{ "name": "RAG CHATBOT Main", "nodes": [ { "parameters": { "rules": { "values": [ { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "strict", "version": 2 }, "conditions": [ { "leftValue": "={{ $json.type }}", "rightValue": "video", "operator": { "type": "string", "operation": "equals" }, "id": "ee97bdcd-85e9-4a53-9e77-74ff9d8811cd" } ], "combinator": "and" } }, { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "strict", "version": 2 }, "conditions": [ { "id": "57cddf6d-0a6a-43d2-b8a8-d79ee18948cc", "leftValue": "={{ $json.type }}", "rightValue": "web", "operator": { "type": "string", "operation": "equals" } } ], "combinator": "and" } }, { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "strict", "version": 2 }, "conditions": [ { "id": "72df165a-aac1-4b28-a212-d4f0b4e287d6", "leftValue": "={{ $json.type }}", "rightValue": "file", "operator": { "type": "string", "operation": "equals", "name": "filter.operator.equals" } } ], "combinator": "and" } } ] }, "options": {} }, "type": "n8n-nodes-base.switch", "typeVersion": 3.2, "position": [ 1780, -140 ], "id": "b9750e31-4775-498c-865a-2e21f5049980", "name": "Switch" }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "strict", "version": 2 }, "conditions": [ { "id": "66c450c0-67d3-43b5-af09-58d197191a99", "leftValue": "={{ $('Telegram Trigger').item.json.message.document.file_name }}", "rightValue": "", "operator": { "type": "string", "operation": "exists", "singleValue": true } } ], "combinator": "and" }, "options": {} }, "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 960, -80 ], "id": "932dca78-1f92-41c0-9bf3-b13bcec39696", "name": "file?" }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "strict", "version": 2 }, "conditions": [ { "id": "dba766ff-d7e2-4b0c-bcb5-5433a1cb9042", "leftValue": "={{ $('Telegram Trigger').item.json.message.document.mime_type }}", "rightValue": "^(text/plain|application/pdf|application/vnd\\.openxmlformats-officedocument\\.wordprocessingml\\.document)$", "operator": { "type": "string", "operation": "notRegex" } } ], "combinator": "and" }, "options": {} }, "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 1100, -280 ], "id": "c5d1005d-e68e-4182-ba67-862807f32265", "name": "Format ok?" }, { "parameters": { "chatId": "={{ $('Telegram Trigger').item.json.message.from.id }}", "text": "\u041f\u0440\u0438\u0448\u043b\u0438\u0442\u0435 \u0444\u0430\u0439\u043b\u044b \u0432 \u0444\u043e\u0440\u043c\u0430\u0442\u0430\u0445 txt, docx, pdf.", "additionalFields": { "appendAttribution": false } }, "type": "n8n-nodes-base.telegram", "typeVersion": 1.2, "position": [ 1340, -280 ], "id": "619c90b1-af63-4418-89c3-1d03810b4417", "name": "Format Error", "credentials": { "telegramApi": { "name": "" } } }, { "parameters": { "resource": "file", "fileId": "={{ $json.file_id }}" }, "type": "n8n-nodes-base.telegram", "typeVersion": 1.2, "position": [ 2280, 480 ], "id": "79f69f51-9384-43fc-825e-a9490674ee79", "name": "File", "credentials": { "telegramApi": { "name": "" } } }, { "parameters": { "updates": [ "message", "callback_query" ], "additionalFields": {} }, "type": "n8n-nodes-base.telegramTrigger", "typeVersion": 1.2, "position": [ -580, 520 ], "id": "9232fbfd-e214-407e-9b17-9be50cf2b179", "name": "Telegram Trigger", "credentials": { "telegramApi": { "name": "" } } }, { "parameters": { "model": { "__rl": true, "mode": "list", "value": "gpt-4o-mini" }, "options": {} }, "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "typeVersion": 1.2, "position": [ 2300, -1080 ], "id": "ce999632-a114-4397-8334-9a151bdf252b", "name": "OpenAI Chat Model", "credentials": { "openAiApi": { "name": "" } } }, { "parameters": { "descriptionType": "manual", "toolDescription": "Use MCP client for video transcription", "operation": "executeTool", "toolName": "={{ $fromAI(\"tool\", \"the tool selected\") }}", "toolParameters": "={\n \"videoUrl\": \"{{ $fromAI('url', 'URL of the page to transcribe') }}\"\n }" }, "type": "n8n-nodes-mcp.mcpClientTool", "typeVersion": 1, "position": [ 2600, -1080 ], "id": "ad11b3a5-d7a8-44d6-94b0-bccd9227538f", "name": "Transcribe", "credentials": { "mcpClientApi": { "name": "" } } }, { "parameters": { "options": { "systemMessage": "You are an AI agent integrated into n8n for YouTube video transcription.\n\n**Task:**\n1. **Process Links:**\n * When you receive one or more YouTube video links, process them **sequentially**, one after the other.\n * For each link, use the `executetool` tool.\n * When calling `executetool`, you **must** use the following JSON structure to specify the tool and its parameters, substituting the actual link into the `videoUrl` field:\n ```json\n {\n \"tool\": \"get-youtube-transcript\",\n \"Tool_Parameters\": {\n \"videoUrl\": \"INSERT_VIDEO_LINK_HERE\"\n }\n }\n ```\n2. **Format Response:**\n * Collect the result from the `executetool` execution (i.e., the output of the `get-youtube-transcript` tool) for each processed link.\n * In the final response, for each link, include the **standard success message and result** (including the transcription text) that is typically generated after using the `get-youtube-transcript` tool.\n * Present these standard outputs for each link sequentially within one message, ensuring they are clearly separated (e.g., by a blank line).\n}" } }, "type": "@n8n/n8n-nodes-langchain.agent", "typeVersion": 1.8, "position": [ 2360, -1220 ], "id": "5215625f-44a5-45f9-860b-2821f3b560f4", "name": "Paid transcription" }, { "parameters": { "content": "## VIDEO TRANSCRIPT (PAID, API DUMPLINGAI)\n", "height": 360, "width": 520, "color": 4 }, "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ 2240, -1300 ], "id": "33598b24-6a86-46b3-a2fc-5e8826d5b46f", "name": "Sticky Note" }, { "parameters": { "executeOnce": false, "command": "=yt-dlp --cookies \"/home/node/cookies.txt\" -x --audio-format mp3 -o \"{{$json.dynamicAudioPath}}\" '{{ $json.url }}'\n\n" }, "type": "n8n-nodes-base.executeCommand", "typeVersion": 1, "position": [ 2440, -600 ], "id": "237012f8-3399-45fa-b74c-c40380f879dc", "name": "Audio extract", "executeOnce": false }, { "parameters": { "fileSelector": "={{ $('Set Names').item.json.dynamicAudioPath }}", "options": {} }, "type": "n8n-nodes-base.readWriteFile", "typeVersion": 1, "position": [ 2660, -600 ], "id": "81b0060b-2880-4290-b369-284f2b043f81", "name": "Upload binary", "executeOnce": false }, { "parameters": { "assignments": { "assignments": [ { "id": "9a5bb0d7-223c-48a4-b12e-8fd86657a43d", "name": "video_id", "value": "={{$json.idx_in_batch}}", "type": "string" }, { "id": "0b22482a-49f1-46e3-833b-d3230ceeebc7", "name": "dynamicAudioPath", "value": "={{`/home/node/temp_audio/${$execution.id}_${$itemIndex}.mp3`}}", "type": "string" } ] }, "includeOtherFields": true, "options": {} }, "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 2220, -600 ], "id": "39f663d0-c735-48bd-a1b0-056321a4c130", "name": "Set Names" }, { "parameters": { "content": "## VIDEO TRANSCRIPT (FREE, LOCAL)\n", "height": 380, "width": 1440, "color": 7 }, "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ 2040, -820 ], "id": "a42a0764-b3c5-4f99-ad01-1aea5fad07f9", "name": "Sticky Note1" }, { "parameters": { "method": "POST", "url": "http://whisper-asr:9000/asr?output=srt", "sendBody": true, "contentType": "multipart-form-data", "bodyParameters": { "parameters": [ { "parameterType": "formBinaryData", "name": "audio_file", "inputDataFieldName": "data" } ] }, "options": {} }, "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [ 2860, -600 ], "id": "6f8e7897-ca10-4b9d-9de0-30aaba143232", "name": "Whisper Transcribe", "executeOnce": false }, { "parameters": { "model": "deepseek/deepseek-chat-v3-0324", "options": {} }, "type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter", "typeVersion": 1, "position": [ 2240, 20 ], "id": "ba1ef08d-e8fb-49ce-8ac2-ca74dd6230ff", "name": "OpenRouter Chat Model1", "credentials": { "openRouterApi": { "name": "" } } }, { "parameters": { "operation": "executeTool", "toolName": "firecrawl_scrape", "toolParameters": "={\n \"url\": \"{{ $fromAI('url', 'URL of the page to scrape') }}\",\n \"formats\": [\n \"markdown\"\n ],\n \"onlyMainContent\": true,\n \"waitFor\": 1000,\n \"timeout\": 30000,\n \"mobile\": false,\n \"includeTags\": [\n \"article\",\n \"main\",\n \".DocSearch-content\"\n ],\n \"excludeTags\": [\n \"nav\",\n \"footer\",\n \"header\",\n \"script\",\n \"style\"\n ],\n \"skipTlsVerification\": false\n}" }, "type": "n8n-nodes-mcp.mcpClientTool", "typeVersion": 1, "position": [ 2740, 0 ], "id": "e78cbe22-111b-4d6b-b9a5-efbd3cecfb16", "name": "Firecrawl scrape", "credentials": { "mcpClientApi": { "name": "" } }, "disabled": true }, { "parameters": { "mode": "runOnceForEachItem", "jsCode": "// 1. \u0443\u0431\u0440\u0430\u0442\u044c ```json \u2026 ```\nlet raw = $json.output ?? '';\nraw = raw.replace(/^```json\\s*/i,'').replace(/```$/i,'').trim();\n\n// 2. parse\nlet obj;\ntry { obj = JSON.parse(raw); } catch { obj = {}; }\n\n// 3. meta \u0438\u0437 Merge\nconst {\n batch_id,\n idx_in_batch,\n type = 'web',\n url,\n expected_map // \u2190 \u0441\u0447\u0451\u0442\u0447\u0438\u043a\u0438 \u043e\u0442 Split & Tag\n} = $json;\n\n// 4. \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\nreturn {\n json: {\n batch_id,\n idx_in_batch,\n type,\n url: obj.url ?? url,\n language: obj.language ?? null,\n title: obj.title ?? null,\n text: obj.text ?? '',\n expected_map, // \u2190 \u043f\u0440\u043e\u043a\u0438\u0434\u044b\u0432\u0430\u0435\u043c \u0431\u0435\u0437 \u0438\u0437\u043c\u0435\u043d\u0435\u043d\u0438\u0439\n retrieved_at: new Date().toISOString(),\n error: (obj.text ?? '').startsWith('ERROR')\n }\n};\n" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 2820, -160 ], "id": "a4c2fb78-2322-4e6f-95ae-1347ef63917a", "name": "Scrape Parser" }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "strict", "version": 2 }, "conditions": [ { "id": "641b9fae-4349-4893-a217-3688c2133df8", "leftValue": "={{ $json.error }}", "rightValue": true, "operator": { "type": "boolean", "operation": "equals" } } ], "combinator": "and" }, "options": {} }, "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 3000, -160 ], "id": "f93be6a9-9997-46fc-a469-d14b135ed1a2", "name": "Error check" }, { "parameters": { "chatId": "={{ $('Telegram Trigger').item.json.message.from.id }}", "text": "Scrape error", "additionalFields": { "appendAttribution": false } }, "type": "n8n-nodes-base.telegram", "typeVersion": 1.2, "position": [ 3200, -340 ], "id": "127e87cb-6ae6-4d59-8be5-ebef772cdb8e", "name": "Telegram", "credentials": { "telegramApi": { "name": "" } } }, { "parameters": { "content": "## SCRAPING (PAID, API FIRECRAWL.DEV)\n", "height": 520, "width": 1440, "color": 7 }, "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ 2040, -360 ], "id": "40aa9240-4446-4525-ac72-b72eb4ed833c", "name": "Sticky Note2" }, { "parameters": { "promptType": "define", "text": "={{ $json.url }}\nor\n{{ $json.chatInput }}", "hasOutputParser": true, "options": { "systemMessage": "You will receive URL/URL's in the user prompt.\nProcess it with scrape tool once for each url and return a single JSON object\u2014no arrays, no extra text. ONLY ON\nUSE EXACTLY ONE SCRAPETOOL CALL PER URL \u2014 NO MORE, NO LESS. \nTHE NUMBER OF SCRAPE CALLS MUST MATCH THE NUMBER OF URLS. \nDO NOT POST-PROCESS SCRAPE RESULTS WITH THE LANGUAGE MODEL \u2014 JUST COLLECT AND RETURN THEM AS RAW JSON.\nIF YOU RECEIVE TEXT FROM URL - DID NOT SEND IT URL AGAIN TO SCRAPE!!!!!\nSteps\n1. Run `scrapetool` with:\n {\n \"url\": ,\n \"format\": \"markdown\",\n \"cleaned\": true,\n \"renderJs\": true\n }\n\n2. If scraping fails \u2192 return:\n {\n \"url\": ,\n \"language\": null,\n \"title\": null,\n \"text\": \"ERROR: Failed to scrape URL\"\n }\n\n3. If scraping succeeds \u2192\n \u2022 Extract the best possible page title (prefer `result.metadata.title`, otherwise use the first ) \u2192 `title`.\n \u2022 Take the Markdown body, remove all boilerplate and irrelevant content:\n - navigation menus, cookie banners, polls, \u201cEdit this page\u201d links, \u201cWas this page helpful?\u201d, mailto: links, user feedback forms, share buttons, site footers, and similar UI elements.\n \u2022 Do NOT translate the title or the text\u2014return them in the original language.\n \u2022 Detect the language of the cleaned `text` (ISO 639-1, e.g., \"en\", \"ru\") and return as `language`.\n \u2022 If the cleaned body is empty \u2192 return:\n \"text\": \"INFO: No relevant content found\"\n \u2022 Normalize the output text: remove meaningless characters like repeated dashes or empty lines, use standard `\\n`, `\\n\\n` for paragraph formatting.\n\nDo not delete url in text if it part of a text (and it is important for the meaning)\n\nReturn exactly that JSON object and nothing else.\n" } }, "type": "@n8n/n8n-nodes-langchain.agent", "typeVersion": 1.8, "position": [ 2280, -140 ], "id": "fb039661-5af7-4b14-aa00-d242c165ae6d", "name": "Ai Scraping", "alwaysOutputData": false }, { "parameters": { "content": "## LOCAL EXTRACTOR TXT/PDF/PDF+IMG", "height": 420, "width": 1440, "color": 7 }, "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ 2040, 240 ], "id": "7f6a0213-f157-4e6b-a887-47fcee0d7309", "name": "Sticky Note3" }, { "parameters": { "content": "# \u041c\u041e\u0414\u0423\u041b\u042c \u0418\u0417\u0412\u041b\u0415\u0427\u0415\u041d\u0418\u042f \u041a\u041e\u041d\u0422\u0415\u041d\u0422\u0410\n", "height": 1600, "width": 1620, "color": 4 }, "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ 1940, -900 ], "id": "7266d7a1-524a-40ca-b5a7-0e7d111a3452", "name": "Sticky Note4" }, { "parameters": { "jsCode": "// 0. \u0441\u043e\u0431\u0438\u0440\u0430\u0435\u043c \u0432\u0445\u043e\u0434\nconst rows = [];\nfor (const el of $input.all()) {\n const j = el.json;\n if (Array.isArray(j.items)) rows.push(...j.items);\n else rows.push(j);\n}\nif (!rows.length) return []; // \u043d\u0435\u0447\u0435\u0433\u043e \u043e\u0431\u0440\u0430\u0431\u0430\u0442\u044b\u0432\u0430\u0442\u044c\n\n// 1. \u0441\u0447\u0438\u0442\u0430\u0435\u043c, \u0441\u043a\u043e\u043b\u044c\u043a\u043e \u043e\u0431\u044a\u0435\u043a\u0442\u043e\u0432 \u043a\u0430\u0436\u0434\u043e\u0433\u043e \u0442\u0438\u043f\u0430 \u0432\u0441\u0442\u0440\u0435\u0442\u0438\u043b\u043e\u0441\u044c\nconst expectedMap = {};\nrows.forEach(r => expectedMap[r.type] = (expectedMap[r.type] || 0) + 1);\n\nconst batchId = $execution.id;\nconst fallback = (id, i) => `file_${id || i}.bin`;\n\n// 2. \u0444\u043e\u0440\u043c\u0438\u0440\u0443\u0435\u043c \u0432\u044b\u0445\u043e\u0434\u043d\u044b\u0435 \u044d\u043b\u0435\u043c\u0435\u043d\u0442\u044b\nreturn rows.map((r, i) => {\n const item = { ...r };\n\n if (item.type === 'file') {\n item.file_name = item.file_name || fallback(item.file_id, i);\n }\n\n return {\n json: {\n batch_id: batchId,\n idx_in_batch: i,\n expected_map: expectedMap, // \u2190 { web:3, video:2, file:1 }\n ...item // type, url / file_id / file_name \u2026\n }\n };\n});\n" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 1560, -60 ], "id": "ee6c898d-8509-4c1c-abac-2d7f6085a4fc", "name": "Split & Tag" }, { "parameters": { "aggregate": "aggregateAllItemData", "destinationFieldName": "items", "options": {} }, "type": "n8n-nodes-base.aggregate", "typeVersion": 1, "position": [ 3960, -140 ], "id": "bc85b801-7a3f-421b-87d1-d85ef6d4ba3a", "name": "Aggregate" }, { "parameters": { "jsCode": "const items = $json.items || [];\nif (!items.length) return [];\n\n// \u0441\u043a\u043e\u043b\u044c\u043a\u043e \u0434\u043e\u043b\u0436\u043d\u043e \u0431\u044b\u0442\u044c (\u0431\u0435\u0440\u0451\u043c \u0438\u0437 \u043f\u0435\u0440\u0432\u043e\u0433\u043e \u044d\u043b\u0435\u043c\u0435\u043d\u0442\u0430 \u043f\u0430\u0440\u0442\u0438\u0438)\nconst need = items[0].expected_map || {};\n\n// \u0441\u043a\u043e\u043b\u044c\u043a\u043e \u0444\u0430\u043a\u0442\u0438\u0447\u0435\u0441\u043a\u0438 \u043f\u0440\u0438\u0448\u043b\u043e\nconst got = {};\nitems.forEach(it => got[it.type] = (got[it.type] || 0) + 1);\n\n// \u0433\u043e\u0442\u043e\u0432\u044b \u043b\u0438 \u0432\u0441\u0435 \u0442\u0438\u043f\u044b \u0432 \u043d\u0443\u0436\u043d\u043e\u043c \u043a\u043e\u043b\u0438\u0447\u0435\u0441\u0442\u0432\u0435?\nconst ready = Object.keys(need)\n .every(t => (got[t] || 0) >= need[t]);\n\nif (ready) {\n // \u0432\u044b\u043f\u0443\u0441\u043a\u0430\u0435\u043c \u0432\u0441\u044e \u043f\u0430\u0440\u0442\u0438\u044e \u043f\u043e \u043e\u0434\u043d\u043e\u043c\u0443 item\n return items.map(it => ({ json: it }));\n}\n\n// \u0435\u0449\u0451 \u0436\u0434\u0451\u043c \u2014 \u043d\u0438\u0447\u0435\u0433\u043e \u043d\u0435 \u043e\u0442\u0434\u0430\u0451\u043c\nreturn [];\n\n" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 4120, -140 ], "id": "45e13cdc-7398-4c57-999d-4532afd9c4a0", "name": "Gatekeeper" }, { "parameters": { "includeOtherFields": true, "options": {} }, "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 2380, -300 ], "id": "ebb7ccf0-2178-422f-8d36-a355ba81a838", "name": "Keep meta scraping" }, { "parameters": { "includeOtherFields": true, "options": {} }, "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 2480, 320 ], "id": "4ba43fb1-b51e-455d-8284-361abfeb4155", "name": "Keep meta file" }, { "parameters": { "mode": "combine", "combineBy": "combineByPosition", "options": {} }, "type": "n8n-nodes-base.merge", "typeVersion": 3.1, "position": [ 2640, -160 ], "id": "be91d867-c5a7-456c-a4f3-44bcc3845b89", "name": "Merge scraping" }, { "parameters": { "mode": "combine", "combineBy": "combineByPosition", "options": {} }, "type": "n8n-nodes-base.merge", "typeVersion": 3.1, "position": [ 2960, 340 ], "id": "48fa5fe4-fc76-4317-8d68-3a043d8a918f", "name": "Merge file" }, { "parameters": { "jsCode": "// ---------- 0) \u0423\u043d\u0438\u0432\u0435\u0440\u0441\u0430\u043b\u044c\u043d\u0430\u044f \u0440\u0430\u0441\u043f\u0430\u043a\u043e\u0432\u043a\u0430 \u0432\u0445\u043e\u0434\u0430 ----------\nfunction unwrapText(input) {\n let cur = input;\n for (let i = 0; i < 3; i++) { // \u0441\u043d\u0438\u043c\u0430\u0435\u043c \u0432\u043b\u043e\u0436\u0435\u043d\u043d\u044b\u0435 JSON-\u043e\u0431\u0451\u0440\u0442\u043a\u0438\n if (typeof cur === 'string') {\n try { cur = JSON.parse(cur); continue; } catch { break; }\n }\n break;\n }\n if (Array.isArray(cur)) {\n if (cur[0] && typeof cur[0].text === 'string') return cur[0].text;\n if (typeof cur[0] === 'string') return cur[0];\n }\n if (cur && typeof cur === 'object' && typeof cur.text === 'string') return cur.text;\n return String(cur ?? '');\n}\n\n// ---------- 1) \u0411\u0435\u0440\u0451\u043c \u0441\u044b\u0440\u043e\u0439 \u0442\u0435\u043a\u0441\u0442 ----------\nconst rawInner = unwrapText($json.text).replace(/\\r/g, '');\n\n// ---------- 2) \u0420\u0435\u0436\u0435\u043c \u043f\u043e \u043c\u0430\u0440\u043a\u0435\u0440\u0430\u043c \u0438 \u0441\u043e\u0431\u0438\u0440\u0430\u0435\u043c \u0441\u043e\u0434\u0435\u0440\u0436\u0438\u043c\u043e\u0435 \u043c\u0435\u0436\u0434\u0443 \u043d\u0438\u043c\u0438 ----------\nconst re = /--- (?:Page \\d+|OCR Text from Image on Page \\d+) ---\\n?([\\s\\S]*?)(?=--- (?:Page \\d+|OCR Text from Image on Page \\d+) ---|$)/g;\nlet m, chunks = [];\nwhile ((m = re.exec(rawInner)) !== null) {\n const t = m[1].trim();\n if (t) chunks.push(t);\n}\n\n// ---------- 3) \u041d\u043e\u0440\u043c\u0430\u043b\u0438\u0437\u0443\u0435\u043c \u0434\u043e \u0430\u0431\u0437\u0430\u0446\u0435\u0432 ----------\nlet text = chunks.join('\\n')\n .replace(/[ \\t]+$/gm, '') // \u0445\u0432\u043e\u0441\u0442\u043e\u0432\u044b\u0435 \u043f\u0440\u043e\u0431\u0435\u043b\u044b\n .replace(/\\n{3,}/g, '\\n\\n'); // \u043c\u0430\u043a\u0441\u0438\u043c\u0443\u043c \u0434\u0432\u043e\u0439\u043d\u043e\u0439 \u043f\u0443\u0441\u0442\u043e\u0439\n\nconst paras = text\n .split(/\\n{2,}/)\n .map(p => p\n .replace(/-\\n(?=\\p{L})/gu, '') // \u0441\u043d\u044f\u0442\u044c \u043f\u0435\u0440\u0435\u043d\u043e\u0441\u044b \u0441\u043b\u043e\u0432\n .replace(/\\n+/g, ' ') // \u043e\u0434\u0438\u043d\u043e\u0447\u043d\u044b\u0435 \u043f\u0435\u0440\u0435\u0432\u043e\u0434\u044b -> \u043f\u0440\u043e\u0431\u0435\u043b\n .replace(/[ \\t]+/g, ' ')\n .trim()\n )\n .filter(Boolean);\n\n// ---------- 4) \u0412\u043e\u0437\u0432\u0440\u0430\u0442 \u0432 \u0444\u043e\u0440\u043c\u0430\u0442\u0435 n8n ----------\nreturn [{ json: { text: paras.join('\\n\\n') } }];\n" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 2660, 480 ], "id": "dcc5d292-e428-4ed2-af1b-836a9793af15", "name": "Text Structured" }, { "parameters": { "mode": "combine", "combineBy": "combineByPosition", "options": {} }, "type": "n8n-nodes-base.merge", "typeVersion": 3.1, "position": [ 3160, -740 ], "id": "b6f0875e-31c4-4551-a038-e1eb17dd594f", "name": "Merge transcribe" }, { "parameters": { "includeOtherFields": true, "options": {} }, "type": "n8n-nodes-base.set", "typeVersion": 3.4, "position": [ 2220, -760 ], "id": "de142345-5ce8-4f89-bb58-6936de721ac0", "name": "Keep meta transcript" }, { "parameters": { "jsCode": "const items = $input.all();\n\nreturn items.map(({ json }) => {\n const {\n batch_id,\n idx_in_batch,\n type = 'video',\n expected_map,\n url,\n data = ''\n } = json;\n\n // 1. \u0420\u0430\u0437\u0431\u043e\u0440 SRT \u2014 \u0443\u0431\u0438\u0440\u0430\u0435\u043c \u043d\u043e\u043c\u0435\u0440 \u0441\u0442\u0440\u043e\u043a\u0438 \u0438 \u0442\u0430\u0439\u043c\u043a\u043e\u0434\u044b\n const lines = data\n .split(/\\n{2,}/)\n .map(block => block.split('\\n').slice(2)) // \u0443\u0431\u0438\u0440\u0430\u0435\u043c \u043d\u043e\u043c\u0435\u0440 \u0438 \u0442\u0430\u0439\u043c\u043a\u043e\u0434\n .flat()\n .filter(Boolean);\n\n const cleanText = lines.join('\\n').trim();\n\n // 2. \u042f\u0437\u044b\u043a\n const lang = /[\u0430-\u044f\u0451]/i.test(cleanText) ? 'ru' : 'en';\n\n // 3. \u0412\u043e\u0437\u0432\u0440\u0430\u0442\n return {\n json: {\n batch_id,\n idx_in_batch,\n type,\n url,\n language: lang,\n text: cleanText,\n expected_map,\n retrieved_at: new Date().toISOString(),\n error: !cleanText\n }\n };\n});\n\n" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 3340, -740 ], "id": "646b141c-86a6-4e88-b3de-f0c2f3fda31a", "name": "Video parser" }, { "parameters": { "executeOnce": false, "command": "=rm \"{{ $('Set Names').item.json.dynamicAudioPath }}\"" }, "type": "n8n-nodes-base.executeCommand", "typeVersion": 1, "position": [ 3160, -600 ], "id": "f1ec86ea-e0ec-49a2-a60e-55894c16e176", "name": "Temp delete" }, { "parameters": { "method": "POST", "url": "http://flask-app:5000/process_pdf", "sendBody": true, "contentType": "multipart-form-data", "bodyParameters": { "parameters": [ { "parameterType": "formBinaryData", "name": "pdf", "inputDataFieldName": "data" } ] }, "options": {} }, "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [ 2480, 480 ], "id": "f6b6d595-30bf-4527-9311-35f3748c5865", "name": "Extractor" }, { "parameters": { "mode": "runOnceForEachItem", "jsCode": "// \u0431\u0430\u0437\u043e\u0432\u044b\u0435 \u043f\u043e\u043b\u044f \u0438\u0437 Merge-\u0443\u0437\u043b\u0430\nconst {\n batch_id,\n idx_in_batch,\n type = 'file',\n expected_map, // \u2190 \u0441\u0447\u0451\u0442\u0447\u0438\u043a\u0438 \u043f\u0440\u0438\u0448\u043b\u0438 \u0438\u0437 Split & Tag\n file_id,\n file_name,\n text\n} = $json;\n\n/* \u043e\u0447\u0435\u043d\u044c \u0433\u0440\u0443\u0431\u043e\u0435 \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\u0438\u0435 \u044f\u0437\u044b\u043a\u0430 */\nconst lang = /[\u0430-\u044f\u0451]/i.test(text) ? 'ru' : 'en';\n\nreturn {\n json: {\n batch_id,\n idx_in_batch,\n type, // \"file\"\n file_name, // \u0441\u043e\u0445\u0440\u0430\u043d\u044f\u0435\u043c\n language: lang,\n text,\n expected_map, // \u2190 \u043f\u0440\u043e\u043a\u0438\u0434\u044b\u0432\u0430\u0435\u043c \u043a\u0430\u043a \u0435\u0441\u0442\u044c\n retrieved_at: new Date().toISOString(),\n error: !text || text.startsWith('ERROR')\n }\n};\n" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 3200, 340 ], "id": "87d67225-5fb1-4c33-bc6e-74ada56bbc89", "name": "File Parser" }, { "parameters": { "content": "## \u041c\u041e\u0414\u0423\u041b\u042c \u041f\u041e\u0414\u0413\u041e\u0422\u041e\u0412\u041a\u0418 \u0418\u041d\u0424\u041e\u0420\u041c\u0410\u0426\u0418\u0418 \u0418 \u042d\u041c\u0411\u0415\u0414\u0414\u0418\u041d\u0413\u0410", "height": 480, "width": 1180, "color": 4 }, "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ 4300, -320 ], "id": "05f6f8d8-512c-4328-b0e9-467d84301c4e", "name": "Sticky Note5" }, { "parameters": { "numberInputs": 3 }, "type": "n8n-nodes-base.merge", "typeVersion": 3.1, "position": [ 3780, -140 ], "id": "7ec25deb-9d0a-4cb7-8e86-aab542cfb919", "name": "Merge all" }, { "parameters": { "jsCode": "// --- \u041d\u0410\u0427\u0410\u041b\u041e \u041a\u041e\u0414\u0410 \u0414\u041b\u042f \u0423\u0417\u041b\u0410 n8n Clean & Format ---\n\n// \u0421\u044e\u0434\u0430 \u0434\u043e\u0431\u0430\u0432\u043b\u044f\u0439\u0442\u0435 \u0432\u0430\u0448\u0438 \u0440\u0435\u0433\u0443\u043b\u044f\u0440\u043d\u044b\u0435 \u0432\u044b\u0440\u0430\u0436\u0435\u043d\u0438\u044f \u0434\u043b\u044f \u0443\u0434\u0430\u043b\u0435\u043d\u0438\u044f \"\u043c\u0443\u0441\u043e\u0440\u0430\".\n// \u041e\u043d\u0438 \u0434\u043e\u043b\u0436\u043d\u044b \u0431\u044b\u0442\u044c \u0434\u043e\u0441\u0442\u0430\u0442\u043e\u0447\u043d\u043e \u043e\u0431\u0449\u0438\u043c\u0438, \u0447\u0442\u043e\u0431\u044b \u0440\u0430\u0431\u043e\u0442\u0430\u0442\u044c \u0434\u043b\u044f \u0440\u0430\u0437\u043d\u044b\u0445 \u0434\u043e\u043a\u0443\u043c\u0435\u043d\u0442\u043e\u0432.\n// \u041f\u0440\u0438\u043c\u0435\u0440 \u0438\u0437 \u0432\u0430\u0448\u0435\u0433\u043e \u0434\u043e\u043a\u0443\u043c\u0435\u043d\u0442\u0430, \u043d\u043e \u043b\u0443\u0447\u0448\u0435 \u043e\u0431\u043e\u0431\u0449\u0430\u0442\u044c \u0438\u043b\u0438 \u0438\u043c\u0435\u0442\u044c \u0441\u043f\u0438\u0441\u043e\u043a \u0442\u0430\u043a\u0438\u0445 \u043f\u0430\u0442\u0442\u0435\u0440\u043d\u043e\u0432.\nconst BOILERPLATE_PATTERNS = [\n /^back to top$/i,\n /^was this page helpful\\?$/i,\n /^thanks? for your feedback$/i,\n // \u0414\u043e\u0431\u0430\u0432\u044c\u0442\u0435 \u0441\u044e\u0434\u0430 \u0434\u0440\u0443\u0433\u0438\u0435 \u043f\u0430\u0442\u0442\u0435\u0440\u043d\u044b, \u043d\u0430\u043f\u0440\u0438\u043c\u0435\u0440:\n // /^\u0421\u043a\u0430\u0447\u0430\u043d\u043e \u0441 \u0441\u0430\u0439\u0442\u0430 - SuperSliv\\.biz - \u041f\u0440\u0438\u0441\u043e\u0435\u0434\u0438\u043d\u044f\u0439\u0441\u044f!$/gim,\n // /^SuperSliv\\.biz - \u0422\u0432\u043e\u0439 \u043b\u0443\u0447\u0448\u0438\u0439 \u0412\u042b\u0411\u041e\u0420!$/gim,\n // /\\^ \u0423\u0411\u041e\u0419\u041d\u042b\u0415 Oe/g, // \u0415\u0441\u043b\u0438 \u044d\u0442\u043e \u043f\u043e\u0441\u0442\u043e\u044f\u043d\u043d\u044b\u0439 \u0430\u0440\u0442\u0435\u0444\u0430\u043a\u0442\n];\n\nfunction cleanInline(str) {\n // \u0412\u0430\u0448\u0430 \u0441\u0443\u0449\u0435\u0441\u0442\u0432\u0443\u044e\u0449\u0430\u044f \u0444\u0443\u043d\u043a\u0446\u0438\u044f \u0434\u043b\u044f \u043e\u0447\u0438\u0441\u0442\u043a\u0438 inline-\u0440\u0430\u0437\u043c\u0435\u0442\u043a\u0438\n return str\n .replace(/\\[([^\\\\]]+?)\\]\\((https?:\\/\\/[^\\\\)]+?)\\)/gi, '$1 ($2)')\n .replace(/\\[([^\\\\]]+?)\\]/g, '$1')\n .replace(/(\\*\\*|__)(.*?)\\1/g, '$2')\n .replace(/(\\*|_)(.*?)\\1/g, '$2')\n .replace(/`([^`]+?)`/g, '$1');\n}\n\nfunction needsParagraphBreak(prevLineTrimmed, currentLineTrimmed) {\n // \u0412\u0430\u0448\u0430 \u0441\u0443\u0449\u0435\u0441\u0442\u0432\u0443\u044e\u0449\u0430\u044f \u0444\u0443\u043d\u043a\u0446\u0438\u044f \u0434\u043b\u044f \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\u0438\u044f \u043d\u0435\u043e\u0431\u0445\u043e\u0434\u0438\u043c\u043e\u0441\u0442\u0438 \u0440\u0430\u0437\u0440\u044b\u0432\u0430 \u0430\u0431\u0437\u0430\u0446\u0430\n if (!prevLineTrimmed) return false;\n const lastCharPrev = prevLineTrimmed.slice(-1);\n const firstCharCurr = currentLineTrimmed.charAt(0);\n // \u041f\u0440\u043e\u0432\u0435\u0440\u044f\u0435\u043c, \u0437\u0430\u043a\u0430\u043d\u0447\u0438\u0432\u0430\u0435\u0442\u0441\u044f \u043b\u0438 \u043f\u0440\u0435\u0434\u044b\u0434\u0443\u0449\u0430\u044f \u0441\u0442\u0440\u043e\u043a\u0430 \u043d\u0430 \u043f\u0443\u043d\u043a\u0442\u0443\u0430\u0446\u0438\u044e \u043a\u043e\u043d\u0446\u0430 \u043f\u0440\u0435\u0434\u043b\u043e\u0436\u0435\u043d\u0438\u044f\n // \u0438 \u043d\u0430\u0447\u0438\u043d\u0430\u0435\u0442\u0441\u044f \u043b\u0438 \u0442\u0435\u043a\u0443\u0449\u0430\u044f \u0441 \u0437\u0430\u0433\u043b\u0430\u0432\u043d\u043e\u0439 \u0431\u0443\u043a\u0432\u044b (\u043f\u0440\u043e\u0441\u0442\u043e\u0439 \u044d\u0432\u0440\u0438\u0441\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u0439 \u043f\u043e\u0434\u0445\u043e\u0434)\n return '.!?:\uff1a'.includes(lastCharPrev) && firstCharCurr === firstCharCurr.toUpperCase() && /[A-Z\u0410-\u042f\u0401]/.test(firstCharCurr);\n}\n\nfunction cleanText(raw = '') {\n raw = raw.replace(/\\r\\n?/g, '\\n'); // \u0423\u043d\u0438\u0444\u0438\u043a\u0430\u0446\u0438\u044f \u043a\u043e\u043d\u0446\u043e\u0432 \u0441\u0442\u0440\u043e\u043a\n const lines = raw.split('\\n');\n\n const paras = []; // \u041c\u0430\u0441\u0441\u0438\u0432 \u0434\u043b\u044f \u0445\u0440\u0430\u043d\u0435\u043d\u0438\u044f \u0433\u043e\u0442\u043e\u0432\u044b\u0445 \u0430\u0431\u0437\u0430\u0446\u0435\u0432\n let buf = ''; // \u0411\u0443\u0444\u0435\u0440 \u0434\u043b\u044f \u043d\u0430\u043a\u043e\u043f\u043b\u0435\u043d\u0438\u044f \u0442\u0435\u043a\u0443\u0449\u0435\u0433\u043e \u0430\u0431\u0437\u0430\u0446\u0430\n\n const flush = () => {\n const trimmedBuf = buf.trim();\n if (trimmedBuf) { // \u0414\u043e\u0431\u0430\u0432\u043b\u044f\u0435\u043c \u0432 paras, \u0442\u043e\u043b\u044c\u043a\u043e \u0435\u0441\u043b\u0438 \u0431\u0443\u0444\u0435\u0440 \u043d\u0435 \u043f\u0443\u0441\u0442\u043e\u0439 \u043f\u043e\u0441\u043b\u0435 trim\n paras.push(trimmedBuf);\n }\n buf = ''; // \u041e\u0447\u0438\u0449\u0430\u0435\u043c \u0431\u0443\u0444\u0435\u0440\n };\n\n let previousLineTrimmed = ''; // \u0425\u0440\u0430\u043d\u0438\u043c \u043f\u0440\u0435\u0434\u044b\u0434\u0443\u0449\u0443\u044e \u043e\u0431\u0440\u0430\u0431\u043e\u0442\u0430\u043d\u043d\u0443\u044e \u0441\u0442\u0440\u043e\u043a\u0443 \u0434\u043b\u044f needsParagraphBreak\n\n for (let i = 0; i < lines.length; i++) {\n let currentLineRawTrimmed = lines[i].trim(); // \u0422\u0435\u043a\u0443\u0449\u0430\u044f \u0441\u0442\u0440\u043e\u043a\u0430, \u043e\u0447\u0438\u0449\u0435\u043d\u043d\u0430\u044f \u043e\u0442 \u043f\u0440\u043e\u0431\u0435\u043b\u043e\u0432 \u043f\u043e \u043a\u0440\u0430\u044f\u043c\n\n // 1. \u041f\u0440\u043e\u043f\u0443\u0441\u043a \u043f\u0443\u0441\u0442\u044b\u0445 \u0441\u0442\u0440\u043e\u043a \u0438 \u0441\u0431\u0440\u043e\u0441 \u0431\u0443\u0444\u0435\u0440\u0430 (\u043d\u0430\u0447\u0430\u043b\u043e \u043d\u043e\u0432\u043e\u0433\u043e \u0430\u0431\u0437\u0430\u0446\u0430)\n if (!currentLineRawTrimmed) {\n flush();\n previousLineTrimmed = ''; // \u0421\u0431\u0440\u0430\u0441\u044b\u0432\u0430\u0435\u043c \u043f\u0440\u0435\u0434\u044b\u0434\u0443\u0449\u0443\u044e \u0441\u0442\u0440\u043e\u043a\u0443, \u0442\u0430\u043a \u043a\u0430\u043a \u0431\u044b\u043b \u0440\u0430\u0437\u0440\u044b\u0432\n continue;\n }\n\n // 2. \u041f\u0440\u043e\u043f\u0443\u0441\u043a \"\u043c\u0443\u0441\u043e\u0440\u043d\u044b\u0445\" \u0441\u0442\u0440\u043e\u043a\n if (BOILERPLATE_PATTERNS.some(rx => rx.test(currentLineRawTrimmed)) || currentLineRawTrimmed.startsWith('![')) {\n flush(); // \u0421\u0431\u0440\u0430\u0441\u044b\u0432\u0430\u0435\u043c \u0431\u0443\u0444\u0435\u0440 \u043f\u0435\u0440\u0435\u0434 \u043f\u0440\u043e\u043f\u0443\u0441\u043a\u043e\u043c \u043c\u0443\u0441\u043e\u0440\u043d\u043e\u0439 \u0441\u0442\u0440\u043e\u043a\u0438\n previousLineTrimmed = ''; // \u0421\u0431\u0440\u0430\u0441\u044b\u0432\u0430\u0435\u043c \u043f\u0440\u0435\u0434\u044b\u0434\u0443\u0449\u0443\u044e \u0441\u0442\u0440\u043e\u043a\u0443\n continue;\n }\n\n const markerRx = /^\\s*(#{1,6}|[-*\u2022]|\\d+\\.)\\s+/; // \u041c\u0430\u0440\u043a\u0435\u0440\u044b \u0437\u0430\u0433\u043e\u043b\u043e\u0432\u043a\u043e\u0432 \u0438 \u0441\u043f\u0438\u0441\u043a\u043e\u0432\n const isMarkerLine = markerRx.test(currentLineRawTrimmed);\n let textToProcess = currentLineRawTrimmed;\n\n if (isMarkerLine) {\n // \u0415\u0441\u043b\u0438 \u0442\u0435\u043a\u0443\u0449\u0430\u044f \u0441\u0442\u0440\u043e\u043a\u0430 - \u044d\u0442\u043e \u043d\u043e\u0432\u044b\u0439 \u043c\u0430\u0440\u043a\u0435\u0440 (\u0437\u0430\u0433\u043e\u043b\u043e\u0432\u043e\u043a/\u044d\u043b\u0435\u043c\u0435\u043d\u0442 \u0441\u043f\u0438\u0441\u043a\u0430),\n // \u0438 \u0432 \u0431\u0443\u0444\u0435\u0440\u0435 \u0443\u0436\u0435 \u0447\u0442\u043e-\u0442\u043e \u0435\u0441\u0442\u044c (\u043f\u0440\u0435\u0434\u044b\u0434\u0443\u0449\u0438\u0439 \u0430\u0431\u0437\u0430\u0446 \u0438\u043b\u0438 \u044d\u043b\u0435\u043c\u0435\u043d\u0442 \u0441\u043f\u0438\u0441\u043a\u0430), \u0441\u0431\u0440\u0430\u0441\u044b\u0432\u0430\u0435\u043c \u0431\u0443\u0444\u0435\u0440.\n flush();\n textToProcess = currentLineRawTrimmed.replace(markerRx, '').trim(); // \u0423\u0434\u0430\u043b\u044f\u0435\u043c \u043c\u0430\u0440\u043a\u0435\u0440\n }\n\n textToProcess = cleanInline(textToProcess); // \u041f\u0440\u0438\u043c\u0435\u043d\u044f\u0435\u043c inline \u043e\u0447\u0438\u0441\u0442\u043a\u0443\n\n // 3. \u041b\u043e\u0433\u0438\u043a\u0430 \u0444\u043e\u0440\u043c\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u044f \u0430\u0431\u0437\u0430\u0446\u0435\u0432\n if (!buf) { // \u0415\u0441\u043b\u0438 \u0431\u0443\u0444\u0435\u0440 \u043f\u0443\u0441\u0442 (\u043d\u0430\u0447\u0430\u043b\u043e \u043d\u043e\u0432\u043e\u0433\u043e \u0430\u0431\u0437\u0430\u0446\u0430)\n buf = textToProcess;\n } else {\n // \u0411\u0443\u0444\u0435\u0440 \u043d\u0435 \u043f\u0443\u0441\u0442, \u0440\u0435\u0448\u0430\u0435\u043c, \u043a\u0430\u043a \u0434\u043e\u0431\u0430\u0432\u0438\u0442\u044c \u0442\u0435\u043a\u0443\u0449\u0438\u0439 \u0442\u0435\u043a\u0441\u0442:\n // \u043a\u0430\u043a \u043f\u0440\u043e\u0434\u043e\u043b\u0436\u0435\u043d\u0438\u0435 \u0442\u0435\u043a\u0443\u0449\u0435\u0433\u043e \u0430\u0431\u0437\u0430\u0446\u0430 \u0438\u043b\u0438 \u043d\u0430\u0447\u0430\u0442\u044c \u043d\u043e\u0432\u044b\u0439.\n // needsParagraphBreak \u0441\u0440\u0430\u0432\u043d\u0438\u0432\u0430\u0435\u0442 \u043f\u0440\u0435\u0434\u044b\u0434\u0443\u0449\u0443\u044e \u0434\u043e\u0431\u0430\u0432\u043b\u0435\u043d\u043d\u0443\u044e \u0432 \u0431\u0443\u0444\u0435\u0440 \u0441\u0442\u0440\u043e\u043a\u0443 (\u0438\u043b\u0438 \u0435\u0435 \u043a\u043e\u043d\u0435\u0446)\n // \u0441 \u0442\u0435\u043a\u0443\u0449\u0435\u0439 \u043e\u0431\u0440\u0430\u0431\u0430\u0442\u044b\u0432\u0430\u0435\u043c\u043e\u0439 \u0441\u0442\u0440\u043e\u043a\u043e\u0439 textToProcess.\n // \u0412\u0430\u0436\u043d\u043e: `previousLineTrimmed` \u0437\u0434\u0435\u0441\u044c \u0434\u043e\u043b\u0436\u043d\u0430 \u0431\u044b\u0442\u044c \u043f\u043e\u0441\u043b\u0435\u0434\u043d\u0435\u0439 *\u044d\u0444\u0444\u0435\u043a\u0442\u0438\u0432\u043d\u043e \u0434\u043e\u0431\u0430\u0432\u043b\u0435\u043d\u043d\u043e\u0439* \u0441\u0442\u0440\u043e\u043a\u043e\u0439.\n if (needsParagraphBreak(previousLineTrimmed, textToProcess) && !isMarkerLine) {\n // \u0415\u0441\u043b\u0438 \u043d\u0443\u0436\u0435\u043d \u0440\u0430\u0437\u0440\u044b\u0432 \u0430\u0431\u0437\u0430\u0446\u0430 \u0418 \u0442\u0435\u043a\u0443\u0449\u0430\u044f \u0441\u0442\u0440\u043e\u043a\u0430 \u043d\u0435 \u044f\u0432\u043b\u044f\u0435\u0442\u0441\u044f \u043d\u0430\u0447\u0430\u043b\u043e\u043c \u043d\u043e\u0432\u043e\u0433\u043e \u044d\u043b\u0435\u043c\u0435\u043d\u0442\u0430 \u0441\u043f\u0438\u0441\u043a\u0430\n // (\u0447\u0442\u043e\u0431\u044b \u043d\u0435 \u0440\u0430\u0437\u0440\u044b\u0432\u0430\u0442\u044c \u0441\u0440\u0430\u0437\u0443 \u043f\u043e\u0441\u043b\u0435 \u043c\u0430\u0440\u043a\u0435\u0440\u0430, \u0435\u0441\u043b\u0438 \u043e\u043d \u0441\u0430\u043c \u043f\u043e \u0441\u0435\u0431\u0435 \u043d\u0435 \u0442\u0440\u0435\u0431\u0443\u0435\u0442 \u0440\u0430\u0437\u0440\u044b\u0432\u0430)\n flush();\n buf = textToProcess;\n } else {\n // \u041f\u0440\u043e\u0434\u043e\u043b\u0436\u0430\u0435\u043c \u0442\u0435\u043a\u0443\u0449\u0438\u0439 \u0430\u0431\u0437\u0430\u0446/\u044d\u043b\u0435\u043c\u0435\u043d\u0442 \u0441\u043f\u0438\u0441\u043a\u0430, \u0434\u043e\u0431\u0430\u0432\u043b\u044f\u044f \u043f\u0440\u043e\u0431\u0435\u043b\n buf += ' ' + textToProcess;\n }\n }\n previousLineTrimmed = textToProcess.split('\\n').pop()?.trim() || ''; // \u041e\u0431\u043d\u043e\u0432\u043b\u044f\u0435\u043c previousLineTrimmed \u043f\u043e\u0441\u043b\u0435\u0434\u043d\u0435\u0439 \u0447\u0430\u0441\u0442\u044c\u044e \u043e\u0431\u0440\u0430\u0431\u043e\u0442\u0430\u043d\u043d\u043e\u0433\u043e \u0442\u0435\u043a\u0441\u0442\u0430\n }\n\n flush(); // \u0421\u0431\u0440\u043e\u0441 \u043e\u0441\u0442\u0430\u0442\u043a\u043e\u0432 \u0438\u0437 \u0431\u0443\u0444\u0435\u0440\u0430 \u043f\u043e\u0441\u043b\u0435 \u043e\u043a\u043e\u043d\u0447\u0430\u043d\u0438\u044f \u0446\u0438\u043a\u043b\u0430\n\n return paras.join('\\n\\n'); // \u0421\u043e\u0435\u0434\u0438\u043d\u044f\u0435\u043c \u0432\u0441\u0435 \u0430\u0431\u0437\u0430\u0446\u044b \u0434\u0432\u043e\u0439\u043d\u044b\u043c \u043f\u0435\u0440\u0435\u043d\u043e\u0441\u043e\u043c \u0441\u0442\u0440\u043e\u043a\u0438\n}\n\n// \u2500\u2500 n8n mapping (\u0432\u0430\u0448\u0430 \u0441\u0443\u0449\u0435\u0441\u0442\u0432\u0443\u044e\u0449\u0430\u044f \u043b\u043e\u0433\u0438\u043a\u0430 \u043c\u0430\u043f\u043f\u0438\u043d\u0433\u0430) \u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\nreturn items.map(({ json }) => {\n const {\n idx_in_batch,\n type = 'web',\n text = '',\n url,\n file_name,\n title,\n language = null,\n retrieved_at = new Date().toISOString()\n } = json;\n\n const cleaned = cleanText(text); // \u041f\u0440\u0438\u043c\u0435\u043d\u044f\u0435\u043c \u043e\u0431\u043d\u043e\u0432\u043b\u0435\u043d\u043d\u0443\u044e \u0444\u0443\u043d\u043a\u0446\u0438\u044e \u043e\u0447\u0438\u0441\u0442\u043a\u0438\n\n const out = {\n type,\n text: cleaned,\n language,\n retrieved_at,\n };\n\n // \u0421\u043e\u0445\u0440\u0430\u043d\u044f\u0435\u043c \u043e\u0441\u0442\u0430\u043b\u044c\u043d\u044b\u0435 \u043f\u043e\u043b\u044f, \u043a\u0430\u043a \u0432 \u0432\u0430\u0448\u0435\u043c \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b\u044c\u043d\u043e\u043c \u043a\u043e\u0434\u0435\n if (idx_in_batch !== undefined) out.idx_in_batch = idx_in_batch;\n if (type === 'file' && file_name) out.file_name = file_name;\n if (type === 'web' && title) out.title = title;\n if ((type === 'web' || type === 'video') && url) out.url = url;\n\n return { json: out };\n});\n// --- \u041a\u041e\u041d\u0415\u0426 \u041a\u041e\u0414\u0410 \u0414\u041b\u042f \u0423\u0417\u041b\u0410 n8n Clean & Format ---\n" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 4340, -140 ], "id": "d33fd7ce-0964-4a07-95f3-4430a7efe15e", "name": "Clean & Format" }, { "parameters": { "jsCode": "// \u041f\u043e\u043b\u0443\u0447\u0430\u0435\u043c \u0434\u0430\u043d\u043d\u044b\u0435 \u0438\u0437 \u0432\u0445\u043e\u0434\u0430\nconst results = Array.isArray($json.results) ? $json.results[0] : $json.results;\n\n// \u041c\u0435\u0442\u0430-\u0434\u0430\u043d\u043d\u044b\u0435 \u0438\u0437 Clean & Format\nconst meta = $('Clean & Format').first().json;\n\nconst sourceType = meta.type || '';\nconst title = meta.title || '';\nconst url = meta.url || '';\nconst fileName = meta.file_name || '';\nconst language = meta.language || '';\nconst retrievedAt = meta.retrieved_at || new Date().toISOString();\n\n// \u0424\u043e\u0440\u043c\u0438\u0440\u0443\u0435\u043c \u043e\u0431\u044a\u0435\u043a\u0442\u044b \u0434\u043b\u044f \u043e\u0442\u043f\u0440\u0430\u0432\u043a\u0438 \u0432 \u0411\u0414\nconst items = (results.texts || []).map((text, i) => ({\n type: sourceType,\n language: language,\n retrieved_at: retrievedAt,\n paragraph_idx: i,\n paragraph_text: text || '',\n embedding: results.embeddings?.[i] || null,\n title: title,\n url: url,\n file_name: fileName\n}));\n\nreturn { json: { items } };\n\n" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 5340, -180 ], "id": "e3ab0a5a-e67d-4ca4-9b72-16634dbe2927", "name": "Results" }, { "parameters": { "method": "POST", "url": "https://uhfliwtnkedtzbepfshw.supabase.co/rest/v1/documents_paragraphs", "authentication": "predefinedCredentialType", "nodeCredentialType": "supabaseApi", "sendBody": true, "specifyBody": "json", "jsonBody": "={{ $json.items }}", "options": {} }, "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [ 5740, -180 ], "id": "3f27d20f-c61b-4058-bbcf-1907183c02b5", "name": "PUSH TO DB", "alwaysOutputData": true, "credentials": { "supabaseApi": { "name": "<your credential>" } } }, { "parameters": { "content": "### \u0421\u0411\u041e\u0420 \u0418\u041d\u0424\u041e\u0420\u041c\u0410\u0426\u0418\u0418 \u0418 \u041e\u0416\u0418\u0414\u0410\u041d\u0418\u0415 \u0412\u0421\u0415\u0425 \u0414\u041e\u041a\u0423\u041c\u0415\u041d\u0422\u041e\u0412", "height": 220, "width": 540, "color": 5 }, "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ 3720, -200 ], "id": "f44ae631-c193-4a3e-bb3f-741bfdc420e7", "name": "Sticky Note6" }, { "parameters": { "chatId": "={{$json[\"message\"][\"chat\"][\"id\"]}}", "text": "\u0420\u0435\u0436\u0438\u043c \u0440\u0430\u0431\u043e\u0442\u044b:", "replyMarkup": "inlineKeyboard", "inlineKeyboard": { "rows": [ { "row": { "buttons": [ { "text": "\u0427\u0430\u0442", "additionalFields": { "callback_data": "chat" } }, { "text": "\u0411\u0430\u0437\u0430", "additionalFields": { "callback_data": "documents" } }, { "text": "(Clean chat)", "additionalFields": { "callback_data": "clean_chat" } }, { "text": "(Clean base)", "additionalFields": { "callback_data": "clean_base" } } ] } } ] }, "additionalFields": { "appendAttribution": false } }, "type": "n8n-nodes-base.telegram", "typeVersion": 1.2, "position": [ 1060, 440 ], "id": "fa4bb1b2-3ef1-4d44-b4ff-634cf47fccde", "name": "Mode menu", "credentials": { "telegramApi": { "name": "<your credential>" } } }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "strict", "version": 2 }, "conditions": [ { "id": "468aee87-e709-4059-946c-1ae0f8ce972d", "leftValue": "={{$json[\"callback_query\"]}}", "rightValue": "", "operator": { "type": "object", "operation": "notExists", "singleValue": true } } ], "combinator": "and" }, "options": {} }, "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 600, 520 ], "id": "33b7b193-fffd-45b5-872e-9d1bfd3b0826", "name": "Button/Text?" }, { "parameters": { "chatId": "={{ $('Telegram Trigger').item.json.message.chat.id }}", "text": "\u0412\u044b\u0431\u0435\u0440\u0438\u0442\u0435 \u0440\u0435\u0436\u0438\u043c \u0440\u0430\u0431\u043e\u0442\u044b:", "replyMarkup": "inlineKeyboard", "inlineKeyboard": { "rows": [ { "row": { "buttons": [ { "text": "\u0427\u0430\u0442", "additionalFields": { "callback_data": "chat" } }, { "text": "\u0411\u0430\u0437\u0430", "additionalFields": { "callback_data": "documents" } } ] } } ] }, "additionalFields": { "appendAttribution": false } }, "type": "n8n-nodes-base.telegram", "typeVersion": 1.2, "position": [ 1660, 440 ], "id": "1405fcdb-d91a-4da3-a053-21f285229aac", "name": "Mode menu1", "credentials": { "telegramApi": { "name": "<your credential>" } } }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "strict", "version": 2 }, "conditions": [ { "id": "c0b93697-8388-4239-88c5-c116725df95e", "leftValue": "={{ $json.current_mode }}", "rightValue": "", "operator": { "type": "string", "operation": "empty", "singleValue": true } } ], "combinator": "and" }, "options": {} }, "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 1480, 460 ], "id": "9c429c44-7c3d-4afa-b0bd-d7d9bf69600a", "name": "Mode selected?" }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "strict", "version": 2 }, "conditions": [ { "id": "6acf73f7-2da5-404c-b810-3949ad71be6e", "leftValue": "={{ $('Telegram Trigger').item.json.callback_query.data }}", "rightValue": "chat", "operator": { "type": "string", "operation": "equals", "name": "filter.operator.equals" } } ], "combinator": "and" }, "options": {} }, "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 1300, 840 ], "id": "abe6ae2a-caef-459e-b5ea-d3dc81a44242", "name": "Chat/Base?" }, { "parameters": { "chatId": "={{ $('Telegram Trigger').item.json.callback_query.message.chat.id }}", "text": "=*\u0412\u044b\u0431\u0440\u0430\u043d \u0440\u0435\u0436\u0438\u043c \\\"\u0417\u0430\u0433\u0440\u0443\u0437\u043a\u0430 \u0432 \u0431\u0430\u0437\u0443\\\"\\:* \n\u2022 \u041c\u043e\u0436\u043d\u043e \u043e\u0442\u043f\u0440\u0430\u0432\u0438\u0442\u044c \u0432\u0435\u0431\\-\u0441\u0441\u044b\u043b\u043a\u0443, \u0432\u0438\u0434\u0435\u043e \u0438\u043b\u0438 \u0444\u0430\u0439\u043b \n\u2022 \u0412\u0441\u0451 \u0431\u0443\u0434\u0435\u0442 \u0430\u0432\u0442\u043e\u043c\u0430\u0442\u0438\u0447\u0435\u0441\u043a\u0438 \u0434\u043e\u0431\u0430\u0432\u043b\u0435\u043d\u043e \u0432 \u0431\u0430\u0437\u0443 \n \n_\u041f\u043e\u0434\u0434\u0435\u0440\u0436\u0438\u0432\u0430\u0435\u0442\u0441\u044f_\\: \n\u2022 \u0412\u0435\u0431\\-\u0441\u0441\u044b\u043b\u043a\u0430 \u2014 \u043b\u044e\u0431\u0430\u044f\\, \u0441\u043e\u0434\u0435\u0440\u0436\u0430\u0449\u0430\u044f \u0442\u0435\u043a\u0441\u0442\\. \u0414\u043e 3 \u0448\u0442 \u0437\u0430 \u0440\u0430\u0437\\. \n\u2022 \u0412\u0438\u0434\u0435\u043e \u2014 youtube\\.com \u0438 youtu\\.be\\. \u0414\u043e 3\u0448\u0442 \u0437\u0430 \u0440\u0430\u0437\\. \n\u2022 \u0424\u0430\u0439\u043b\u044b \u2014 pdf \\/ docx \\/ txt\\, \u0442\u0430\u043a \u0436\u0435 \u0438\u0437\u0432\u043b\u0435\u043a\u0430\u0435\u0442\u0441\u044f \u0442\u0435\u043a\u0441\u0442 \u0438\u0437 \u0438\u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u0438\u0439 \u0432\u043d\u0443\u0442\u0440\u0438 \u0444\u0430\u0439\u043b\u043e\u0432\\. 1\u0448\u0442 \u0437\u0430 \u0440\u0430\u0437\\.", "additionalFields": { "parse_mode": "MarkdownV2" } }, "type": "n8n-nodes-base.telegram", "typeVersion": 1.2, "position": [ 1560, 980 ], "id": "7ec4c3f9-34b7-407b-9e8d-58eb76c13d27", "name": "Mode Base", "executeOnce": false, "credentials": { "telegramApi": { "name": "<your credential>" } } }, { "parameters": { "chatId": "={{ $('Telegram Trigger').item.json.callback_query.message.chat.id }}", "text": "=*\u0412\u044b\u0431\u0440\u0430\u043d \u0440\u0435\u0436\u0438\u043c \"\u0427\u0430\u0442\":* \n\u2022 \u041e\u0433\u0440\u0430\u043d\u0438\u0447\u0435\u043d\u0438\u0435 \u043f\u0430\u043c\u044f\u0442\u0438 \u2014 30 \u0441\u043e\u043e\u0431\u0449\u0435\u043d\u0438\u0439 \n\u2022 \u041e\u0431\u0440\u0430\u0449\u0435\u043d\u0438\u0435 \u043a \u0432\u0430\u0448\u0435\u0439 _RAG_ \u0431\u0430\u0437\u0435 \u2014 \u0430\u0432\u0442\u043e\u043c\u0430\u0442\u0438\u0437\u0438\u0440\u043e\u0432\u0430\u043d\u043e", "additionalFields": { "parse_mode": "MarkdownV2" } }, "type": "n8n-nodes-base.telegram", "typeVersion": 1.2, "position": [ 1560, 720 ], "id": "19c4ac86-35f9-42e7-995f-1f2a97d10475", "name": "Mode Chat", "executeOnce": false, "credentials": { "telegramApi": { "name": "<your credential>" } } }, { "parameters": { "method": "POST", "url": "https://uhfliwtnkedtzbepfshw.supabase.co/rest/v1/user_state", "authentication": "predefinedCredentialType", "nodeCredentialType": "supabaseApi", "sendHeaders": true, "specifyHeaders": "json", "jsonHeaders": "{\n \"Prefer\": \"resolution=merge-duplicates\"\n}", "sendBody": true, "contentType": "raw", "rawContentType": "application/json", "body": "={\n \"user_id\": \"{{ $json.callback_query.from.id }}\",\n \"current_mode\": \"{{ $json.callback_query.data }}\",\n \"updated_at\": \"{{ $now }}\"\n}", "options": {} }, "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [ 1080, 840 ], "id": "091de72d-eb78-434f-ae32-7a7937128ba7", "name": "Mode set", "credentials": { "supabaseApi": { "name": "<your credential>" } } }, { "parameters": { "url": "https://uhfliwtnkedtzbepfshw.supabase.co/rest/v1/user_state", "authentication": "predefinedCredentialType", "nodeCredentialType": "supabaseApi", "sendQuery": true, "queryParameters": { "parameters": [ { "name": "user_id", "value": "=eq.{{ $json.message.chat.id }}" } ] }, "options": {} }, "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [ 1300, 460 ], "id": "97b106a4-6d59-43e2-b893-3df905139d9d", "name": "Mode check", "alwaysOutputData": true, "credentials": { "supabaseApi": { "name": "<your credential>" } } }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "strict", "version": 2 }, "conditions": [ { "id": "0b27cf90-ac3f-483a-8d77-e0ee696e3d79", "leftValue": "={{ $json.current_mode }}", "rightValue": "documents", "operator": { "type": "string", "operation": "equals", "name": "filter.operator.equals" } } ], "combinator": "and" }, "options": {} }, "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 1480, 220 ], "id": "635009b8-654a-4243-b445-7102792ed7ab", "name": "Mode type" }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "strict", "version": 2 }, "conditions": [ { "id": "2f1934a9-9f8c-41c3-8bfd-4ebbd79d4404", "leftValue": "={{ $json.callback_query.data }}", "rightValue": "chat", "operator": { "type": "string", "operation": "equals" } }, { "id": "b08f0226-e91e-42fc-a72c-3067c2c71ecf", "leftValue": "={{ $json.callback_query.data }}", "rightValue": "documents", "operator": { "type": "string", "operation": "equals" } } ], "combinator": "or" }, "options": {} }, "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 820, 940 ], "id": "55fb4bfc-3f14-4e63-939c-90ae2856ab03", "name": "Mode/Clean" }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "strict", "version": 2 }, "conditions": [ { "id": "825e42b2-68f5-4f81-bd72-bad4c8f179cf", "leftValue": "={{ $json.callback_query.data }}", "rightValue": "clean_chat", "operator": { "type": "string", "operation": "equals", "name": "filter.operator.equals" } } ], "combinator": "and" }, "options": {} }, "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 1020, 1120 ], "id": "ca153211-4581-4d01-b3e7-7c894ff54a61", "name": "Clean chat/base" }, { "parameters": { "method": "DELETE", "url": "=https://uhfliwtnkedtzbepfshw.supabase.co/rest/v1/chat_messages?user_id=eq.{{ $('Telegram Trigger').item.json.callback_query.from.id }}", "authentication": "predefinedCredentialType", "nodeCredentialType": "supabaseApi", "options": {} }, "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [ 1240, 1040 ], "id": "e7e62e34-9ded-4341-9aa2-9db21fdd9509", "name": "Clean Chat", "credentials": { "supabaseApi": { "name": "<your credential>" } } }, { "parameters": { "url": "=https://uhfliwtnkedtzbepfshw.supabase.co/rest/v1/chat_messages?user_id=eq.{{ $json.message.from.id }}&order=created_at.asc&select=role,message\n\n\n", "authentication": "predefinedCredentialType", "nodeCredentialType": "supabaseApi", "options": { "response": { "response": { "responseFormat": "json" } } } }, "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [ 2160, 1200 ], "id": "1ac24f11-9977-4af7-b0c0-0731d16503f3", "name": "Get history", "alwaysOutputData": true, "credentials": { "supabaseApi": { "name": "<your credential>" } } }, { "parameters": { "options": {} }, "type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter", "typeVersion": 1, "position": [ 2700, 1200 ], "id": "1fafb650-70a8-4344-9595-65c4c26e3614", "name": "OpenRouter Chat Model2", "credentials": { "openRouterApi": { "name": "<your credential>" } } }, { "parameters": { "chatId": "={{ $json.items[0].user_id }}", "text": "={{ $json.items[1].message }}", "additionalFields": { "appendAttribution": false, "parse_mode": "HTML" } }, "type": "n8n-nodes-base.telegram", "typeVersion": 1.2, "position": [ 3420, 820 ], "id": "1b8818e8-d506-45ee-8632-9c615c48a5de", "name": "Telegram1", "alwaysOutputData": true, "credentials": { "telegramApi": { "name": "<your credential>" } } }, { "parameters": { "mode": "combine", "combineBy": "combineByPosition", "options": {} }, "type": "n8n-nodes-base.merge", "typeVersion": 3.1, "position": [ 2520, 1000 ], "id": "8ceed9bd-ea44-46dc-a95b-98bbd60e9462", "name": "Query+Context" }, { "parameters": { "jsCode": "// Run Once for All Items\nconst history = $input.all(); // \u0431\u0435\u0437 .reverse()\nlet context = '';\n\nif (history.length) {\n context = history\n .map(msg => {\n const role = msg.json.role || 'unknown';\n const text = msg.json.message || '';\n return `${role}: ${text}`;\n })\n .join('\\n');\n}\n\nreturn [{ json: { context } }];\n\n\n\n" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 2360, 1200 ], "id": "c510daae-4610-491f-b630-3c2f617f1af9", "name": "Form history", "alwaysOutputData": false }, { "parameters": { "jsCode": "const src = $input.first().json;\n\nconst userId = src?.message?.chat?.id ?? null;\nconst userText = src?.message?.text ?? '';\nconst botText = src.output ?? '';\n\nconst now = new Date();\n\nconst items = [\n {\n user_id: userId,\n message: userText,\n role: 'user',\n created_at: now.toISOString(),\n },\n {\n user_id: userId,\n message: botText,\n role: 'assistant',\n created_at: new Date(now.getTime() + 1000).toISOString(),\n },\n];\n\nreturn [{ json: { items } }];\n" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 3200, 900 ], "id": "cf60b4f2-e6a1-4c1b-a5fb-b0fe48ae4ecf", "name": "Result parser" }, { "parameters": { "method": "POST", "url": "https://uhfliwtnkedtzbepfshw.supabase.co/rest/v1/rpc/insert_and_trim_pairs", "authentication": "predefinedCredentialType", "nodeCredentialType": "supabaseApi", "sendBody": true, "contentType": "raw", "rawContentType": "application/json", "body": "={{ \n JSON.stringify({\n p_items: $json.items, \n p_keep_pairs: 15\n }) \n}}", "options": {} }, "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [ 3420, 1000 ], "id": "5191425d-24cb-4181-8cef-6fca8b6988e9", "name": "Save history", "alwaysOutputData": false, "credentials": { "supabaseApi": { "name": "<your credential>" } } }, { "parameters": { "promptType": "define", "text": "=Chat history: \"{{ $json.context }}\"\nLast message (main): {{ $('Telegram Trigger').item.json.message.text }}\nUse rag-db-query tool for answer about cities.", "hasOutputParser": true, "options": { "systemMessage": "You are an AI assistant in a Telegram chat. Follow these strict constraints. \n\n\u27eb Response Rules\n\u2022 Always reply in **Russian**, concisely and meaningfully. \n\u2022 Use {{ $json.context }} only for dialogue continuity. \n\u2022 Treat **Last message (main)** as the sole user query. \n\u2022 If a question was answered earlier \u2014 point to the previous answer, do not repeat. \n\u2022 Ask for clarification (in Russian) if the request is unclear.\n\n\u27eb Tool: `rag-db-query`\nUse it to everytime retrieve factual data from the knowledge base. \n\n\u27eb When to call\nCall **once** and **only if** the current Last message contains: \n\u2014 \"n8n\"/\"\u043d8\u043d\" \u2022 or phrases \"\u043f\u043e\u0438\u0449\u0438 \u043f\u043e \u0431\u0430\u0437\u0435\", \"\u043f\u0440\u043e\u0432\u0435\u0440\u044c \u0432 \u0431\u0430\u0437\u0435\", \"source\", \"cite\" \u2022 or a URL/filename with \u201c\u0447\u0442\u043e \u0432 \u044d\u0442\u043e\u043c\u2026\u201d / \u201c\u043e \u0447\u0451\u043c \u044d\u0442\u043e\u2026\u201d.\n\n\u27eb Before calling\nRewrite the user message into a clear factual query (remove slang, typos, extra words). \nExample: \nUser \u00bb \u00ab\u0430 \u0432 \u043d8\u043d \u043a\u0430\u043a \u0441\u0434\u0435\u043b\u0430\u0442\u044c \u0447\u0442\u043e\u0431\u044b api \u043d\u0435 \u043a\u0438\u0434\u0430\u043b 429?\u00bb \nQuery \u00bb \u00ab\u043a\u0430\u043a \u043e\u0431\u0440\u0430\u0431\u0430\u0442\u044b\u0432\u0430\u0442\u044c \u043e\u0448\u0438\u0431\u043a\u0443 429 \u0432 n8n \u043f\u0440\u0438 \u043f\u0440\u0435\u0432\u044b\u0448\u0435\u043d\u0438\u0438 \u043b\u0438\u043c\u0438\u0442\u0430 \u0437\u0430\u043f\u0440\u043e\u0441\u043e\u0432\u00bb\n\n\u27eb After the call (YOU MUST DO IT, NO OPTIONS)\n\u2022 If `results` empty \u2192 answer on your own based on your own knowledge and previous answers. \n\u2022 Otherwise: \n 1. Begin the answer by paraphrasing `paragraph_text`. \n 2. Optionally add brief clarifications. \n 3. **Mandatory** grounding block (always print it!):\n\"\u0418\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0438\u044f \u0431\u044b\u043b\u0430 \u0432\u0437\u044f\u0442\u0430 \u0438\u0437 \u0431\u0430\u0437\u044b \u0434\u0430\u043d\u043d\u044b\u0445 ({{ source_type }}, {{ source_identifier }})\"\n(user 'source_type' and 'source_identifier' from rag-db-query response)\n\n\n(omit empty parts, never mention the tool).\n\n\u27eb Forbidden\n\u2022 Hallucinating data. \n\u2022 Triggering the tool based on earlier messages. \n\u2022 Omitting the grounding block when data was used. \n\u2022 Repeating the same answer verbatim.\n\n\u27eb Output\nPlain text only (no JSON) unless explicitly requested.\n\nIf there is no information in the database (unknown), do not write where the information was taken from." } }, "type": "@n8n/n8n-nodes-langchain.agent", "typeVersion": 1.9, "position": [ 2740, 1000 ], "id": "739236c9-99d8-4c74-91c3-61bd6879d3dd", "name": "RAG CHATBOT" }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "strict", "version": 2 }, "conditions": [ { "id": "dcf0db86-e5ee-467f-824f-56db0db51958", "leftValue": "={{ ($json.message?.text?.match(/https?:\\/\\/[^\\s]+/) !== null) || $json.document }}", "rightValue": "", "operator": { "type": "boolean", "operation": "true", "singleValue": true } } ], "combinator": "and" }, "options": {} }, "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 1060, 680 ], "id": "2d4596fa-bf1a-4d1e-b078-a519e587a7d1", "name": "IF", "notes": "IF text have url/file then check mode, if haven't - go to chat faster" }, { "parameters": { "content": "# \u041c\u041e\u0414\u0423\u041b\u042c \u041e\u0411\u0429\u0415\u041d\u0418\u042f \u0421 \u0427\u0410\u0422\u041e\u041c", "height": 640, "width": 1620, "color": 4 }, "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ 1940, 780 ], "id": "fdfe672a-5c1f-4cbd-b5ad-6e1dd6a1eb1e", "name": "Sticky Note7" }, { "parameters": { "conditions": { "options": { "caseSensitive": true, "leftValue": "", "typeValidation": "strict", "version": 2 }, "conditions": [ { "id": "c609cbe5-6ce2-4504-9fb9-36ebe900b1ab", "leftValue": "={{ $json.message.text }}", "rightValue": "/start", "operator": { "type": "string", "operation": "equals", "name": "filter.operator.equals" } } ], "combinator": "and" }, "options": {} }, "type": "n8n-nodes-base.if", "typeVersion": 2.2, "position": [ 820, 500 ], "id": "f381090d-230e-4aca-b1b7-4a13420cef32", "name": "Start/Text?" }, { "parameters": { "content": "### \u041c\u041e\u0414\u0423\u041b\u042c \u0417\u0410\u041d\u0415\u0421\u0415\u041d\u0418\u042f \u0412 \u0411\u0414\n", "height": 220, "width": 400, "color": 4 }, "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ 5600, -240 ], "id": "0639f85c-a4fa-4544-95dd-59cffdc88b8f", "name": "Sticky Note8" }, { "parameters": { "jsCode": "const out = [];\n// \u041f\u043e\u043b\u0443\u0447\u0430\u0435\u043c JSON \u0438\u0437 Telegram \u0442\u0440\u0438\u0433\u0433\u0435\u0440\u0430.\n// \u0423\u0431\u0435\u0434\u0438\u0442\u0435\u0441\u044c, \u0447\u0442\u043e \u0438\u043c\u044f \u0432\u0430\u0448\u0435\u0433\u043e \u0442\u0440\u0438\u0433\u0433\u0435\u0440\u0430 \u0432 n8n - 'Telegram Trigger'\nconst tgInput = $('Telegram Trigger').first();\n\n// \u041f\u0440\u043e\u0432\u0435\u0440\u043a\u0430, \u0447\u0442\u043e tgInput \u0438 \u043d\u0435\u043e\u0431\u0445\u043e\u0434\u0438\u043c\u044b\u0435 \u043f\u043e\u043b\u044f \u0441\u0443\u0449\u0435\u0441\u0442\u0432\u0443\u044e\u0442, \u0447\u0442\u043e\u0431\u044b \u0438\u0437\u0431\u0435\u0436\u0430\u0442\u044c \u043e\u0448\u0438\u0431\u043e\u043a\nif (!tgInput || !tgInput.json || !tgInput.json.message) {\n // \u0415\u0441\u043b\u0438 \u0441\u0442\u0440\u0443\u043a\u0442\u0443\u0440\u0430 \u0434\u0430\u043d\u043d\u044b\u0445 \u043d\u0435 \u0442\u0430, \u043a\u043e\u0442\u043e\u0440\u0443\u044e \u043c\u044b \u043e\u0436\u0438\u0434\u0430\u0435\u043c, \u0432\u043e\u0437\u0432\u0440\u0430\u0449\u0430\u0435\u043c \u043f\u0443\u0441\u0442\u043e\u0439 \u043c\u0430\u0441\u0441\u0438\u0432 items\n // \u042d\u0442\u043e \u043f\u0440\u0435\u0434\u043e\u0442\u0432\u0440\u0430\u0442\u0438\u0442 \u043e\u0448\u0438\u0431\u043a\u0438 \u0432 \u043f\u043e\u0441\u043b\u0435\u0434\u0443\u044e\u0449\u0438\u0445 \u0443\u0437\u043b\u0430\u0445, \u0435\u0441\u043b\u0438 \u0442\u0440\u0438\u0433\u0433\u0435\u0440 \u0441\u0440\u0430\u0431\u043e\u0442\u0430\u0435\u0442 \u0441 \u043d\u0435\u043e\u0436\u0438\u0434\u0430\u043d\u043d\u044b\u043c\u0438 \u0434\u0430\u043d\u043d\u044b\u043c\u0438\n return [{ json: { items: out } }];\n}\nconst tg = tgInput.json;\n\n// \u0422\u0435\u043a\u0441\u0442 \u0441\u043e\u043e\u0431\u0449\u0435\u043d\u0438\u044f \u0438\u043b\u0438 \u043f\u043e\u0434\u043f\u0438\u0441\u044c \u043a \u043c\u0435\u0434\u0438\u0430\u0444\u0430\u0439\u043b\u0443 (\u0434\u043b\u044f \u0438\u0437\u0432\u043b\u0435\u0447\u0435\u043d\u0438\u044f \u0441\u0441\u044b\u043b\u043e\u043a)\nconst text = tg.message.text || tg.message.caption || '';\n\n// --- \u041e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u0430 \u0441\u0441\u044b\u043b\u043e\u043a ---\nif (text) { // \u0423\u0431\u0435\u0434\u0438\u043c\u0441\u044f, \u0447\u0442\u043e text \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\n const urls = (text.match(/https?:\\/\\/[^\\s]+/g) || []);\n for (const url of urls) {\n const lower = url.toLowerCase();\n // \u0412\u0430\u0448\u0430 \u043b\u043e\u0433\u0438\u043a\u0430 \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\u0438\u044f \u0432\u0438\u0434\u0435\u043e \u043c\u043e\u0436\u0435\u0442 \u0431\u044b\u0442\u044c \u0441\u043b\u043e\u0436\u043d\u0435\u0435,\n // \u0437\u0434\u0435\u0441\u044c \u0443\u043f\u0440\u043e\u0449\u0435\u043d\u043d\u0430\u044f \u043f\u0440\u043e\u0432\u0435\u0440\u043a\u0430 \u043d\u0430 YouTube\n if (lower.includes('youtube.com/') || lower.includes('youtu.be/')) {\n out.push({ type: 'video', url: url });\n } else {\n out.push({ type: 'web', url: url });\n }\n }\n}\n\n// --- \u041e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u0430 \u0434\u043e\u043a\u0443\u043c\u0435\u043d\u0442\u043e\u0432 ---\n// \u041f\u043e\u043b\u0435 tg.message.document \u0441\u0443\u0449\u0435\u0441\u0442\u0432\u0443\u0435\u0442, \u0435\u0441\u043b\u0438 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u044c \u043e\u0442\u043f\u0440\u0430\u0432\u0438\u043b \u0444\u0430\u0439\u043b \u043a\u0430\u043a \u0434\u043e\u043a\u0443\u043c\u0435\u043d\u0442\nif (tg.message.document && tg.message.document.file_id) {\n const doc = tg.message.document;\n out.push({\n type: 'file',\n file_id: doc.file_id,\n file_name: doc.file_name || null, // \u0418\u043c\u044f \u0444\u0430\u0439\u043b\u0430 \u0438\u0437 Telegram \u0438\u043b\u0438 null, \u0435\u0441\u043b\u0438 \u0435\u0433\u043e \u043d\u0435\u0442\n // mime_type \u043c\u043e\u0436\u043d\u043e \u0434\u043e\u0431\u0430\u0432\u0438\u0442\u044c \u0437\u0434\u0435\u0441\u044c, \u0435\u0441\u043b\u0438 \u043e\u043d \u0438\u0437\u0432\u0435\u0441\u0442\u0435\u043d \u0438 \u043d\u0443\u0436\u0435\u043d \u0441\u0440\u0430\u0437\u0443:\n // mime_type: doc.mime_type || null\n });\n}\n\n// --- \u041e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u0430 \u0444\u043e\u0442\u043e\u0433\u0440\u0430\u0444\u0438\u0439 (\u0434\u043e\u0431\u0430\u0432\u043b\u0435\u043d\u043e) ---\n// \u041f\u043e\u043b\u0435 tg.message.photo \u0441\u0443\u0449\u0435\u0441\u0442\u0432\u0443\u0435\u0442, \u0435\u0441\u043b\u0438 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u044c \u043e\u0442\u043f\u0440\u0430\u0432\u0438\u043b \u0444\u043e\u0442\u043e\u0433\u0440\u0430\u0444\u0438\u044e.\n// \u042d\u0442\u043e \u043c\u0430\u0441\u0441\u0438\u0432 \u043e\u0431\u044a\u0435\u043a\u0442\u043e\u0432, \u043e\u043f\u0438\u0441\u044b\u0432\u0430\u044e\u0449\u0438\u0445 \u0440\u0430\u0437\u043d\u044b\u0435 \u0440\u0430\u0437\u043c\u0435\u0440\u044b \u043e\u0434\u043d\u043e\u0433\u043e \u0444\u043e\u0442\u043e.\nif (tg.message.photo && Array.isArray(tg.message.photo) && tg.message.photo.length > 0) {\n // \u041e\u0431\u044b\u0447\u043d\u043e \u043f\u043e\u0441\u043b\u0435\u0434\u043d\u0438\u0439 \u044d\u043b\u0435\u043c\u0435\u043d\u0442 \u043c\u0430\u0441\u0441\u0438\u0432\u0430 - \u044d\u0442\u043e \u0444\u043e\u0442\u043e \u0441\u0430\u043c\u043e\u0433\u043e \u0431\u043e\u043b\u044c\u0448\u043e\u0433\u043e \u0434\u043e\u0441\u0442\u0443\u043f\u043d\u043e\u0433\u043e \u0440\u0430\u0437\u043c\u0435\u0440\u0430\n const largestPhoto = tg.message.photo[tg.message.photo.length - 1];\n\n if (largestPhoto && largestPhoto.file_id) {\n out.push({\n type: 'file', // \u041a\u043b\u0430\u0441\u0441\u0438\u0444\u0438\u0446\u0438\u0440\u0443\u0435\u043c \u043a\u0430\u043a 'file', \u0441\u043e\u0433\u043b\u0430\u0441\u043d\u043e \u0432\u0430\u0448\u0435\u043c\u0443 \u0437\u0430\u043f\u0440\u043e\u0441\u0443\n file_id: largestPhoto.file_id,\n // \u0424\u043e\u0442\u043e\u0433\u0440\u0430\u0444\u0438\u0438 \u0432 Telegram \u043d\u0435 \u0438\u043c\u0435\u044e\u0442 \"\u0438\u043c\u0435\u043d\u0438 \u0444\u0430\u0439\u043b\u0430\" \u0432 \u0442\u043e\u043c \u0436\u0435 \u0441\u043c\u044b\u0441\u043b\u0435, \u0447\u0442\u043e \u0438 \u0434\u043e\u043a\u0443\u043c\u0435\u043d\u0442\u044b.\n // \u0413\u0435\u043d\u0435\u0440\u0438\u0440\u0443\u0435\u043c \u0438\u043c\u044f, \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u044f file_unique_id \u0434\u043b\u044f \u0443\u043d\u0438\u043a\u0430\u043b\u044c\u043d\u043e\u0441\u0442\u0438.\n // \u0420\u0430\u0441\u0448\u0438\u0440\u0435\u043d\u0438\u0435 \".jpg\" \u044f\u0432\u043b\u044f\u0435\u0442\u0441\u044f \u043f\u0440\u0435\u0434\u043f\u043e\u043b\u043e\u0436\u0435\u043d\u0438\u0435\u043c; \u0440\u0435\u0430\u043b\u044c\u043d\u044b\u0439 \u0442\u0438\u043f \u0444\u0430\u0439\u043b\u0430\n // \u0431\u0443\u0434\u0435\u0442 \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d \u043f\u043e\u0437\u0436\u0435, \u043f\u0440\u0438 \u0435\u0433\u043e \u0441\u043a\u0430\u0447\u0438\u0432\u0430\u043d\u0438\u0438 \u0438 \u043e\u0431\u0440\u0430\u0431\u043e\u0442\u043a\u0435.\n file_name: `photo_${largestPhoto.file_unique_id || largestPhoto.file_id}.jpg`,\n // mime_type \u0434\u043b\u044f \u0444\u043e\u0442\u043e \u043d\u0430 \u044d\u0442\u043e\u043c \u044d\u0442\u0430\u043f\u0435 \u043d\u0435 \u0438\u0437\u0432\u0435\u0441\u0442\u0435\u043d.\n // \u041e\u043d \u0441\u0442\u0430\u043d\u0435\u0442 \u0438\u0437\u0432\u0435\u0441\u0442\u0435\u043d \u043f\u043e\u0441\u043b\u0435 \u0432\u044b\u0437\u043e\u0432\u0430 getFile \u0438 \u0441\u043a\u0430\u0447\u0438\u0432\u0430\u043d\u0438\u044f.\n });\n }\n}\n\nreturn [{ json: { items: out } }];" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 1320, -60 ], "id": "55718590-4f4d-4ec2-82fb-1c7a5b814d49", "name": "Classificator" }, { "parameters": { "content": "# \u041f\u041e\u0414\u0413\u041e\u0422\u041e\u0412\u041a\u0410 \u0418\u041d\u0424\u041e\u0420\u041c\u0410\u0426\u0418\u0418 \u0414\u041b\u042f \u0420\u0410\u0421\u041f\u0420\u0415\u0414\u0415\u041b\u0415\u041d\u0418\u042f", "height": 540, "width": 1040, "color": 4 }, "type": "n8n-nodes-base.stickyNote", "typeVersion": 1, "position": [ 640, -360 ], "id": "b3429214-5b0c-4cb5-a132-0ac4a7b4def9", "name": "Sticky Note9" }, { "parameters": {}, "type": "n8n-nodes-base.noOp", "typeVersion": 1, "position": [ 1980, 980 ], "id": "99385a09-7c15-4288-90e7-8380158bf750", "name": "Bridge 1" }, { "parameters": { "chatId": "={{ $('Telegram Trigger').item.json.message.from.id }}", "text": "=\u0412\u043d\u0435\u0441\u0435\u043d\u043e.", "additionalFields": { "appendAttribution": false } }, "type": "n8n-nodes-base.telegram", "typeVersion": 1.2, "position": [ 6960, -440 ], "id": "122a33d3-8368-4b2b-8428-0c931f52038b", "name": "Telegram2", "alwaysOutputData": true, "credentials": { "telegramApi": { "name": "<your credential>" } } }, { "parameters": {}, "type": "n8n-nodes-base.noOp", "typeVersion": 1, "position": [ 3000, -1420 ], "id": "16c5d720-be22-475b-b018-d0c52e9a7cf0", "name": "No Operation, do nothing" }, { "parameters": { "mode": "combine", "combineBy": "combineByPosition", "options": {} }, "type": "n8n-nodes-base.merge", "typeVersion": 3.1, "position": [ 6800, -440 ], "id": "f1f304ff-0bd5-4cf8-94bf-c263ee7a03f2", "name": "Merge1" }, { "parameters": { "method": "DELETE", "url": "=https://uhfliwtnkedtzbepfshw.supabase.co/rest/v1/documents_paragraphs", "authentication": "predefinedCredentialType", "nodeCredentialType": "supabaseApi", "options": {} }, "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [ 1220, 1240 ], "id": "fc9e4273-08f5-4290-94d8-e6430c33456a", "name": "Clean Base", "credentials": { "supabaseApi": { "name": "<your credential>" } }, "disabled": true }, { "parameters": { "chatId": "={{ $('Telegram Trigger').item.json.callback_query.message.chat.id }}", "text": "=\u0427\u0430\u0442 \u043e\u0447\u0438\u0449\u0435\u043d\\!", "additionalFields": { "parse_mode": "MarkdownV2" } }, "type": "n8n-nodes-base.telegram", "typeVersion": 1.2, "position": [ 1520, 1220 ], "id": "55dc6507-d76d-4e7b-80a5-e57440130836", "name": "Clean msg", "executeOnce": false, "credentials": { "telegramApi": { "name": "<your credential>" } } }, { "parameters": { "description": "Use for RAG base search. in query write only text.\nUse sources for \"Grounding block\"", "workflowId": { "__rl": true, "value": "NdE0ltECP1WASBdg", "mode": "list", "cachedResultName": "RAG CHATBOT Vector search workflow" }, "workflowInputs": { "mappingMode": "defineBelow", "value": { "query": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('query', ``, 'string') }}" }, "matchingColumns": [ "query" ], "schema": [ { "id": "query", "displayName": "query", "required": false, "defaultMatch": false, "display": true, "canBeUsedToMatch": true, "type": "string", "removed": false } ], "attemptToConvertTypes": false, "convertFieldsToString": false } }, "type": "@n8n/n8n-nodes-langchain.toolWorkflow", "typeVersion": 2.2, "position": [ 2940, 1220 ], "id": "bbc432c1-3d7a-4ff8-8b35-72d2505394a7", "name": "rag-db-query" }, { "parameters": { "descriptionType": "manual", "toolDescription": "Extract and parse content from any web page", "operation": "executeTool", "toolName": "scrape", "toolParameters": "={\n \"url\": \"{{ $fromAI('url', 'URL of the page to scrape') }}\",\n \"format\": \"markdown\",\n \"cleaned\": true,\n \"renderJs\": true\n}\n" }, "type": "n8n-nodes-mcp.mcpClientTool", "typeVersion": 1, "position": [ 2520, 20 ], "id": "64df211f-6acf-40de-9cda-9c94214e89fd", "name": "scrape tool", "credentials": { "mcpClientApi": { "name": "<your credential>" } } }, { "parameters": { "mode": "combine", "combineBy": "combineByPosition", "options": {} }, "type": "n8n-nodes-base.merge", "typeVersion": 3.1, "position": [ 3060, 900 ], "id": "f40054fc-ea1e-4a57-8f4d-2fa65bff7f68", "name": "Merge2" }, { "parameters": { "method": "POST", "url": "http://jina-embed-gpu:8008/embed_late_chunk", "sendBody": true, "bodyParameters": { "parameters": [ { "name": "texts", "value": "={{ $json.texts }}" }, { "name": "strategy", "value": "={{$json.source_type === 'video' ? 'sentence' : 'paragraph'}}" }, { "name": "task", "value": "retrieval.passage" } ] }, "options": {} }, "type": "n8n-nodes-base.httpRequest", "typeVersion": 4.2, "position": [ 5200, -180 ], "id": "ed8d9d27-7973-4dd4-93e1-13c2b91412f4", "name": "HTTP Request" }, { "parameters": { "promptType": "define", "text": "=Content Type: `{{$json.type}}`\nInput Text: `{{$json.text}}`", "hasOutputParser": true, "options": { "systemMessage": "=You are a text processing expert. Your task is to prepare input text for a Retrieval Augmented Generation (RAG) system by splitting it into suitable chunks for embedding.\n\nOverall Instructions:\n1. You will receive `Input Text` and its `Content Type`.\n2. Clean the `Input Text`: Remove any irrelevant elements like HTML tags, boilerplate (headers, footers, ads), navigation links, or other non-content artifacts. Focus on extracting the core textual content.\n3. Condense if too long: If the cleaned text significantly exceeds a reasonable limit for processing (e.g., ~8000 tokens), summarize it to fit, ensuring all key information and meaning are preserved.\n4. Chunk the processed text based on the `Content Type` using the specific rules below.\n5. Output Format: Respond in format: `\"texts\": \"text paragraphs\", \"chunking_strategy\": \"strategy_used\"`. Each paragraph must be separated from the other by symbols \"\\n\\n\".\n\nChunking Rules by Content Type:\n\nIf `Content Type` is \"video\":\n Split the processed text into sentences.\n Aim for semantically complete statements. Merge very short, consecutive sentences if they logically form a single, more complete thought. Remove all \\n\\n.\n The `chunking_strategy` in the output must be \"sentence\".\n\nIf `Content Type` is \"web\" or \"file\":\n Your PRIMARY GOAL is to create text paragraphs where each paragraph contains approximately 250-350 words. This word count is the most important rule for chunking.\n Process the cleaned text to achieve this word count per chunk:\n Start forming a chunk by accumulating words.\n When the current chunk approaches the 250-350 word target, find the nearest sensible semantic boundary (like the end of a sentence or a natural break in topic) to finalize that chunk.\n Do NOT create chunks that are very short (e.g., under 200 words) UNLESS the entire remaining text is less than 200 words.\n If you encounter text segments from the input that appear as very short paragraphs (e.g., separated by many newlines in the source, or single sentences), these should be combined with subsequent text to build chunks that meet the target word count. Do not treat every original line break or short sentence as a reason to start a new chunk if it results in a chunk far below the target word count.\n All final chunks must be semantically coherent.\n Each resulting chunk (paragraph) that meets these criteria should be a separate string in the \"texts\" array.\n The `chunking_strategy` in the output must be \"paragraph\".\n\n*DO IT NORMALLY, DO NOT CUT HALF TEXT OR SOMETHING OTHER SHIT, USE PROMPT, USE ALL TEXT!!!!!!!*" } }, "type": "@n8n/n8n-nodes-langchain.agent", "typeVersion": 1.9, "position": [ 4580, -140 ], "id": "77e0433b-c92e-4562-86d0-25858285a15c", "name": "AI Agent" }, { "parameters": { "options": {} }, "type": "@n8n/n8n-nodes-langchain.lmChatOpenRouter", "typeVersion": 1, "position": [ 4480, 20 ], "id": "4915c114-f43f-4d39-8734-733e4f5bb4cb", "name": "OpenRouter Chat Model3", "credentials": { "openRouterApi": { "name": "<your credential>" } } }, { "parameters": {}, "type": "n8n-nodes-base.merge", "typeVersion": 3.1, "position": [ 4920, -180 ], "id": "3b41523c-3905-4021-800e-e620dc94a7af", "name": "Merge" }, { "parameters": {}, "type": "n8n-nodes-base.noOp", "typeVersion": 1, "position": [ 1800, -1420 ], "id": "3d552cd2-8934-43ed-863b-cd4912e91242", "name": "No Operation, do nothing1" }, { "parameters": { "jsCode": "const firstItem = items[0].json;\nconst secondItem = items[1].json;\n\n// \u041f\u0440\u043e\u0432\u0435\u0440\u043a\u0438 \u043d\u0430 \u043d\u0430\u043b\u0438\u0447\u0438\u0435 \u0434\u0430\u043d\u043d\u044b\u0445 (\u0447\u0442\u043e\u0431\u044b \u043d\u0435 \u043a\u0440\u0430\u0448\u043d\u0443\u043b\u043e\u0441\u044c, \u0435\u0441\u043b\u0438 items \u043c\u0435\u043d\u044c\u0448\u0435 2)\nif (!firstItem || !secondItem) {\n throw new Error('\u041d\u0435\u0434\u043e\u0441\u0442\u0430\u0442\u043e\u0447\u043d\u043e \u0434\u0430\u043d\u043d\u044b\u0445 \u0432 items \u043e\u0442 Merge');\n}\n\n// \u0411\u0435\u0440\u0451\u043c texts: \u0441\u043d\u0430\u0447\u0430\u043b\u0430 \u0441 \u0432\u0435\u0440\u0445\u043d\u0435\u0433\u043e \u0443\u0440\u043e\u0432\u043d\u044f, \u0437\u0430\u0442\u0435\u043c fallback \u0432 output\nlet textsValue = secondItem.texts ?? secondItem.output?.texts;\nif (textsValue == null) {\n throw new Error('\u0412\u043e \u0432\u0442\u043e\u0440\u043e\u043c \u044d\u043b\u0435\u043c\u0435\u043d\u0442\u0435 \u043e\u0442\u0441\u0443\u0442\u0441\u0442\u0432\u0443\u0435\u0442 \u043f\u043e\u043b\u0435 texts');\n}\n\n// \u041e\u0431\u043e\u0440\u0430\u0447\u0438\u0432\u0430\u0435\u043c texts \u0432 \u043c\u0430\u0441\u0441\u0438\u0432, \u0435\u0441\u043b\u0438 \u044d\u0442\u043e \u043d\u0435 \u043c\u0430\u0441\u0441\u0438\u0432\nif (!Array.isArray(textsValue)) {\n textsValue = [textsValue];\n}\n\n// \u0411\u0435\u0440\u0451\u043c \u0441\u0442\u0440\u0430\u0442\u0435\u0433\u0438\u044e \u0447\u0430\u043d\u043a\u0438\u043d\u0433\u0430 \u0441 \u0443\u0447\u0451\u0442\u043e\u043c \u0432\u043e\u0437\u043c\u043e\u0436\u043d\u043e\u0433\u043e \u0440\u0430\u0441\u043f\u043e\u043b\u043e\u0436\u0435\u043d\u0438\u044f\nconst chunkingStrategy =\n secondItem.chunking_strategy ?? secondItem.output?.chunking_strategy ?? null;\n\nreturn [{\n json: {\n language: firstItem.language,\n retrieved_at: firstItem.retrieved_at,\n idx_in_batch: firstItem.idx_in_batch,\n file_name: firstItem.file_name,\n texts: textsValue,\n chunking_strategy: chunkingStrategy,\n }\n}];\n" }, "type": "n8n-nodes-base.code", "typeVersion": 2, "position": [ 5060, -180 ], "id": "77a54843-962a-4c0b-8276-3b3f8af22372", "name": "Code" }, { "parameters": { "jsonSchemaExample": "{\n\t\"texts\": \"text paragraphs\",\n\t\"chunking_strategy\": \"strategy_used\"\n}" }, "type": "@n8n/n8n-nodes-langchain.outputParserStructured", "typeVersion": 1.2, "position": [ 4780, 20 ], "id": "42c657c2-9c58-48e5-bfd3-307fb4940eb4", "name": "Structured Output Parser" } ], "connections": { "Switch": { "main": [ [ { "node": "Set Names", "type": "main", "index": 0 }, { "node": "Keep meta transcript", "type": "main", "index": 0 } ], [ { "node": "Keep meta scraping", "type": "main", "index": 0 }, { "node": "Ai Scraping", "type": "main", "index": 0 } ], [ { "node": "File", "type": "main", "index": 0 }, { "node": "Keep meta file", "type": "main", "index": 0 } ] ] }, "file?": { "main": [ [ { "node": "Format ok?", "type": "main", "index": 0 } ], [ { "node": "Classificator", "type": "main", "index": 0 } ] ] }, "Format ok?": { "main": [ [ { "node": "Format Error", "type": "main", "index": 0 } ], [ { "node": "Classificator", "type": "main", "index": 0 } ] ] }, "Telegram Trigger": { "main": [ [ { "node": "Button/Text?", "type": "main", "index": 0 }, { "node": "No Operation, do nothing1", "type": "main", "index": 0 } ] ] }, "OpenAI Chat Model": { "ai_languageModel": [ [ { "node": "Paid transcription", "type": "ai_languageModel", "index": 0 } ] ] }, "Transcribe": { "ai_tool": [ [ { "node": "Paid transcription", "type": "ai_tool", "index": 0 } ] ] }, "Audio extract": { "main": [ [ { "node": "Upload binary", "type": "main", "index": 0 } ] ] }, "Set Names": { "main": [ [ { "node": "Audio extract", "type": "main", "index": 0 } ] ] }, "Upload binary": { "main": [ [ { "node": "Whisper Transcribe", "type": "main", "index": 0 } ] ] }, "Whisper Transcribe": { "main": [ [ { "node": "Temp delete", "type": "main", "index": 0 }, { "node": "Merge transcribe", "type": "main", "index": 1 } ] ] }, "OpenRouter Chat Model1": { "ai_languageModel": [ [ { "node": "Ai Scraping", "type": "ai_languageModel", "index": 0 } ] ] }, "Firecrawl scrape": { "ai_tool": [ [ { "node": "Ai Scraping", "type": "ai_tool", "index": 0 } ] ] }, "Scrape Parser": { "main": [ [ { "node": "Error check", "type": "main", "index": 0 } ] ] }, "Error check": { "main": [ [ { "node": "Telegram", "type": "main", "index": 0 } ], [ { "node": "Merge all", "type": "main", "index": 1 } ] ] }, "Ai Scraping": { "main": [ [ { "node": "Merge scraping", "type": "main", "index": 1 } ] ] }, "File": { "main": [ [ { "node": "Extractor", "type": "main", "index": 0 } ] ] }, "Split & Tag": { "main": [ [ { "node": "Switch", "type": "main", "index": 0 } ] ] }, "Aggregate": { "main": [ [ { "node": "Gatekeeper", "type": "main", "index": 0 } ] ] }, "Keep meta scraping": { "main": [ [ { "node": "Merge scraping", "type": "main", "index": 0 } ] ] }, "Merge scraping": { "main": [ [ { "node": "Scrape Parser", "type": "main", "index": 0 } ] ] }, "Keep meta file": { "main": [ [ { "node": "Merge file", "type": "main", "index": 0 } ] ] }, "Merge file": { "main": [ [ { "node": "File Parser", "type": "main", "index": 0 } ] ] }, "Text Structured": { "main": [ [ { "node": "Merge file", "type": "main", "index": 1 } ] ] }, "Merge transcribe": { "main": [ [ { "node": "Video parser", "type": "main", "index": 0 } ] ] }, "Keep meta transcript": { "main": [ [ { "node": "Merge transcribe", "type": "main", "index": 0 } ] ] }, "Video parser": { "main": [ [ { "node": "Merge all", "type": "main", "index": 0 } ] ] }, "Extractor": { "main": [ [ { "node": "Text Structured", "type": "main", "index": 0 } ] ] }, "File Parser": { "main": [ [ { "node": "Merge all", "type": "main", "index": 2 } ] ] }, "Gatekeeper": { "main": [ [ { "node": "Clean & Format", "type": "main", "index": 0 } ] ] }, "Merge all": { "main": [ [ { "node": "Aggregate", "type": "main", "index": 0 } ] ] }, "Clean & Format": { "main": [ [ { "node": "AI Agent", "type": "main", "index": 0 }, { "node": "Merge", "type": "main", "index": 0 } ] ] }, "Results": { "main": [ [ { "node": "PUSH TO DB", "type": "main", "index": 0 } ] ] }, "Button/Text?": { "main": [ [ { "node": "Start/Text?", "type": "main", "index": 0 } ], [ { "node": "Mode/Clean", "type": "main", "index": 0 } ] ] }, "Mode selected?": { "main": [ [ { "node": "Mode menu1", "type": "main", "index": 0 } ], [ { "node": "Mode type", "type": "main", "index": 0 } ] ] }, "Mode menu": { "main": [ [] ] }, "Chat/Base?": { "main": [ [ { "node": "Mode Chat", "type": "main", "index": 0 } ], [ { "node": "Mode Base", "type": "main", "index": 0 } ] ] }, "Mode set": { "main": [ [ { "node": "Chat/Base?", "type": "main", "index": 0 } ] ] }, "Mode check": { "main": [ [ { "node": "Mode selected?", "type": "main", "index": 0 } ] ] }, "Mode type": { "main": [ [ { "node": "file?", "type": "main", "index": 0 } ], [ { "node": "Bridge 1", "type": "main", "index": 0 } ] ] }, "Mode/Clean": { "main": [ [ { "node": "Mode set", "type": "main", "index": 0 } ], [ { "node": "Clean chat/base", "type": "main", "index": 0 } ] ] }, "Clean chat/base": { "main": [ [ { "node": "Clean Chat", "type": "main", "index": 0 } ], [ { "node": "Clean Base", "type": "main", "index": 0 } ] ] }, "Get history": { "main": [ [ { "node": "Form history", "type": "main", "index": 0 } ] ] }, "OpenRouter Chat Model2": { "ai_languageModel": [ [ { "node": "RAG CHATBOT", "type": "ai_languageModel", "index": 0 } ] ] }, "Query+Context": { "main": [ [ { "node": "RAG CHATBOT", "type": "main", "index": 0 }, { "node": "Merge2", "type": "main", "index": 0 } ] ] }, "Telegram1": { "main": [ [] ] }, "Form history": { "main": [ [ { "node": "Query+Context", "type": "main", "index": 1 } ] ] }, "Result parser": { "main": [ [ { "node": "Save history", "type": "main", "index": 0 }, { "node": "Telegram1", "type": "main", "index": 0 } ] ] }, "RAG CHATBOT": { "main": [ [ { "node": "Merge2", "type": "main", "index": 1 } ] ] }, "IF": { "main": [ [ { "node": "Mode check", "type": "main", "index": 0 } ], [ { "node": "Bridge 1", "type": "main", "index": 0 } ] ] }, "Start/Text?": { "main": [ [ { "node": "Mode menu", "type": "main", "index": 0 } ], [ { "node": "IF", "type": "main", "index": 0 } ] ] }, "Classificator": { "main": [ [ { "node": "Split & Tag", "type": "main", "index": 0 } ] ] }, "Bridge 1": { "main": [ [ { "node": "Get history", "type": "main", "index": 0 }, { "node": "Query+Context", "type": "main", "index": 0 } ] ] }, "PUSH TO DB": { "main": [ [ { "node": "Merge1", "type": "main", "index": 1 } ] ] }, "No Operation, do nothing": { "main": [ [ { "node": "Merge1", "type": "main", "index": 0 } ] ] }, "Merge1": { "main": [ [ { "node": "Telegram2", "type": "main", "index": 0 } ] ] }, "Clean Chat": { "main": [ [ { "node": "Clean msg", "type": "main", "index": 0 } ] ] }, "rag-db-query": { "ai_tool": [ [ { "node": "RAG CHATBOT", "type": "ai_tool", "index": 0 } ] ] }, "scrape tool": { "ai_tool": [ [ { "node": "Ai Scraping", "type": "ai_tool", "index": 0 } ] ] }, "Merge2": { "main": [ [ { "node": "Result parser", "type": "main", "index": 0 } ] ] }, "HTTP Request": { "main": [ [ { "node": "Results", "type": "main", "index": 0 } ] ] }, "OpenRouter Chat Model3": { "ai_languageModel": [ [ { "node": "AI Agent", "type": "ai_languageModel", "index": 0 } ] ] }, "AI Agent": { "main": [ [ { "node": "Merge", "type": "main", "index": 1 } ] ] }, "Merge": { "main": [ [ { "node": "Code", "type": "main", "index": 0 } ] ] }, "No Operation, do nothing1": { "main": [ [ { "node": "No Operation, do nothing", "type": "main", "index": 0 } ] ] }, "Code": { "main": [ [ { "node": "HTTP Request", "type": "main", "index": 0 } ] ] }, "Structured Output Parser": { "ai_outputParser": [ [ { "node": "AI Agent", "type": "ai_outputParser", "index": 0 } ] ] } }, "active": true, "settings": { "executionOrder": "v1", "timezone": "Asia/Novosibirsk", "callerPolicy": "workflowsFromSameOwner" }, "versionId": "d1cdb770-f912-4b9d-ae8a-2cf2550fd056", "meta": { "templateCredsSetupCompleted": true }, "id": "cb8CPKtHgjtlp9rM", "tags": [] }