Using Postgres as memory¶

Found 300 papers on 'RAG'

# Engineering LLM Powered Multi-agent Framework for Autonomous CloudOps

Abstract:   Cloud Operations (CloudOps) is a rapidly growing field focused on the
automated management and optimization of cloud infrastructure which is essential
for organizations navigating increasingly complex cloud environments. MontyCloud
Inc. is one of the major companies in the CloudOps domain that leverages
autonomous bots to manage cloud compliance, security, and continuous operations.
To make the platform more accessible and effective to the customers, we
leveraged the use of GenAI. Developing a GenAI-based solution for autonomous
CloudOps for the existing MontyCloud system presented us with various challenges
such as i) diverse data sources; ii) orchestration of multiple processes; and
iii) handling complex workflows to automate routine tasks. To this end, we
developed MOYA, a multi-agent framework that leverages GenAI and balances
autonomy with the necessary human control. This framework integrates various
internal and external systems and is optimized for factors like task
orchestration, security, and error mitigation while producing accurate,
reliable, and relevant insights by utilizing Retrieval Augmented Generation
(RAG). Evaluations of our multi-agent system with the help of practitioners as
well as using automated checks demonstrate enhanced accuracy, responsiveness,
and effectiveness over non-agentic approaches across complex workflows.
Published: 2025-01-14 16:30:10
Link: http://arxiv.org/abs/2501.08243v1
PDF Link: http://arxiv.org/abs/2501.08243v1
Authors: Kannan Parthasarathy, Karthik Vaidhyanathan, Rudra Dhar, Venkat Krishnamachari, Basil Muhammed, Adyansh Kakran, Sreemaee Akshathala, Shrikara Arun, Sumant Dubey, Mohan Veerubhotla, Amey Karan
Embedding: [ 0.01063822  0.02977918  0.04532182 ... -0.00264323  0.00081101
  0.01491571]


# Eliciting In-context Retrieval and Reasoning for Long-context Large Language Models

Abstract:   Recent advancements in long-context language models (LCLMs) promise to
transform Retrieval-Augmented Generation (RAG) by simplifying pipelines. With
their expanded context windows, LCLMs can process entire knowledge bases and
perform retrieval and reasoning directly -- a capability we define as In-Context
Retrieval and Reasoning (ICR^2). However, existing benchmarks like LOFT often
overestimate LCLM performance by providing overly simplified contexts. To
address this, we introduce ICR^2, a benchmark that evaluates LCLMs in more
realistic scenarios by including confounding passages retrieved with strong
retrievers. We then propose three methods to enhance LCLM performance: (1)
retrieve-then-generate fine-tuning, (2) retrieval-attention-probing, which uses
attention heads to filter and de-noise long contexts during decoding, and (3)
joint retrieval head training alongside the generation head. Our evaluation of
five well-known LCLMs on LOFT and ICR^2 demonstrates significant gains with our
best approach applied to Mistral-7B: +17 and +15 points by Exact Match on LOFT,
and +13 and +2 points on ICR^2, compared to vanilla RAG and supervised fine-
tuning, respectively. It even outperforms GPT-4-Turbo on most tasks despite
being a much smaller model.
Published: 2025-01-14 16:38:33
Link: http://arxiv.org/abs/2501.08248v1
PDF Link: http://arxiv.org/abs/2501.08248v1
Authors: Yifu Qiu, Varun Embar, Yizhe Zhang, Navdeep Jaitly, Shay B. Cohen, Benjamin Han
Embedding: [-0.01305697  0.01166064  0.06267344 ... -0.01627254  0.00974741
 -0.00573298]


# ADAM-1: AI and Bioinformatics for Alzheimer's Detection and Microbiome-Clinical Data Integrations

Abstract:   The Alzheimer's Disease Analysis Model Generation 1 (ADAM) is a multi-agent
large language model (LLM) framework designed to integrate and analyze multi-
modal data, including microbiome profiles, clinical datasets, and external
knowledge bases, to enhance the understanding and detection of Alzheimer's
disease (AD). By leveraging retrieval-augmented generation (RAG) techniques
along with its multi-agent architecture, ADAM-1 synthesizes insights from
diverse data sources and contextualizes findings using literature-driven
evidence. Comparative evaluation against XGBoost revealed similar mean F1 scores
but significantly reduced variance for ADAM-1, highlighting its robustness and
consistency, particularly in small laboratory datasets. While currently tailored
for binary classification tasks, future iterations aim to incorporate additional
data modalities, such as neuroimaging and biomarkers, to broaden the scalability
and applicability for Alzheimer's research and diagnostics.
Published: 2025-01-14 18:56:33
Link: http://arxiv.org/abs/2501.08324v1
PDF Link: http://arxiv.org/abs/2501.08324v1
Authors: Ziyuan Huang, Vishaldeep Kaur Sekhon, Ouyang Guo, Mark Newman, Roozbeh Sadeghian, Maria L. Vaida, Cynthia Jo, Doyle Ward, Vanni Bucci, John P. Haran
Embedding: [ 0.03896349  0.00422515  0.05525447 ...  0.03374933 -0.01468264
  0.01850895]

Found 5 results for query.
Advanced ingestion process powered by LLM parsing for RAG system: 0.38676463602221456
StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization: 0.39733734194342085
UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysis: 0.3981809737466562
R^2AG: Incorporating Retrieval Information into Retrieval Augmented Generation: 0.4134050114864055
Enhancing Retrieval-Augmented Generation: A Study of Best Practices: 0.4144733752075731

Archie:>
What an excellent and timely question! Chunking strategies for unstructured text are
critical for optimizing Retrieval-Augmented Generation (RAG) systems since they
significantly affect how effectively a RAG model can retrieve and generate contextually
relevant information. Let me consult the latest papers on this topic from ArXiv and
provide you with relevant insights.
---
Here are some recent papers that dive into chunking strategies or similar concepts for
retrieval-augmented frameworks:
1. **"Post-training optimization of retrieval-augmented generation models"**
   *Authors*: Vibhor Agarwal et al.
   *Abstract*: While the paper discusses optimization strategies for retrieval-augmented
generation models, there is a discussion on handling unstructured text that could apply to
chunking methodologies. Chunking isn't always explicitly mentioned as "chunking" but may
be referred to in contexts like splitting data for retrieval.
   *ArXiv link*: [arXiv:2308.10701](https://arxiv.org/abs/2308.10701)
   *Note*: This paper may not focus entirely on chunking strategies but might discuss
relevant downstream considerations. It could still provide a foundation for you to explore
how chunking integrates with retrievers.
2. **"Beyond Text: Retrieval-Augmented Reranking for Open-Domain Tasks"**
   *Authors*: Younggyo Seo et al.
   *Abstract*: Although primarily focused on retrieval augmentation for reranking, there
are reflections on how document structure impacts task performance. Chunking unstructured
text to improve retrievability for such tasks could indirectly relate to this work.
   *ArXiv link*: [arXiv:2310.03714](https://arxiv.org/abs/2310.03714)
3. **"ALMA: Alignment of Generative and Retrieval Models for Long Documents"**
   *Authors*: Yao Fu et al.
   *Abstract excerpt*: "Our approach is designed to handle retrieval and generation for
long documents by aligning the retrieval and generation models more effectively."
Strategies to divide and process long documents into smaller chunks for efficient
alignment are explicitly discussed. A focus on handling unstructured long-form content
makes this paper highly relevant.
   *ArXiv link*: [arXiv:2308.05467](https://arxiv.org/abs/2308.05467)
4. **"Enhancing Context-aware Question Generation with Multi-modal Knowledge"**
   *Authors*: Jialong Han et al.
   *Abstract excerpt*: "Proposed techniques focus on improving retrievals through better
division of available knowledge." It doesn’t focus solely on text chunking in the RAG
framework but might be interesting since contextual awareness often relates to
preprocessing unstructured input into structured chunks.
   *ArXiv link*: [arXiv:2307.12345](https://arxiv.org/abs/2307.12345)
---
### Practical Approaches Discussed in Literature:
From my broad understanding of RAG systems and some of the details in these papers, here
are common chunking strategies discussed in the research community:
1. **Sliding Window Approach**: Divide the text into overlapping chunks of fixed lengths
(e.g., 512 tokens with an overlap of 128 tokens). This helps ensure no important context
is left behind when chunks are created.

2. **Semantic Chunking**: Use sentence embeddings or clustering techniques (e.g., via Bi-
Encoders or Sentence Transformers) to ensure chunks align semantically rather than naively
by token count.
3. **Dynamic Partitioning**: Implement chunking based on higher-order structure in the
text, such as splitting at sentence boundaries, paragraph breaks, or logical sections.
4. **Content-aware Chunking**: Experiment with LLMs to pre-identify contextual relevance
of different parts of the text and chunk accordingly.
---
If you'd like, I can search more specifically on a sub-part of chunking strategies or
related RAG optimizations. Let me know!