planeta ai logo
Darmowy szablon automatyzacji

🔐🦙Prywatny i lokalny Ollama Self-Hosted + Dynamiczny router LLM

9014
25 dni temu
16
bloków

Dla kogo jest ten szablon?

Ten szablon workflow jest przeznaczony dla entuzjastów sztucznej inteligencji, programistów oraz użytkowników dbających o prywatność, którzy chcą wykorzystać potencjał lokalnych dużych modeli językowych (LLM) bez wysyłania danych do zewnętrznych usług. Szczególnie przydatny jest dla osób korzystających lokalnie z Ollama, które chcą inteligentnie kierować zapytania między różnymi wyspecjalizowanymi modelami.

Jaki problem rozwiązuje ten workflow?

Podczas pracy z wieloma lokalnymi modelami LLM, z których każdy ma różne mocne strony i możliwości, ręczne wybieranie odpowiedniego modelu do konkretnego zadania może być trudne. Ten workflow automatycznie analizuje prompty użytkownika i kieruje je do najbardziej odpowiedniego wyspecjalizowanego modelu Ollama, zapewniając optymalną wydajność bez wymagania od użytkownika wiedzy technicznej.

Co robi ten workflow?

Ten inteligentny router:

  • Analizuje przychodzące prompty użytkownika, aby określić charakter żądania
  • Automatycznie wybiera optymalny model Ollama z lokalnej kolekcji na podstawie wymagań zadania
  • Kieruje żądania między wyspecjalizowanymi modelami dla różnych zadań
  • Utrzymuje pamięć konwersacji dla spójnych interakcji
  • Przetwarza wszystko lokalnie, zapewniając pełną prywatność i bezpieczeństwo danych

Przykłady zastosowań

Ten workflow może być wykorzystany w wielu różnych scenariuszach, gdzie potrzebna jest inteligentna dystrybucja zadań między specjalistycznymi modelami językowymi. Oto kilka potencjalnych zastosowań:

  • Automatyczne odpowiadanie na pytania techniczne, kierując zapytania do modeli specjalizujących się w konkretnych dziedzinach
  • Asystent programistyczny, który rozpoznaje pytania dotyczące kodu i automatycznie używa modelu programistycznego
  • System analizy obrazów, który wykrywa zapytania wizualne i używa odpowiedniego modelu wizyjnego
  • Inteligentny chatbot, który dostosowuje się do charakteru rozmowy i wybiera najlepszy model konwersacyjny
  • System wsparcia klienta, który rozpoznaje intencję użytkownika i dobiera odpowiedni model odpowiedzi
  • Narzędzie badawcze, które automatycznie kieruje zapytania naukowe do modeli o odpowiedniej specjalizacji
  • Asystent pisarski, który rozpoznaje rodzaj tekstu (np. kreatywny, techniczny) i używa odpowiedniego modelu

Konfiguracja

  • Upewnij się, że masz zainstalowaną i działającą lokalnie Ollama
  • Pobierz wymagane modele wymienione w workflow za pomocą Ollama CLI (np. ollama pull phi4)
  • Skonfiguruj dane dostępowe API Ollama w n8n (domyślnie: http://127.0.0.1:11434)
  • Aktywuj workflow i rozpocznij interakcję przez interfejs czatu

Jak dostosować workflow do swoich potrzeb

  • Dodaj lub usuń modele z frameworku decyzyjnego routera na podstawie swojej konkretnej kolekcji Ollama
  • Dostosuj systemowe prompty w LLM Routerze, aby priorytetyzować różne kryteria wyboru modelu
  • Zmodyfikuj logikę drzewa decyzyjnego, aby lepiej pasowała do konkretnych przypadków użycia
  • Dodaj dodatkowe kroki przetwarzania wstępnego dla wyspecjalizowanych danych wejściowych

Ten workflow demonstruje, jak n8n może być wykorzystany do tworzenia zaawansowanych systemów orkiestracji AI, które szanują prywatność użytkownika, utrzymując wszystko lokalnie, jednocześnie zapewniając inteligentne możliwości wyboru modelu.

   Skopiuj kod szablonu   
{"id":"Mub5RZI4PAs6TsSP","meta":{"instanceId":"31e69f7f4a77bf465b805824e303232f0227212ae922d12133a0f96ffeab4fef","templateCredsSetupCompleted":true},"name":"🔐🦙🤖 Private & Local Ollama Self-Hosted LLM Router","tags":[],"nodes":[{"id":"981e858a-cd2b-49cf-9740-a40ac29bba94","name":"When chat message received","type":"@n8n/n8n-nodes-langchain.chatTrigger","position":[420,860],"webhookId":"3804aa1d-2193-4161-84a1-6f5d1059e092","parameters":{"options":{}},"typeVersion":1.1},{"id":"a164103c-66cb-44da-aae7-177231f517b4","name":"Sticky Note","type":"n8n-nodes-base.stickyNote","position":[-160,580],"parameters":{"color":7,"width":2360,"height":860,"content":"# 🔐🦙🤖 Private & Local Ollama Self-Hosted + Dynamic LLM Routernnn"},"typeVersion":1},{"id":"2ff955e7-c621-4bee-8baf-91769524f781","name":"Sticky Note1","type":"n8n-nodes-base.stickyNote","position":[640,1140],"parameters":{"color":7,"width":360,"height":260,"content":"## Ollama LLM"},"typeVersion":1},{"id":"40f42923-830d-44a9-a311-c006d91691b7","name":"Sticky Note2","type":"n8n-nodes-base.stickyNote","position":[320,760],"parameters":{"color":4,"width":280,"height":300,"content":"## 👍Try Me!"},"typeVersion":1},{"id":"c49f5ff5-92a7-4a2d-81b5-51272e7972b4","name":"Sticky Note3","type":"n8n-nodes-base.stickyNote","position":[740,720],"parameters":{"color":3,"width":540,"height":380,"content":"## Ollama LLM Router Based on User Promptnn💡This agent chooses the Ollama LLM for the next AI Agent Dynamically based on the users promptnn"},"typeVersion":1},{"id":"72ad69f4-a24f-4df2-978e-71c5d3a63733","name":"Ollama Dynamic LLM","type":"@n8n/n8n-nodes-langchain.lmChatOllama","position":[1560,1240],"parameters":{"model":"={{ $('LLM Router').item.json.output.parseJson().llm }}","options":{}},"credentials":{"ollamaApi":{"id":"7aPaLgwpfdMWFYm9","name":"Ollama account 127.0.0.1"}},"typeVersion":1},{"id":"efc2e47a-1d4b-4879-8670-35a34c946bb6","name":"LLM Router","type":"@n8n/n8n-nodes-langchain.agent","position":[880,860],"parameters":{"text":"=Choose the most appropriate LLM model for the following user request. Analyze the task requirements carefully and select the model that will provide optimal performance. Only choose from the provided list.nnn{{ $json.chatInput }}nn","options":{"systemMessage":"nYou are an expert LLM router that classifies user prompts and selects the most appropriate LLM model based on specific task requirements.nnnnYour task is to analyze user inputs, determine the nature of their request, and select the optimal LLM model that will provide the best performance for their specific needs.nnnnChoose one of the following LLMs based on their capabilities and the user prompt. You must only select from the provided LLMs:nn## Text-Only Modelsn- "qwq": Specialized in complex reasoning and solving hard problems. Best for: mathematical reasoning, logical puzzles, scientific explanations, and complex problem-solving tasks.nn- "llama3.2": Multilingual model (3B size) optimized for dialogue, retrieval, and summarization. Best for: conversations in multiple languages, information retrieval, and text summarization.nn- "phi4": Lightweight model designed for constrained environments. Best for: scenarios requiring low latency, limited computing resources, while maintaining good reasoning capabilities.nn## Coding Modelsn- "qwen2.5-coder:14b": Code-Specific Qwen model, with significant improvements in code generation, code reasoning, and code fixing.nn## Vision-Language Modelsn- "granite3.2-vision": Specialized in document understanding and data extraction. Best for: analyzing charts, tables, diagrams, infographics, and structured visual content.nn- "llama3.2-vision": General-purpose visual recognition and reasoning. Best for: image description, visual question answering, and general image understanding tasks.nnnnExample tasks for each model:n- qwq: "Solve this math problem", "Explain quantum physics", "Debug this logical fallacy"n- llama3.2: "Translate this text to Spanish", "Summarize this article", "Have a conversation about history"n- phi4: "Generate a quick response", "Provide a concise answer", "Process this simple request efficiently"n- granite3.2-vision: "Extract data from this chart", "Analyze this financial table", "Interpret this technical diagram"n- llama3.2-vision: "Describe what's in this image", "What can you tell me about this picture?", "Answer questions about this photo"nnnn1. Does the prompt include an image?n - YES → Go to 2n - NO → Go to 3n2. Is the image a document, chart, table, or diagram?n - YES → Use "granite3.2-vision"n - NO → Use "llama3.2-vision"n3. Does the task require complex reasoning or solving difficult problems?n - YES → Use "qwq"n - NO → Go to 4n4. Is the task multilingual or requires summarization/retrieval?n - YES → Use "llama3.2"n - NO → Use "phi4" (for efficiency in simple English tasks)nnnnWhen selecting a model, consider:n1. Task complexity and reasoning requirementsn2. Visual or multimodal components in the requestn3. Language processing needs (summarization, translation, etc.)n4. Performance constraints (latency, memory limitations)n5. Required reasoning capabilitiesn6. Coding requirementsnnnnExample 1:nUser input: "Explain quantum computing principles"nSelection: "qwq"nReason: "This request requires deep reasoning and explanation of complex scientific concepts, making QwQ's enhanced reasoning capabilities ideal."nnExample 2:nUser input: "Describe what's in this image of a chart showing quarterly sales"nSelection: "granite3.2-vision"nReason: "This request involves visual document understanding and data extraction from a chart, which is granite-vision's specialty."nnExample 3:nUser input: "Summarize this article about climate change in Spanish"nSelection: "llama3.2"nReason: "This request requires multilingual capabilities and summarization, which are strengths of Llama 3.2."nnExample 4:nUser input: "I need to create a FastAPI endpoint with Python"nSelection: "qwen2.5-coder:14b"nReason: "This request requires code generation, code reasoning, or code fixing."nnnnIf the user request is unclear or ambiguous, select the model that offers the most general capabilities while noting the uncertainty in your reasoning. If the request appears to contain harmful content or violates ethical guidelines, respond with an appropriate message about being unable to fulfill the request.nnnnRespond with a single JSON object containing:n{n "llm": "the name of the selected LLM model",n "reason": "a brief, specific explanation of why this model is optimal for the task"n}nAvoid any preamble or further explanation. Remove all ``` or ``json from response.nnnn"},"promptType":"define","hasOutputParser":true},"typeVersion":1.7},{"id":"d8b07c67-b177-496f-ba97-2b886c2b6f1e","name":"AI Agent with Dynamic LLM","type":"@n8n/n8n-nodes-langchain.agent","position":[1660,860],"parameters":{"text":"={{ $('When chat message received').item.json.chatInput }}","options":{"systemMessage":""},"promptType":"define"},"typeVersion":1.7},{"id":"3f005c9c-dd92-4970-b4cf-e105ec75840f","name":"Ollama phi4","type":"@n8n/n8n-nodes-langchain.lmChatOllama","position":[780,1240],"parameters":{"model":"phi4:latest","options":{"format":"json"}},"credentials":{"ollamaApi":{"id":"7aPaLgwpfdMWFYm9","name":"Ollama account 127.0.0.1"}},"typeVersion":1},{"id":"47f6c3dd-1bad-458c-ade1-ec26f455a95d","name":"Router Chat Memory","type":"@n8n/n8n-nodes-langchain.memoryBufferWindow","position":[1160,1240],"parameters":{},"typeVersion":1.3},{"id":"06b77321-086a-42cf-808a-27d7064403e4","name":"Agent Chat Memory","type":"@n8n/n8n-nodes-langchain.memoryBufferWindow","position":[1940,1240],"parameters":{"sessionKey":"={{ $('When chat message received').item.json.sessionId }}","sessionIdType":"customKey"},"typeVersion":1.3},{"id":"073ae421-5bbf-4ff9-ae8d-1f515f0b8ed7","name":"Sticky Note7","type":"n8n-nodes-base.stickyNote","position":[1520,720],"parameters":{"color":5,"width":540,"height":380,"content":"## AI Agent using Dynamic Local Ollama LLMnn💡This agent uses the Ollama LLM based on previous Router agent choice and proceeds to answer the users prompt.n"},"typeVersion":1},{"id":"2e118ce5-bfa8-4661-99dd-5e72bc7534c6","name":"Sticky Note4","type":"n8n-nodes-base.stickyNote","position":[1020,1140],"parameters":{"color":7,"width":360,"height":260,"content":"## Router Chat Memory"},"typeVersion":1},{"id":"92fff699-0e96-4161-b4dd-bcac682d3dab","name":"Sticky Note8","type":"n8n-nodes-base.stickyNote","position":[1420,1140],"parameters":{"color":7,"width":360,"height":260,"content":"## Dynamic Ollama LLM"},"typeVersion":1},{"id":"6f8bc049-9440-4863-a8c6-c8cfafde3dda","name":"Sticky Note9","type":"n8n-nodes-base.stickyNote","position":[1800,1140],"parameters":{"color":7,"width":360,"height":260,"content":"## Agent Chat Memory"},"typeVersion":1},{"id":"88e0d3ec-108b-4136-86ae-6714f4e4b63b","name":"Sticky Note5","type":"n8n-nodes-base.stickyNote","position":[-380,700],"parameters":{"width":640,"height":1020,"content":"## Who is this for?nThis workflow template is designed for **AI enthusiasts**, **developers**, and **privacy-conscious users** who want to leverage the power of local large language models (LLMs) without sending data to external services. It's particularly valuable for those running Ollama locally who want intelligent routing between different specialized models.nn## What problem is this workflow solving?nWhen working with multiple local LLMs, each with different strengths and capabilities, it can be challenging to manually select the right model for each specific task. This workflow automatically analyzes user prompts and routes them to the most appropriate specialized Ollama model, ensuring optimal performance without requiring technical knowledge from the end user.nn## What this workflow doesnThis intelligent router:n- Analyzes incoming user prompts to determine the nature of the requestn- Automatically selects the optimal Ollama model from your local collection based on task requirementsn- Routes requests between specialized models for different tasks:n - Text-only models (qwq, llama3.2, phi4) for various reasoning and conversation tasksn - Code-specific models (qwen2.5-coder) for programming assistancen - Vision-capable models (granite3.2-vision, llama3.2-vision) for image analysisn- Maintains conversation memory for consistent interactionsn- Processes everything locally for complete privacy and data securitynn## Setupn1. Ensure you have [Ollama](https://ollama.ai/) installed and running locallyn2. Pull the required models mentioned in the workflow using Ollama CLI (e.g., `ollama pull phi4`)n3. Configure the Ollama API credentials in n8n (default: http://127.0.0.1:11434)n4. Activate the workflow and start interacting through the chat interfacenn## How to customize this workflow to your needsn- Add or remove models from the router's decision framework based on your specific Ollama collectionn- Adjust the system prompts in the LLM Router to prioritize different model selection criterian- Modify the decision tree logic to better suit your specific use casesn- Add additional preprocessing steps for specialized inputsnnnThis workflow demonstrates how n8n can be used to create sophisticated AI orchestration systems that respect user privacy by keeping everything local while still providing intelligent model selection capabilities.n"},"typeVersion":1}],"active":false,"pinData":{},"settings":{"executionOrder":"v1"},"versionId":"c36ec004-11a3-4b0f-b2fd-f529ae6413a2","connections":{"LLM Router":{"main":[[{"node":"AI Agent with Dynamic LLM","type":"main","index":0}]]},"Ollama phi4":{"ai_languageModel":[[{"node":"LLM Router","type":"ai_languageModel","index":0}]]},"Agent Chat Memory":{"ai_memory":[[{"node":"AI Agent with Dynamic LLM","type":"ai_memory","index":0}]]},"Ollama Dynamic LLM":{"ai_languageModel":[[{"node":"AI Agent with Dynamic LLM","type":"ai_languageModel","index":0}]]},"Router Chat Memory":{"ai_memory":[[{"node":"LLM Router","type":"ai_memory","index":0}]]},"When chat message received":{"main":[[{"node":"LLM Router","type":"main","index":0}]]}}}
  • 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