Improve SpringAI models AOT support

- Fix various issues for bedrok/llama2/titan/choere,palm2,openai,azure-openai and vertex
 - Addd demo tests: https://github.com/tzolov/spring-ai-aot-tests
 - Fix broken Ollama AOT configuration
 - Code style & doc improvements for onnx transformer client

 Part of #360
This commit is contained in:
Christian Tzolov
2024-02-25 23:28:23 +01:00
parent 4e270ac75a
commit 21fc676fba
20 changed files with 279 additions and 40 deletions

View File

@@ -81,7 +81,7 @@ List<List<Double>> embeddings = embeddingClient.embed(List.of("Hello world", "Wo
----
Note that when created manually, you must call the `afterPropertiesSet()` after setting the properties and before using the client.
NOTE: that when created manually, you must call the `afterPropertiesSet()` after setting the properties and before using the client.
The first `embed()` call downloads the large ONNX model and caches it on the local file system.
Therefore, the first call might take longer than usual.