llama-stack-mirror/llama_stack
Ben Browning 1e673010e4 fix: OpenAI API chat completion messages with image_url
This fixes the OpenAI API chat completions endpoint to accept messages
with image_url references. Previously, we were using the
InterleavedContent type which was actually a Llama Stack API type that
happened to work for text message parts, but the schema differs for
image message parts.

So, this adds OpenAI-specific schema classes to handle text and image
chat completions message parts.

Signed-off-by: Ben Browning <bbrownin@redhat.com>
2025-04-13 13:39:56 -04:00
..
apis fix: OpenAI API chat completion messages with image_url 2025-04-13 13:39:56 -04:00
cli fix: misleading help text for 'llama stack build' and 'llama stack run' (#1910) 2025-04-12 01:19:11 -07:00
distribution fix: misc fixes for tests kill horrible warnings 2025-04-12 17:12:11 -07:00
models feat: support '-' in tool names (#1807) 2025-04-12 14:23:03 -07:00
providers fix: misc fixes for tests kill horrible warnings 2025-04-12 17:12:11 -07:00
strong_typing chore: more mypy checks (ollama, vllm, ...) (#1777) 2025-04-01 17:12:39 +02:00
templates feat: add batch inference API to llama stack inference (#1945) 2025-04-12 11:41:12 -07:00
__init__.py export LibraryClient 2024-12-13 12:08:00 -08:00
env.py refactor(test): move tools, evals, datasetio, scoring and post training tests (#1401) 2025-03-04 14:53:47 -08:00
log.py chore: Remove style tags from log formatter (#1808) 2025-03-27 10:18:21 -04:00
schema_utils.py fix: dont check protocol compliance for experimental methods 2025-04-12 16:26:32 -07:00