Apps/ImageApi
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

refactor: use &str for generate_photo_description image parameter

Browse Source 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Cameron
2026-03-18 16:56:27 -04:00
parent dd0715c081
commit b31b4b903c
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/ai/ollama.rs
View File

@@ -483,11 +483,11 @@ Analyze the image and use specific details from both the visual content and the
/// Generate a brief visual description of a photo for use in RAG query enrichment. /// Generate a brief visual description of a photo for use in RAG query enrichment.
/// Returns 1-2 sentences describing people, location, and activity visible in the image. /// Returns 1-2 sentences describing people, location, and activity visible in the image.
/// Only called when the model has vision capabilities. /// Only called when the model has vision capabilities.
pub async fn generate_photo_description(&self, image_base64: String) -> Result<String> { pub async fn generate_photo_description(&self, image_base64: &str) -> Result<String> {
let prompt = "Briefly describe what you see in this image in 1-2 sentences. \ let prompt = "Briefly describe what you see in this image in 1-2 sentences. \
Focus on the people, location, and activity."; Focus on the people, location, and activity.";
let system = "You are a scene description assistant. Be concise and factual."; let system = "You are a scene description assistant. Be concise and factual.";
let images = vec![image_base64]; let images = vec![image_base64.to_string()];
let description = self let description = self
.generate_with_images(prompt, Some(system), Some(images)) .generate_with_images(prompt, Some(system), Some(images))