Academia Analyzer: Multi-Agent RAG System for Research Synthesis
1. Introduction and Project Purpose (What is this about?)
The volume of academic literature is growing exponentially, making it difficult for researchers to stay current. The Academia Analyzer Agent solves this problem by providing an automated, multi-agent system that ingests raw research documents (PDFs/Text) and synthesizes them into structured, high-value executive summaries.
This project serves as the Module 2 MVP deliverable, demonstrating mastery over Multi-Agent Orchestration and Tool Integration.
Core Objectives:
- Automated Synthesis: Transforms dense academic text into clear Hypotheses, Methodologies, and Findings.
- Grounded Generation: Uses Retrieval-Augmented Generation (RAG) to ensure every summary is backed by the actual content of the paper, minimizing hallucinations.
- Orchestration: Utilizes LangGraph to coordinate file ingestion, data extraction, and final synthesis.
2. System Architecture: LangGraph Orchestration (Why does it matter?)
The system utilizes a sequential pipeline where three specialized agents collaborate to process the document.
| Agent | Role & Responsibility | Key Tool Integration |
|---|---|---|
| 1. DocumentIngestorAgent | Ingestion & Indexing. Reads local PDF/Text files, chunks the content, and builds the vector search index. | PDF Reader Tool (pypdf, TextLoader) & RAG Retriever (FAISS). |
| 2. ThesisExtractorAgent | Data Extraction. Identifies the paper's core hypothesis and technical keywords using NLP. | Keyword Extractor Tool (nltk). |
| 3. InsightSynthesizerAgent | Final Synthesis. Generates the Executive Summary and Key Findings using the RAG context. | LLM API (OpenRouter) & Pydantic Parser (Structured Output). |
Flow Narrative
- Ingest: The user uploads a file via Streamlit. Agent 1 chunks the text and creates a FAISS index.
- Extract: Agent 2 scans the raw text to extract frequency-based keywords and topic focus areas.
- Synthesize: Agent 3 combines the RAG context and the extracted keywords to generate a structured
InsightSummaryJSON object.
3. Technical Credibility and Validation (Can I trust it?)
To ensure high technical quality, the system employs rigorous methodology for document processing and output generation.
A. RAG Configuration (Verifiable Evidence)
The RAG index is configured to handle complex academic language:
| Setting | Value | Rationale |
|---|---|---|
| Text Chunk Size | 1500 tokens | Larger chunk size chosen to capture full academic arguments and methodology sections without breaking context. |
| Text Chunk Overlap | 250 tokens | Ensures continuity between pages and paragraphs. |
| Embedding Model | HuggingFaceEmbeddings(all-MiniLM-L6-v2) | Fast, efficient local embedding model suitable for scientific text. |
B. Code Evidence
The complete, working code is available in the linked GitHub repository.
Code Repository: https://github.com/maddiravi/academia-analyzer-agent
4. Usability and Operational Features (Can I use it?)
A. User Interface
The system is delivered via a Streamlit web application (app.py), allowing users to easily upload research papers via a drag-and-drop interface and view the analysis in real-time.
B. Quick-Start Guide
- Clone the Repository:
git clone [https://github.com/maddiravi/academia-analyzer-agent](https://github.com/maddiravi/academia-analyzer-agent) cd academia-analyzer-agent pip install -r requirements.txt - Configuration: Create a
.envfile with yourOPENROUTER_API_KEY. - Launch:
python -m streamlit run app.py
C. Successful Execution Proof
D. Future Directions
Future work will focus on:
- Multi-Paper Comparison: Allowing users to upload multiple PDFs to compare methodologies.
- Citation Extraction: Adding a specific tool to extract and format bibliography references.
BY RAVI KANTH MADDI