Darmowy szablon automatyzacji

Bezproblemowe zarządzanie pocztą e-mail dzięki podsumowaniom i przeglądom opartym na sztucznej inteligencji

19478
28 dni temu
31
bloków

Jak to działa

Ten szablon automatyzuje obsługę przychodzących wiadomości e-mail, podsumowuje ich treść, generuje odpowiedzi z wykorzystaniem techniki RAG (Retrieval-Augmented Generation) oraz wymaga zatwierdzenia przed wysłaniem odpowiedzi. Proces został podzielony na dwie główne sekcje:

Obsługa i podsumowanie wiadomości e-mail

Proces rozpoczyna się od węzła Email Trigger (IMAP), który nasłuchuje nowych wiadomości w wybranej skrzynce odbiorczej. Po odebraniu wiadomości, węzeł Markdown konwertuje jej zawartość HTML na tekst, a następnie węzeł Email Summarization Chain wykorzystuje sztuczną inteligencję do stworzenia zwięzłego podsumowania (do 100 słów).

Generowanie odpowiedzi i zatwierdzanie

Węzeł Write email generuje profesjonalną odpowiedź na podstawie podsumowania, dbając o zwięzłość i profesjonalizm. Przed wysłaniem odpowiedzi, system przesyła projekt wiadomości przez Gmail do ręcznego zatwierdzenia. Jeśli odpowiedź zostanie zaakceptowana, jest wysyłana do nadawcy za pomocą węzła Send Email. W przeciwnym razie, wiadomość wraca do edycji. Dodatkowo, węzeł Text Classifier kategoryzuje odpowiedzi jako "Zatwierdzone" lub "Odrzucone", co decyduje o dalszym przebiegu procesu.

Konfiguracja

Aby wdrożyć ten szablon w swoim środowisku n8n, wykonaj następujące kroki:

Konfiguracja podstawowa

Rozpocznij od skonfigurowania instancji n8n lokalnie lub w chmurze. Zaimportuj dostarczony plik JSON do swojego workspace'u i upewnij się, że wszystkie wymagane dane uwierzytelniające (IMAP, SMTP, klucze API OpenAI itp.) są poprawnie skonfigurowane w sekcji Credentials.

Dostosowanie

Dostosuj parametry zgodnie z potrzebami biznesowymi, w tym warunki sprawdzane przez węzły warunkowe (np. Approve?). Zmodyfikuj szablony wiadomości dla modeli AI, aby odpowiadały tonowi i stylowi organizacji. Upewnij się, że mapowania między polami są poprawne, szczególnie gdy dane są przesyłane do systemów zewnętrznych, takich jak Google Sheets.

Przykłady zastosowań

Ten szablon automatyzacji może być wykorzystywany w różnych scenariuszach biznesowych, takich jak:

  • Automatyczna obsługa zapytań od klientów
  • Przetwarzanie zgłoszeń wsparcia technicznego
  • Odpowiedzi na często zadawane pytania (FAQ)
  • Potwierdzanie otrzymania zamówień lub dokumentów
  • Zarządzanie rekrutacją (potwierdzanie otrzymania CV)
  • Obsługa zapytań od partnerów biznesowych
  • Automatyczne przypomnienia i follow-upy

   Skopiuj kod szablonu   
{"id":"nkPjDxMrrkKbgHaV","meta":{"instanceId":"a4bfc93e975ca233ac45ed7c9227d84cf5a2329310525917adaf3312e10d5462","templateCredsSetupCompleted":true},"name":"Effortless Email Management with AI","tags":[],"nodes":[{"id":"9d77e26f-de2b-4bd4-b0f0-9924a8f459a6","name":"Email Trigger (IMAP)","type":"n8n-nodes-base.emailReadImap","position":[-2000,-180],"parameters":{"options":{}},"credentials":{"imap":{"id":"k31W9oGddl9pMDy4","name":"IMAP info@n3witalia.com"}},"typeVersion":2},{"id":"cf2d020b-b125-4a20-8694-8ed0f7acf755","name":"Markdown","type":"n8n-nodes-base.markdown","position":[-1740,-180],"parameters":{"html":"={{ $json.textHtml }}","options":{}},"typeVersion":1},{"id":"41bfceff-0155-4643-be60-ee301e2d69e1","name":"Send Email","type":"n8n-nodes-base.emailSend","position":[400,-320],"webhookId":"a79ae1b4-648c-4cb4-b6cd-04ea3c1d9314","parameters":{"html":"={{ $('Edit Fields').item.json.email }}","options":{},"subject":"=Re: {{ $('Email Trigger (IMAP)').item.json.subject }}","toEmail":"={{ $('Email Trigger (IMAP)').item.json.from }}","fromEmail":"={{ $('Email Trigger (IMAP)').item.json.to }}"},"credentials":{"smtp":{"id":"hRjP3XbDiIQqvi7x","name":"SMTP info@n3witalia.com"}},"typeVersion":2.1},{"id":"2aff581a-8b64-405c-b62f-74bf189fd7b1","name":"Qdrant Vector Store","type":"@n8n/n8n-nodes-langchain.vectorStoreQdrant","position":[-320,600],"parameters":{"mode":"retrieve-as-tool","options":{},"toolName":"company_knowladge_base","toolDescription":"Extracts information regarding the request made.","qdrantCollection":{"__rl":true,"mode":"id","value":"=COLLECTION"},"includeDocumentMetadata":false},"credentials":{"qdrantApi":{"id":"iyQ6MQiVaF3VMBmt","name":"QdrantApi account"}},"typeVersion":1},{"id":"6e3f6df0-8924-47d9-855c-51205d19e86d","name":"Embeddings OpenAI","type":"@n8n/n8n-nodes-langchain.embeddingsOpenAi","position":[-440,800],"parameters":{"options":{}},"credentials":{"openAiApi":{"id":"CDX6QM4gLYanh0P4","name":"OpenAi account"}},"typeVersion":1.2},{"id":"37ac411b-4a74-44d1-917e-b07d1c9ca221","name":"Email Summarization Chain","type":"@n8n/n8n-nodes-langchain.chainSummarization","position":[-1480,-180],"parameters":{"options":{"binaryDataKey":"={{ $json.data }}","summarizationMethodAndPrompts":{"values":{"prompt":"=Write a concise summary of the following in max 100 words:nn"{{ $json.data }}"nnDo not enter the total number of words used.","combineMapPrompt":"=Write a concise summary of the following in max 100 words:nn"{{ $json.data }}"nnDo not enter the total number of words used."}}},"operationMode":"nodeInputBinary"},"typeVersion":2},{"id":"91edbac9-847b-4f31-a8dd-09418bd93642","name":"Write email","type":"@n8n/n8n-nodes-langchain.agent","position":[-1040,-180],"parameters":{"text":"=Write the text to reply to the following email:nn{{ $json.response.text }}","options":{"systemMessage":"You are an expert at answering emails. You need to answer them professionally based on the information you have. This is a business email. Be concise and never exceed 100 words. Only the body of the email, not create the subject"},"promptType":"define","hasOutputParser":true},"typeVersion":1.7},{"id":"1da0e72a-db97-4216-a1a5-038cebaf7e10","name":"OpenAI","type":"@n8n/n8n-nodes-langchain.lmChatOpenAi","position":[-180,280],"parameters":{"model":{"__rl":true,"mode":"list","value":"gpt-4o-mini","cachedResultName":"gpt-4o-mini"},"options":{}},"credentials":{"openAiApi":{"id":"CDX6QM4gLYanh0P4","name":"OpenAi account"}},"typeVersion":1.2},{"id":"af2d6284-4c8f-4a07-b689-d0f55aaabd26","name":"Gmail","type":"n8n-nodes-base.gmail","position":[-300,-180],"webhookId":"d6dd2e7c-90ea-4b65-9c64-523d2541a054","parameters":{"sendTo":"info@n3w.it","message":"=

MESSAGE

n{{ $('Email Trigger (IMAP)').item.json.textHtml }}nn

AI RESPONSE

n{{ $json.email }}","options":{},"subject":"=[Approval Required] {{ $('Email Trigger (IMAP)').item.json.subject }}","operation":"sendAndWait","responseType":"freeText"},"credentials":{"gmailOAuth2":{"id":"nyuHvSX5HuqfMPlW","name":"Gmail account (n3w.it)"}},"typeVersion":2.1},{"id":"aaccc4a6-ce53-4813-8247-65bd1a9d5639","name":"Text Classifier","type":"@n8n/n8n-nodes-langchain.textClassifier","position":[-60,-180],"parameters":{"options":{"systemPromptTemplate":"Please classify the text provided by the user into one of the following categories: {categories}, and use the provided formatting instructions below. Don't explain, and only output the json."},"inputText":"={{ $json.data.text }}","categories":{"categories":[{"category":"Approved","description":"The email has been reviewed and accepted as-is. The human explicitly or implicity express approva, indicating that no changes ar needed.nnExample:n"Ok",n"Approvato",n"Invia""},{"category":"Declined","description":"The email has been reviewd, but the human request modifications before it sent link tweaks, removing parts, rewording etc... This could include suggested edits, rewording or major revision."}]}},"typeVersion":1},{"id":"b46de5d9-1a2e-4d28-930b-e18fb1d7876e","name":"Edit Fields","type":"n8n-nodes-base.set","position":[-580,-180],"parameters":{"options":{},"assignments":{"assignments":[{"id":"35d7c303-42f4-4dd1-b41e-6eb087c23c3d","name":"email","type":"string","value":"={{ $json.output }}"}]}},"typeVersion":3.4},{"id":"36ce51c6-8ee1-4230-84c0-40e259eafb1a","name":"When clicking ‘Test workflow’","type":"n8n-nodes-base.manualTrigger","position":[-1340,-1300],"parameters":{},"typeVersion":1},{"id":"21a0c991-65dc-483e-9b98-5cedaba7ae13","name":"Create collection","type":"n8n-nodes-base.httpRequest","position":[-1040,-1440],"parameters":{"url":"https://QDRANTURL/collections/COLLECTION","method":"POST","options":{},"jsonBody":"{n "filter": {}n}","sendBody":true,"sendHeaders":true,"specifyBody":"json","authentication":"genericCredentialType","genericAuthType":"httpHeaderAuth","headerParameters":{"parameters":[{"name":"Content-Type","value":"application/json"}]}},"credentials":{"httpHeaderAuth":{"id":"qhny6r5ql9wwotpn","name":"Qdrant API (Hetzner)"}},"typeVersion":4.2},{"id":"9a048d7d-bcdf-40b7-b33a-94b811083eac","name":"Refresh collection","type":"n8n-nodes-base.httpRequest","position":[-1040,-1180],"parameters":{"url":"https://QDRANTURL/collections/COLLECTION/points/delete","method":"POST","options":{},"jsonBody":"{n "filter": {}n}","sendBody":true,"sendHeaders":true,"specifyBody":"json","authentication":"genericCredentialType","genericAuthType":"httpHeaderAuth","headerParameters":{"parameters":[{"name":"Content-Type","value":"application/json"}]}},"credentials":{"httpHeaderAuth":{"id":"qhny6r5ql9wwotpn","name":"Qdrant API (Hetzner)"}},"typeVersion":4.2},{"id":"db494d2d-5390-4f83-9b87-3409fef31a7d","name":"Get folder","type":"n8n-nodes-base.googleDrive","position":[-820,-1180],"parameters":{"filter":{"driveId":{"__rl":true,"mode":"list","value":"My Drive","cachedResultUrl":"https://drive.google.com/drive/my-drive","cachedResultName":"My Drive"},"folderId":{"__rl":true,"mode":"id","value":"=test-whatsapp"}},"options":{},"resource":"fileFolder"},"credentials":{"googleDriveOAuth2Api":{"id":"HEy5EuZkgPZVEa9w","name":"Google Drive account"}},"typeVersion":3},{"id":"e30dbe6f-482e-47f9-b5b8-62c1113e6c8b","name":"Download Files","type":"n8n-nodes-base.googleDrive","position":[-600,-1180],"parameters":{"fileId":{"__rl":true,"mode":"id","value":"={{ $json.id }}"},"options":{"googleFileConversion":{"conversion":{"docsToFormat":"text/plain"}}},"operation":"download"},"credentials":{"googleDriveOAuth2Api":{"id":"HEy5EuZkgPZVEa9w","name":"Google Drive account"}},"typeVersion":3},{"id":"492d48d8-4997-4f04-902b-041da3210417","name":"Default Data Loader","type":"@n8n/n8n-nodes-langchain.documentDefaultDataLoader","position":[-200,-980],"parameters":{"options":{},"dataType":"binary"},"typeVersion":1},{"id":"0cf45d10-3cbf-4eb6-ab30-11f264b3aa8d","name":"Token Splitter","type":"@n8n/n8n-nodes-langchain.textSplitterTokenSplitter","position":[-240,-820],"parameters":{"chunkSize":300,"chunkOverlap":30},"typeVersion":1},{"id":"7d60f569-c34e-49a8-ba9a-88cf33083136","name":"Sticky Note3","type":"n8n-nodes-base.stickyNote","position":[-840,-1500],"parameters":{"color":6,"width":880,"height":220,"content":"# STEP 1nn## Create Qdrant CollectionnChange:n- QDRANTURLn- COLLECTION"},"typeVersion":1},{"id":"e86b18c4-d7e8-4e81-b520-dbd8125edf38","name":"Sticky Note4","type":"n8n-nodes-base.stickyNote","position":[-1060,-1240],"parameters":{"color":4,"width":620,"height":400,"content":"# STEP 2nnnnnnnnnnnnn## Documents vectorization with Qdrant and Google DrivenChange:n- QDRANTURLn- COLLECTION"},"typeVersion":1},{"id":"05f65120-ef31-4c67-ac18-e68a8353909c","name":"Qdrant Vector Store1","type":"@n8n/n8n-nodes-langchain.vectorStoreQdrant","position":[-360,-1180],"parameters":{"mode":"insert","options":{},"qdrantCollection":{"__rl":true,"mode":"id","value":"=COLLECTION"}},"credentials":{"qdrantApi":{"id":"iyQ6MQiVaF3VMBmt","name":"QdrantApi account"}},"typeVersion":1},{"id":"c15fd52f-b142-408e-af06-aeed10a1cf85","name":"Embeddings OpenAI1","type":"@n8n/n8n-nodes-langchain.embeddingsOpenAi","position":[-380,-980],"parameters":{"options":{}},"credentials":{"openAiApi":{"id":"CDX6QM4gLYanh0P4","name":"OpenAi account"}},"typeVersion":1.1},{"id":"3e47224f-3deb-450b-b825-f16c5f860f28","name":"Sticky Note","type":"n8n-nodes-base.stickyNote","position":[-2020,-600],"parameters":{"color":3,"width":580,"height":260,"content":"# STEP 3 - MAIN FLOWnnn## How it worksnThis workflow automates the handling of incoming emails, summarizes their content, generates appropriate responses using a retrieval-augmented generation (RAG) approach, and obtains approval or suggestions before sending replies. nnYou can quickly integrate Gmail and Outlook via the appropriate trigger nodes"},"typeVersion":1},{"id":"63097039-58cb-4e0f-9fb6-6bf868275519","name":"DeepSeek Chat Model","type":"@n8n/n8n-nodes-langchain.lmChatDeepSeek","position":[-1560,40],"parameters":{"options":{}},"credentials":{"deepSeekApi":{"id":"sxh1rfZxonXV83hS","name":"DeepSeek account"}},"typeVersion":1},{"id":"c86d6eeb-cf08-429f-b5b4-60b317071035","name":"Sticky Note2","type":"n8n-nodes-base.stickyNote","position":[-1500,-260],"parameters":{"width":320,"height":240,"content":"Chain that summarizes the received email"},"typeVersion":1},{"id":"4afc8b00-d1e5-473c-a71e-1299c84c546e","name":"Sticky Note5","type":"n8n-nodes-base.stickyNote","position":[-1060,-260],"parameters":{"width":340,"height":240,"content":"Agent that retrieves business information from a vector database and processes the response"},"typeVersion":1},{"id":"be1762ff-729b-4b83-9139-16f835b748f2","name":"Sticky Note1","type":"n8n-nodes-base.stickyNote","position":[-1800,-260],"parameters":{"height":240,"content":"Convert email to Markdown format for better understanding of LLM models"},"typeVersion":1},{"id":"f818ede7-895a-4860-91d3-f08cc32ec0e3","name":"Sticky Note6","type":"n8n-nodes-base.stickyNote","position":[-380,-380],"parameters":{"color":4,"height":360,"content":"## IMPORTANTnnFor the "Send Draft" node, you need to send the draft email to a Gmail address because it is the only one that allows the "Send and wait for response" function."},"typeVersion":1},{"id":"929b525a-912b-4f7b-a6e7-dfeb88a446c8","name":"Sticky Note7","type":"n8n-nodes-base.stickyNote","position":[-100,-260],"parameters":{"width":360,"height":240,"content":"Based on the suggestion received, the text classifier can understand whether the feedback received approves the generated email or not."},"typeVersion":1},{"id":"2468e643-013f-4925-ab35-c8ef4ee6eed2","name":"Email Reviewer","type":"@n8n/n8n-nodes-langchain.agent","position":[380,-40],"parameters":{"text":"=Review at the following email:n{{ $('Edit Fields').item.json.email }}nnFeedback from human:n{{ $json.data.text }}","options":{"systemMessage":"If you are an expert in reviewing emails before sending them. You need to review and structure them in such a way that you can send them. It must be in HTML format and you can insert (if you think it is appropriate) only HTML characters such as
, , ,

where necessary. Be concise and never exceed 100 words. Only the body of the email"},"promptType":"define","hasOutputParser":true},"typeVersion":1.7},{"id":"ecd9d3f8-2e79-4e5f-a73d-48de60441376","name":"Sticky Note8","type":"n8n-nodes-base.stickyNote","position":[340,-120],"parameters":{"width":340,"height":220,"content":"The Email Reviewer agent, taking inspiration from human feedback, rewrites the email"},"typeVersion":1}],"active":false,"pinData":{},"settings":{"executionOrder":"v1"},"versionId":"de11da52-1513-4797-8070-b64e84b84158","connections":{"Gmail":{"main":[[{"node":"Text Classifier","type":"main","index":0}]]},"OpenAI":{"ai_languageModel":[[{"node":"Write email","type":"ai_languageModel","index":0},{"node":"Email Reviewer","type":"ai_languageModel","index":0},{"node":"Text Classifier","type":"ai_languageModel","index":0}]]},"Markdown":{"main":[[{"node":"Email Summarization Chain","type":"main","index":0}]]},"Get folder":{"main":[[{"node":"Download Files","type":"main","index":0}]]},"Edit Fields":{"main":[[{"node":"Gmail","type":"main","index":0}]]},"Write email":{"main":[[{"node":"Edit Fields","type":"main","index":0}]]},"Download Files":{"main":[[{"node":"Qdrant Vector Store1","type":"main","index":0}]]},"Email Reviewer":{"main":[[{"node":"Edit Fields","type":"main","index":0}]]},"Token Splitter":{"ai_textSplitter":[[{"node":"Default Data Loader","type":"ai_textSplitter","index":0}]]},"Text Classifier":{"main":[[{"node":"Send Email","type":"main","index":0}],[{"node":"Email Reviewer","type":"main","index":0}]]},"Embeddings OpenAI":{"ai_embedding":[[{"node":"Qdrant Vector Store","type":"ai_embedding","index":0}]]},"Embeddings OpenAI1":{"ai_embedding":[[{"node":"Qdrant Vector Store1","type":"ai_embedding","index":0}]]},"Refresh collection":{"main":[[{"node":"Get folder","type":"main","index":0}]]},"DeepSeek Chat Model":{"ai_languageModel":[[{"node":"Email Summarization Chain","type":"ai_languageModel","index":0}]]},"Default Data Loader":{"ai_document":[[{"node":"Qdrant Vector Store1","type":"ai_document","index":0}]]},"Qdrant Vector Store":{"ai_tool":[[{"node":"Write email","type":"ai_tool","index":0},{"node":"Email Reviewer","type":"ai_tool","index":0}]]},"Email Trigger (IMAP)":{"main":[[{"node":"Markdown","type":"main","index":0}]]},"Email Summarization Chain":{"main":[[{"node":"Write email","type":"main","index":0}]]},"When clicking ‘Test workflow’":{"main":[[{"node":"Create collection","type":"main","index":0},{"node":"Refresh collection","type":"main","index":0}]]}}}

  • SMTP
  • email
  • human
  • form
  • wait
  • hitl
  • approval
  • API
  • Request
  • URL
  • Build
  • cURL
  • LangChain
  • Chat
  • Conversational
  • Plan and Execute
  • ReAct
  • Tools
Planeta AI 2025 
magic-wandmenu linkedin facebook pinterest youtube rss twitter instagram facebook-blank rss-blank linkedin-blank pinterest youtube twitter instagram