yuvrajangadsingh/vemb
httpie for embeddings. Embed text, images, audio, video, and PDFs from the command line.
Leverages Google's Gemini Embedding 2, a natively multimodal model that projects all content types (text, images, audio, video, PDFs) into a single vector space. Supports batch processing with JSONL output, configurable embedding dimensions (128-3072), task-specific encoding modes (RETRIEVAL_QUERY, etc.), and a built-in search command that caches embeddings locally to avoid re-processing unchanged files. Designed for CLI-first workflows with stdin piping and auto-detection of file types.
Available on PyPI.
Stars
3
Forks
—
Language
Python
License
MIT
Category
Last pushed
Mar 19, 2026
Monthly downloads
205
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/yuvrajangadsingh/vemb"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
FlagOpen/FlagEmbedding
Retrieval and Retrieval-augmented LLMs
Blaizzy/mlx-embeddings
MLX-Embeddings is the best package for running Vision and Language Embedding models locally on...
qdrant/fastembed
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
Merck/Sapiens
Sapiens is a human antibody language model based on BERT.
amansrivastava17/embedding-as-service
One-Stop Solution to encode sentence to fixed length vectors from various embedding techniques