Linghua Jin articles - 35 total
Best realtime context for coding agents https://cocoindex.io/blogs/index-code-base-for-rag/
A post by Linghua Jin
![[Boost]](https://media2.dev.to/dynamic/image/width=1000,height=500,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fdnxj5wrwpu2tygmcqg8p.png)
[Boost]
Multimodal Face Recognition Pipeline with CocoIndex: Real-Time...
Multimodal Face Recognition Pipeline with CocoIndex: Real-Time Image and Vector Search
CocoIndex supports multi-modal processing natively - it could process both text and image with the...
Context + Reliable LLM e.g., Claude code will be the future of coding agents. Checkout cocoindex that brings fresh context for reliable coding agents! https://github.com/cocoindex-io/cocoindex
Build Real-Time Codebase Indexing for AI...
Build Real-Time Codebase Indexing for AI Coding agents
In this blog, we will show you how to index a codebase for RAG with CocoIndex. CocoIndex provides...
Do you need academic research insights to back up your AI Agents?
Beyond Embeddings: Building...
Beyond Embeddings: Building Metadata-Rich Indexes from Academic PDFs
In this blog we will walk through a comprehensive example of indexing research papers with extracting...
https://github.com/cocoindex-io/cocoindex Super simple ETL to get data ready for AI agents. Write in Python, with Rust 🦀 performance . Appreciate a github star!
A post by Linghua Jin
![[Boost]](https://media2.dev.to/dynamic/image/width=1000,height=500,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fihg4aau3l9ifqyrvzbwv.png)
[Boost]
Build Real-Time Knowledge Graphs from...
Build Real-Time Knowledge Graphs from Documents Using CocoIndex + Kuzu (with LLMs & Live Updates)
A blazing-fast, end-to-end open source pipeline for turning documents into queryable knowledge graphs...
Stream from S3 in Real-Time: CocoIndex Brings True Incremental Processing to the Cloud
🚀 CocoIndex https://github.com/cocoindex-io/cocoindex Now Supports Amazon S3 for Native, Real-Time...
How to build image search with semantic understanding
In this blog, we will build live image search and query it with natural language. For example, you...
In this walkthrough, we’ll show how to build a semantic image search engine powered by multimodal AI – searchable with natural language in real time, with data insight to understand what’s going on step by step.
How to build index with text embeddings ...
How to build index with text embeddings
In this blog, we will build index with text embeddings and query it with natural language. We try to...
🎉 CocoIndex hits 1,000 stars – powering real-time data for AI
We’ve been building CocoIndex, an ultra performant real-time data transformation framework for AI,...
product recommendation with LLM and knowledge graph
Real-Time Knowledge Graph for Product...
Real-Time Knowledge Graph for Product recommendation with LLM taxonomy extraction
In this blog, we will build a knowledge graph for product recommendations using taxonomy and...
![[Boost]](https://media2.dev.to/dynamic/image/width=1000,height=500,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2F0uqp47mc2gvsk5obn4gl.png)
[Boost]
Build Real-Time Knowledge Graph For Documents with LLM LJ...
Build Real-Time Knowledge Graph For Documents with LLM
CocoIndex makes it easy to build and maintain knowledge graphs with continuous source updates. In...
LLM to extract and auto generate knowledge graph - step by step, in ~100 lines of python
In this blog, we will use CocoIndex to extract relationships/ontologies using LLM and build a...
CocoIndex Changelog 2025-04-05
In the past 2 weeks, we added incremental processing with live update mode, evaluation utilities,...
Continuous update ETL on source updates, automatically
Today, we are excited to announce the support of continuous updates for long-running pipelines in...
How to do incremental processing for ETL - by examples
We could take a look at a few examples to understand what CocoIndex handles behind the scene for...
Incremental processing to keep low latency sync for your ETL
Incremental processing is one of the core values provided by CocoIndex. In CocoIndex, users declare...
Implement Contextual Retrieval for RAG
Anthropic has published a great article about Contextual Retrieval that suggests the combination of...
Efficiently process large files for RAG
When building data indexing pipelines, handling large files efficiently presents unique challenges....
Automate structured data extraction from PDF / Word by OpenAI and CocoIndex
In this blog, we will show you how to use OpenAI API to extract structured data from patient intake...
Is RAG Still Needed? Retrieval Beyond Vector Embeddings
The rise of Large Language Models (LLMs) has sparked an ongoing debate: do we still need...
Step by Step guide to ingest Google Drive for RAG
Overview In this blog, we will show you how to use CocoIndex to build text embeddings from...