llama-stack-mirror/llama_stack/templates
Matthew Farrellee 79c9e46582 feat(openai): add configurable base_url support with OPENAI_BASE_URL env var
- Add base_url field to OpenAIConfig with default "https://api.openai.com/v1"
- Update sample_run_config to support OPENAI_BASE_URL environment variable
- Modify get_base_url() to return configured base_url instead of hardcoded value
- Add comprehensive test suite covering:
  - Default base URL behavior
  - Custom base URL from config
  - Environment variable override
  - Config precedence over environment variables
  - Client initialization with configured URL
  - Model availability checks using configured URL

This enables users to configure custom OpenAI-compatible API endpoints
via environment variables or configuration files.
2025-07-26 06:04:00 -04:00
..
ci-tests feat(openai): add configurable base_url support with OPENAI_BASE_URL env var 2025-07-26 06:04:00 -04:00
dell fix: separate build and run provider types (#2917) 2025-07-25 12:39:26 -07:00
meta-reference-gpu fix: separate build and run provider types (#2917) 2025-07-25 12:39:26 -07:00
nvidia feat(starter)!: simplify starter distro; litellm model registry changes (#2916) 2025-07-25 15:02:04 -07:00
open-benchmark feat(openai): add configurable base_url support with OPENAI_BASE_URL env var 2025-07-26 06:04:00 -04:00
postgres-demo fix: separate build and run provider types (#2917) 2025-07-25 12:39:26 -07:00
starter feat(openai): add configurable base_url support with OPENAI_BASE_URL env var 2025-07-26 06:04:00 -04:00
watsonx fix: separate build and run provider types (#2917) 2025-07-25 12:39:26 -07:00
__init__.py Auto-generate distro yamls + docs (#468) 2024-11-18 14:57:06 -08:00
template.py fix: separate build and run provider types (#2917) 2025-07-25 12:39:26 -07:00