phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-21 11:42:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

removing the base64 encoding

Browse source 
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo 2025-06-13 14:13:20 -04:00
parent e0f1788e9e
commit 5ef31f6752
3 changed files with 2 additions and 27 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -71,7 +71,6 @@ from llama_stack.providers.utils.inference.openai_compat import (
process_chat_completion_stream_response,
process_completion_response,
process_completion_stream_response,
process_embedding_b64_encoded_input,
)
from llama_stack.providers.utils.inference.prompt_adapter import (
chat_completion_request_to_prompt,
@ -397,6 +396,7 @@ class OllamaInferenceAdapter(
if model_obj.provider_resource_id is None:
raise ValueError(f"Model {model} has no provider_resource_id set")
# Note, at the moment Ollama does not support encoding_format, dimensions, and user parameters
params = prepare_openai_embeddings_params(
model=model_obj.provider_resource_id,
input=input,
@ -404,9 +404,6 @@ class OllamaInferenceAdapter(
dimensions=dimensions,
user=user,
)
# Note, at the moment Ollama does not support encoding_format, dimensions, and user parameters
# but we implement the encoding here
params = process_embedding_b64_encoded_input(params)
response = await self.openai_client.embeddings.create(**params)
data = b64_encode_openai_embeddings_response(response.data, encoding_format)