Ashwin Bharambe 14f973a64f Make LlamaStackLibraryClient work correctly (#581) ... This PR does a few things: - it moves "direct client" to llama-stack repo instead of being in the llama-stack-client-python repo - renames it to `LlamaStackLibraryClient` - actually makes synchronous generators work - makes streaming and non-streaming work properly In many ways, this PR makes things finally "work" ## Test Plan See a `library_client_test.py` I added. This isn't really quite a test yet but it demonstrates that this mode now works. Here's the invocation and the response: ``` INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct python llama_stack/distribution/tests/library_client_test.py ollama ``` 		2024-12-07 14:59:36 -08:00
..
bedrock	Update more distribution docs to be simpler and partially codegen'ed	2024-11-20 22:03:44 -08:00
cerebras	Cerebras Inference Integration (#265)	2024-12-03 21:15:32 -08:00
databricks	Inference to use provider resource id to register and validate (#428)	2024-11-12 20:02:00 -08:00
fireworks	fix 3.2-1b fireworks	2024-11-19 14:20:07 -08:00
nvidia	allow env NVIDIA_BASE_URL to set NVIDIAConfig.url (#531)	2024-11-26 17:46:44 -08:00
ollama	Make LlamaStackLibraryClient work correctly (#581)	2024-12-07 14:59:36 -08:00
sample	migrate model to Resource and new registration signature (#410)	2024-11-08 16:12:57 -08:00
tgi	Tgi fixture (#519)	2024-11-25 13:17:02 -08:00
together	fix llama stack build for together & llama stack build from templates (#479)	2024-11-18 22:29:16 -08:00
vllm	use logging instead of prints (#499)	2024-11-21 11:32:53 -08:00
__init__.py	impls -> inline, adapters -> remote (#381)	2024-11-06 14:54:05 -08:00