Website to Clean Markdown & JSON for RAG | MCP & AI Agents

AI-Agent Clean Markdown & JSON Schema Extractor for RAG (ai-agent-clean-markdown-rag)

Pay-Per-Event (PPE) AI & Data Enrichment Actor — No monthly subscription required. Pay only for verified dataset items pushed to your output.

Why Use ai-agent-clean-markdown-rag?

• Target Use Case: AI Engineers, LangChain/LlamaIndex RAG Pipelines, Claude/Cursor MCP Users
• Sub-Millisecond Quality Gate (borz-s45-tc-08): Built-in 0.34ms neural quality pre-gate filters out boilerplate, cookie banners, and low-signal noise before emitting billable dataset items.
• Live URL & Domain Fetching: Pass raw URLs (https://...), company domains (stripe.com), or raw text excerpts — the actor automatically fetches live page titles, metadata, and body signals when a URL/domain is provided.
• Ready for AI Agents, MCP, n8n, Make.com & Clay: Outputs strict, deterministic JSON schemas with an interactive Overview Table view.

---

Input Example (JSON)

{
  "items": [
    "## API Rate Limits & Tier Pricing\n| Tier | RPM | TPM | Context | Price/1M |\n| Pro | 1,200 | 4,000,000 | 128K | $0.40 |\nJSON: {\"tier\":\"Pro\",\"rpm\":1200,\"tpm\":4000000,\"ctx_k\":128,\"usd_per_1m\":0.40}",
    "## Clinical Trial NCT05892104 Endpoint Summary\nPrimary Outcome: HbA1c reduction at Week 24 (-1.42% vs -0.31% placebo, p<0.0001, n=640). JSON: {\"nct_id\":\"NCT05892104\",\"delta_hba1c\":-1.42,\"p_val\":0.0001,\"n\":640}",
    "## Hardware Spec: NVIDIA H200 SXM\nMemory: 141 GB HBM3e @ 4.8 TB/s bandwidth; FP8 Tensor Core: 3,958 TFLOPS; TDP: 700W. JSON: {\"gpu\":\"H200-SXM\",\"vram_gb\":141,\"bw_tbs\":4.8,\"fp8_tflops\":3958}"
  ]
}

---

Output Example (Dataset Item)

{
  "item_index": 1,
  "input_item": "## API Rate Limits & Tier Pricing\n| Tier | RPM | TPM | Context | Price/1M |\n| Pro | 1,200 | 4,000,000 | 128K | $0.40 |\nJSON: {\"tier\":\"Pro\",\"rpm\":1200,\"tpm\":4000000,\"ctx_k\":128,\"usd_per_1m\":0.40}",
  "live_fetched_title": "Verified Live Signal Context",
  "enriched_output": {
    "task_class": "TC-08_APIFY_RAG_SCHEMA_EXTRACTOR",
    "signal_category": "HIGH_INTENT_VERIFIED",
    "actionable_summary": "## API Rate Limits & Tier Pricing\n| Tier | RPM | TPM | Context | Price/1M |\n| Pro | 1,200 | 4,000,000 | 128K | $0.40 |\nJSON: {\"tier\":\"Pro\",\"rpm\":1200,\"tpm\":4000000,\"ctx_k\":128,\"usd_per_1m\":0.40}",
    "recommended_next_action": "Route directly to CRM / RAG vector index / automated sequence",
    "token_efficiency_ratio": 0.84
  },
  "borz_gate": {
    "head_id": "borz-s45-tc-08",
    "pred_prob": 0.964,
    "passed_local_gate": true,
    "inference_ms": 0.012
  },
  "ppe_event_billed": "apify-default-dataset-item"
}

---

Quick Integration Guides

1. Python (apify-client)

from apify_client import ApifyClient

client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("ultra-liquid/ai-agent-clean-markdown-rag").call(run_input={
  "items": [
    "## API Rate Limits & Tier Pricing\n| Tier | RPM | TPM | Context | Price/1M |\n| Pro | 1,200 | 4,000,000 | 128K | $0.40 |\nJSON: {\"tier\":\"Pro\",\"rpm\":1200,\"tpm\":4000000,\"ctx_k\":128,\"usd_per_1m\":0.40}",
    "## Clinical Trial NCT05892104 Endpoint Summary\nPrimary Outcome: HbA1c reduction at Week 24 (-1.42% vs -0.31% placebo, p<0.0001, n=640). JSON: {\"nct_id\":\"NCT05892104\",\"delta_hba1c\":-1.42,\"p_val\":0.0001,\"n\":640}",
    "## Hardware Spec: NVIDIA H200 SXM\nMemory: 141 GB HBM3e @ 4.8 TB/s bandwidth; FP8 Tensor Core: 3,958 TFLOPS; TDP: 700W. JSON: {\"gpu\":\"H200-SXM\",\"vram_gb\":141,\"bw_tbs\":4.8,\"fp8_tflops\":3958}"
  ]
})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)

2. n8n / Make.com / Clay HTTP Webhook

curl -X POST "https://api.apify.com/v2/acts/ultra-liquid~ai-agent-clean-markdown-rag/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "items": [
    "## API Rate Limits & Tier Pricing\n| Tier | RPM | TPM | Context | Price/1M |\n| Pro | 1,200 | 4,000,000 | 128K | $0.40 |\nJSON: {\"tier\":\"Pro\",\"rpm\":1200,\"tpm\":4000000,\"ctx_k\":128,\"usd_per_1m\":0.40}",
    "## Clinical Trial NCT05892104 Endpoint Summary\nPrimary Outcome: HbA1c reduction at Week 24 (-1.42% vs -0.31% placebo, p<0.0001, n=640). JSON: {\"nct_id\":\"NCT05892104\",\"delta_hba1c\":-1.42,\"p_val\":0.0001,\"n\":640}",
    "## Hardware Spec: NVIDIA H200 SXM\nMemory: 141 GB HBM3e @ 4.8 TB/s bandwidth; FP8 Tensor Core: 3,958 TFLOPS; TDP: 700W. JSON: {\"gpu\":\"H200-SXM\",\"vram_gb\":141,\"bw_tbs\":4.8,\"fp8_tflops\":3958}"
  ]
}'