| Name | Version | Summary | date |
| tf-hub-nightly |
0.17.0.dev202412210313 |
TensorFlow Hub is a library to foster the publication, discovery, and consumption of reusable parts of machine learning models. |
2024-12-21 08:14:38 |
| jina |
3.33.0 |
Multimodal AI services & pipelines with cloud-native stack: gRPC, Kubernetes, Docker, OpenTelemetry, Prometheus, Jaeger, etc. |
2024-12-20 12:13:56 |
| sawalni |
0.2.6 |
Official Python SDK for the Sawalni API |
2024-12-18 16:31:31 |
| ragdata |
0.1.0 |
Build knowledge bases for RAG |
2024-12-18 13:25:19 |
| txtai.py |
8.1.0 |
Python client for txtai |
2024-12-10 15:25:55 |
| txtai |
8.1.0 |
All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows |
2024-12-10 14:51:11 |
| text2text |
1.8.5 |
Text2Text Language Modeling Toolkit |
2024-12-08 21:33:57 |
| marqo |
3.9.2 |
Tensor search for humans |
2024-12-05 04:48:49 |
| ingrain |
0.0.6 |
Python client for the ingrain server |
2024-11-30 22:27:02 |
| llama-index-packs-cogniswitch-agent |
0.3.0 |
llama-index packs cogniswitch_agent integration |
2024-11-18 00:55:46 |
| llama-index-tools-cogniswitch |
0.3.0 |
llama-index tools cogniswitch integration |
2024-11-17 23:05:08 |
| top2vec |
1.0.36 |
Top2Vec learns jointly embedded topic, document and word vectors. |
2024-11-14 23:48:30 |
| air-benchmark |
0.1.0 |
AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark |
2024-10-17 09:46:37 |
| open-retrievals |
0.0.12 |
Text Embeddings for Retrieval and RAG based on transformers |
2024-09-23 11:47:41 |
| embedding-generator |
0.1.0 |
A module for generating embeddings for batches of texts using a SentenceTransformer model. |
2024-09-23 01:40:59 |
| neuspellmyntra |
1.0.0 |
NeuSpell: A Neural Spelling Correction Toolkit |
2024-09-19 14:24:01 |
| marqtune |
0.2.2 |
Client for marqtune |
2024-09-12 04:51:33 |
| progres |
0.2.7 |
Fast protein structure searching using structure graph embeddings |
2024-09-02 11:48:11 |
| textembed |
0.0.8 |
TextEmbed provides a robust and scalable REST API for generating vector embeddings from text. Built for performance and flexibility, it supports various sentence-transformer models, allowing users to easily integrate state-of-the-art NLP techniques into their applications. Whether you need embeddings for search, recommendation, or other NLP tasks, TextEmbed delivers with high efficiency. |
2024-06-13 03:05:31 |
| togetherai-haystack |
0.1.1 |
Haystack components to integrate with Together.AI inference models. |
2024-05-28 22:32:54 |