phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-15 15:22:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: Fix embedding model listing and usage for watsonx

Browse source 
Signed-off-by: Bill Murdock <bmurdock@redhat.com>
This commit is contained in:
Bill Murdock 2025-10-03 16:16:55 -04:00
parent 999c28e809
commit ecafe40a84
2 changed files with 36 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/providers/utils/inference/openai_compat.py
View file

@ -1405,7 +1405,7 @@ def prepare_openai_embeddings_params(
def b64_encode_openai_embeddings_response(
response_data: dict, encoding_format: str | None = "float"
response_data: list[dict], encoding_format: str | None = "float"
) -> list[OpenAIEmbeddingData]:
"""
Process the OpenAI embeddings response to encode the embeddings in base64 format if specified.
@ -1414,12 +1414,12 @@ def b64_encode_openai_embeddings_response(
for i, embedding_data in enumerate(response_data):
if encoding_format == "base64":
byte_array = bytearray()
for embedding_value in embedding_data.embedding:
for embedding_value in embedding_data["embedding"]:
byte_array.extend(struct.pack("f", float(embedding_value)))
response_embedding = base64.b64encode(byte_array).decode("utf-8")
else:
response_embedding = embedding_data.embedding
response_embedding = embedding_data["embedding"]
data.append(
OpenAIEmbeddingData(
embedding=response_embedding,