33 lines
1.5 KiB
Django/Jinja
33 lines
1.5 KiB
Django/Jinja
{#- Qwen3-VL-Reranker chat template for multimodal reranking -#}
|
|
{#- This template formats query-document pairs for yes/no relevance judgment -#}
|
|
{#- Supports text, images, and videos in both query and documents -#}
|
|
<|im_start|>system
|
|
Judge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be "yes" or "no".<|im_end|>
|
|
<|im_start|>user
|
|
<Instruct>: {{ instruct | default("Given a search query, retrieve relevant candidates that answer the query.") }}
|
|
{#- Process query content -#}
|
|
<Query>: {%- for content in query -%}
|
|
{%- if content.type == 'image' or 'image' in content or 'image_url' in content -%}
|
|
<|vision_start|><|image_pad|><|vision_end|>
|
|
{%- elif content.type == 'video' or 'video' in content -%}
|
|
<|vision_start|><|video_pad|><|vision_end|>
|
|
{%- elif 'text' in content -%}
|
|
{{ content.text }}
|
|
{%- elif content.type == 'text' -%}
|
|
{{ content.text }}
|
|
{%- endif -%}
|
|
{%- endfor %}
|
|
{#- Process document content -#}
|
|
{{ '\n' }}<Document>: {%- for content in document -%}
|
|
{%- if content.type == 'image' or 'image' in content or 'image_url' in content -%}
|
|
<|vision_start|><|image_pad|><|vision_end|>
|
|
{%- elif content.type == 'video' or 'video' in content -%}
|
|
<|vision_start|><|video_pad|><|vision_end|>
|
|
{%- elif 'text' in content -%}
|
|
{{ content.text }}
|
|
{%- elif content.type == 'text' -%}
|
|
{{ content.text }}
|
|
{%- endif -%}
|
|
{%- endfor %}<|im_end|>
|
|
<|im_start|>assistant{{ '\n' }}
|