https://github.com/trflorian/pydantic-ai-retry-fallback

Retry/Fallback with Pydantic-AI
https://github.com/trflorian/pydantic-ai-retry-fallback

antrophic api claude gemini google gpt llm openai pydantic-ai python

Last synced: about 2 months ago
JSON representation

Retry/Fallback with Pydantic-AI

• Host: GitHub
• URL: https://github.com/trflorian/pydantic-ai-retry-fallback
• Owner: trflorian
• Created: 2025-04-23T19:23:55.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2025-04-23T19:47:27.000Z (about 1 year ago)
• Last Synced: 2025-04-24T00:59:11.755Z (about 1 year ago)
• Topics: antrophic, api, claude, gemini, google, gpt, llm, openai, pydantic-ai, python
• Language: Python
• Homepage:
• Size: 29.3 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Retry / Fallback with Pydantic-AI

This project highlights a simple way to increase robustness when working with external APIs, such as LLM APIs from OpenAi, Google or Anthropic.

## Concepts

![schema](https://github.com/user-attachments/assets/44821b3a-7979-4b83-9ebe-b9ea37bd089d)

### Retry

Call the same api multiple times if a temporary problem prevents successfull responses.

### Fallback

Calling different models in case a provider is not reachable.

## Quickstart

### Prerequisites

- [uv](https://docs.astral.sh/uv/) package manager

- API keys for desired provider, see `.env.example` for reference

### Run Project

```

uv run main.py

```