Search

More Filters

Show More
Add Listing
Go Back

LlamaIndex Agent

0
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

This repository implements an Llama Index based Agentic-RAG system designed for PDF question-answering. It demonstrates an intelligent agent that decides between multiple retrieval pipelines to handle different types of user queries, specifically a summarization query engine and a vector query engine. The project includes instructional notebooks that introduce LlamaIndex concepts, step-by-step development of an Agentic-RAG system, and a customization notebook that shows how to perform PDF Q/A using the Phi3 3.8B model. Support code is organized into utils.py and a Gradio application in app.py for a runnable demo. The README lists technologies used such as Gradio for the app, nomic-embed-text for embeddings, and Ollama as a local LLM backend. A separate repository is noted for a Dockerized deployment. The materials and scripts target a Linux environment with guidance for installing dependencies and running the demo.

Links

Stars
13
App URL
https://github.com/swastikmaiti/LlamaIndex-Agent
Github Repository
https://github.com/swastikmaiti/LlamaIndex-Agent/blob/main/README.md

Categorization

App Details

Features
The repository provides a compact set of features to build and run an Agentic-RAG PDF Q/A system. It exposes two specialized pipelines: a summarization pipeline and a question-answering pipeline, and an agent that selects which pipeline(s) to invoke based on the query. It is built on LlamaIndex for retrieval-augmented generation workflows and uses Phi3 3.8B as the LLM with nomic-embed-text for embeddings. A Gradio app offers a simple interface for interaction. Development artifacts include multiple Jupyter notebooks that explain concepts and provide code, a utilities module consolidating helper functions, and an app.py entrypoint. The README documents make targets for installing dependencies, downloading and starting Ollama, and pulling models for local use. A Docker implementation is referenced for containerized deployment.
Use Cases
This project helps practitioners and learners build a more flexible RAG solution by replacing a single end-to-end pipeline with an agent that chooses specialized pipelines based on query intent, improving relevance for different question types. It is practical for extracting answers from PDF documents by combining retrieval, summarization, and vector search approaches. The included notebooks serve as tutorials to teach LlamaIndex and Agentic-RAG development, while utils.py and app.py provide reusable code and a ready-to-run Gradio demo for experimentation. Local deployment guidance using Ollama and make targets to fetch models reduce external dependencies for offline testing. The referenced Docker repository supports packaging and deployment. Hardware and environment notes specify Linux and modest RAM requirements to help users plan resources.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1230)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (766)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

yutu

0 (0 review)
listing image

cyber-doctor

0 (0 review)
listing image

LLM-Powered-RAG-System

0 (0 review)
listing image

vibevideo-mcp

0 (0 review)
listing image

xpert

0 (0 review)

Featured Listings

Tags

Please fill the required fields*