RRULE_Extractor/chat_template.jinja

{%- set image_placeholder = '<|vision_start|><|image_pad|><|vision_end|>' -%}
{%- for message in messages -%}
    {%- if message['role'] == 'system' -%}
        {{- '<|im_start|>system
' -}}
        {%- if message['content'] is string -%}
            {{- message['content'] | trim -}}
        {%- endif -%}
        {{- '<|im_end|>
' -}}
    {%- elif message['role'] == 'user' -%}
        {%- if loop.first -%}
            {{- '<|im_start|>system
' -}}
            {%- if template -%}
                {#--- If template, extraction task ---#}
                {{- 'You are NuExtract, an information extraction tool created by NuMind.' -}}
            {%- else -%}
                {#--- Else, template generation task ---#}
                {{- 'You are a helpful assistant.' -}}
            {%- endif -%}
            {{ '<|im_end|>
' }}
        {%- endif -%}
        {{- '<|im_start|>' + message['role'] + '
' -}}
        {%- if template -%}
            {#--- Template Section ---#}
            {{- '# Template:
' -}}
            {{- template -}}
            {{- '
' -}}

            {%- if examples -%}
                {#--- Examples can only exist in the extraction task ---#}
                {{- '# Examples:
' -}}
                {%- for example in examples -%}
                    {{- '## Input:
' -}}
                    {%- if example['input'] is mapping and (example['input']['type'] == 'image' or example['input']['type'] == 'image_url') -%}
                        {{- image_placeholder | trim -}}
                    {%- elif example['input'] == '<image>' -%}
                        {#--- Keep compatibility with <image> for now ---#}
                        {{- image_placeholder | trim -}}
                    {%- else -%}
                        {#--- Text input example ---#}
                        {{- example['input'] -}}
                    {%- endif -%}
                    {{- '
' -}}
                    {{- '## Output:
' -}}
                    {{- example['output'] -}}
                    {{- '
' -}}
                {%- endfor -%}
            {%- endif -%}
            {{- '# Context:
' -}}
        {%- endif -%}

        {%- if message['content'] is string -%}
            {#--- Simple string content ---#}
            {{- message['content'] | trim -}}
        {%- elif message['content'] is mapping and (message['content']['type'] == 'image' or message['content']['type'] == 'image_url') -%}
            {{- image_placeholder | trim -}}
        {%- else -%}
            {#--- List of content items (mixed text/images) ---#}
            {#--- First, determine what the actual input content is (not ICL images) ---#}
            {%- set ns = namespace(has_text_input=false, text_content='') -%}

            {#--- Count content types and identify actual input document ---#}
            {%- for content in message['content'] -%}
                {%- if content is mapping and content.get('type') == 'text' -%}
                    {%- if content.get('text') != '<image>' -%}
                        {#--- Keep compatibility with <image> for now ---#}
                        {%- set ns.has_text_input = true -%}
                        {%- set ns.text_content = content['text'] -%}
                    {%- endif -%}
                {%- elif content is string -%}
                    {%- if content != '<image>' -%}
                        {#--- Keep compatibility with <image> for now ---#}
                        {%- set ns.has_text_input = true -%}
                        {%- set ns.text_content = content -%}
                    {%- endif -%}
                {%- endif -%}
            {%- endfor -%}

            {#--- Determine what to output based on actual input type ---#}
            {%- if ns.has_text_input -%}
                {#--- Main input is text, so output the text content ---#}
                {{- ns.text_content | trim -}}
            {%- else -%}
                {#--- Main input is image or <image> placeholder ---#}
                {%- set ns2 = namespace(found_image=false) -%}
                {%- for content in message['content'] -%}
                    {%- if content is mapping and (content.get('type') == 'image' or content.get('type') == 'image_url') and not ns2.found_image -%}
                        {{- image_placeholder | trim -}}
                        {%- set ns2.found_image = true -%}
                    {%- elif content is mapping and content.get('type') == 'text' and content.get('text') == '<image>' and not ns2.found_image -%}
                        {#--- Keep compatibility with <image> for now ---#}
                        {{- image_placeholder | trim -}}
                        {%- set ns2.found_image = true -%}
                    {%- elif content is string and content == '<image>' and not ns2.found_image -%}
                        {#--- Keep compatibility with <image> for now ---#}
                        {{- image_placeholder | trim -}}
                        {%- set ns2.found_image = true -%}
                    {%- endif -%}
                {%- endfor -%}
            {%- endif -%}
        {%- endif -%}
        {{- '<|im_end|>
'}}

    {%- elif message['role'] == 'assistant' -%}
        {{- '<|im_start|>assistant
' -}}
        {%- if message['content'] is string -%}
            {{- message['content'] | trim -}}
        {%- elif message['content'] is iterable and message['content'] is not string -%}
            {%- for content in message['content'] -%}
                {%- if content is mapping and content.get('type') == 'text' -%}
                    {{- content['text'] | trim -}}
                {%- elif content is string -%}
                    {{- content | trim -}}
                {%- endif -%}
            {%- endfor -%}
        {%- endif -%}
        {{- '<|im_end|>
' -}}
    {%- endif -%}
{%- endfor -%}
{%- if add_generation_prompt -%}
    {{- '<|im_start|>assistant
' -}}
{%- endif -%}