HTML to Markdown for LlamaIndex
Clean web documentation into structured Markdown headings and tables before passing into LlamaIndex node parsers for sharper retrieval accuracy.
Why engineering teams use EdgeDocAPI
- Preserves h1–h6 document hierarchy so LlamaIndex node parsers split accurately
- Converts HTML tables cleanly into GitHub-Flavored Markdown tables
- Eliminates boilerplate navbars and footers that pollute vector similarity
Copy-Paste Integration (/v1/url-to-markdown)
curl -X POST https://api.docopsapi.com/v1/url-to-markdown \
-H "Authorization: Bearer edk_live_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"url":"https://example.com/documentation","include_links":true}'import requests
resp = requests.post(
"https://api.docopsapi.com/v1/url-to-markdown",
headers={"Authorization": "Bearer edk_live_YOUR_API_KEY"},
json={
"url": "https://example.com/documentation",
"include_links": true
},
timeout=15,
)
resp.raise_for_status()
print(resp.json())const res = await fetch("https://api.docopsapi.com/v1/url-to-markdown", {
method: "POST",
headers: {
"Authorization": "Bearer edk_live_YOUR_API_KEY",
"Content-Type": "application/json",
},
body: JSON.stringify({
"url": "https://example.com/documentation",
"include_links": true
}),
});
if (!res.ok) throw new Error(`HTTP ${res.status}`);
const data = await res.json();
console.log(data);