Darmowy szablon automatyzacji

Personal Shopper Chatbot dla WooCommerce z RAG przy użyciu Google Drive i openAI

9381
2 mies. temu
25
bloków


Inteligentny asystent zakupowy z OpenAI, RAG i WooCommerce

Ten szablon automatyzacji łączy możliwości OpenAI, Retrieval-Augmented Generation (RAG) oraz WooCommerce, tworząc inteligentnego asystenta zakupowego. Automatyzacja obsługuje dwa główne scenariusze:

  • Wyszukiwanie produktów: Wyodrębnia intencje użytkownika (słowa kluczowe, zakresy cenowe, SKU) i pobiera pasujące produkty z WooCommerce.
  • Ogólne zapytania: Odpowiada na pytania dotyczące sklepu (np. godziny otwarcia, polityki) wykorzystując RAG i dokumenty przechowywane w Google Drive.

Jak to działa

1. Interakcja czatu i wykrywanie intencji

Wyzwalacz czatu: Rozpoczyna się, gdy użytkownik wysyła wiadomość.

Ekstraktor informacji: Wykorzystuje OpenAI do analizy wiadomości i określenia, czy użytkownik szuka produktu czy zadaje ogólne pytanie.

Przykład wyodrębnionych danych:

{
  "search": true,
  "keyword": "czerwone torebki",
  "priceRange": { "min": 50, "max": 100 },
  "SKU": "BAG123",
  "category": "akcesoria damskie"
}

2. Wyszukiwanie produktów (integracja WooCommerce)

Agent AI: Jeśli search: true, przekierowuje żądanie do narzędzia personal_shopper.

Węzeł WooCommerce: Wykonuje zapytanie do sklepu WooCommerce używając wyodrębnionych parametrów.

3. Ogólne zapytania (system RAG)

Narzędzie RAG: Jeśli search: false, wykorzystuje Qdrant Vector Store do wyszukiwania informacji o sklepie.

Integracja z Google Drive: Dokumenty są przechowywane w Google Drive, dzielone na fragmenty i osadzane w Qdrant.

Konfiguracja

1. Konfiguracja systemu RAG

  • Prześlij dokumenty sklepu do Google Drive
  • Zaktualizuj węzeł Google Drive2 identyfikatorem folderu
  • Skonfiguruj Qdrant Vector Store

2. Konfiguracja OpenAI i WooCommerce

  • Dodaj klucz API do wszystkich węzłów OpenAI
  • Połącz swój sklep WooCommerce

3. Dostosowanie agenta AI

  • Modyfikuj prompt systemowy ekstraktora intencji
  • Aktualizuj opis narzędzia RAG

Przykłady zastosowań

Ten szablon automatyzacji idealnie sprawdzi się w e-commerce, oferując inteligentną pomoc zarówno w wyszukiwaniu produktów, jak i odpowiadaniu na pytania klientów. Oto kilka potencjalnych zastosowań:

  • Automatyczne odpowiadanie na pytania o dostępność produktów
  • Pomoc w wyszukiwaniu produktów według określonych kryteriów
  • Udostępnianie informacji o polityce zwrotów i wymian
  • Podawanie aktualnych promocji i ofert specjalnych
  • Odpowiadanie na pytania dotyczące czasu dostawy
  • Pomoc w doborze produktów według preferencji klienta
  • Automatyzacja obsługi często zadawanych pytań (FAQ)

Potrzebujesz pomocy w dostosowaniu? Skontaktuj się ze mną w celu konsultacji i wsparcia.


   Skopiuj kod szablonu   
{"id":"fqQcmSdoVqnPeGHj","meta":{"instanceId":"a4bfc93e975ca233ac45ed7c9227d84cf5a2329310525917adaf3312e10d5462","templateCredsSetupCompleted":true},"name":"OpenAI Personal Shopper with RAG and WooCommerce","tags":[],"nodes":[{"id":"635901e5-4afd-4c81-a63e-52f1b863a025","name":"When chat message received","type":"@n8n/n8n-nodes-langchain.chatTrigger","position":[-200,280],"webhookId":"bd3a878c-50b0-4d92-906f-e768a65c1485","parameters":{"options":{}},"typeVersion":1.1},{"id":"d11cd97c-1539-462d-858c-8758cf1a8278","name":"Window Buffer Memory","type":"@n8n/n8n-nodes-langchain.memoryBufferWindow","position":[620,580],"parameters":{"sessionKey":"={{ $('Edit Fields').item.json.sessionId }}","sessionIdType":"customKey"},"typeVersion":1.3},{"id":"02bb43e4-f26e-4906-8049-c49d3fecd817","name":"Calculator","type":"@n8n/n8n-nodes-langchain.toolCalculator","position":[760,580],"parameters":{},"typeVersion":1},{"id":"ad6058dd-b429-4f3c-b68a-7e3d98beec83","name":"Edit Fields","type":"n8n-nodes-base.set","position":[20,280],"parameters":{"options":{},"assignments":{"assignments":[{"id":"7015c229-f9fe-4c77-b2b9-4ac09a3a3cb1","name":"sessionId","type":"string","value":"={{ $json.sessionId }}"},{"id":"f8fc0044-6a1a-455b-a435-58931a8c4c8e","name":"chatInput","type":"string","value":"={{ $json.chatInput }}"}]}},"typeVersion":3.4},{"id":"43f7ee25-4529-4558-b5ea-c2a722b0bce5","name":"OpenAI Chat Model","type":"@n8n/n8n-nodes-langchain.lmChatOpenAi","position":[500,580],"parameters":{"options":{}},"credentials":{"openAiApi":{"id":"CDX6QM4gLYanh0P4","name":"OpenAi account"}},"typeVersion":1},{"id":"8b5ec20d-8735-4030-8113-717d578928eb","name":"RAG","type":"@n8n/n8n-nodes-langchain.toolVectorStore","position":[1000,580],"parameters":{"name":"informazioni_negozio","description":"Informazioni relative al negozio: orari di apertura, indirizzo, contatti, informazioni generali"},"typeVersion":1},{"id":"0fd0f1d6-41df-43d4-9418-0685afad409a","name":"Qdrant Vector Store","type":"@n8n/n8n-nodes-langchain.vectorStoreQdrant","position":[900,780],"parameters":{"options":{},"qdrantCollection":{"__rl":true,"mode":"list","value":"scarperia","cachedResultName":"scarperia"}},"credentials":{"qdrantApi":{"id":"iyQ6MQiVaF3VMBmt","name":"QdrantApi account"}},"typeVersion":1},{"id":"72084a2e-0e47-4723-a004-585ae8b67ae3","name":"Embeddings OpenAI","type":"@n8n/n8n-nodes-langchain.embeddingsOpenAi","position":[840,940],"parameters":{"options":{}},"credentials":{"openAiApi":{"id":"CDX6QM4gLYanh0P4","name":"OpenAi account"}},"typeVersion":1.1},{"id":"30d398a3-2331-4a3d-898d-c184779c7ef3","name":"OpenAI Chat Model1","type":"@n8n/n8n-nodes-langchain.lmChatOpenAi","position":[1200,800],"parameters":{"options":{}},"credentials":{"openAiApi":{"id":"CDX6QM4gLYanh0P4","name":"OpenAi account"}},"typeVersion":1},{"id":"e10a8024-51ec-4553-a1fa-dbaa49a4d2c2","name":"personal_shopper","type":"n8n-nodes-base.wooCommerceTool","position":[880,580],"parameters":{"options":{"sku":"={{ $('Information Extractor').item.json.output.SKU }}","search":"={{ $('Information Extractor').item.json.output.keyword }}","maxPrice":"={{ $('Information Extractor').item.json.output.price_max }}","minPrice":"={{ $('Information Extractor').item.json.output.price_min }}","stockStatus":"instock"},"operation":"getAll"},"credentials":{"wooCommerceApi":{"id":"d4EQtVORkOCNQZAm","name":"WooCommerce (Scarperia)"}},"typeVersion":1},{"id":"f0c53b0d-7173-4ec9-8fb4-f8f45d9ceedc","name":"Information Extractor","type":"@n8n/n8n-nodes-langchain.informationExtractor","position":[220,280],"parameters":{"text":"={{ $json.chatInput }}","options":{"systemPromptTemplate":"You are an intelligent assistant for a shoe and accessories store (mainly bags). Your task is to analyze the input text coming from a chat and determine if the user is looking for a product. If the user is looking for a product, you need to extract the following information:n1. The keyword (keyword) useful for the search.n2. Any minimum or maximum prices specified.n3. An SKU (product code) if mentioned.n4. The name of the category to search in, if specified.nnInstructions:n1. Identify the intent: Determine if the user is looking for a specific product.n2. Extract the information:n- If the user is looking for a product, identify:n- Set the type "search" to true. Otherwise, set it to falsen- The keywords.n- Any minimum or maximum prices (e.g. "less than 50 euros", "between 30 and 60 euros").n- An SKU (e.g. "ABC123 code").n- The category name (e.g. "t-shirts", "jeans", "women", "men").n3. Output format: Return a JSON object with the given structure"},"schemaType":"manual","inputSchema":"{n "search_intent": true,n "search_params": [n { "type": "search", "value": "ture or false" },n { "type": "keyword", "value": "valore_keyword" },n { "type": "min_price", "value": "valore_min_price" },n { "type": "max_price", "value": "valore_max_price" },n { "type": "sku", "value": "valore_sku" },n { "type": "category", "value": "valore_categoria" }n ]n }"},"typeVersion":1},{"id":"8386e554-e2f1-42c8-881f-a06e8099f718","name":"OpenAI Chat Model2","type":"@n8n/n8n-nodes-langchain.lmChatOpenAi","position":[200,460],"parameters":{"options":{}},"credentials":{"openAiApi":{"id":"CDX6QM4gLYanh0P4","name":"OpenAi account"}},"typeVersion":1.1},{"id":"4ff30e15-1bf5-4750-a68a-e72f86a4f32c","name":"Google Drive2","type":"n8n-nodes-base.googleDrive","position":[320,-440],"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":"list","value":"1lmnqpLFKS-gXmXT92C5VG0P1XlcoeFOb","cachedResultUrl":"https://drive.google.com/drive/folders/1lmnqpLFKS-gXmXT92C5VG0P1XlcoeFOb","cachedResultName":"Scarperia Salò - RAG"}},"options":{},"resource":"fileFolder"},"credentials":{"googleDriveOAuth2Api":{"id":"HEy5EuZkgPZVEa9w","name":"Google Drive account"}},"typeVersion":3},{"id":"b4ca79b2-220b-4290-a33a-596250c8fd2d","name":"Google Drive1","type":"n8n-nodes-base.googleDrive","position":[520,-440],"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":"18f5e068-ad4a-4be7-987c-83ed5791f012","name":"Embeddings OpenAI3","type":"@n8n/n8n-nodes-langchain.embeddingsOpenAi","position":[680,-260],"parameters":{"options":{}},"credentials":{"openAiApi":{"id":"CDX6QM4gLYanh0P4","name":"OpenAi account"}},"typeVersion":1.1},{"id":"43693ee0-a2a3-44d3-86de-4156af84e251","name":"Default Data Loader2","type":"@n8n/n8n-nodes-langchain.documentDefaultDataLoader","position":[880,-220],"parameters":{"options":{},"dataType":"binary"},"typeVersion":1},{"id":"f0d351e5-faee-49a4-a43c-985785c3d2c8","name":"Token Splitter1","type":"@n8n/n8n-nodes-langchain.textSplitterTokenSplitter","position":[960,-60],"parameters":{"chunkSize":300,"chunkOverlap":30},"typeVersion":1},{"id":"ff77338e-4dac-4261-87a1-10a21108f543","name":"When clicking ‘Test workflow’","type":"n8n-nodes-base.manualTrigger","position":[-200,-440],"parameters":{},"typeVersion":1},{"id":"72484893-875a-4e8b-83fc-ca137e812050","name":"HTTP Request","type":"n8n-nodes-base.httpRequest","position":[40,-440],"parameters":{"url":"https://QDRANTURL/collections/NAME/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":"5837e3ac-e3d1-45b6-bd67-8c3d03bf0a1e","name":"Sticky Note","type":"n8n-nodes-base.stickyNote","position":[-20,-500],"parameters":{"width":259.7740863787376,"height":234.1528239202657,"content":"Replace the URL and Collection name with your own"},"typeVersion":1},{"id":"79baf424-e647-4a80-a19e-c023ad3b1860","name":"Qdrant Vector Store1","type":"@n8n/n8n-nodes-langchain.vectorStoreQdrant","position":[760,-440],"parameters":{"mode":"insert","options":{},"qdrantCollection":{"__rl":true,"mode":"list","value":"scarperia","cachedResultName":"scarperia"}},"credentials":{"qdrantApi":{"id":"iyQ6MQiVaF3VMBmt","name":"QdrantApi account"}},"typeVersion":1},{"id":"17015f50-a3a8-4e62-9816-7e71127c1ea1","name":"Sticky Note1","type":"n8n-nodes-base.stickyNote","position":[-220,-640],"parameters":{"color":3,"width":1301.621262458471,"height":105.6212624584717,"content":"## Step 1 nCreate a collectiopn on your Qdrant instance. Then create a basic RAG system with documents uploaded to Google Drive and embedded in the Qdrant vector database"},"typeVersion":1},{"id":"0ddbf6be-fa2d-4412-8e85-fe108cd6e84d","name":"Sticky Note2","type":"n8n-nodes-base.stickyNote","position":[1020,980.0000000000001],"parameters":{"color":3,"width":1301.621262458471,"height":105.6212624584717,"content":"## Step 1 nCreate a basic RAG system with documents uploaded to Google Drive and embedded in the Qdrant vector database"},"typeVersion":1},{"id":"3782a22d-b3a7-44ea-ad36-fa4382c9fcfd","name":"Sticky Note3","type":"n8n-nodes-base.stickyNote","position":[-200,120],"parameters":{"color":3,"width":1301.621262458471,"height":105.6212624584717,"content":"## Step 2 nThe Information Extractor tries to understand if the request is related to products and if so, it extracts the useful information to filter the products available on WooCommerce by calling the "personal_shopper". If it is a general question, the RAG system is called"},"typeVersion":1},{"id":"d4d1fb16-3f54-4c1a-ab4e-bcf86d897e9d","name":"AI Agent","type":"@n8n/n8n-nodes-langchain.agent","position":[580,280],"parameters":{"text":"={{ $('When chat message received').item.json.chatInput }}","options":{"systemMessage":"=You are an intelligent assistant for a clothing store. Your task is to analyze the input text from a chat and determine if the user is looking for a product.nnBehavior:n- If the user is looking for a product the "search" field of the following JSON is set to true and you must pass the following JSON as input to the "personal_shopper" tool to extract:nn```jsonn{{ JSON.stringify($json.output) }}n```nn- If the user asks questions related to the store such as address or opening hours, you must use the "RAG" tool"},"promptType":"define"},"typeVersion":1.7}],"active":false,"pinData":{},"settings":{"executionOrder":"v1"},"versionId":"47513e11-8e9f-4b7c-b3de-e15cf00a1200","connections":{"RAG":{"ai_tool":[[{"node":"AI Agent","type":"ai_tool","index":0}]]},"Calculator":{"ai_tool":[[{"node":"AI Agent","type":"ai_tool","index":0}]]},"Edit Fields":{"main":[[{"node":"Information Extractor","type":"main","index":0}]]},"HTTP Request":{"main":[[{"node":"Google Drive2","type":"main","index":0}]]},"Google Drive1":{"main":[[{"node":"Qdrant Vector Store1","type":"main","index":0}]]},"Google Drive2":{"main":[[{"node":"Google Drive1","type":"main","index":0}]]},"Token Splitter1":{"ai_textSplitter":[[{"node":"Default Data Loader2","type":"ai_textSplitter","index":0}]]},"personal_shopper":{"ai_tool":[[{"node":"AI Agent","type":"ai_tool","index":0}]]},"Embeddings OpenAI":{"ai_embedding":[[{"node":"Qdrant Vector Store","type":"ai_embedding","index":0}]]},"OpenAI Chat Model":{"ai_languageModel":[[{"node":"AI Agent","type":"ai_languageModel","index":0}]]},"Embeddings OpenAI3":{"ai_embedding":[[{"node":"Qdrant Vector Store1","type":"ai_embedding","index":0}]]},"OpenAI Chat Model1":{"ai_languageModel":[[{"node":"RAG","type":"ai_languageModel","index":0}]]},"OpenAI Chat Model2":{"ai_languageModel":[[{"node":"Information Extractor","type":"ai_languageModel","index":0}]]},"Qdrant Vector Store":{"ai_vectorStore":[[{"node":"RAG","type":"ai_vectorStore","index":0}]]},"Default Data Loader2":{"ai_document":[[{"node":"Qdrant Vector Store1","type":"ai_document","index":0}]]},"Window Buffer Memory":{"ai_memory":[[{"node":"AI Agent","type":"ai_memory","index":0}]]},"Information Extractor":{"main":[[{"node":"AI Agent","type":"main","index":0}]]},"When chat message received":{"main":[[{"node":"Edit Fields","type":"main","index":0}]]},"When clicking ‘Test workflow’":{"main":[[{"node":"HTTP Request","type":"main","index":0}]]}}}
  • API
  • Request
  • URL
  • Build
  • cURL
  • LangChain
  • Chat
  • Conversational
  • Plan and Execute
  • ReAct
  • Tools
  • NER
  • parse
  • parsing
  • JSON
  • data extraction
  • structured
Planeta AI 2025 
magic-wandmenu linkedin facebook pinterest youtube rss twitter instagram facebook-blank rss-blank linkedin-blank pinterest youtube twitter instagram