Loading video...

Video Failed to Load

Go Home

generated multi-modal embeddings of my bookmarks using Google DeepMind’s new Gemini Embedding 2, allowing low-dim spatialisation using UMAP and high-dim similarity querying via different media types.

hturan's profile picture

harley turan

13,013 subscribers

25,117 views • 3 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Integrate Gemini and Imagen APIs into your Flutter applications using the `firebase_ai` package 🪄🔥 In this video, you'll discover different model types for generative content and image generation, constructing multi-modal prompts, and handling responses.
2:20

Integrate Gemini and Imagen APIs into your Flutter applications using the `firebase_ai` package 🪄🔥 In this video, you'll discover different model types for generative content and image generation, constructing multi-modal prompts, and handling responses.

Flutter

14,874 views • 3 months ago

[HQ Gameplay Of New 9.6k Vita Outfit] [Via: Dim]
0:00

[HQ Gameplay Of New 9.6k Vita Outfit] [Via: Dim]

HI3_InfoCenter

19,269 views • 1 year ago

[Ver 8.1 Elysia Astral Ring] Gameplay of Ely’s astral ring and new ult [Via: Dim]
0:29

[Ver 8.1 Elysia Astral Ring] Gameplay of Ely’s astral ring and new ult [Via: Dim]

HI3_InfoCenter

173,398 views • 1 year ago

[8.2 Beta Sushang Gameplay] Gameplay of the new Sushang battlesuit [Via: Dim]
1:52

[8.2 Beta Sushang Gameplay] Gameplay of the new Sushang battlesuit [Via: Dim]

HI3_InfoCenter

52,711 views • 1 year ago

Multilingual voice AI tutor using the new Cartesia Sonic-2 voice model and Google DeepMind Gemini 2.0 Flash native audio understanding ...
0:48

Multilingual voice AI tutor using the new Cartesia Sonic-2 voice model and Google DeepMind Gemini 2.0 Flash native audio understanding ...

kwindla

18,793 views • 1 year ago

SynthID, our imperceptible watermark for AI-generated content, is expanding to more partners. We’re also adding new ways to find out if content was generated using AI - just ask in the Google Gemini or in Google Search.
0:55

SynthID, our imperceptible watermark for AI-generated content, is expanding to more partners. We’re also adding new ways to find out if content was generated using AI - just ask in the Google Gemini or in Google Search.

Google DeepMind

5,501,158 views • 1 month ago

Start building with Gemini Embedding 2, our most capable and first fully multimodal embedding model built on the Gemini architecture. Now available in preview via the Gemini API and in Vertex AI.
0:37

Start building with Gemini Embedding 2, our most capable and first fully multimodal embedding model built on the Gemini architecture. Now available in preview via the Gemini API and in Vertex AI.

Google AI Developers

30,484,245 views • 3 months ago

LINNEA GAMEPLAY Via Dim #GenshinImpact
2:37

LINNEA GAMEPLAY Via Dim #GenshinImpact

About Snezhnaya ❄️

803,910 views • 4 months ago

NICOLE GAMEPLAY Via Dim #GenshinImpact
3:00

NICOLE GAMEPLAY Via Dim #GenshinImpact

About Snezhnaya ❄️

1,959,979 views • 2 months ago

LOHEN SHOWCASE -Via Dim #GenshinImpact
1:31

LOHEN SHOWCASE -Via Dim #GenshinImpact

Genshin Universe❄️

81,854 views • 2 months ago

NICOLE SHOWCASE -Via Dim #GenshinImpact
1:52

NICOLE SHOWCASE -Via Dim #GenshinImpact

Genshin Universe

63,246 views • 2 months ago

LOHEN GAMEPLAY Via Dim #GenshinImpact
2:33

LOHEN GAMEPLAY Via Dim #GenshinImpact

About Snezhnaya ❄️

1,206,651 views • 2 months ago

COLUMBINA GAMEPLAY -Via Dim #GenshinImpact
2:29

COLUMBINA GAMEPLAY -Via Dim #GenshinImpact

Genshin Universe ❄️

1,151,025 views • 7 months ago

ODETTE GAMEPLAY Via Dim #GenshinImpact
2:40

ODETTE GAMEPLAY Via Dim #GenshinImpact

About Snezhnaya ❄️

762,566 views • 3 days ago

Cissia Animations: via Dim
2:13

Cissia Animations: via Dim

Zenless Zone Leaks

223,908 views • 4 months ago

jina-embeddings-v5-omni is here! Our first universal embedding model for text, images, audio, and video. Available in two sizes: small (1.57B, 1024-dim, 32K context) and nano (0.95B, 768-dim, 8K context). Both support Matryoshka truncation down to 32 dimensions. v5-omni is back-compatible: if you already use jina-embeddings-v5-text-small/nano, the existing text indexes work with v5-omni out of the box. Without reindexing the text, just index your multimodal content with v5-omni and start searching images, audio, and video.
1:00

jina-embeddings-v5-omni is here! Our first universal embedding model for text, images, audio, and video. Available in two sizes: small (1.57B, 1024-dim, 32K context) and nano (0.95B, 768-dim, 8K context). Both support Matryoshka truncation down to 32 dimensions. v5-omni is back-compatible: if you already use jina-embeddings-v5-text-small/nano, the existing text indexes work with v5-omni out of the box. Without reindexing the text, just index your multimodal content with v5-omni and start searching images, audio, and video.

Jina AI

133,435 views • 1 month ago

Dump all the images, videos, text, and audio data that you have into Supabase (storage + database), and make them searchable using the new Gemini Embedding 2 model! I know we all miss him a lot!
5:58

Dump all the images, videos, text, and audio data that you have into Supabase (storage + database), and make them searchable using the new Gemini Embedding 2 model! I know we all miss him a lot!

Tyler Shukert

11,446 views • 3 months ago

4.1 ASHVEIL GAMEPLAY -Via Dim #HonkaiStarRail
2:22

4.1 ASHVEIL GAMEPLAY -Via Dim #HonkaiStarRail

Star Rail Universe

379,352 views • 4 months ago

SANDRONE AGAINST HILICHURL Via Dim #GenshinImpact
0:24

SANDRONE AGAINST HILICHURL Via Dim #GenshinImpact

About NodKrai🌙

217,028 views • 1 month ago