Linghua Jin

building CocoIndex - data infra for AI, ex-google tech lead ⭐https://github.com/cocoindex-io/cocoindex

San Francisco Joined on Feb 28, 2025 https://github.com/cocoindex-io/cocoindex

Linghua Jin

Dec 7

AI Agents Are Goldfish: Why Your LLM Forgets Everything (And How to Fix It)

#ai #machinelearning #rust #opensource

3 min read

Want to connect with Linghua Jin?

Create an account to connect with Linghua Jin. You can also sign in below to proceed if you already have an account.

Create Account

Already have an account? Sign in

Linghua Jin

Dec 6

I built an open source Rust engine that just hit Trending — here's why agents can't live without fresh data

#rust #ai #opensource #agents

4 min read

Linghua Jin

Dec 5

I built a real-time Hacker News trend tracker in one weekend (step-by-step guide)

#tutorial #webdev #python #api

3 min read

Linghua Jin

Dec 4

Automate Python Manual Extraction: Build End-to-End PDF -> LLM -> SQL Flows with CocoIndex, Ollama, and Postgres

#python #llm #dataengineering #etl

3 min read

Linghua Jin

Dec 4

Turn Your PDF Library into a Searchable Research Database (in ~100 Lines with CocoIndex)

#python #ai #rag #datascience

4 min read

Linghua Jin for CocoIndex

Dec 2

How I Built a Semantic Search Engine with CocoIndex

#opensource #python #tutorial #ai

3 min read

Linghua Jin

Dec 2

Why AI ETL Needs Different Primitives: Lessons from Building CocoIndex in Rust 🦀

#rust #ai #etl #datascience

4 min read

Linghua Jin

Dec 1

Why Your Image Search Sucks (And How ColPali + Multi-Vector Indexing Fixes It)

#ai #machinelearning #python

4 min read

Linghua Jin

Nov 30

Stop Grepping Your Monorepo: Real-Time Codebase Indexing with CocoIndex

#ai #devtools #rag #postgres

5 min read

Linghua Jin

Nov 27

I Built a Real-Time HackerNews Search Engine with 50 Lines of Python (No Airflow, No Kafka)

#python #tutorial #api #database

3 min read

Linghua Jin for CocoIndex

Jul 29

Multimodal Face Recognition Pipeline with CocoIndex: Real-Time Image and Vector Search

#showdev #programming #python #ai

5 min read

Linghua Jin for CocoIndex

Jul 13

Build Real-Time Codebase Indexing for AI Coding agents

#showdev #programming #ai #python

6 min read

Linghua Jin for CocoIndex

Jul 11

Beyond Embeddings: Building Metadata-Rich Indexes from Academic PDFs

#showdev #programming #ai #python

7 min read

Linghua Jin for CocoIndex

Jun 4

Build Real-Time Knowledge Graphs from Documents Using CocoIndex + Kuzu (with LLMs & Live Updates)

#showdev #programming #python #opensource

4 min read

Linghua Jin for CocoIndex

May 30

Stream from S3 in Real-Time: CocoIndex Brings True Incremental Processing to the Cloud

#showdev #ai #programming #python

6 min read

Linghua Jin for CocoIndex

May 25

How to build image search with semantic understanding

#showdev #programming #python #opensource

6 min read

Linghua Jin for CocoIndex

May 24

How to build index with text embeddings

#showdev #opensource #ai #python

3 min read

Linghua Jin for CocoIndex

May 13

🎉 CocoIndex hits 1,000 stars – powering real-time data for AI

#showdev #programming #opensource #datascience

4 min read

Linghua Jin for CocoIndex

May 8

Real-Time Knowledge Graph for Product recommendation with LLM taxonomy extraction

#showdev #opensource #programming #python

7 min read

Linghua Jin for CocoIndex

May 1

Build Real-Time Knowledge Graph For Documents with LLM

#showdev #opensource #programming #python

7 min read

Linghua Jin

Apr 24

LLM to extract and auto generate knowledge graph - step by step, in ~100 lines of python

#ai #python #programming #tutorial

9 min read

Linghua Jin

Apr 8

CocoIndex Changelog 2025-04-05

#ai #programming #python #datascience

5 min read

Linghua Jin

Apr 8

Continuous update ETL on source updates, automatically

#ai #datascience #python #programming

4 min read

Linghua Jin for CocoIndex

Apr 8

How to do incremental processing for ETL - by examples

#ai #datascience #wecoded #python

5 min read

Linghua Jin

Apr 7

Incremental processing to keep low latency sync for your ETL

#showdev #ai #datascience #opensource

2 min read

Linghua Jin

Apr 1

Implement Contextual Retrieval for RAG

1 min read

Linghua Jin

Mar 30

Efficiently process large files for RAG

#ai #programming #datascience #rag

3 min read

Linghua Jin

Mar 28

Automate structured data extraction from PDF / Word by OpenAI and CocoIndex

#showdev #ai #machinelearning

6 min read

Linghua Jin

Mar 27

Is RAG Still Needed? Retrieval Beyond Vector Embeddings

#discuss #ai #rag #datascience

3 min read

Linghua Jin

Mar 26

Step by Step guide to ingest Google Drive for RAG

#discuss #ai #machinelearning #datascience

7 min read

Linghua Jin

Mar 24

Want AI to Actually Understand Your Code? This Tool Says It Can Help

#discuss #programming #ai #opensource

7 min read

Linghua Jin for CocoIndex

Mar 18

On-premise structured extraction with LLM using Ollama

#discuss #ai #opensource #programming

6 min read

Linghua Jin

Mar 15

Data Indexing and Common Challenges

#discuss #rag #ai #opensource

3 min read

Linghua Jin

Mar 11

[Open Source Project] Fresh Data For AI

#discuss #ai #python #opensource

2 min read

Linghua Jin

Mar 9

Open-Source ETL to prepare data for RAG 🦀 🐍

#ai #python #opensource #datascience

1 min read

1 Week Community Wellness Streak

Writing Debut

CocoIndex

Want to connect with Linghua Jin?