From a00c5ba4b8f7973cbfc01c438f8f5e373c79ad1b Mon Sep 17 00:00:00 2001 From: Matthias Guillitte Date: Wed, 2 Jul 2025 13:43:45 +0200 Subject: [PATCH] Fix prompt, unescaped double quote --- .../FileTools/VideoDescriptor/OCRLLMVideoDescriptor.php | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/app/Services/FileTools/VideoDescriptor/OCRLLMVideoDescriptor.php b/app/Services/FileTools/VideoDescriptor/OCRLLMVideoDescriptor.php index ebd7eb2..a228e93 100644 --- a/app/Services/FileTools/VideoDescriptor/OCRLLMVideoDescriptor.php +++ b/app/Services/FileTools/VideoDescriptor/OCRLLMVideoDescriptor.php @@ -108,7 +108,7 @@ Your response must strictly follow this JSON format: ## Rules 1. Analyze all provided inputs: screenshot number, timestamp, OCR result snippet, and LLM description for each frame. -2. The core goal is to produce one concise, coherent, and engaging video description that captures the essence of the entire reel ("the whole thing"). +2. The core goal is to produce one concise, coherent, and engaging video description that captures the essence of the entire reel (\"the whole thing\"). 3. Individual frame descriptions can be inaccurate or contradictory (e.g., object changes drastically between frames). Prioritize consistency across multiple frames unless strongly contradicted by a clear majority. 4. Do not generate separate JSON objects for each screenshot; only produce one final `answer` string summarizing the video as a whole at the end of your reasoning. 5. Pay special attention to identifying any underlying joke, humor, or satirical element present in the reel based on the collective information.