͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
New multimodal Gemini Embedding model 🚀 | | |
| | We just launched Gemini Embedding 2 in the Gemini API with a new multimodal input to make it easier to build advanced RAG and semantic search systems. It now natively maps text, image, video, audio, and PDF inputs into a single, unified embedding space. Why you'll like multimodal embeddings - Simplified tech stack: Replace multiple models with one that processes multimodal content natively.
- Multimodal RAG: Improve accuracy and performance by retrieving information from different file types simultaneously.
- Cross-modal search: Match a text query to a relevant image, video clip, or audio segment, all in one index.
| | |
| | Start using the newest embeddings with this embed_content method: | | |
from google import genai from google.genai import types client = genai.Client()
with open("example.png", "rb") as f: image_bytes = f.read()
with open("sample.mp3", "rb") as f: audio_bytes = f.read()
# Here we embed text, image, and audio result = client.models.embed_content( model="gemini-embedding-2-preview", contents=[ "What is the meaning of life?", types.Part.from_bytes( data=image_bytes, mime_type="image/png", ), types.Part.from_bytes( data=audio_bytes, mime_type="audio/mpeg", ), ], ) print(result.embeddings) | | | |
We support commonly used vector databases such as Vertex AI, Weaviate, Qdrant, and ChromaDB to efficiently store, index, and retrieve high-dimensional embeddings. | | |
| | The Google AI Studio team | | |
| | This email was sent to pulipuli.chen@gmail.com because you signed up to receive emails about Google AI. If you do not wish to receive these emails, please unsubscribe. | | |
