Use pre-built environments for popular frameworks like Streamlit, FastAPI, vLLM, SGLang, and Ollama.
Native app integrations
Flyte ships with a set of pre-built AppEnvironment integrations that wrap popular frameworks and serving runtimes, so you can deploy common app types without writing the integration glue yourself. Each integration provides a ready-to-use environment class: just configure your app, image, resources, and scaling, and Flyte handles the rest.
If you’re new to apps in Flyte, start with Introducing apps for an overview, then see Build apps to learn how to build custom app environments from scratch.
When to use a native integration
Use a native integration when your app fits one of the supported frameworks and you want:
- A minimal, opinionated setup: sensible defaults for the framework, no boilerplate
- First-class support: features like model streaming, OpenAI-compatible APIs, and passthrough auth wired in for you
- Faster time-to-deploy: focus on your app logic, not on packaging and serving plumbing
For app types not covered here, build a custom AppEnvironment using the patterns in the Build apps section.
Available integrations
| Integration | Framework | Typical use case |
|---|---|---|
| Streamlit app | Streamlit | Interactive dashboards and data apps |
| FastAPI app | FastAPI | REST APIs, webhooks, and backend services |
| vLLM endpoint | vLLM | High-throughput LLM inference with an OpenAI-compatible API |
| SGLang endpoint | SGLang | Structured generation and LLM serving with an OpenAI-compatible API |
| Ollama endpoint | Ollama | Lightweight local-style LLM serving with an OpenAI-compatible API |
| Flyte webhook | FastAPI | Pre-built HTTP endpoints for common Flyte control plane operations |
See Inference for choosing between serving a model yourself and calling a hosted provider.
Next steps
- Streamlit app: Build interactive Streamlit dashboards
- FastAPI app: Create REST APIs and backend services
- vLLM endpoint: Serve large language models with vLLM
- SGLang endpoint: Serve LLMs with SGLang for structured generation
- Ollama endpoint: Serve lightweight LLMs with Ollama
- Flyte webhook: Pre-built webhook for common Flyte operations