An open API service providing package, version and dependency metadata of many open source software ecosystems and registries.

pypi.org "multimodal" keyword

video-vit 0.0.4 ๐Ÿ’ฐ
Paper - Pytorch
2 versions - Latest release: over 2 years ago - 228 downloads last month - 9 stars on GitHub - 1 maintainer
raggify 0.3.3
llama index based library for building multimodal RAG systems
15 versions - Latest release: 7 months ago - 61 downloads last month - 0 stars on GitHub - 1 maintainer
Top 7.0% on pypi.org
lollms 11.0.0
A python library for AI personality definition
273 versions - Latest release: over 1 year ago - 4 dependent repositories - 5.22 thousand downloads last month - 91 stars on GitHub - 1 maintainer
datachain 1.2.4
Wrangle unstructured AI data at scale
290 versions - Latest release: about 3 years ago - 1 dependent package - 20 thousand downloads last month - 2,805 stars on GitHub - 3 maintainers
Top 1.6% on pypi.org
nemo-toolkit 3.0.0
NeMo - a toolkit for Conversational AI
109 versions - Latest release: 4 days ago - 4 dependent packages - 27 dependent repositories - 1.6 million downloads last month - 11,448 stars on GitHub - 3 maintainers
Top 1.2% on pypi.org
bentoml 1.4.39
BentoML: The easiest way to serve AI apps and models
219 versions - Latest release: 3 months ago - 13 dependent packages - 499 dependent repositories - 252 thousand downloads last month - 6,591 stars on GitHub - 3 maintainers
Top 6.0% on pypi.org
ms-swift 4.4.2
Swift: Scalable lightWeight Infrastructure for Fine-Tuning
132 versions - Latest release: 20 days ago - 2 dependent packages - 9 dependent repositories - 121 thousand downloads last month - 2,752 stars on GitHub - 1 maintainer
xtuner 0.2.0
An efficient, flexible and full-featured toolkit for fine-tuning large models
27 versions - Latest release: about 1 year ago - 1.29 thousand downloads last month - 5,173 stars on GitHub - 1 maintainer
Top 2.8% on pypi.org
mmpretrain 1.2.0
OpenMMLab Model Pretraining Toolbox and Benchmark
9 versions - Latest release: over 2 years ago - 1 dependent package - 60 dependent repositories - 14.6 thousand downloads last month - 3,847 stars on GitHub - 1 maintainer
tenderness 0.3.0
Text rendering library with pipelines for synthetic document generation
4 versions - Latest release: 6 days ago - 42 downloads last month - 4 stars on GitHub - 1 maintainer
Top 1.3% on pypi.org
mmcls 0.25.0
OpenMMLab Image Classification Toolbox and Benchmark
33 versions - Latest release: over 3 years ago - 13 dependent packages - 255 dependent repositories - 23.2 thousand downloads last month - 3,847 stars on GitHub - 1 maintainer
embestore 1.0.1
โ˜๏ธ Build multimodal AI applications with cloud-native stack
5 versions - Latest release: over 3 years ago - 23 downloads last month - 21,543 stars on GitHub - 1 maintainer
vtai 0.7.11 ๐Ÿ’ฐ
VT.ai - Minimal multimodal AI chat app with dynamic conversation routing
37 versions - Latest release: 4 months ago - 69 downloads last month - 118 stars on GitHub - 1 maintainer
freegenius 0.3.16 ๐Ÿ’ฐ
FreeGenius AI, an advanced AI assistant that is capable of engaging in conversation and performin...
219 versions - Latest release: almost 2 years ago - 575 downloads last month - 134 stars on GitHub - 1 maintainer
letmedoit 3.0.4 ๐Ÿ’ฐ
LetMeDoIt AI, an advanced AI assistant, leveraging the capabilities of AI models, to resolve dail...
246 versions - Latest release: over 1 year ago - 1 dependent package - 599 downloads last month - 134 stars on GitHub - 1 maintainer
letmedoit-android 0.0.98 ๐Ÿ’ฐ
LetMeDoIt AI, an advanced AI assistant, leveraging the capabilities of ChatGPT API, Gemini Pro an...
85 versions - Latest release: over 2 years ago - 230 downloads last month - 134 stars on GitHub - 1 maintainer
toolmateai 0.3.16 ๐Ÿ’ฐ
ToolMate AI is a cutting-edge AI companion that seamlessly integrates agents, tools, and plugins ...
1 version - Latest release: almost 2 years ago - 13 downloads last month - 134 stars on GitHub - 1 maintainer
cybertask 2.1.61 ๐Ÿ’ฐ
CyberTask AI, an advanced AI assistant, leveraging the capabilities of ChatGPT API, Gemini Pro an...
113 versions - Latest release: over 2 years ago - 569 downloads last month - 134 stars on GitHub - 1 maintainer
jetson-examples 0.2.11
Running Gen AI models and applications on NVIDIA Jetson devices with one-line command
30 versions - Latest release: 10 days ago - 568 downloads last month - 270 stars on GitHub - 1 maintainer
latentlens 0.1.0
Interpret what hidden representations encode via contextual nearest neighbors
1 version - Latest release: 6 months ago - 23 downloads last month - 38 stars on GitHub - 1 maintainer
llava-torch 1.2.2
Towards GPT-4 like large language and visual assistant.
6 versions - Latest release: over 2 years ago - 251 downloads last month - 19,083 stars on GitHub - 1 maintainer
groqchat 0.0.17 ๐Ÿ’ฐ
A terminal chatbot, powered by Groq Cloud API (Windows / macOS / Linux / Android / iOS)
15 versions - Latest release: almost 2 years ago - 80 downloads last month - 17 stars on GitHub - 1 maintainer
gchat 0.0.16 ๐Ÿ’ฐ
A terminal chatbot, powered by Groq Cloud API (Windows / macOS / Linux / Android / iOS)
9 versions - Latest release: about 2 years ago - 44 downloads last month - 17 stars on GitHub - 1 maintainer
weilink 0.6.2
Lightweight Python SDK for WeChat iLink Bot protocol
14 versions - Latest release: 4 months ago - 1.51 thousand downloads last month - 10 stars on GitHub - 1 maintainer
quatrix 0.2.1
Q-Compass architecture โ€” RL-grounded sequence mixing for text, vision, audio, world modeling, and...
4 versions - Latest release: 3 months ago - 27 downloads last month - 0 stars on GitHub - 1 maintainer
easyinstruct 0.1.2
An Easy-to-use Instruction Processing Framework for Large Language Models.
8 versions - Latest release: over 2 years ago - 1 dependent repositories - 148 downloads last month - 407 stars on GitHub - 3 maintainers
multimodal-reader-mcp 0.1.0
FastMCP server for reading local audio and video files with Google Gen AI.
1 version - Latest release: 5 months ago - 58 downloads last month - 1 maintainer
autodistill-chat-gpt 0.0.1
Images to inference with no labeling (use foundation models to train supervised models).
1 version - Latest release: about 3 years ago - 23 downloads last month - 1,735 stars on GitHub - 2 maintainers
gats-torch 0.0.1 ๐Ÿ’ฐ
gats - Pytorch
1 version - Latest release: over 2 years ago - 32 downloads last month - 9 stars on GitHub - 1 maintainer
mlcvzoo-mmpretrain 0.1.0
MLCVZoo MMPretrain Package
1 version - Latest release: over 1 year ago - 113 downloads last month - 3,640 stars on GitHub - 1 maintainer
Top 3.2% on pypi.org
rerun-sdk 0.35.0
The Rerun Logging SDK
267 versions - Latest release: 18 days ago - 9 dependent packages - 5 dependent repositories - 2.8 million downloads last month - 11,273 stars on GitHub - 1 maintainer
smartpipe-cli 1.6.0
Semantic pipes and queries for your terminal - PDFs, images, audio, video, and text through Unix ...
10 versions - Latest release: 27 days ago - 331 downloads last month - 1 stars on GitHub - 1 maintainer
mmae 0.2.2
Package for multimodal autoencoders with Bregman divergences.
4 versions - Latest release: about 6 years ago - 1 dependent repositories - 26 downloads last month - 19 stars on GitHub - 1 maintainer
pyspur 0.1.18
PySpur is a Graph UI for building AI Agents in Python
18 versions - Latest release: over 1 year ago - 158 downloads last month - 5,769 stars on GitHub - 1 maintainer
Top 0.7% on pypi.org
open-clip-torch 3.3.0
Open reproduction of consastive language-image pretraining (CLIP) and related.
55 versions - Latest release: 5 months ago - 76 dependent packages - 1,154 dependent repositories - 3.14 million downloads last month - 9,704 stars on GitHub - 2 maintainers
Top 0.7% on pypi.org
pyod 3.6.4 ๐Ÿ’ฐ
A Python library for anomaly detection across tabular, time series, graph, text, image, and audio...
115 versions - Latest release: 8 days ago - 50 dependent packages - 498 dependent repositories - 5 million downloads last month - 9,952 stars on GitHub - 1 maintainer
edge-assistant 0.1.0
Unified multimodal CLI assistant built on OpenAI's latest Responses API
1 version - Latest release: 11 months ago - 55 downloads last month - 1 maintainer
Top 1.6% on pypi.org
docarray 0.41.0
The data structure for multimodal data
741 versions - Latest release: over 1 year ago - 58 dependent packages - 1,390 dependent repositories - 106 thousand downloads last month - 3,123 stars on GitHub - 1 maintainer
livekit-agents 1.6.9
A powerful framework for building realtime voice AI agents
213 versions - Latest release: 3 days ago - 7 dependent packages - 4.58 million downloads last month - 920 stars on GitHub - 1 maintainer
livekit-plugins-google 1.6.9
Agent Framework plugin for services from Google Cloud
151 versions - Latest release: 3 days ago - 1.12 million downloads last month - 3,748 stars on GitHub - 1 maintainer
livekit-plugins-openai 1.6.9
Agent Framework plugin for services from OpenAI
177 versions - Latest release: 3 days ago - 3.18 million downloads last month - 3,748 stars on GitHub - 1 maintainer
livekit-plugins-elevenlabs 1.6.9
Agent Framework plugin for voice synthesis with ElevenLabs' API.
156 versions - Latest release: 3 days ago - 1.81 million downloads last month - 3,748 stars on GitHub - 1 maintainer
livekit-plugins-anthropic 1.6.9
Agent Framework plugin for services from Anthropic
128 versions - Latest release: 3 days ago - 887 thousand downloads last month - 3,748 stars on GitHub - 1 maintainer
pixelmemory 0.1.0
Multimodal Memory for AI Agents and MCP.
1 version - Latest release: about 1 year ago - 12 downloads last month - 7 stars on GitHub - 1 maintainer
proactivebench 0.1.1
Benchmark utilities and environments for evaluating multimodal LLMs' proactiveness.
2 versions - Latest release: 5 months ago - 75 downloads last month - 24 stars on GitHub - 1 maintainer
lica-gdb 0.2.1 ๐Ÿ’ฐ
GDB: GraphicDesignBench โ€” benchmark suite for evaluating vision-language models on graphic design...
4 versions - Latest release: 4 months ago - 114 downloads last month - 6 stars on GitHub - 1 maintainer
haystack-pixeltable 0.1.1
Haystack Document Store and Retriever backed by Pixeltable multimodal data infrastructure.
2 versions - Latest release: 6 days ago - 24 downloads last month - 1 maintainer
swarmauri_agent_realtime 0.1.0.dev4
Provider-neutral realtime multimodal agent for Swarmauri live models.
1 version - Latest release: 1 day ago - 1 maintainer
mcif-bench 1.0
Repository with the code for the multilingual and multimodal benchmark MCIF
1 version - Latest release: 8 months ago - 67 downloads last month - 11 stars on GitHub - 1 maintainer
glue3d 0.3.0
Official project for GLUE3D.
5 versions - Latest release: 9 months ago - 91 downloads last month - 2 stars on GitHub - 1 maintainer
fine-tuner 0.0.0
Jina is the cloud-native neural search framework for any kind of data
1 version - Latest release: almost 5 years ago - 1 dependent repositories - 38 downloads last month - 19,631 stars on GitHub - 1 maintainer
apiz 0.2.0
Official Python SDK for the apiz.ai AI generation platform
2 versions - Latest release: 4 months ago - 67 downloads last month - 3 stars on GitHub - 1 maintainer
granular 0.23.1
Fast format for datasets
57 versions - Latest release: 24 days ago - 2.31 thousand downloads last month - 17 stars on GitHub - 1 maintainer
llmgate 0.8.3
Lightweight, provider-agnostic LLM calling library โ€” OpenAI, Gemini, Anthropic, Groq, Mistral, Co...
9 versions - Latest release: 3 months ago - 82 downloads last month - 2 stars on GitHub - 1 maintainer
videodb-capture-bin 0.3.1
Binary container for VideoDB Capture runtime
6 versions - Latest release: 4 months ago - 291 downloads last month - 96 stars on GitHub - 1 maintainer
videodb 0.5.1
VideoDB Python SDK
35 versions - Latest release: 17 days ago - 1 dependent package - 23.8 thousand downloads last month - 96 stars on GitHub - 1 maintainer
crossmodalnet 0.1.0
Interpretable modeling of time-resolved single-cell gene-protein expression.
1 version - Latest release: 3 months ago - 13 downloads last month - 3 stars on GitHub - 1 maintainer
everalgo-parser 0.2.1
EverAlgo parser: multimodal raw-file parsing (image / audio / document / video / url) into Parsed...
3 versions - Latest release: about 2 months ago - 5.36 thousand downloads last month - 23 stars on GitHub - 1 maintainer
sinapsis 0.2.27
Modular and Universal AI platform
28 versions - Latest release: 5 months ago - 3.13 thousand downloads last month - 40 stars on GitHub - 1 maintainer
Top 2.6% on pypi.org
stability-sdk 0.8.6
Python SDK for interacting with stability.ai APIs
28 versions - Latest release: over 2 years ago - 12 dependent packages - 24 dependent repositories - 29.2 thousand downloads last month - 2,437 stars on GitHub - 1 maintainer
imagine-mcp 1.10.1 ๐Ÿ’ฐ
MCP server for image/video understanding & generation (Gemini/OpenAI/Grok)
71 versions - Latest release: 24 days ago - 1.7 thousand downloads last month - 4 stars on GitHub - 1 maintainer
omni-image-tools-mcp 0.6.2
MCP server with image tools (vision + processing) supporting multiple providers
3 versions - Latest release: 3 days ago - 0 stars on GitHub - 1 maintainer
axquant 1.6.1
CLI toolkit for converting supported MLX language and multimodal checkpoints
7 versions - Latest release: 2 days ago - 0 stars on GitHub - 1 maintainer
abstractflow 0.3.17
Gateway-first visual workflow authoring for AbstractFramework
15 versions - Latest release: 2 months ago - 305 downloads last month - 5 stars on GitHub - 1 maintainer
papermage 0.20.0
Papermage. Casting magic over scientific PDFs.
8 versions - Latest release: over 2 years ago - 410 downloads last month - 802 stars on GitHub - 3 maintainers
emotion-framework 1.0.1
Multimodal emotion recognition framework for video analysis
2 versions - Latest release: 7 months ago - 10 downloads last month - 1 maintainer
Top 4.5% on pypi.org
ppdiffusers 0.29.0
PPDiffusers: Diffusers toolbox implemented based on PaddlePaddle
19 versions - Latest release: almost 2 years ago - 1 dependent package - 65 dependent repositories - 2.71 thousand downloads last month - 724 stars on GitHub - 1 maintainer
Top 9.4% on pypi.org
uform 3.1.3
Pocket-Sized Multimodal AI for Content Understanding and Generation
39 versions - Latest release: 11 months ago - 1 dependent package - 1 dependent repositories - 6.38 thousand downloads last month - 678 stars on GitHub - 2 maintainers
polymathic-aion 0.0.2
AstronomIcal Omnimodal Network - Polymathic's Large Omnimodal Model for Astronomy
2 versions - Latest release: about 1 year ago - 526 downloads last month - 144 stars on GitHub - 1 maintainer
cmmdf 0.1.0
A short description of the package
1 version - Latest release: over 2 years ago - 49 downloads last month - 1 maintainer
pyxenium 0.4.6
Xenium I/O, multimodal analysis, topology workflows, contour-native spatial profiling, GMI infere...
12 versions - Latest release: 3 months ago - 154 downloads last month - 1 maintainer
hpsv3 1.0.0
HPSv3: Towards Wide-Spectrum Human Preference Score - A VLM-based preference model for image qual...
1 version - Latest release: about 1 year ago - 2.04 thousand downloads last month - 0 stars on GitHub - 1 maintainer
linmult 2.1.1
General-purpose Multimodal Transformer with Linear Complexity Attention Mechanism.
20 versions - Latest release: 3 days ago - 1 dependent package - 1.49 thousand downloads last month - 2 stars on GitHub - 1 maintainer
mm-ctx 0.13.2
Fast, multimodal context for agents.
23 versions - Latest release: 2 months ago - 1.49 thousand downloads last month - 68 stars on GitHub - 1 maintainer
lexoid 0.1.22
Multimodal document parser for high quality data understanding and extraction
22 versions - Latest release: 2 months ago - 107 downloads last month - 44 stars on GitHub - 3 maintainers
pytorch-search 0.6.8
Jina is the cloud-native neural search solution powered by the state-of-the-art AI and deep learning
2 versions - Latest release: almost 6 years ago - 1 dependent repositories - 18 downloads last month - 19,631 stars on GitHub - 1 maintainer
cmon-ai 0.42.6
Build multimodal AI services via cloud native technologies ยท Neural Search ยท Generative AI ยท MLOps
4 versions - Latest release: about 3 years ago - 43 downloads last month - 1 maintainer
autodistill-blip2 0.0.1
Images to inference with no labeling (use foundation models to train supervised models).
1 version - Latest release: about 3 years ago - 28 downloads last month - 1,786 stars on GitHub - 2 maintainers
omnimodkit 0.0.9
Get structured output from multimodal AI models and integrate them into multitool agents
9 versions - Latest release: 11 months ago - 59 downloads last month - 1 stars on GitHub - 1 maintainer
tensorflow-search 0.6.8
Jina is the cloud-native neural search solution powered by the state-of-the-art AI and deep learning
2 versions - Latest release: almost 6 years ago - 1 dependent repositories - 100 downloads last month - 21,824 stars on GitHub - 1 maintainer
heretic-llm-notebook 1.1.1
Fully automatic censorship removal for language models (Notebook & Multimodal Edition)
9 versions - Latest release: 9 months ago - 799 downloads last month - 27,186 stars on GitHub - 1 maintainer
mcp-recognize-image 0.3.0
MCP server that lets text-only models 'see' images via configurable vision LLM providers with pri...
3 versions - Latest release: about 1 month ago - 1 maintainer
mime-files-reader 0.2.1
A tool to process various file types (images, PDFs, audio) using Google Generative AI
2 versions - Latest release: about 1 year ago - 578 downloads last month - 4 stars on GitHub - 1 maintainer
maestro-loader 0.1.2
Loader for the maestro-eeg-dataset (multimodal EEG/gaze/IMU/audio/video AAD dataset on HuggingFace).
3 versions - Latest release: 3 months ago - 38 downloads last month - 1 maintainer
vortex-data 0.83.0
Python bindings for Vortex, an Apache Arrow-compatible toolkit for working with compressed array ...
60 versions - Latest release: 17 days ago - 146 thousand downloads last month - 3,124 stars on GitHub - 1 maintainer
autodistill-vertex 0.0.1
Images to inference with no labeling (use foundation models to train supervised models).
1 version - Latest release: about 3 years ago - 121 downloads last month - 1,786 stars on GitHub - 2 maintainers
autodistll-grounded-sam 0.0.5
Automatically distill large foundational models into smaller, in-domain models for deployment
1 version - Latest release: about 3 years ago - 22 downloads last month - 2,753 stars on GitHub - 1 maintainer
Top 4.3% on pypi.org
autodistill 0.1.29
Distill large foundational models into smaller, domain-specific models for deployment
32 versions - Latest release: over 1 year ago - 39 dependent packages - 2 dependent repositories - 3.73 thousand downloads last month - 1,735 stars on GitHub - 3 maintainers
Top 3.5% on pypi.org
mteb 2.18.16
Massive Text Embedding Benchmark
774 versions - Latest release: 5 days ago - 6 dependent packages - 25 dependent repositories - 2.79 million downloads last month - 1,441 stars on GitHub - 4 maintainers
lmms_eval 0.7.2
A framework for evaluating large multi-modality language models
24 versions - Latest release: about 2 months ago - 12 thousand downloads last month - 4,351 stars on GitHub - 1 maintainer
live-bench 0.0.0.dev0
Live Bench
1 version - Latest release: about 2 years ago - 39 downloads last month - 4,351 stars on GitHub - 1 maintainer
Top 9.3% on pypi.org
simplemem 0.1.0
Efficient Lifelong Memory for LLM Agents
1 version - Latest release: 7 months ago - 545 downloads last month - 3,680 stars on GitHub - 1 maintainer
matilda-sc 0.2.1
Multi-task framework for single-cell multimodal data (classification, dimension reduction, featur...
3 versions - Latest release: about 1 month ago - 48 downloads last month - 22 stars on GitHub - 3 maintainers
easyrerank 0.2.4
A premium, self-contained Python module for local (llama.cpp) and remote (Jina AI, OpenRouter) se...
6 versions - Latest release: about 2 months ago - 1 maintainer
genkit 0.9.0
Genkit AI Framework
18 versions - Latest release: 10 days ago - 6.31 thousand downloads last month - 6,323 stars on GitHub - 1 maintainer
genkit-plugin-anthropic 0.9.0
Deprecated: This package has been renamed to genkit-anthropic.
7 versions - Latest release: 10 days ago - 1.11 thousand downloads last month - 1 maintainer
genkit-plugin-compat-oai 0.9.0
Deprecated: This package has been renamed to genkit-openai.
10 versions - Latest release: 10 days ago - 1.76 thousand downloads last month - 1 maintainer
genkit-plugin-google-genai 0.9.0
Deprecated: This package has been renamed to genkit-google-genai.
15 versions - Latest release: 10 days ago - 4.49 thousand downloads last month - 1 maintainer
genkit-plugin-flask 0.9.0
Deprecated: This package has been renamed to genkit-flask.
13 versions - Latest release: 10 days ago - 138 downloads last month - 1 maintainer
genkit-plugin-google-cloud 0.9.0
Deprecated: This package has been renamed to genkit-google-cloud.
9 versions - Latest release: 10 days ago - 212 downloads last month - 1 maintainer