flashrag-dev 0.1.4.dev20250222__tar.gz → 0.1.4.dev20250224__tar.gz

{flashrag_dev-0.1.4.dev20250222 → flashrag_dev-0.1.4.dev20250224}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: flashrag_dev
-Version: 0.1.4.dev20250222
+Version: 0.1.4.dev20250224
 Summary: A library for efficient Retrieval-Augmented Generation research
 Home-page: https://github.com/RUC-NLPIR/FlashRAG
 Author: Jiajie Jin, Yutao Zhu, Chenghao Zhang, Xinyu Yang, Zhicheng Dou
@@ -90,11 +90,13 @@ FlashRAG is still under development and there are many issues and room for impro
 - [x] Support OpenAI models
 - [x] Provdide instructions for each component
 - [x] Integrate sentence Transformers
+- [x] Support multimodal RAG
 - [ ] Inlcude more RAG approaches
 - [ ] Add more evaluation metrics (e.g., Unieval, name-entity F1) and benchmarks (e.g., RGB benchmark)
 - [ ] Enhance code adaptability and readability
 
 ## :page_with_curl: Changelog
+[25/02/24] We have added support for **multimodal RAG**, including **MLLMs like Llava, Qwen, InternVL**, and various **multimodal retrievers with Clip architecture**. More information can be found in our new version of arxiv article. Try it🔥!
 
 [25/01/21] Our technical paper [FlashRAG: A Python Toolkit for Efficient RAG Research](https://arxiv.org/abs/2405.13576) is honored to have been accepted to the Resource Track of the 2025 **ACM Web Conference (WWW 2025)**. Please Check it out!
 

{flashrag_dev-0.1.4.dev20250222 → flashrag_dev-0.1.4.dev20250224}/README.md

@@ -73,11 +73,13 @@ FlashRAG is still under development and there are many issues and room for impro
 - [x] Support OpenAI models
 - [x] Provdide instructions for each component
 - [x] Integrate sentence Transformers
+- [x] Support multimodal RAG
 - [ ] Inlcude more RAG approaches
 - [ ] Add more evaluation metrics (e.g., Unieval, name-entity F1) and benchmarks (e.g., RGB benchmark)
 - [ ] Enhance code adaptability and readability
 
 ## :page_with_curl: Changelog
+[25/02/24] We have added support for **multimodal RAG**, including **MLLMs like Llava, Qwen, InternVL**, and various **multimodal retrievers with Clip architecture**. More information can be found in our new version of arxiv article. Try it🔥!
 
 [25/01/21] Our technical paper [FlashRAG: A Python Toolkit for Efficient RAG Research](https://arxiv.org/abs/2405.13576) is honored to have been accepted to the Resource Track of the 2025 **ACM Web Conference (WWW 2025)**. Please Check it out!
 

{flashrag_dev-0.1.4.dev20250222 → flashrag_dev-0.1.4.dev20250224}/flashrag/retriever/index_builder.py

@@ -210,6 +210,8 @@ class Index_Builder:
         retriever = bm25s.BM25(corpus=corpus, backend="numba")
         retriever.index(corpus_tokens)
         retriever.save(self.save_dir, corpus=None)
+        tokenizer.save_vocab(self.save_dir)
+        tokenizer.save_stopwords(self.save_dir)
 
         print("Finish!")
 

{flashrag_dev-0.1.4.dev20250222 → flashrag_dev-0.1.4.dev20250224}/flashrag/retriever/retriever.py

@@ -255,6 +255,8 @@ class BM25Retriever(BaseTextRetriever):
             else:
                 stemmer = Stemmer.Stemmer("english")
                 self.tokenizer = bm25s.tokenization.Tokenizer(stopwords='en', stemmer=stemmer)
+                self.tokenizer.load_stopwords(self.index_path)
+                self.tokenizer.load_vocab(self.index_path)
 
             self.searcher.corpus = self.corpus
             self.searcher.backend = "numba"

flashrag_dev-0.1.4.dev20250224/flashrag/version.py

@@ -0,0 +1 @@
+__version__ = "0.1.4dev20250224"

{flashrag_dev-0.1.4.dev20250222 → flashrag_dev-0.1.4.dev20250224}/flashrag_dev.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: flashrag-dev
-Version: 0.1.4.dev20250222
+Version: 0.1.4.dev20250224
 Summary: A library for efficient Retrieval-Augmented Generation research
 Home-page: https://github.com/RUC-NLPIR/FlashRAG
 Author: Jiajie Jin, Yutao Zhu, Chenghao Zhang, Xinyu Yang, Zhicheng Dou
@@ -90,11 +90,13 @@ FlashRAG is still under development and there are many issues and room for impro
 - [x] Support OpenAI models
 - [x] Provdide instructions for each component
 - [x] Integrate sentence Transformers
+- [x] Support multimodal RAG
 - [ ] Inlcude more RAG approaches
 - [ ] Add more evaluation metrics (e.g., Unieval, name-entity F1) and benchmarks (e.g., RGB benchmark)
 - [ ] Enhance code adaptability and readability
 
 ## :page_with_curl: Changelog
+[25/02/24] We have added support for **multimodal RAG**, including **MLLMs like Llava, Qwen, InternVL**, and various **multimodal retrievers with Clip architecture**. More information can be found in our new version of arxiv article. Try it🔥!
 
 [25/01/21] Our technical paper [FlashRAG: A Python Toolkit for Efficient RAG Research](https://arxiv.org/abs/2405.13576) is honored to have been accepted to the Resource Track of the 2025 **ACM Web Conference (WWW 2025)**. Please Check it out!
 

flashrag_dev-0.1.4.dev20250222/flashrag/version.py

@@ -1 +0,0 @@
-__version__ = "0.1.4dev20250222"