phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-03 19:57:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Address comments

Browse source
This commit is contained in:
Jiayi 2025-09-28 15:11:23 -07:00
parent 816b68fdc7
commit cf386ad8f8
2 changed files with 8 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

12
docs/docs/providers/batches/index.mdx
View file

@ -18,14 +18,14 @@ title: Batches
## Overview ## Overview
The Batches API enables efficient processing of multiple requests in a single operation, The Batches API enables efficient processing of multiple requests in a single operation,
particularly useful for processing large datasets, batch evaluation workflows, and particularly useful for processing large datasets, batch evaluation workflows, and
cost-effective inference at scale. cost-effective inference at scale.
The API is designed to allow use of openai client libraries for seamless integration. The API is designed to allow use of openai client libraries for seamless integration.
This API provides the following extensions: This API provides the following extensions:
- idempotent batch creation - idempotent batch creation
Note: This API is currently under active development and may undergo changes. Note: This API is currently under active development and may undergo changes.
This section contains documentation for all available providers for the **batches** API. This section contains documentation for all available providers for the **batches** API.

4
llama_stack/providers/remote/inference/nvidia/nvidia.py
View file

@ -146,7 +146,7 @@ class NVIDIAInferenceAdapter(OpenAIMixin, Inference):
# Convert query to text format # Convert query to text format
if isinstance(query, str): if isinstance(query, str):
query_text = query query_text = query
elif hasattr(query, "text"): elif isinstance(query, OpenAIChatCompletionContentPartTextParam):
query_text = query.text query_text = query.text
else: else:
raise ValueError("Query must be a string or text content part") raise ValueError("Query must be a string or text content part")
@ -156,7 +156,7 @@ class NVIDIAInferenceAdapter(OpenAIMixin, Inference):
for item in items: for item in items:
if isinstance(item, str): if isinstance(item, str):
passages.append({"text": item}) passages.append({"text": item})
elif hasattr(item, "text"): elif isinstance(item, OpenAIChatCompletionContentPartTextParam):
passages.append({"text": item.text}) passages.append({"text": item.text})
else: else:
raise ValueError("Items must be strings or text content parts") raise ValueError("Items must be strings or text content parts")