phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 19:59:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

address feedback

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-12-11 16:24:37 -08:00
parent e167e9eb93
commit 5821ec9ef3
12 changed files with 61 additions and 76 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -36,6 +36,7 @@ from llama_stack.providers.utils.inference.openai_compat import (
from llama_stack.providers.utils.inference.prompt_adapter import (
chat_completion_request_to_prompt,
completion_request_to_prompt,
content_has_media,
convert_image_media_to_url,
request_has_media,
)
@ -323,8 +324,12 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
) -> EmbeddingsResponse:
model = await self.model_store.get_model(model_id)
assert all(
not content_has_media(content) for content in contents
), "Ollama does not support media for embeddings"
response = await self.client.embed(
model=model.provider_resource_id, input=contents
model=model.provider_resource_id,
input=[interleaved_text_media_as_str(content) for content in contents],
)
embeddings = response["embeddings"]