This workflow follows the HTTP Request → RSS Feed Read recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"name": "PulseMosaic-v1.1-Main",
"nodes": [
{
"id": "a1-001",
"name": "Manual Trigger",
"type": "n8n-nodes-base.manualTrigger",
"typeVersion": 1,
"position": [
240,
300
],
"parameters": {}
},
{
"id": "a1-002",
"name": "Schedule Trigger",
"type": "n8n-nodes-base.scheduleTrigger",
"typeVersion": 1.1,
"position": [
240,
420
],
"parameters": {
"rule": {
"interval": [
{
"field": "hours",
"hoursInterval": 4
}
]
}
}
},
{
"id": "a1-003",
"name": "Init",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
460,
360
],
"parameters": {
"jsCode": "return [{\n json: {\n topics: [\"ai safety\", \"model context protocol\", \"n8n automation\", \"vector databases\", \"prompt injection\"],\n endpoints: {\n stackoverflow: \"https://api.stackexchange.com/2.3/search/advanced?order=desc&sort=activity&site=stackoverflow&q=\",\n github: \"https://api.github.com/search/repositories?q=\",\n arxiv: \"https://export.arxiv.org/api/query?search_query=all:\"\n },\n rss_feeds: [\n \"https://hnrss.org/frontpage\",\n \"https://www.nasa.gov/rss/dyn/breaking_news.rss\"\n ],\n config: {\n cache_ttl_minutes: 45,\n dedupe_ttl_days: 10,\n min_score: 5,\n max_items_total: 30,\n enable_llm_summary: true,\n ZAI_API_KEY: $env.ZAI_API_KEY || \"\",\n ZAI_BASE_URL: $env.ZAI_BASE_URL || \"https://api.z.ai/api/paas/v4\",\n ZAI_MODEL: $env.ZAI_MODEL || \"glm-5\"\n }\n }\n}];"
}
},
{
"id": "a1-004",
"name": "Split Out RSS",
"type": "n8n-nodes-base.splitOut",
"typeVersion": 1,
"position": [
680,
240
],
"parameters": {
"fieldToSplitOut": "rss_feeds",
"destinationFieldName": "rss_url"
}
},
{
"id": "a1-005",
"name": "RSS Feed Read",
"type": "n8n-nodes-base.rssFeedRead",
"typeVersion": 1,
"position": [
900,
240
],
"parameters": {
"url": "={{ $json.rss_url }}"
}
},
{
"id": "a1-006",
"name": "Normalize RSS",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1120,
240
],
"parameters": {
"jsCode": "const items = [];\nconst data = $input.all();\nfor (const item of data) {\n const feedUrl = item.json.rss_url;\n const entries = Array.isArray(item.json) ? item.json : (item.json.items || []);\n for (const entry of entries) {\n items.push({\n json: {\n source: \"rss\",\n topic: null,\n title: entry.title || \"Untitled\",\n url: entry.link || entry.url || \"\",\n published_at: entry.pubDate || entry.isoDate || null,\n raw_score: 0,\n score: 5,\n summary_raw: entry.contentSnippet || entry.description || null,\n summary: null,\n meta: { author: entry.creator || null, venue: feedUrl, cached: false }\n }\n });\n }\n}\nreturn items.length > 0 ? items : [{ json: { __empty: true, __stream: \"rss\" } }];"
}
},
{
"id": "a1-007",
"name": "Split Out Topics",
"type": "n8n-nodes-base.splitOut",
"typeVersion": 1,
"position": [
680,
480
],
"parameters": {
"fieldToSplitOut": "topics",
"destinationFieldName": "topic"
}
},
{
"id": "a1-008",
"name": "Prepare Worker Input",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
900,
480
],
"parameters": {
"jsCode": "const init = $('Init').first().json;\nreturn [{\n json: {\n topic: $json.topic,\n config: init.config,\n endpoints: init.endpoints\n }\n}];"
}
},
{
"id": "a1-009",
"name": "Execute Worker",
"type": "n8n-nodes-base.executeWorkflow",
"typeVersion": 1,
"position": [
1120,
480
],
"parameters": {
"workflowId": "PulseMosaic-v1.1-Worker",
"options": {}
}
},
{
"id": "a1-010",
"name": "Merge Streams",
"type": "n8n-nodes-base.merge",
"typeVersion": 2.1,
"position": [
1340,
360
],
"parameters": {
"mode": "append"
}
},
{
"id": "a1-011",
"name": "Finalize",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
1560,
360
],
"parameters": {
"jsCode": "const st = $getWorkflowStaticData('global');\nif (!st.seen) st.seen = {};\nconst now = Date.now();\nconst config = $('Init').first().json.config;\nconst ttl = config.dedupe_ttl_days * 24 * 60 * 60 * 1000;\n\n// Prune old entries\nfor (const url in st.seen) {\n if (now - st.seen[url] > ttl) delete st.seen[url];\n}\n\nlet candidates = 0;\nlet newItems = 0;\nlet cachedHits = 0;\nlet apiCalls = 0;\nlet failedCalls = 0;\nconst bySource = {};\nconst items = [];\n\nconst input = $input.all();\nfor (const item of input) {\n const i = item.json;\n if (i.__empty) continue;\n candidates++;\n if (!bySource[i.source]) bySource[i.source] = 0;\n bySource[i.source]++;\n if (i.meta && i.meta.cached) cachedHits++;\n if (i.__meta) {\n if (i.__meta.api_calls) apiCalls += i.__meta.api_calls;\n if (i.__meta.failed_calls) failedCalls += i.__meta.failed_calls;\n }\n \n if (i.score >= config.min_score && i.url && !st.seen[i.url]) {\n st.seen[i.url] = now;\n newItems++;\n items.push(i);\n }\n}\n\nitems.sort((a, b) => b.score - a.score);\nconst finalItems = items.slice(0, config.max_items_total);\n\nreturn [{\n json: {\n config,\n stats: {\n candidates_total: candidates,\n new_items: newItems,\n cached_hits: cachedHits,\n api_calls: apiCalls,\n failed_calls: failedCalls,\n by_source: bySource\n },\n items: finalItems,\n run_id: $execution.id,\n generated_at: new Date().toISOString()\n }\n}];"
}
},
{
"id": "a1-012",
"name": "Check LLM",
"type": "n8n-nodes-base.if",
"typeVersion": 2,
"position": [
1780,
360
],
"parameters": {
"conditions": {
"options": {
"caseSensitive": true
},
"conditions": [
{
"leftValue": "={{ $json.config.enable_llm_summary }}",
"rightValue": true,
"operator": {
"type": "boolean",
"operation": "equals"
}
},
{
"leftValue": "={{ $json.config.ZAI_API_KEY }}",
"rightValue": "",
"operator": {
"type": "string",
"operation": "isNotEmpty"
}
}
],
"combinator": "and"
}
}
},
{
"id": "a1-013",
"name": "Prepare LLM",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
2000,
260
],
"parameters": {
"jsCode": "const topItems = $json.items.slice(0, 12).map(i => ({ url: i.url, title: i.title, summary_raw: i.summary_raw || '' }));\nconst content = `Summarize these items in JSON format {\"summaries\":[{\"url\",\"summary\"}]}. Max 20 words per summary.\\n` + JSON.stringify(topItems);\nreturn [{\n json: {\n ...$json,\n llm_payload: {\n model: $json.config.ZAI_MODEL,\n messages: [{ role: \"user\", content }],\n temperature: 0.2,\n response_format: { type: \"json_object\" }\n }\n }\n}];"
}
},
{
"id": "a1-014",
"name": "HTTP LLM",
"type": "n8n-nodes-base.httpRequest",
"typeVersion": 4.2,
"position": [
2220,
260
],
"parameters": {
"method": "POST",
"url": "={{ $json.config.ZAI_BASE_URL + '/chat/completions' }}",
"authentication": "none",
"sendHeaders": true,
"headerParameters": {
"parameters": [
{
"name": "Authorization",
"value": "={{ 'Bearer ' + $json.config.ZAI_API_KEY }}"
},
{
"name": "Content-Type",
"value": "application/json"
}
]
},
"sendBody": true,
"specifyBody": "json",
"jsonBody": "={{ { model: $json.llm_payload.model, messages: $json.llm_payload.messages, temperature: $json.llm_payload.temperature, response_format: $json.llm_payload.response_format } }}",
"options": {
"continueOnFail": true
}
}
},
{
"id": "a1-015",
"name": "Apply Summaries",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
2440,
260
],
"parameters": {
"jsCode": "const prev = $('Prepare LLM').first().json;\nlet items = prev.items;\nconst resp = $json;\n\nif (resp?.choices?.[0]?.message?.content) {\n try {\n const parsed = JSON.parse(resp.choices[0].message.content);\n if (parsed.summaries && Array.isArray(parsed.summaries)) {\n const map = new Map(parsed.summaries.map(s => [s.url, s.summary]));\n items = items.map(i => ({ ...i, summary: map.get(i.url) || i.summary_raw || i.title }));\n }\n } catch (e) {\n items = items.map(i => ({ ...i, summary: i.summary_raw || i.title }));\n }\n} else {\n items = items.map(i => ({ ...i, summary: i.summary_raw || i.title }));\n}\n\nreturn [{ json: { ...prev, items } }];"
}
},
{
"id": "a1-016",
"name": "Fallback Summary",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
2000,
460
],
"parameters": {
"jsCode": "const items = $json.items.map(i => ({ ...i, summary: i.summary_raw || i.title }));\nreturn [{ json: { ...$json, items } }];"
}
},
{
"id": "a1-017",
"name": "QA Lint",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
2660,
360
],
"parameters": {
"jsCode": "const data = $json;\nif (!Array.isArray(data.items)) throw new Error('Items must be array');\nfor (const i of data.items) {\n if (!i.url || typeof i.url !== 'string') throw new Error('Invalid URL');\n if (typeof i.score !== 'number') throw new Error('Invalid score');\n const s = JSON.stringify(i);\n if (s.includes('{{')) throw new Error('Contains mustache');\n}\nreturn [{ json: data }];"
}
},
{
"id": "a1-018",
"name": "Build Final",
"type": "n8n-nodes-base.code",
"typeVersion": 2,
"position": [
2880,
360
],
"parameters": {
"jsCode": "const data = $json;\nconst lines = [];\nconst groups = {};\nfor (const i of data.items) {\n if (!groups[i.source]) groups[i.source] = [];\n groups[i.source].push(i);\n}\nfor (const [src, items] of Object.entries(groups)) {\n lines.push(`## ${src}`);\n for (const i of items) {\n lines.push(`- [${i.title}](${i.url}) (score ${i.score})`);\n }\n}\nreturn [{\n json: {\n run_id: data.run_id,\n generated_at: data.generated_at,\n topics: $('Init').first().json.topics,\n stats: data.stats,\n items: data.items,\n digest_markdown: lines.join('\\n')\n }\n}];"
}
}
],
"connections": {
"Manual Trigger": {
"main": [
[
{
"node": "Init",
"type": "main",
"index": 0
}
]
]
},
"Schedule Trigger": {
"main": [
[
{
"node": "Init",
"type": "main",
"index": 0
}
]
]
},
"Init": {
"main": [
[
{
"node": "Split Out RSS",
"type": "main",
"index": 0
},
{
"node": "Split Out Topics",
"type": "main",
"index": 0
}
]
]
},
"Split Out RSS": {
"main": [
[
{
"node": "RSS Feed Read",
"type": "main",
"index": 0
}
]
]
},
"RSS Feed Read": {
"main": [
[
{
"node": "Normalize RSS",
"type": "main",
"index": 0
}
]
]
},
"Normalize RSS": {
"main": [
[
{
"node": "Merge Streams",
"type": "main",
"index": 0
}
]
]
},
"Split Out Topics": {
"main": [
[
{
"node": "Prepare Worker Input",
"type": "main",
"index": 0
}
]
]
},
"Prepare Worker Input": {
"main": [
[
{
"node": "Execute Worker",
"type": "main",
"index": 0
}
]
]
},
"Execute Worker": {
"main": [
[
{
"node": "Merge Streams",
"type": "main",
"index": 1
}
]
]
},
"Merge Streams": {
"main": [
[
{
"node": "Finalize",
"type": "main",
"index": 0
}
]
]
},
"Finalize": {
"main": [
[
{
"node": "Check LLM",
"type": "main",
"index": 0
}
]
]
},
"Check LLM": {
"main": [
[
{
"node": "Prepare LLM",
"type": "main",
"index": 0
}
],
[
{
"node": "Fallback Summary",
"type": "main",
"index": 0
}
]
]
},
"Prepare LLM": {
"main": [
[
{
"node": "HTTP LLM",
"type": "main",
"index": 0
}
]
]
},
"HTTP LLM": {
"main": [
[
{
"node": "Apply Summaries",
"type": "main",
"index": 0
}
]
]
},
"Apply Summaries": {
"main": [
[
{
"node": "QA Lint",
"type": "main",
"index": 0
}
]
]
},
"Fallback Summary": {
"main": [
[
{
"node": "QA Lint",
"type": "main",
"index": 0
}
]
]
},
"QA Lint": {
"main": [
[
{
"node": "Build Final",
"type": "main",
"index": 0
}
]
]
}
}
}
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
PulseMosaic-v1.1-Main. Uses rssFeedRead, httpRequest. Event-driven trigger; 18 nodes.
Source: https://github.com/turtir-ai/n8n-workflow-studio/blob/main/public/fixtures/PulseMosaic-v1.1-Main.json — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
GoldPulse-v1.1-Single. Uses rssFeedRead, httpRequest. Event-driven trigger; 33 nodes.
RSS Feed Read, HTTP Request
AegisPulse-v1.1-Single. Uses rssFeedRead, httpRequest. Event-driven trigger; 31 nodes.
RSS Feed Read, HTTP Request
QuorumPulse-v1.1-Single. Uses rssFeedRead, httpRequest. Event-driven trigger; 29 nodes.
RSS Feed Read, HTTP Request
PulseMosaic-v2-Single. Uses rssFeedRead, httpRequest. Event-driven trigger; 25 nodes.
RSS Feed Read, HTTP Request
PulseMosaic-v3.1-Single. Uses rssFeedRead, httpRequest. Event-driven trigger; 25 nodes.
RSS Feed Read, HTTP Request