The dynamic sessions in Azure Container
Apps is a fast, sandboxed, ephemeral compute, suitable for running AI-generated,
untrusted code at scale in hostile multi-tenancy scenarios. Each session has
full compute isolation using Hyper-V.
There are two modes:
- Code
interpreter sessions:. You can run Python code using
preinstalled popular Python packages. More languages and runtimes are planned
in the future.
To build AI agents or copilots, large language
models (LLMs) are paired with a code interpreter. A code interpreter enables an
agent or copilot application to extend an LLM’s abilities to perform complex
tasks such as solving mathematical and reasoning problems, analyzing data, and
generating graphics and charts.
You can build your own copilots by adding code
interpreter sessions to popular frameworks like LangChain, LlamaIndex, and
Semantic Kernel in just few lines of code.
- Custom
container sessions: You can use a custom container to create
a code interpreter for your specific needs, such as preinstalling dependencies
or supporting a different language.
You can also build a custom container to run
any application that requires secure sandboxed environments. Some example
scenarios include:
- A web-based code editing sandbox
- A SaaS application that can be extended
by end users with custom code snippets
- A hosted Jupyter Notebook service
Learn
more.