Skip to main content

CustomChat

A chat app for your documents. Ask a question, follow the citations, and keep the conversation going. Configure the model, sources and look in your browser.

It starts in offline Demo mode, with no API key or paid calls. Demo uses built-in answers, not a live AI model.

CustomChat answering a question with sources in offline Demo mode

Install and start

With uv installed, run:

uvx customchat-app start --directory my-chat

The app opens in your browser. Your settings, documents and chats stay in my-chat. Press Ctrl+C to stop; run the same command from the same folder to return.

Without uv, use the one-command installer for macOS, Linux or Windows. It installs what it needs without changing your system Python. For pip, install customchat-app in a virtual environment with Python 3.10 or newer. The package named customchat on PyPI is a different project.

Configure

  1. Open Configuration. In Answers, choose a provider, model and any required key, then test the connection and save.
  2. Add your documents or web links. Choose which sources the chat should use.
  3. In Appearance, choose a look and adjust the title, colors and fonts.

For help, type in Find a setting or open Guide. Ask AI asks your selected model about settings and may cost money.

Build with AI drafts a setup from your description. Choose a provider and model first, describe the app, then review, validate and save the draft. Restart to apply it. Generated code does not run automatically. Model requests may cost money.

Build with AI describe step with an example prompt

Keep keys out of YAML and Git. Check sources for important answers; citations are not a guarantee of correctness.

Install options · Configuration reference · Hosting

MIT license. Harsh Kashyap and Shela Wu. Advisor: Dennis Shasha. Related project: Custom-Nerd.

Metadata

Release files for customchat-app 0.1.31

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

Source distribution (sdist)

Source distribution for customchat-app 0.1.31
File Size Uploaded
customchat_app-0.1.31.tar.gz 9.3 MB Details

Built distribution (wheel)

Table of built distributions (wheels) for customchat-app 0.1.31
File Interpreter ABI Platform
customchat_app-0.1.31-py3-none-any.whl Python 3 none any Details

Total release size: 18.5 MB

Release files / customchat_app-0.1.31.tar.gz

Download URL customchat_app-0.1.31.tar.gz
Size 9.3 MB
Tags Source
SHA-256 checksum
How to use checksums
aae63b72952597fecf65ef0ae323f2a9edb3507b7f5105085c67364a40204192
BLAKE2b-256 checksum
How to use checksums
d7810f4751475e31fdb34c358283bfc7282c69230aad422885075b7db5983a13
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 14, 2026.

Transparency log

Release files / customchat_app-0.1.31-py3-none-any.whl

Download URL customchat_app-0.1.31-py3-none-any.whl
Size 9.2 MB
Tags Python 3
SHA-256 checksum
How to use checksums
06d2c25519c3caad81de57b1fcb2766c8ea59f6ca19656779f9e20c30175b15b
BLAKE2b-256 checksum
How to use checksums
07a27e672c4e4843d35276796e9ce9156399d1468c22728e3b2a0b6f81ae519f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 14, 2026.

Transparency log
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