automatisation intelligente. Automatisation du processus RFP avec un assistant OpenAI
- •Compte Google et informations d'identification Gmail API
- •Token Bot Slack ou URL Webhook
- •Point de terminaison HTTP Webhook (généré automatiquement par n8n)
- •Clé API OpenAI
Nœuds utilisés (23)
Catégorie
{
"meta": {
"instanceId": "26ba763460b97c249b82942b23b6384876dfeb9327513332e743c5f6219c2b8e"
},
"nodes": [
{
"id": "51dbe3b4-42f6-43c9-85dc-42ae49be6ba9",
"name": "Obtenir les données d'APP",
"type": "n8n-nodes-base.extractFromFile",
"position": [
1003,
278
],
"parameters": {
"options": {},
"operation": "pdf"
},
"typeVersion": 1
},
{
"id": "c42e6bfc-a426-4d12-bf95-f3fe6e944631",
"name": "Analyseur de sortie de liste d'éléments",
"type": "@n8n/n8n-nodes-langchain.outputParserItemList",
"position": [
2140,
540
],
"parameters": {
"options": {}
},
"typeVersion": 1
},
{
"id": "1703e9c3-f49e-4272-ad11-0b9d4e9a76c6",
"name": "Pour chaque question...",
"type": "n8n-nodes-base.splitInBatches",
"position": [
2460,
340
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "a54fa4ee-6f67-41a9-89fe-fd9f2bf094de",
"name": "Note adhésive",
"type": "n8n-nodes-base.stickyNote",
"position": [
760,
60
],
"parameters": {
"color": 7,
"width": 532.597092515486,
"height": 508.1316876142587,
"content": "## 1. API to Trigger Workflow\n[Read more about using Webhooks](https://docs.n8n.io/integrations/builtin/core-nodes/n8n-nodes-base.webhook/)\n\nThis workflow requires the user to submit the RFP document via an API request. It's a common pattern to use the webhook node for this purpose. Be sure to secure this webhook endpoint in production!"
},
"typeVersion": 1
},
{
"id": "fdef005f-7838-4b8c-8af4-4b7c6f947ee2",
"name": "Définir les variables",
"type": "n8n-nodes-base.set",
"position": [
1143,
278
],
"parameters": {
"mode": "raw",
"options": {},
"jsonOutput": "={\n \"doc_title\": \"{{ $('Wait for Request').item.json.body.title }}\",\n \"doc_filename\": \"{{ $('Wait for Request').item.json.body.id }} | {{ $('Wait for Request').item.json.body.title }} | {{ $now.format('yyyyMMddhhmmss') }}| RFP Response\",\n \"reply_to\": \"{{ $('Wait for Request').item.json.body.reply_to }}\"\n}\n"
},
"typeVersion": 3.3
},
{
"id": "a64f6274-62fc-42fb-b7c7-5aa85746c621",
"name": "Note adhésive1",
"type": "n8n-nodes-base.stickyNote",
"position": [
1320,
148.42417112849222
],
"parameters": {
"color": 7,
"width": 493.289385759178,
"height": 418.29352785836636,
"content": "## 2. Create a new Doc to Capture Responses For RFP Questions\n[Read more about working with Google Docs](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.googledocs/)\n\nFor each RFP we process, let's create its very own document to store the results. It will serve as a draft document for the RFP response."
},
"typeVersion": 1
},
{
"id": "2b3df6af-c1ab-44a1-8907-425944294477",
"name": "Créer un nouveau document de réponse à l'APP",
"type": "n8n-nodes-base.googleDocs",
"position": [
1420,
340
],
"parameters": {
"title": "={{ $json.doc_filename }}",
"folderId": "=1y0I8MH32maIWCJh767mRE_NMHC6A3bUu"
},
"credentials": {
"googleDocsOAuth2Api": {
"id": "V0G0vi1DRj7Cqbp9",
"name": "Google Docs account"
}
},
"typeVersion": 2
},
{
"id": "0bf30bef-2910-432b-b5eb-dee3fe39b797",
"name": "Note adhésive2",
"type": "n8n-nodes-base.stickyNote",
"position": [
1840,
110.52747078833045
],
"parameters": {
"color": 7,
"width": 500.1029039641811,
"height": 599.9895116376663,
"content": "## 3. Identifying Questions using AI\n[Read more about Question & Answer Chain](https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainretrievalqa/)\n\nUsing the power of LLMs, we're able to extract the RFP questionnaire regardless of original formatting or layout. This allows AutoRFP to handle a wide range of RFPs without requiring explicit extraction rules for edge cases.\n\nAdditionally, We'll use the Input List Output Parser to return a list of questions for further processing."
},
"typeVersion": 1
},
{
"id": "1c064047-1f6a-47c8-bb49-85b4d6f8e854",
"name": "Note adhésive3",
"type": "n8n-nodes-base.stickyNote",
"position": [
2380,
84.66944065837868
],
"parameters": {
"color": 7,
"width": 746.3888903304862,
"height": 600.3660610069576,
"content": "## 4. Generating Question & Answer Pairs with AI\n[Read more about using OpenAI Assistants in n8n](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-langchain.openai/)\n\nBy preparing an OpenAI Assistant with marketing material and sales documents about our company and business, we are able to use AI to answer RFP questions with the accurate and relevant context. Potentially allowing sales teams to increase the number of RFPs they can reply to.\n\nThis portion of the workflow loops through and answers each question individually for better answers. We can record the Question and Answer pairings to the RFP response document we created earlier."
},
"typeVersion": 1
},
{
"id": "e663ba01-e9a6-4247-9d97-8f796d29d72a",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1960,
540
],
"parameters": {
"options": {}
},
"credentials": {
"openAiApi": {
"id": "8gccIjcuf3gvaoEr",
"name": "OpenAi account"
}
},
"typeVersion": 1
},
{
"id": "ec0b439e-9fd8-4960-b8bb-04f4f7814a0a",
"name": "Note adhésive4",
"type": "n8n-nodes-base.stickyNote",
"position": [
300,
60
],
"parameters": {
"width": 421.778219154496,
"height": 515.8006969458895,
"content": "## Try It Out!\n\n**This workflow does the following:**\n* Receives a RFP document via webhook\n* Creates a new RFP response document via Google Docs\n* Uses LLMs to extract the questions from the RFP document into a questions list\n* Loops through each question and uses an OpenAI Assistant to generate an answer. Saving each answer into the response document.\n* Once complete, sends a gmail and slack notification to the team.\n\n\n📃**Example Documents**\nTo run this workflow, you'll need to following 2 documents:\n* [RFP Document](https://drive.google.com/file/d/1G42h4Vz2lBuiNCnOiXF_-EBP1MaIEVq5/view?usp=sharing)\n* [Example Company Document](https://drive.google.com/file/d/16WywCYcxBgYHXB3TY3wXUTyfyG2n_BA0/view?usp=sharing)\n\n### Need Help?\nJoin the [Discord](https://discord.com/invite/XPKeKXeB7d) or ask in the [Forum](https://community.n8n.io/)!\n\nHappy Hacking!"
},
"typeVersion": 1
},
{
"id": "244ff32d-9bc4-4a67-a6c2-4a7dc308058e",
"name": "Note adhésive5",
"type": "n8n-nodes-base.stickyNote",
"position": [
3160,
80
],
"parameters": {
"color": 7,
"width": 474.3513281516049,
"height": 390.51033452105344,
"content": "## 5. Send Notification Once Completed\n[Read more about using Slack](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.slack)\n\n\nFinally, we can use a number of ways to notify the sales team when the process is complete. Here, we've opted to send the requesting user an email with a link to the RFP response document."
},
"typeVersion": 1
},
{
"id": "94243b69-43b8-4731-9a6b-2934db832cc6",
"name": "Envoyer une notification de chat",
"type": "n8n-nodes-base.slack",
"position": [
3440,
280
],
"parameters": {
"text": "=RFP document \"{{ $('Set Variables').item.json.title }}\" completed!",
"select": "channel",
"channelId": {
"__rl": true,
"mode": "name",
"value": "RFP-channel"
},
"otherOptions": {}
},
"credentials": {
"slackApi": {
"id": "VfK3js0YdqBdQLGP",
"name": "Slack account"
}
},
"typeVersion": 2.1
},
{
"id": "391d7e07-2a6d-4c4d-bf42-9cc5466cc1b5",
"name": "Envoyer une notification par e-mail",
"type": "n8n-nodes-base.gmail",
"position": [
3240,
280
],
"parameters": {
"sendTo": "={{ $('Set Variables').item.json.reply_to }}",
"message": "=Your RFP document \"{{ $('Set Variables').item.json.title }}\" is now complete!",
"options": {},
"subject": "=RFP Questionnaire \"{{ $('Set Variables').item.json.title }}\" Completed!",
"emailType": "text"
},
"credentials": {
"gmailOAuth2": {
"id": "Sf5Gfl9NiFTNXFWb",
"name": "Gmail account"
}
},
"typeVersion": 2.1
},
{
"id": "34115f45-21ff-49a0-95f4-1fed53b53583",
"name": "Ajouter des métadonnées au document de réponse",
"type": "n8n-nodes-base.googleDocs",
"position": [
1600,
340
],
"parameters": {
"actionsUi": {
"actionFields": [
{
"text": "=Title: {{ $('Set Variables').item.json.doc_title }}\nDate generated: {{ $now.format(\"yyyy-MM-dd @ hh:mm\") }}\nRequested by: {{ $('Set Variables').item.json.reply_to }}\nExecution Id: http://localhost:5678/workflow/{{ $workflow.id }}/executions/{{ $execution.id }}\n\n---\n\n",
"action": "insert"
}
]
},
"operation": "update",
"documentURL": "={{ $json.id }}"
},
"credentials": {
"googleDocsOAuth2Api": {
"id": "V0G0vi1DRj7Cqbp9",
"name": "Google Docs account"
}
},
"typeVersion": 2
},
{
"id": "f285d896-ba15-4f8a-b041-7cbcbe2e1050",
"name": "Note adhésive6",
"type": "n8n-nodes-base.stickyNote",
"position": [
783,
238
],
"parameters": {
"width": 192.30781285767205,
"height": 306.5264325350084,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n🚨**Required**\n* Use a tool such as Postman to send data to the webhook."
},
"typeVersion": 1
},
{
"id": "b6e4e40e-b10b-48f2-bfe2-1ad38b1c6518",
"name": "Enregistrer la question et la réponse dans le document de réponse",
"type": "n8n-nodes-base.googleDocs",
"position": [
2940,
460
],
"parameters": {
"actionsUi": {
"actionFields": [
{
"text": "={{ $runIndex+1 }}. {{ $json.content }}\n{{ $json.output }}\n\n",
"action": "insert"
}
]
},
"operation": "update",
"documentURL": "={{ $('Create new RFP Response Document').item.json.id }}"
},
"credentials": {
"googleDocsOAuth2Api": {
"id": "V0G0vi1DRj7Cqbp9",
"name": "Google Docs account"
}
},
"typeVersion": 2
},
{
"id": "ae8cc28f-4fd3-41d7-8a30-2675f58d1067",
"name": "Note adhésive7",
"type": "n8n-nodes-base.stickyNote",
"position": [
2600,
440
],
"parameters": {
"width": 306.8994213707367,
"height": 481.01365258903786,
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n🚨**Required**\nYou'll need to create an OpenAI Assistant to use this workflow.\n* Sign up for [OpenAI Dashboard](https://platform.openai.com) if you haven't already.\n* Create an [OpenAI Assistant](https://platform.openai.com/playground/assistants)\n* Upload the [example company doc](https://drive.google.com/file/d/16WywCYcxBgYHXB3TY3wXUTyfyG2n_BA0/view?usp=sharing) to the assistant.\n\nThe assistant will use the company doc to answer the questions."
},
"typeVersion": 1
},
{
"id": "81825554-5cbe-469b-8511-a92d5ea165cb",
"name": "Note adhésive8",
"type": "n8n-nodes-base.stickyNote",
"position": [
3200,
460
],
"parameters": {
"width": 386.79263167741857,
"height": 94.04968721739164,
"content": "🚨**Required**\n* Update the email address to send to in Gmail Node.\n* Update the channel and message for Slack."
},
"typeVersion": 1
},
{
"id": "25a57ca0-6789-499c-873b-07aba40530ed",
"name": "Répondre à la question avec contexte",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
2620,
460
],
"parameters": {
"text": "={{ $json.response.text }}",
"prompt": "define",
"options": {},
"resource": "assistant",
"assistantId": {
"__rl": true,
"mode": "list",
"value": "asst_QBI5lLKOsjktr3DRB4MwrgZd",
"cachedResultName": "Nexus Digital Solutions Bot"
}
},
"credentials": {
"openAiApi": {
"id": "8gccIjcuf3gvaoEr",
"name": "OpenAi account"
}
},
"typeVersion": 1.3
},
{
"id": "1b4cc83b-a793-47c1-9dd6-0d7484db07b4",
"name": "Attendre la demande",
"type": "n8n-nodes-base.webhook",
"position": [
823,
278
],
"webhookId": "35e874df-2904-494e-a9f5-5a3f20f517f8",
"parameters": {
"path": "35e874df-2904-494e-a9f5-5a3f20f517f8",
"options": {},
"httpMethod": "POST"
},
"typeVersion": 2
},
{
"id": "2f97e3e6-c100-4045-bcb3-6fbd17cfb420",
"name": "Extraire les questions de l'APP",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
1960,
380
],
"parameters": {
"text": "=You have been given a RFP document as part of a tender process of a buyer. Please extract all questions intended for the supplier. You must ensure the questions extracted are exactly has they are written in the RFP document.\n\n<RFP>{{ $('Get RFP Data').item.json.text }}<RFP>",
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.4
},
{
"id": "4945b975-ac84-406e-8482-44cfa5679ef9",
"name": "Note adhésive9",
"type": "n8n-nodes-base.stickyNote",
"position": [
760,
600
],
"parameters": {
"color": 5,
"width": 529.9947173986736,
"height": 157.64231937074243,
"content": "### Example Webhook Request\ncurl --location 'https://<n8n_webhook_url>' \\\n--form 'id=\"RFP001\"' \\\n--form 'title=\"BlueChip Travel and StarBus Web Services\"' \\\n--form 'reply_to=\"jim@example.com\"' \\\n--form 'data=@\"k9pnbALxX/RFP Questionnaire.pdf\"'\n"
},
"typeVersion": 1
}
],
"pinData": {},
"connections": {
"51dbe3b4-42f6-43c9-85dc-42ae49be6ba9": {
"main": [
[
{
"node": "fdef005f-7838-4b8c-8af4-4b7c6f947ee2",
"type": "main",
"index": 0
}
]
]
},
"fdef005f-7838-4b8c-8af4-4b7c6f947ee2": {
"main": [
[
{
"node": "2b3df6af-c1ab-44a1-8907-425944294477",
"type": "main",
"index": 0
}
]
]
},
"1b4cc83b-a793-47c1-9dd6-0d7484db07b4": {
"main": [
[
{
"node": "51dbe3b4-42f6-43c9-85dc-42ae49be6ba9",
"type": "main",
"index": 0
}
]
]
},
"e663ba01-e9a6-4247-9d97-8f796d29d72a": {
"ai_languageModel": [
[
{
"node": "2f97e3e6-c100-4045-bcb3-6fbd17cfb420",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"1703e9c3-f49e-4272-ad11-0b9d4e9a76c6": {
"main": [
[
{
"node": "391d7e07-2a6d-4c4d-bf42-9cc5466cc1b5",
"type": "main",
"index": 0
}
],
[
{
"node": "25a57ca0-6789-499c-873b-07aba40530ed",
"type": "main",
"index": 0
}
]
]
},
"c42e6bfc-a426-4d12-bf95-f3fe6e944631": {
"ai_outputParser": [
[
{
"node": "2f97e3e6-c100-4045-bcb3-6fbd17cfb420",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"391d7e07-2a6d-4c4d-bf42-9cc5466cc1b5": {
"main": [
[
{
"node": "94243b69-43b8-4731-9a6b-2934db832cc6",
"type": "main",
"index": 0
}
]
]
},
"2f97e3e6-c100-4045-bcb3-6fbd17cfb420": {
"main": [
[
{
"node": "1703e9c3-f49e-4272-ad11-0b9d4e9a76c6",
"type": "main",
"index": 0
}
]
]
},
"34115f45-21ff-49a0-95f4-1fed53b53583": {
"main": [
[
{
"node": "2f97e3e6-c100-4045-bcb3-6fbd17cfb420",
"type": "main",
"index": 0
}
]
]
},
"25a57ca0-6789-499c-873b-07aba40530ed": {
"main": [
[
{
"node": "b6e4e40e-b10b-48f2-bfe2-1ad38b1c6518",
"type": "main",
"index": 0
}
]
]
},
"2b3df6af-c1ab-44a1-8907-425944294477": {
"main": [
[
{
"node": "34115f45-21ff-49a0-95f4-1fed53b53583",
"type": "main",
"index": 0
}
]
]
},
"b6e4e40e-b10b-48f2-bfe2-1ad38b1c6518": {
"main": [
[
{
"node": "1703e9c3-f49e-4272-ad11-0b9d4e9a76c6",
"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 ?
Avancé - Intelligence Artificielle
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
Jimleuk
@jimleukFreelance consultant based in the UK specialising in AI-powered automations. I work with select clients tackling their most challenging projects. For business enquiries, send me an email at hello@jimle.uk LinkedIn: https://www.linkedin.com/in/jimleuk/ X/Twitter: https://x.com/jimle_uk
Partager ce workflow