For AI agents: a documentation index is available at /llms.txt — every docs page also has a markdown twin (append .md to the page URL).
LlamaIndex → PDF with makesPDF
The makespdf[llamaindex] extra exposes two LlamaIndex FunctionTools over the makesPDF hosted API — markdown → PDF and stored-template/inline-DSL → PDF. Both write a temp .pdf and return its path.
Install
pip install "makespdf[llamaindex]"
export MAKESPDF_API_KEY=... # mint at https://makespdf.com/settings/api-keys?ref=llamaindexThe LlamaIndex import happens inside the factory, so import makespdf never imports a framework. A missing extra raises ImportError naming the pip extra.
The two tools
| Tool | Endpoint | Arguments |
|---|---|---|
| makespdf_render_md | POST /api/v1/md | markdown |
| makespdf_render | POST /api/v1/render | template_id or dsl, plus data_json |
makespdf_render takes exactly one of template_id ("invoice-classic") or dsl, plus data_json for {{vars}}. Both tools return a temp .pdf path.
Example
from makespdf import MakesPDFClient
from makespdf.integrations.demo import MARKDOWN_DEMO, DSL_DEMO
from makespdf.integrations.llamaindex import get_llamaindex_tools
md_tool, render_tool = get_llamaindex_tools(MakesPDFClient())
print(md_tool.call(MARKDOWN_DEMO)) # markdown -> PDF path
print(render_tool.call(dsl=DSL_DEMO, data_json='{"name": "Ada"}')) # DSL -> PDF pathget_llamaindex_tools() returns (md_tool, render_tool); .call() forwards the tool’s arguments. LangChain agents want the LangChain shim instead; CrewAI agents want the CrewAI shim.
Demo data
Every framework page here renders the same shared demo values, defined once in makespdf.integrations.demo, so the examples stay directly comparable:
MARKDOWN_DEMO = "# Invoice INV-2026-001\n\nHello **Ada** — total **$7,095.00**.\n"
DSL_DEMO = (
'const template = doc({ size: "A4" }, page(col(s("Hello {{name}}"))));\n'
'const sampleData = { name: "World" };\n'
)
DATA_DEMO = {"name": "Ada"}
TEMPLATE_ID_DEMO = "invoice-classic"Billing and limits
Billing matches the underlying endpoint: both /md and /render cost 1 credit per 10 pages on success, and every failure path deducts zero. Markdown input is capped at 200KB of text — inline data: images are excluded from that budget, the request body is capped at 15MB — and inline DSL at 512KB. Rate limit: 10,000 renders/hour per caller.