File tree Expand file tree Collapse file tree
Expand file tree Collapse file tree Original file line number Diff line number Diff line change @@ -102,18 +102,12 @@ When processing images, you can control the detail level:
102102- ** High detail** - Better accuracy for complex images but uses more tokens
103103- ** Low detail** - Faster processing with fewer tokens for simple images
104104
105- The default variable selector for vision is ` sys .files` which automatically picks up files from the Start node.
105+ The default variable selector for vision is ` userinput .files` which automatically picks up files from the User Input node.
106106
107107<Frame caption = " File processing with multimodal LLMs" >
108108 <img src = " https://assets-docs.dify.ai/2024/11/05b3d4a78038bc7afbb157078e3b2b26.png" alt = " File Processing" />
109109</Frame >
110110
111- For conversation history in completion models, insert conversation variables to maintain multi-turn context:
112-
113- <Frame caption = " Using conversation history variables" >
114- <img src = " https://assets-docs.dify.ai/dify-enterprise-mintlify/en/guides/workflow/node/b8642f8c6e3f562fceeefae83628fd68.png" alt = " Conversation History" />
115- </Frame >
116-
117111## Jinja2 Template Support
118112
119113LLM prompts support Jinja2 templating for advanced variable handling. When you use Jinja2 mode (` edition_type: "jinja2" ` ), you can:
You can’t perform that action at this time.
0 commit comments