You are a developer assistant where you only provide the code…
- User
Assistant: User: System: You are a developer assistant where you only provide the code for a question. No explanation required. Write a simple json sample. Given the transcript segments, can you generate a list of highlights with start and end times for the video using multiple segments? Please meet the following constraints:
- The highlights should be a direct part of the video and should not be out of context. - The highlights should be interesting and clippable, providing value to the viewer. - The highlights should be 20 to 60 seconds MAXIMUM. - The highlights should include more than one segment to provide context and continuity. - The highlights should not cut off in the middle of a sentence or idea. - The highlight should be disregarded if it is not a complete thought - The user provided highlight phrases should be used to generate the highlights - The highlights should be based on the relevance of the segments to the highlight phrases - The highlights should be scored out of 100 based on the relevance of the segments to the highlight phrases. - The score should be greater than 80 Respond with the following JSON schema with valid JSON syntax for highlights: {'$defs': {'Highlight': {'properties': {'title': {'description': 'Title of the Video highlight', 'title': 'Title', 'type': 'string'}, 'start_time': {'description': 'Start time of the video highlight', 'title': 'Start Time', 'type': 'number'}, 'end_time': {'description': 'End time of the video highlight', 'title': 'End Time', 'type': 'number'}, 'score': {'description': 'Score of the video highlight', 'title': 'Score', 'type': 'number'}}, 'required': ['title', 'start_time', 'end_time', 'score'], 'title': 'Highlight', 'type': 'object'}}, 'properties': {'chapters': {'description': 'List of Highlights', 'items': {'$ref': '#/$defs/Highlight'}, 'title': 'Chapters', 'type': 'array'}}, 'required': ['chapters'], 'title': 'HighlightSchema', 'type': 'object'} Each highlight should have the following fields: - title: title of the highlight - start_time: start time of the highlight as a float in seconds - end_time: end time of the highlight as a float in seconds - score: score of the highlight as a float out of 100User: Key Phrases: Funny
[2581.66 - 2582.06]: Right [2582.06 - 2583.80]: So what's going on here, buddy? [2584.18 - 2585.72]: My close friends have seen her [2585.72 - 2587.30]: Well, like they don't look at them [2587.30 - 2587.64]: Don't look at them [2587.64 - 2588.74]: Oh, okay, okay [2588.74 - 2591.44]: So like, like, people have seen her [2591.44 - 2591.76]: Yeah [2592.24 - 2593.18]: She's a real person [2593.18 - 2593.96]: She's a... [2593.96 - 2594.74]: This isn't, she goes to another school [2594.74 - 2595.70]: She goes to another school [2595.70 - 2597.02]: Oh, she goes to a different school [2597.02 - 2598.06]: Right, got pretty much [2598.06 - 2598.64]: Across town [2598.64 - 2599.26]: Across town [2599.26 - 2599.94]: Okay [2599.94 - 2601.48]: Try to beat the allegations here [2601.48 - 2602.34]: Alright, so here's the deal [2604.36 - 2605.18]: You're doing a good job [2605.18 - 2605.98]: You're doing a very good job [2606.40 - 2607.86]: So this girl that you're seeing now [2607.86 - 2608.64]: might be Asian [2608.64 - 2610.14]: But have you, have you dated [2610.14 - 2612.20]: many other races or girls or no? [2612.54 - 2614.28]: Um, I've been around the world [2614.28 - 2615.56]: Oh, you haven't taken her [2615.56 - 2617.38]: I'm not dating, I mean, like, just, you know [2617.38 - 2618.12]: They're talking up [2618.12 - 2619.62]: Sharing, sharing, sharing love [2619.62 - 2620.58]: Yeah, swap a bit [2620.58 - 2620.74]: Sharing love [2620.74 - 2621.82]: I'm a lover, not a fighter [2621.82 - 2622.50]: Yeah, yeah [2622.50 - 2623.42]: I'll make it wrestling [2623.42 - 2625.22]: Yeah, I'll make it wrestling [2625.22 - 2626.92]: Yeah, I like the whites [2628.32 - 2629.02]: Why is that? [2630.56 - 2632.16]: He does, he only dates white girls [2632.16 - 2632.74]: Is that true? [2633.16 - 2633.52]: Exclusively [2633.52 - 2634.58]: I thought you had a... [2634.58 - 2635.84]: Are you, are you, are you married? [2636.46 - 2636.80]: No, not [2637.52 - 2638.88]: He got out of a long-term relationship [2638.88 - 2639.64]: I get out of a long time [2639.64 - 2641.12]: With a woman who was Asian [2641.12 - 2641.54]: Okay [2641.54 - 2643.04]: But now since then, he's gone [2643.74 - 2644.34]: Real white [2644.34 - 2645.90]: I'm just going on a white tour right now [2645.90 - 2646.10]: Yeah [2646.86 - 2648.52]: So, like, mostly just like up in [2648.52 - 2650.40]: Washington DC or here's some [2650.40 - Assistant: Assistant:
- Assistant
{ "chapters": [ { "title": "Funny Discussion about Friends and Relationships", "start_time": 2581.66, "end_time": 2595.70, "score": 85.2 }, { "title": "Lighthearted Banter on Dating Preferences", "start_time": 2601.48, "end_time": 2621.82, "score": 83.5 }, { "title": "Hilarious Take on Dating and Race", "start_time": 2630.56, "end_time": 2645.90, "score": 81.7 } ] }
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.