awesome-text-embeddings
A curated list of text embedding models, benchmarks, and tools for semantic search, retrieval, and classification.
https://github.com/metawake/awesome-text-embeddings
Last synced: 3 days ago
JSON representation
-
Benchmarks & Leaderboards
-
Multimodal Embeddings
-
-
General Purpose
-
API Services
-
Open Source
- Llama-Embed-Nemotron-8B
- stella-en-1.5B-v5
- gte-large-en-v1.5
- mxbai-embed-large-v1
- snowflake-arctic-embed-l
- bge-large-en-v1.5 - tested |
- gte-base-en-v1.5
- SFR-Embedding-2_R - BY-NC-4.0 | Strong retrieval, long context |
- bge-base-en-v1.5
- nomic-embed-text-v1.5
- e5-large-v2
- e5-base-v2
-
-
Horizon
-
Late Chunking
-
LLM-Based Embeddings
- Paper (ICLR 2025)
- Paper - NLP/llm2vec) |
-
Multimodal Embeddings
-
Unified Generation + Embedding
- Paper - 7B) |
-
-
Quick Picks
- text-embedding-3-large
- NV-Embed-v2 - BY-NC |
- nomic-embed-text-v2-moe
- multilingual-e5-large
- voyage-code-2 - built, 16k context |
-
Related Lists
-
Tutorials
- awesome-vector-databases
- awesome-rag - augmented generation
- awesome-semantic-search
- awesome-local-ai
-
-
Rerankers
-
Domain-Specific
- rerank-english-v3.0 - ready, easy to integrate |
- bge-reranker-v2-m3
- bge-reranker-large - focused, strong quality |
- ms-marco-MiniLM-L-12-v2
- jina-reranker-v2-base-multilingual
- mxbai-rerank-large-v1
-
-
Resources
-
Papers
- Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
- MTEB: Massive Text Embedding Benchmark
- Text and Code Embeddings by Contrastive Pre-Training
- Improving Text Embeddings with Large Language Models - based embedding training (E5-mistral)
- BGE M3-Embedding - lingual, multi-functionality, multi-granularity
- Matryoshka Representation Learning
- NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
- Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings - context embeddings
- Text Embeddings Reveal (Almost) As Much As Text
- BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation
-
Tutorials
-
-
Specialized
-
Code Embeddings
- StarEncoder - based, open source |
- codebert-base
-
Domain-Specific
-
Long-Context
-
Multilingual
-
-
Tools & Evaluation
Categories
Sub Categories
Keywords
embeddings
5
information-retrieval
5
llm
4
sentence-transformers
3
nlp
3
benchmark
3
sentence-embeddings
3
retrieval
3
dataset
2
vector-search
2
retrieval-augmented-generation
2
rag
2
sbert
2
semantic-search
2
huggingface
2
neural-search
1
reranking
1
multimodal
1
multilingual-nlp
1
mteb
1
low-resource-nlp
1
evaluation
1
clustering
1
bitext-mining
1
text-semantic-similarity
1
openai
1
text-embeddings
1
bert-embeddings
1
ml
1
ai
1
vector-search-engine
1
vector-database
1
similarity-search
1
search-engine
1
nearest-neighbor-search
1
embeddings-similarity
1
embedding-similarity
1
approximate-nearest-neighbor-search
1
multilingual
1
zero-shot-retrieval
1
retrieval-models
1
question-generation
1
pytorch
1
passage-retrieval
1
elasticsearch
1
dpr
1
deep-learning
1
colbert
1
bert
1
semantic-similarity
1