This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
\nThe following papers were recommended by the Semantic Scholar API
\n- \n
- BERGEN: A Benchmarking Library for Retrieval-Augmented Generation (2024) \n
- Searching for Best Practices in Retrieval-Augmented Generation (2024) \n
- SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs (2024) \n
- RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs (2024) \n
- RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems (2024) \n
Please give a thumbs up to this comment if you found it helpful!
\nIf you want recommendations for any Paper on Hugging Face checkout this Space
\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend
This is fantastic work—really impressive!
\nI’m part of the team at TeraVera, and we’ve recently launched a Secure AI solution that supports document upload and instant Q&A using RAG under the hood.
\nIf you’d like to check it out or share feedback, we’d love to hear your thoughts.
\nPlease check out: https://www.teravera.com/
\nAlso, to request the API access and documentation, please sign up here: www.teravera.com/api-access-form/
\n","updatedAt":"2025-07-03T13:11:49.786Z","author":{"_id":"685d307973fb7cd23dbf137d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/wPicwv8_TH94gljbA-rg5.png","fullname":"Sohan Varghese","name":"SohanVichat","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":15,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8528696298599243},"editors":["SohanVichat"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/wPicwv8_TH94gljbA-rg5.png"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2408.02545","authors":[{"_id":"66b1dda98b1fc211c927e850","user":{"_id":"62d93cd728f9c86a4031562e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62d93cd728f9c86a4031562e/ix_LD-wjW8vCltosCVUmV.jpeg","isPro":false,"fullname":"Daniel Fleischer","user":"danf","type":"user"},"name":"Daniel Fleischer","status":"claimed_verified","statusLastChangedAt":"2024-08-06T08:53:56.279Z","hidden":false},{"_id":"66b1dda98b1fc211c927e851","user":{"_id":"63e0c8875c6964861ebb0c49","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63e0c8875c6964861ebb0c49/yzkhPSxgXtJCM62iMBOOK.jpeg","isPro":false,"fullname":"Moshe Berchansky","user":"mber","type":"user"},"name":"Moshe Berchansky","status":"admin_assigned","statusLastChangedAt":"2024-08-06T13:17:11.172Z","hidden":false},{"_id":"66b1dda98b1fc211c927e852","user":{"_id":"6013c64031d84a3bb7650038","avatarUrl":"/avatars/e05ca715004b39e79472399f75010bda.svg","isPro":false,"fullname":"Moshe Wasserblat","user":"moshew","type":"user"},"name":"Moshe Wasserblat","status":"admin_assigned","statusLastChangedAt":"2024-08-06T13:17:18.216Z","hidden":false},{"_id":"66b1dda98b1fc211c927e853","user":{"_id":"605714b1861b9d53d9c4b8db","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/605714b1861b9d53d9c4b8db/5kpnfrvnIKRBjmQsMJKk-.jpeg","isPro":false,"fullname":"Peter Izsak","user":"peterizsak","type":"user"},"name":"Peter Izsak","status":"admin_assigned","statusLastChangedAt":"2024-08-06T13:17:24.275Z","hidden":false}],"publishedAt":"2024-08-05T15:16:24.000Z","submittedOnDailyAt":"2024-08-06T08:28:52.225Z","title":"RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented\n Generation","submittedOnDailyBy":{"_id":"60107b385ac3e86b3ea4fc34","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1627505688463-60107b385ac3e86b3ea4fc34.jpeg","isPro":true,"fullname":"Daniel van Strien","user":"davanstrien","type":"user"},"summary":"Implementing Retrieval-Augmented Generation (RAG) systems is inherently\ncomplex, requiring deep understanding of data, use cases, and intricate design\ndecisions. Additionally, evaluating these systems presents significant\nchallenges, necessitating assessment of both retrieval accuracy and generative\nquality through a multi-faceted approach. We introduce RAG Foundry, an\nopen-source framework for augmenting large language models for RAG use cases.\nRAG Foundry integrates data creation, training, inference and evaluation into a\nsingle workflow, facilitating the creation of data-augmented datasets for\ntraining and evaluating large language models in RAG settings. This integration\nenables rapid prototyping and experimentation with various RAG techniques,\nallowing users to easily generate datasets and train RAG models using internal\nor specialized knowledge sources. We demonstrate the framework effectiveness by\naugmenting and fine-tuning Llama-3 and Phi-3 models with diverse RAG\nconfigurations, showcasing consistent improvements across three\nknowledge-intensive datasets. Code is released as open-source in\nhttps://github.com/IntelLabs/RAGFoundry.","upvotes":40,"discussionId":"66b1ddaa8b1fc211c927e88c","githubRepo":"https://github.com/intellabs/ragfoundry","githubRepoAddedBy":"auto","ai_summary":"RAG Foundry is an open-source framework integrating data creation, training, inference, and evaluation to facilitate the augmentation of large language models for RAG use cases, demonstrating improved performance across diverse datasets.","ai_keywords":["Retrieval-Augmented Generation (RAG)","data creation","training","inference","evaluation","RAG Foundry","data-augmented datasets","Llama-3","Phi-3","knowledge-intensive datasets"],"githubStars":767},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"60107b385ac3e86b3ea4fc34","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1627505688463-60107b385ac3e86b3ea4fc34.jpeg","isPro":true,"fullname":"Daniel van Strien","user":"davanstrien","type":"user"},{"_id":"62d93cd728f9c86a4031562e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62d93cd728f9c86a4031562e/ix_LD-wjW8vCltosCVUmV.jpeg","isPro":false,"fullname":"Daniel Fleischer","user":"danf","type":"user"},{"_id":"6270324ebecab9e2dcf245de","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6270324ebecab9e2dcf245de/cMbtWSasyNlYc9hvsEEzt.jpeg","isPro":false,"fullname":"Kye Gomez","user":"kye","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"605714b1861b9d53d9c4b8db","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/605714b1861b9d53d9c4b8db/5kpnfrvnIKRBjmQsMJKk-.jpeg","isPro":false,"fullname":"Peter Izsak","user":"peterizsak","type":"user"},{"_id":"606d6349f1259f30578520ad","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/606d6349f1259f30578520ad/72_XrFfgQ6p9tgJj5Bc5U.png","isPro":false,"fullname":"Jonathan Mamou","user":"jmamou","type":"user"},{"_id":"6055ae5d25cd24537dd59dc5","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6055ae5d25cd24537dd59dc5/eswozkCirLrnyhufN8_-f.jpeg","isPro":false,"fullname":"Daniel Korat","user":"danielkorat","type":"user"},{"_id":"5f8907c65d083370c711f284","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1616423186722-5f8907c65d083370c711f284.jpeg","isPro":false,"fullname":"Ofir Zafrir","user":"ofirzaf","type":"user"},{"_id":"63e0c8875c6964861ebb0c49","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63e0c8875c6964861ebb0c49/yzkhPSxgXtJCM62iMBOOK.jpeg","isPro":false,"fullname":"Moshe Berchansky","user":"mber","type":"user"},{"_id":"63869d1e81fe8c678a3a9422","avatarUrl":"/avatars/3bb8728057fa2ba0e24f5ceb1600068d.svg","isPro":true,"fullname":"Zach Mustafa","user":"Zmu","type":"user"},{"_id":"61e7c06064d3c6c929057bee","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/61e7c06064d3c6c929057bee/QxULx1EA1bgmjXxupQX4B.jpeg","isPro":false,"fullname":"蓋瑞王","user":"gary109","type":"user"},{"_id":"606c344fa0e75b0dd0135633","avatarUrl":"/avatars/bd13e3c006573db51fcdf74b016d1aa3.svg","isPro":false,"fullname":"Shira Guskin","user":"sguskin","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":3}">RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generation
Abstract
RAG Foundry is an open-source framework integrating data creation, training, inference, and evaluation to facilitate the augmentation of large language models for RAG use cases, demonstrating improved performance across diverse datasets.
Implementing Retrieval-Augmented Generation (RAG) systems is inherently complex, requiring deep understanding of data, use cases, and intricate design decisions. Additionally, evaluating these systems presents significant challenges, necessitating assessment of both retrieval accuracy and generative quality through a multi-faceted approach. We introduce RAG Foundry, an open-source framework for augmenting large language models for RAG use cases. RAG Foundry integrates data creation, training, inference and evaluation into a single workflow, facilitating the creation of data-augmented datasets for training and evaluating large language models in RAG settings. This integration enables rapid prototyping and experimentation with various RAG techniques, allowing users to easily generate datasets and train RAG models using internal or specialized knowledge sources. We demonstrate the framework effectiveness by augmenting and fine-tuning Llama-3 and Phi-3 models with diverse RAG configurations, showcasing consistent improvements across three knowledge-intensive datasets. Code is released as open-source in https://github.com/IntelLabs/RAGFoundry.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- BERGEN: A Benchmarking Library for Retrieval-Augmented Generation (2024)
- Searching for Best Practices in Retrieval-Augmented Generation (2024)
- SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs (2024)
- RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs (2024)
- RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems (2024)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
This is fantastic work—really impressive!
I’m part of the team at TeraVera, and we’ve recently launched a Secure AI solution that supports document upload and instant Q&A using RAG under the hood.
If you’d like to check it out or share feedback, we’d love to hear your thoughts.
Please check out: https://www.teravera.com/
Also, to request the API access and documentation, please sign up here: www.teravera.com/api-access-form/
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper