From 4b5e6e2d2ec1489d96541ee9d937afe4b944f7dc Mon Sep 17 00:00:00 2001 From: Sonam Pankaj Date: Fri, 10 Jan 2025 00:03:43 +0100 Subject: [PATCH 1/5] v0.5 release notes --- docs/blog/posts/Journey.md | 4 ++-- docs/blog/posts/v0.5.md | 20 ++++++++++++++++++++ 2 files changed, 22 insertions(+), 2 deletions(-) create mode 100644 docs/blog/posts/v0.5.md diff --git a/docs/blog/posts/Journey.md b/docs/blog/posts/Journey.md index 2af4b606..b9868d84 100644 --- a/docs/blog/posts/Journey.md +++ b/docs/blog/posts/Journey.md @@ -50,7 +50,7 @@ And thus, vector streaming was born. It's time to release 0.3 because we underwent major code refactoring. All the major functions are refactored, making calling models more intuitive and optimized. Check out our docs and usage. We also added audio modality and different types of ingestions. -We only supported dense, so we expanded the types of embedding we could support. We went for sparse and started supporting ColPali, Onnx, and Candle. +We only supported dense, so we expanded the types of embedding we could support. We went for sparse and started supporting ColPali, ColBert, ModernBert, Reranker, Jina V3. ## What We Got Right @@ -61,7 +61,7 @@ We also released benches comparing it with other inference and to our suprise it We presented Embedanything at many conferences, like Pydata Global, Elastic, voxel 51 meetups, AI builders, etc. Additionally, we forged collaborations with major brands like Weaviate and Elastic, a strategy we’re excited to continue expanding in 2025. -[Weaviate Collab](https://www.youtube.com/watch?v=OJRWPLQ44Dw) +[Elastic Collab](https://www.youtube.com/live/OzQopxkxHyY?si=shJ2hADyPPsYWmIF) ## What We Initially Got Wrong diff --git a/docs/blog/posts/v0.5.md b/docs/blog/posts/v0.5.md new file mode 100644 index 00000000..12b1af8b --- /dev/null +++ b/docs/blog/posts/v0.5.md @@ -0,0 +1,20 @@ +We are thrilled to share that EmbedAnything version 0.5 is out now and comprise of insane development like support for ModernBert and ReRanker models. Along with Ingestion pipeline support for DocX, and HTML let’s get in details. + +The best of all have been support for late-interaction model, both ColPali and ColBERT on onnx. + +1. ModernBert Support: Well it made quite a splash, and we were obliged to add it, in the fastest inference engine, embedanything. In addition to being faster and more accurate, ModernBERT also increases context length to 8k tokens (compared to just 512 for most encoders), and is the first encoder-only model that includes a large amount of code in its training data. +2. ColPali- Onnx :  Running the ColPali model directly on a local machine might not always be feasible. To address this, we developed a **quantized version of ColPali**. Find it on our hugging face, link [here](https://huggingface.co/starlight-ai/colpali-v1.2-merged-onnx). You could also run it both on Candle and on ONNX. +3. ColBERT: ColBERT is a *fast* and *accurate* retrieval model, enabling scalable BERT-based search over large text collections in tens of milliseconds. +4. ReRankers: EmbedAnything recently contributed for the support of reranking models to Candle so as to add it in our own library. It can support any kind of reranking models. Precision meets performance! Use reranking models to refine your retrieval results for even greater accuracy. +5. Jina V3: Also contributed to V3 models, for Jina can seamlessly integrate any V3 model. +6. 𝗗𝗢𝗖𝗫 𝗣𝗿𝗼𝗰𝗲𝘀𝘀𝗶𝗻𝗴 + + Effortlessly extract text from .docx files and convert it into embeddings. Simplify your document workflows like never before! + +7. 𝗛𝗧𝗠𝗟 𝗣𝗿𝗼𝗰𝗲𝘀𝘀𝗶𝗻𝗴: + Parsing and embedding HTML documents just got easier! + + ✅ Extract rich metadata with embeddings + ✅ Handle code blocks separately for better context + +Supercharge your documentation retrieval with these advanced capabilities. \ No newline at end of file From e1c6390b7eb27347e52abc329d84dbc44922fa65 Mon Sep 17 00:00:00 2001 From: Sonam Pankaj Date: Fri, 10 Jan 2025 00:10:38 +0100 Subject: [PATCH 2/5] v0.5 release notes. --- docs/blog/posts/v0.5.md | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/docs/blog/posts/v0.5.md b/docs/blog/posts/v0.5.md index 12b1af8b..dd86695a 100644 --- a/docs/blog/posts/v0.5.md +++ b/docs/blog/posts/v0.5.md @@ -1,3 +1,13 @@ +--- +draft: false +date: 2025-1-31 +authors: + - sonam + - akshay +slug: colpali-vision-rag +title: Optimize VLM Tokens with EmbedAnything x ColPali +--- + We are thrilled to share that EmbedAnything version 0.5 is out now and comprise of insane development like support for ModernBert and ReRanker models. Along with Ingestion pipeline support for DocX, and HTML let’s get in details. The best of all have been support for late-interaction model, both ColPali and ColBERT on onnx. From 51b685118fd2b980497609bd6b9f131dade45bc4 Mon Sep 17 00:00:00 2001 From: Sonam Pankaj Date: Fri, 10 Jan 2025 12:24:00 +0100 Subject: [PATCH 3/5] v0.5 updates --- README.md | 8 +++++--- docs/blog/posts/v0.5.md | 17 +++++++++-------- 2 files changed, 14 insertions(+), 11 deletions(-) diff --git a/README.md b/README.md index 0b5f66e0..82d3e695 100644 --- a/README.md +++ b/README.md @@ -21,7 +21,7 @@

- Inference, ingestion, and indexing – supercharged by Rust 🦀 + Inference, Ingestion, and Indexing – supercharged by Rust 🦀
Python docs »
@@ -73,9 +73,11 @@ EmbedAnything is a minimalist, highly performant, lightning-fast, lightweight, m - **Local Embedding** : Works with local embedding models like BERT and JINA - **ONNX Models**: Works with ONNX models for BERT and ColPali -- **ColPali** : Support for ColPali in GPU version +- **ColPali** : Support for ColPali in GPU version both on ONNX and Candle - **Splade** : Support for sparse embeddings for hybrid - **ReRankers** : Support for ReRanking Models for better RAG. +- **ColBERT** : Support for ColBert on ONNX +- **ModernBERT**: Increase your token length to 8K - **Cloud Embedding Models:**: Supports OpenAI and Cohere. - **MultiModality** : Works with text sources like PDFs, txt, md, Images JPG and Audio, .WAV - **Rust** : All the file processing is done in rust for speed and efficiency @@ -121,7 +123,7 @@ data = embed_anything.embed_file("file_address", embedder=model, config=config) | Bert | All Bert based models | | CLIP | openai/clip-* | | Whisper| [OpenAI Whisper models](https://huggingface.co/collections/openai/whisper-release-6501bba2cf999715fd953013)| -| ColPali | vidore/colpali-v1.2-merged | +| ColPali | starlight-ai/colpali-v1.2-merged-onnx| | Colbert | answerdotai/answerai-colbert-small-v1, jinaai/jina-colbert-v2 and more | | Splade | [Splade Models](https://huggingface.co/collections/naver/splade-667eb6df02c2f3b0c39bd248) and other Splade like models | | Reranker | [Jina Reranker Models](https://huggingface.co/jinaai/jina-reranker-v2-base-multilingual), Xenova/bge-reranker | diff --git a/docs/blog/posts/v0.5.md b/docs/blog/posts/v0.5.md index dd86695a..74fcf5d7 100644 --- a/docs/blog/posts/v0.5.md +++ b/docs/blog/posts/v0.5.md @@ -1,6 +1,6 @@ --- draft: false -date: 2025-1-31 +date: 2025-1-10 authors: - sonam - akshay @@ -12,16 +12,17 @@ We are thrilled to share that EmbedAnything version 0.5 is out now and comprise The best of all have been support for late-interaction model, both ColPali and ColBERT on onnx. -1. ModernBert Support: Well it made quite a splash, and we were obliged to add it, in the fastest inference engine, embedanything. In addition to being faster and more accurate, ModernBERT also increases context length to 8k tokens (compared to just 512 for most encoders), and is the first encoder-only model that includes a large amount of code in its training data. -2. ColPali- Onnx :  Running the ColPali model directly on a local machine might not always be feasible. To address this, we developed a **quantized version of ColPali**. Find it on our hugging face, link [here](https://huggingface.co/starlight-ai/colpali-v1.2-merged-onnx). You could also run it both on Candle and on ONNX. -3. ColBERT: ColBERT is a *fast* and *accurate* retrieval model, enabling scalable BERT-based search over large text collections in tens of milliseconds. -4. ReRankers: EmbedAnything recently contributed for the support of reranking models to Candle so as to add it in our own library. It can support any kind of reranking models. Precision meets performance! Use reranking models to refine your retrieval results for even greater accuracy. -5. Jina V3: Also contributed to V3 models, for Jina can seamlessly integrate any V3 model. -6. 𝗗𝗢𝗖𝗫 𝗣𝗿𝗼𝗰𝗲𝘀𝘀𝗶𝗻𝗴 +1. **ModernBert** Support: Well it made quite a splash, and we were obliged to add it, in the fastest inference engine, embedanything. In addition to being faster and more accurate, ModernBERT also increases context length to 8k tokens (compared to just 512 for most encoders), and is the first encoder-only model that includes a large amount of code in its training data. +2. **ColPali- Onnx** :  Running the ColPali model directly on a local machine might not always be feasible. To address this, we developed a **quantized version of ColPali**. Find it on our hugging face, link [here](https://huggingface.co/starlight-ai/colpali-v1.2-merged-onnx). You could also run it both on Candle and on ONNX. +3. **ColBERT**: ColBERT is a *fast* and *accurate* retrieval model, enabling scalable BERT-based search over large text collections in tens of milliseconds. +4. **ReRankers:** EmbedAnything recently contributed for the support of reranking models to Candle so as to add it in our own library. It can support any kind of reranking models. Precision meets performance! Use reranking models to refine your retrieval results for even greater accuracy. +5. **Jina V3:** Also contributed to V3 models, for Jina can seamlessly integrate any V3 model. +6. **𝗗𝗢𝗖𝗫 𝗣𝗿𝗼𝗰𝗲𝘀𝘀𝗶𝗻𝗴** Effortlessly extract text from .docx files and convert it into embeddings. Simplify your document workflows like never before! -7. 𝗛𝗧𝗠𝗟 𝗣𝗿𝗼𝗰𝗲𝘀𝘀𝗶𝗻𝗴: +7. **𝗛𝗧𝗠𝗟 𝗣𝗿𝗼𝗰𝗲𝘀𝘀𝗶𝗻𝗴:** + Parsing and embedding HTML documents just got easier! ✅ Extract rich metadata with embeddings From 6480f9a2c04cab0b7c63dd2125ba3ed59a5ad174 Mon Sep 17 00:00:00 2001 From: Sonam Pankaj Date: Fri, 10 Jan 2025 12:26:37 +0100 Subject: [PATCH 4/5] updates release notes --- docs/blog/posts/v0.5.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/blog/posts/v0.5.md b/docs/blog/posts/v0.5.md index 74fcf5d7..d9312e9d 100644 --- a/docs/blog/posts/v0.5.md +++ b/docs/blog/posts/v0.5.md @@ -4,8 +4,8 @@ date: 2025-1-10 authors: - sonam - akshay -slug: colpali-vision-rag -title: Optimize VLM Tokens with EmbedAnything x ColPali +slug: modernBERT +title: version 0.5 --- We are thrilled to share that EmbedAnything version 0.5 is out now and comprise of insane development like support for ModernBert and ReRanker models. Along with Ingestion pipeline support for DocX, and HTML let’s get in details. From 223e9b9860cf38ab10f7c26df84dce772968fc3a Mon Sep 17 00:00:00 2001 From: Sonam Pankaj Date: Fri, 10 Jan 2025 13:21:22 +0100 Subject: [PATCH 5/5] rectified --- docs/blog/posts/v0.5.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/blog/posts/v0.5.md b/docs/blog/posts/v0.5.md index d9312e9d..42239c49 100644 --- a/docs/blog/posts/v0.5.md +++ b/docs/blog/posts/v0.5.md @@ -1,6 +1,6 @@ --- draft: false -date: 2025-1-10 +date: 2025-01-01 authors: - sonam - akshay