Lightnews — Scholar-powered news

LlamaIndex @llamaindex.bsky.social · 14h

In this walkthrough, @cle-does-things.bsky.social shows how to spin up, connect, and scale your services with minimal overhead.

🎥 Watch the demo: youtu.be/gPR0pMtY--c
👩‍💻 Try it yourself: github.com/AstraBert/w...
📚 Learn more: developers.llamaindex.ai/python/work...

Introduction

developers.llamaindex.ai

1 2

LlamaIndex @llamaindex.bsky.social · 14h

What if you could orchestrate your entire microservices setup using LlamaIndex Workflows?

That’s the idea we explored, and the result is a working demo that brings together @docker.com, Apache Kafka and Workflows to manage a small scale e-commerce system.

1 1 2

LlamaIndex @llamaindex.bsky.social · 1d

We’re bringing AI agents to the insurance frontier at #ITCVegas2025 🦙
See how LlamaIndex is helping insurers streamline claims, underwriting & CX.

📅 Pre-book a meeting → get exclusive LlamaIndex swag 👇
🔗 landing.llamaindex.ai/itcvegas2025

#AIinInsurance #InsurTech #LlamaIndex

LlamaIndex @llamaindex.bsky.social · 4d

Learn how to classify contract types: developers.llamaindex.ai/python/clou...

Classify Contract Types

developers.llamaindex.ai

LlamaIndex @llamaindex.bsky.social · 4d

In this example, we show you how to distinguish between affiliate agreements and co-branding contracts. The system doesn't just tell you "this is an affiliate agreement" - it explains exactly why, citing specific document language and structural elements.

1

LlamaIndex @llamaindex.bsky.social · 4d

📄 Define custom classification rules with simple descriptions instead of complex ML models
🤖 Get both classification results AND detailed reasoning explaining why each document was categorized
🎯 Works great for legal documents, contracts, and any structured document types

1

LlamaIndex @llamaindex.bsky.social · 4d

Classify documents automatically with LlamaClassify - no more manual sorting through contracts and legal documents.

Our new classification service lets you build intelligent document sorting systems that understand content and provide reasoning for their decisions:

1 1

LlamaIndex @llamaindex.bsky.social · 5d

We love seeing efficient models like this that make powerful embeddings accessible everywhere, especially for edge deployments where every MB counts.

See the full technical deep-dive and integration examples: huggingface.co/blog/embedd...

Welcome EmbeddingGemma, Google's new efficient embedding model

huggingface.co

LlamaIndex @llamaindex.bsky.social · 5d

The model achieves top rankings on the Massive Text Embedding Benchmark while being small enough for mobile devices. Plus, it's easily fine-tunable - the blog shows how fine-tuning on medical data created a model that outperforms much larger alternatives.

1

LlamaIndex @llamaindex.bsky.social · 5d

EmbeddingGemma, a compact 308M parameter multilingual embedding model, perfect for on-device RAG applications - and we've made it super easy to integrate with LlamaIndex!

🛠️ Ready-to-use integration with LlamaIndex's HuggingFaceEmbedding class - just specify the query and document prompts

1 1

LlamaIndex @llamaindex.bsky.social · 6d

⚙️ Extraction - Using LLMs to pull specific fields and entities with schema validation. Ideal for extracting specific info for downstream tasks.

Read the full technical guide 👉www.llamaindex.ai/blog/parse-...

LlamaIndex @llamaindex.bsky.social · 6d

🔍 Parsing - Converting unstructured documents into structured markdown while preserving layout, tables, and formatting. Perfect for applications where you need full document context.

1

LlamaIndex @llamaindex.bsky.social · 6d

📄 Parse vs. Extract: Two Fundamental Approaches to Document Processing

Building document agents? Knowing when to parse versus when to extract is fundamental to getting your architecture right.

In this deep dive, @tuana.dev breaks down: