Skip to main content

Documentation Buddy

CI PyPI version Python versions License: MIT Downloads FastAPI

Add an AI assistant to your /docs page.

Try the Standalone Demo

Installation

pip install docbuddy

Run the standalone page locally with the command:

docbuddy --port 9000

Python Integration

from fastapi import FastAPI
from docbuddy import setup_docs

app = FastAPI()
setup_docs(app)  # replaces default /docs

That's it! Visit /docs

API Explorer Chat Interface
API Explorer Chat Interface with Tools
Workflow Panel LLM Settings
Workflow Panel LLM Settings

Features

  • 💬 Chat interface with full OpenAPI context
  • 🤖 LLM Settings panel with local providers (Ollama, LM Studio, vLLM, Custom)
  • 🔗 Tool-calling for API Requests
  • 🎨 Dark/light theme support

Using the Chat

Ask questions like:

  • "What endpoints are available?"
  • "Create a curl cmd for adding a new user"
  • "Ping health"

Enable tool calling in the settings to allow the assistant to make API requests on your behalf.

Standalone Mode

If you prefer manual control, run DocBuddy from the repo root:

  1. Run python3 -m http.server 8080 from the repo root
  2. Visit in your browser http://localhost:8080/docs/index.html

Note: Due to browser security restrictions (CORS), if you want to use local LLMs (Ollama, LM Studio, vLLM), you must run DocBuddy locally instead of from the GitHub Pages hosted version.

LLM Settings

  1. Choose your local LLM provider (Ollama, LM Studio, vLLM, or Custom)
  2. Enter the API endpoint for your LLM (e.g. http://localhost:1234/v1 for LMStudio)
  3. Verify that the plugin can connect to your LLM provider and select a model from the drop down after.
  4. Enable tool calling if you want the assistant to make API requests on your behalf.

Some local LLM providers will require users to enable CORS in their API settings to allow the plugin to connect.

Demo Server

uvicorn examples.demo_server:app --reload --host 0.0.0.0 --port 3333

Development

pip install -e ".[dev]"

pytest tests/
pre-commit run --all-files

Metadata

Release files for docbuddy 0.7.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for docbuddy 0.7.0
File Size Uploaded Provenance Actions
docbuddy-0.7.0.tar.gz 1.1 MB Without provenance Details for docbuddy-0.7.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for docbuddy 0.7.0
File Interpreter ABI Platform Actions
docbuddy-0.7.0-py3-none-any.whl Python 3 none any Details for docbuddy-0.7.0-py3-none-any.whl

Total release size: 1.2 MB

Release files / docbuddy-0.7.0.tar.gz

Download URL docbuddy-0.7.0.tar.gz
Size 1.1 MB
Tags Source
SHA-256 checksum
How to use checksums
ae95a7ba6c3954d52f15a4e208ed97a238101971198079d03894eff431df6190
BLAKE2b-256 checksum
How to use checksums
e44de84d03467875be0e65cdbc2ce15affa06d745a6af883f35c7b1d3b7d1f5b
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.13.12

Release files / docbuddy-0.7.0-py3-none-any.whl

Download URL docbuddy-0.7.0-py3-none-any.whl
Size 82.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
c536cca9da2d223aefdd4fd0917f36fddeb29ea65f029d2d0608783f2f65905f
BLAKE2b-256 checksum
How to use checksums
d5698b7fb1b8bb1bf16dbe7b9ddab8844f8bab41fa7ffed0a1b1cedc284a2f6e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.13.12

Security for docbuddy 0.7.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page