LLAMPHouse

Serving Your LLM Apps, Scalable and Reliable.
Explore the docs »

· Report Bug · Request Feature

Building LLM-powered applications is easier than ever, with countless frameworks helping you craft intelligent workflows in Python. But when it’s time to deploy at scale, the challenges begin.

Most tutorials suggest spinning up a FastAPI server with an endpoint — but what happens when scalability and reliability becomes critical?

That’s where LLAMPHouse comes in.

LLAMPHouse provides a self-hosted, production-ready server that mimics OpenAI’s Assistant API while giving you full control over execution. Whether you're using LangChain, LlamaIndex, or your own custom framework, LLAMPHouse lets you deploy, scale, and customize your LLM apps—without sacrificing flexibility.

Take control of your LLM infrastructure and build AI-powered apps on your own terms with LLAMPHouse. 🚀

pip install llamphouse

Set the database URL in the environment variable:

DATABASE_URL="postgresql://postgres:password@localhost/llamphouse"

For examples, please refer to the Examples

1. Clone the repository
2. Install the library pip install .

This is only required if you want to push the package to PyPi.

1. python setup.py sdist bdist_wheel
2. git tag -a v1.0.0 -m "Release version 1.0.0"
3. git push

1. Build/Install the latest solution locally
2. Run the test: pytest

To run a local database:

1. docker run --rm -d --name postgres -e POSTGRES_USER=postgres -e POSTGRES_PASSWORD=password -p 5432:5432 postgres
2. docker exec -it postgres psql -U postgres -c 'CREATE DATABASE llamphouse;'

To create a new database revision: alembic revision --autogenerate -m "Added account table"

To upgrade the database with the latest revision: alembic upgrade head

To downgrade back to the base version: alembic downgrade base

• Assistants
  • Create -> created in code
  • List
  • Retrieve
  • Modify -> only in code
  • Delete -> only in code
• Threads
  • Create
  • Retrieve
  • Modify
  • Delete
• Messages
  • Create
  • List
  • Retrieve
  • Modify
  • Delete
• Runs
  • Create
  • Create thread and run
  • List
  • Retrieve
  • Modify
  • Submit tool outputs
  • Cancel
• Run steps
  • List
  • Retrieve
• Vector stores
  • Create -> depends on implementation
  • List
  • Retrieve
  • Modify
  • Delete -> depends on implementation
• Vector store files
  • Create
  • List
  • Retrieve
  • Delete
• Vector store file batches
  • Create
  • Retrieve
  • Cancel
  • List
• Streaming
  • Message delta
  • Run step object
  • Assistant stream

Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

See LICENSE for more information.

Project Admin: Pieter van der Deen - email