LLM diagram generation library for Mermaid, PlantUML, and draw.io style workflows.
Project description
llm-draw
Generate diagram source from natural-language prompts using LLMs.
llm-draw infers the diagram type and output format from your prompt, then
returns Mermaid, PlantUML, draw.io XML, or Markdown diagram text.
Install
Install from PyPI:
python -m pip install "llm-draw[openai]"
Other extras are available for specific integrations:
python -m pip install "llm-draw[langchain]"
Example
import os
from llm_draw import LlmDraw
client = LlmDraw(provider="openai")
result = client.generate(
prompt="Show a web app with browser, API, PostgreSQL, Redis, and Stripe.",
apikey=os.environ["OPENAI_API_KEY"],
model_id="gpt-4.1-mini",
)
print(result.content)
print(result.diagram_type, result.output_format)
CLI
export OPENAI_API_KEY="..."
llm-draw \
"Draw a payment workflow with fraud checks and refund handling" \
--model-id gpt-4.1-mini \
--output workflow.mmd
llm-draw writes inferred metadata to stderr and writes diagram source to
stdout, unless --output is provided.
Supported Diagrams
- Architecture, system architecture, network, AWS, Azure, GCP, Kubernetes, Terraform
- Flowchart, process flow, workflow, process map, BPMN, swimlane, state, sequence
- ERD, UML, use case, block, data flow, user flow, user journey map, org chart
- Mermaid editor and PlantUML editor modes
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file llm_draw-0.1.2.tar.gz.
File metadata
- Download URL: llm_draw-0.1.2.tar.gz
- Upload date:
- Size: 12.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1b6e674c0108137a7e0c860868b4f8504146974be6f0d4f260fd5c8744b67eb2
|
|
| MD5 |
749cc630c631f7621e4ba466c3db9a4a
|
|
| BLAKE2b-256 |
5af990426a191cbbd33ed2183b15e17ac8875fa6540c80be5e7f73bfa56bd7db
|
File details
Details for the file llm_draw-0.1.2-py3-none-any.whl.
File metadata
- Download URL: llm_draw-0.1.2-py3-none-any.whl
- Upload date:
- Size: 15.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e92f9c01a475ec9613deb028b8bad0067895eafb4a2d43a1c999fad82dbde82f
|
|
| MD5 |
90bbe86fa6b4ea4a7565ef16b5347c92
|
|
| BLAKE2b-256 |
b6e13392d9fa659327aa12af35b2eea09a13a8dc9e28fec7f1078c54a6d5f0a9
|