Sign in

Linghua Jin

@badmonster0.bsky.social
91 followers 393 following 136 posts

building CocoIndex🥥 - #opensource data infra for AI, ex-google tech lead github.com/cocoindex-io/cocoindex 🥥🌴

PostsRepliesMedia
Linghua Jin @badmonster0.bsky.social · 01/12/2025
Why #CocoIndex chose Rust: blazing-fast dataflow, predictable performance, and memory safety without GC pauses. When you’re doing real-time incremental updates at scale, every microsecond matters — Rust lets us push the limits without sacrificing correctness. #rustlang
120
Linghua Jin @badmonster0.bsky.social · 21/11/2025
Improve your ai data pipeline throughput x times by adaptive batching cocoindex.io/blogs/batching #ai #opensource
cocoindex.io
Adaptive Batching - 5x throughput on your data pipelines | CocoIndex
Discover how CocoIndex delivers automatic batch processing for GPU workloads and machine learning pipelines. Framework-level batching optimizes performance for text embeddings and other AI operations ...
041
Linghua Jin @badmonster0.bsky.social · 20/11/2025
Thinking in Rust: Ownership, Access, and Memory Safety - cocoindex.io/blogs/rust-o... #rustlang
cocoindex.io
Thinking in Rust: Ownership, Access, and Memory Safety | CocoIndex
A mental framework for Rust's memory safety concepts. Think systematically about ownership, references, Send, Sync, and Rc, Arc, RefCell, Mutex, etc.
031
Linghua Jin @badmonster0.bsky.social · 13/11/2025
CocoIndex made to #1 Github trending global in Rust - data transformation engine. Grateful to the Rust open source community and all the amazing Rustaceans for the support 💛 #rustlang #github #opensource
283
Linghua Jin @badmonster0.bsky.social · 09/10/2025
vibe coding, not vibe data www.youtube.com/watch?v=crV7... #ai #youtube #llm #data #opensource
youtube.com
Fast Iterate Your Indexing Strategy 🚀
YouTube video by CocoIndex
051
Linghua Jin @badmonster0.bsky.social · 02/10/2025
Happy Hacktoberfest! Trick-or-treat 🎃🎃 CocoIndex - github.com/cocoindex-io... - tagged with hacktoberfest and fun issues, and ready to go ! Rust 🦀 and Python 🐍 #opensource #hacktoberfest #hacktoberfest-2025
030
Linghua Jin @badmonster0.bsky.social · 05/09/2025
🛒 Building + Explaining a real-time product recommendation engine with LLM + Graph DB - #OpenSource 🚀 Tutorial: cocoindex.io/docs/example... 🌟 Repo: github.com/cocoindex-io...
061
Linghua Jin @badmonster0.bsky.social · 14/08/2025
CocoIndex - github.com/cocoindex-io... - Build fresh knowledge for AI made to the top 3 in trending github in #rustlang! 🌟 star if you like it! Let's go Rust 🦀. Data infra project should be on #Rustlang. #opensource #buildinpublic
073
Linghua Jin @badmonster0.bsky.social · 12/08/2025
Multi-dimensional vectors? That’s how AI understands everything — text, images, audio, all at once. We broke it down here. cocoindex.io/blogs/multi-... 🌟Star the repo if you like it! github.com/cocoindex-io... #opensource #Vision #LLM #AI #buildinpublic
cocoindex.io
Multi-Dimensional Vector Support in CocoIndex | CocoIndex
CocoIndex natively handles typed multi-dimensional vectors — from simple arrays to multi-vector embeddings, unlocks multimodal AI pipelines at scale.
162
Linghua Jin @badmonster0.bsky.social · 10/08/2025
Effortless code context for AI - Star github.com/cocoindex-io... if you like it! link to full write up cocoindex.io/blogs/index-...
130
Linghua Jin @badmonster0.bsky.social · 07/08/2025
Best realtime context for coding agents cocoindex.io/blogs/index-... #vibecoding #opensource #claude #ai #llm #startup #data #tech #codingagents #agents #openai #cursor #windsurf
cocoindex.io
Build Real-Time Codebase Indexing for AI Code Generation | CocoIndex
Indexing codebase for RAG with CocoIndex and Tree-sitter in real-time: chunking, embedding, semantic search, and build vector index for efficient retrieval.
051
Linghua Jin @badmonster0.bsky.social · 05/08/2025
CocoIndex (github.com/cocoindex-io...) now supports custom targets - make the AI agents to operate on always-current context effortlessly. Checkout - cocoindex.io/blogs/custom... #opensource #LEGO #buildinpublic
github.com
GitHub - cocoindex-io/cocoindex: Data transformation framework for AI. Ultra performant, with incremental processing.
Data transformation framework for AI. Ultra performant, with incremental processing. - cocoindex-io/cocoindex
052
Linghua Jin @badmonster0.bsky.social · 25/07/2025
Indexing Faces for Scalable Visual Search 🚀 Build your own Google‑style photo finder in minutes with face detection, embeddings and Qdrant 🔍 with step-by-step preview. 🌟 Repo (appreciate a star!): github.com/cocoindex-io... 👀 Tutorial: cocoindex.io/blogs/face-d... #OpenSource #Python
cocoindex.io
Indexing Faces for Scalable Visual Search - Build your own Google Photo Search | CocoIndex
Build a scalable face detection and recognition pipeline using CocoIndex. This tutorial covers extracting and embedding faces from images, structuring data for visual search, and exporting to a vect...
121
Linghua Jin @badmonster0.bsky.social · 22/07/2025
Build image search and query with natural language with vision model CLIP - 100 lines of python. Use LLM for image recognition. Time to repurpose for Coldplay CAM real-time integration 😜 cocoindex.io/blogs/live-i... Github: github.com/cocoindex-io... #LLM #ColdPlay #ColdPlayCam
cocoindex.io
Build image search and query with natural language with vision model CLIP | CocoIndex
Indexing images with CocoIndex and Vision Model in real-time: multi-modal embedding, and build vector index for efficient retrieval.
020
Linghua Jin @badmonster0.bsky.social · 16/07/2025
A holistic, top-down perspective on Rust’s ownership, permission, and memory safety model cocoindex.io/blogs/rust-o... #Rustlang #Programming #MemorySafty #Data
cocoindex.io
Thinking in Rust: Ownership, Access, and Memory Safety | CocoIndex
A mental framework for Rust's memory safety concepts. Think systematically about ownership, references, Send, Sync, and Rc, Arc, RefCell, Mutex, etc.
051
Linghua Jin @badmonster0.bsky.social · 13/07/2025
Context + Reliable LLM e.g., Claude code will be the future of coding agents. Checkout Cocoindex that brings fresh context for reliable coding agents! github.com/cocoindex-io... (Appreciate a star!) Full blog here: cocoindex.io/blogs/index-... #opensource #codeagent
cocoindex.io
Build Real-Time Codebase Indexing for AI Code Generation | CocoIndex
Indexing codebase for RAG with CocoIndex and Tree-sitter in real-time: chunking, embedding, semantic search, and build vector index for efficient retrieval.
061
Reposted by Linghua Jin
HackerNoon @hackernoon.com · 11/07/2025
How to index academic research papers by extracting metadata (e.g., title, authors, abstract) for AI agents and AI workflows using LLMs and CocoIndex. #ai
hackernoon.com
Turn Your PDF Library into a Searchable Research Database with 100 Lines of Code
032
Linghua Jin @badmonster0.bsky.social · 11/07/2025
Build real-time knowledge graph from documents with LLM youtu.be/2KVkpUGRtnk?... Checkout - github.com/cocoindex-io... #OpenSource #Dev #TechTalkSky #IndieTechFeed
youtu.be
Build Real-Time Knowledge Graph For Documents with LLM
YouTube video by CocoIndex
021
Linghua Jin @badmonster0.bsky.social · 10/07/2025
📚 Build LLM-ready, metadata-rich indexes from academic papers PDF in minutes. Get started: 🔗https://cocoindex.io/blogs/academic-papers-indexing Repo: 🌟 github.com/cocoindex-io... #LLM #RAG #SemanticSearch #opensource #DataInfrastructure #KnowledgeGraphs #VectorSearch #DevTools #OpenSource
152
Reposted by Linghua Jin
HackerNoon @hackernoon.com · 07/07/2025
Unlock the power of Retrieval-Augmented Generation (RAG) by indexing your codebase. Learn why it matters, how to do it with smart chunking, embeddings, and more #ai
hackernoon.com
Your Repo Has Secrets. Indexing Tells AI Where They Are.
011
Linghua Jin @badmonster0.bsky.social · 08/07/2025
3rd repo of the day 🦀! - Github Trending 🚀 Checkout - github.com/cocoindex-io... #opensource #rustlang
020
Linghua Jin @badmonster0.bsky.social · 07/07/2025
CocoIndex Crossed 2k stars last week with one day on Github Trending in Rust 🦀 . Thank you everyone who contributed, starred the repo and shared the love! Let’s making the best ETL framework for AI 🚀 ! github.com/cocoindex-io... #RustLang #opensource
040
Linghua Jin @badmonster0.bsky.social · 06/07/2025
github.com/cocoindex-io... Transform data for AI got to @github.com Rust Trending this week 🚀! @github-trending.bsky.social #rustlang #opensource
github.com
GitHub - cocoindex-io/cocoindex: Data transformation framework for AI. Ultra performant, with incremental processing.
Data transformation framework for AI. Ultra performant, with incremental processing. - cocoindex-io/cocoindex
031
Linghua Jin @badmonster0.bsky.social · 05/07/2025
build code index for your coding agents ~ in 10 min cocoindex.io/blogs/index-... appreciate a star on my repo: github.com/cocoindex-io... #coding #opensource
cocoindex.io
Build Real-Time Codebase Indexing for AI Code Generation | CocoIndex
Indexing codebase for RAG with CocoIndex and Tree-sitter in real-time: chunking, embedding, semantic search, and build vector index for efficient retrieval.
030
Linghua Jin @badmonster0.bsky.social · 04/07/2025
wow cocoindex got to @github.com trending yesterday in Rust 🦀. But i missed the moment. Anyways, way to go! github.com/cocoindex-io... Super simple ETL to prepare data for AI. Write in python, with Rust performance. Grateful that this blog happens to capture it #github #opensource #rustlang
170
Linghua Jin @badmonster0.bsky.social · 03/07/2025
github.com/cocoindex-io... Prepare data like LEGO. Few lines in Python, powered by Rust 🦀 for ultra performance Appreciate a star for the repo #opensource #buildinpublic #rustlang
061
Linghua Jin @badmonster0.bsky.social · 01/07/2025
CocoIndex - super simple etl to prepare data for ai agents, with dynamic index - cross 2k Github stars today. github.com/cocoindex-io... When sources get updates, it automatically syncs to targets with minimal computation needed. Open source & on-prem ready. ⭐️ Star if it is helpful :)
131
Linghua Jin @badmonster0.bsky.social · 30/06/2025
Homepage v2 - cocoindex.io Ultra performant ETL for AI, within 100 lines of python code. Appreciate a star 🌟 on github.com/cocoindex-io...
121
Linghua Jin @badmonster0.bsky.social · 26/06/2025
🚀 Introducing CocoInsight - Make your AI data pipeline exceptionally easy to understand — step-by-step. 🌟Works with CocoIndex: github.com/cocoindex-io... 🎉Now live: youtube.com/watch?v=MMrp... #AI #DataEngineering #LLM #RAG #OpenSource #VibeCoding #AIInfrastructure #MLOps #LLMInfra #CocoIndex
042
Linghua Jin @badmonster0.bsky.social · 23/06/2025
🚀 CocoIndex now officially supports LiteLLM. You can now plug any LiteLLM-supported model directly into your Coco AI data pipelines — making it even easier to run, experiment, and scale with your favorite LLMs. cocoindex.io/docs/ai/llm#... 🌟Github: github.com/cocoindex-io... #LLM #data #AI #etl
github.com
GitHub - cocoindex-io/cocoindex: Real-time data transformation framework for AI. Ultra performant, with incremental processing.
Real-time data transformation framework for AI. Ultra performant, with incremental processing. - cocoindex-io/cocoindex
031
Linghua Jin @badmonster0.bsky.social · 09/06/2025
🚀 Build Real-Time #Codebase Indexing for LLMs with Tree-sitter for coding agents. ~100 lines of Python get started: 🔗 cocoindex.io/blogs/index-... repo: 🌟 github.com/cocoindex-io...
141
Linghua Jin @badmonster0.bsky.social · 03/06/2025
CocoIndex now provides native support for #Kuzu as a target graph data store. #Kuzu is a graph database that is designed to be fast, scalable, and easy to use. This integration features a high performance knowledge graph stack with real-time updates. cocoindex.io/blogs/kuzu-i...
120
Linghua Jin @badmonster0.bsky.social · 03/06/2025
We're excited to roll out a packed update over ~15 releases focused on real-time, incremental data processing — all with developers in mind at @cocoindex.bsky.social . Here's what's new 🎉 #Opensource #buildinpublic #AIInfra #DataEngineering #LLMInfra #PythonDev #DataInfrastructure #LLM #GitHub
150
Linghua Jin @badmonster0.bsky.social · 02/06/2025
A super easy to use and maintain data framework for AI (embeddings, knowledge graph, structured extraction). Update the data in real-time out of the box. ~100 lines python for production grade pipeline. github.com/cocoindex-io... #rustlang #python #programming #data #tech #engineering
github.com
GitHub - cocoindex-io/cocoindex: Real-time data transformation framework for AI. Ultra performant, with incremental processing.
Real-time data transformation framework for AI. Ultra performant, with incremental processing. - cocoindex-io/cocoindex
020
Linghua Jin @badmonster0.bsky.social · 31/05/2025
Most user-facing AI agents need data freshness. When users update documents, it's unexpected to see stale information in search results. If the search result is fed into an AI agent, it may mean unexpected response to users. It's more dangerous - users may take unexpected response without noticing.
031
Linghua Jin @badmonster0.bsky.social · 30/05/2025
I know it is not my fault .... 😂
020
Reposted by Linghua Jin
HackerNoon @hackernoon.com · 30/05/2025
Learn how to build a real-time, incremental ETL pipeline using Amazon S3, SQS, and CocoIndex for efficient, low-latency data transformation and vector embedding #ai
hackernoon.com
Real-Time S3 Processing Arrives on CocoIndex via AWS SQS Integration
162
Linghua Jin @badmonster0.bsky.social · 30/05/2025
CocoIndex now natively supports Amazon S3 as a data source, allowing seamless integration with your storage. Combined with support for AWS Simple Queue Service (SQS), CocoIndex enables true real-time, incremental processing of data as it's updated in S3. Read more: cocoindex.io/blogs/s3-inc...
github.com
GitHub - cocoindex-io/cocoindex: Real-time data transformation framework for AI. Ultra performant, with incremental processing.
Real-time data transformation framework for AI. Ultra performant, with incremental processing. - cocoindex-io/cocoindex
030
Linghua Jin @badmonster0.bsky.social · 30/05/2025
🚀 Just launched: CocoIndex now supports real-time incremental processing from #AmazonS3 with #AmazonSQS. If your AI agent needs fresh data in production systems, take a look (with end to end example). 📖 Dive in: cocoindex.io/blogs/s3-inc... 🌟Repo: github.com/cocoindex-io... #OpenSource #Data
cocoindex.io
Real-time data transformation pipeline with Amazon S3 bucket, SQS and CocoIndex | CocoIndex
Build real-time data transformation pipeline with S3 and CocoIndex.
141
Linghua Jin @badmonster0.bsky.social · 28/05/2025
Preparing data is highly use-case based and there is no one-size-fits-all solution. With all the latest advancements in models, there is no single best solution for all cases, and it's also a balance of multiple factors in terms of quality, performance, pricing, etc.
110
Linghua Jin @badmonster0.bsky.social · 26/05/2025
CocoIndex github.com/cocoindex-io... follows the idea of Dataflow programming model. Each transformation creates a new field solely based on input fields, without hidden states and value mutation. All data before/after each transformation is observable, with lineage out of the box. #programming
010
Linghua Jin @badmonster0.bsky.social · 25/05/2025
🔥 #CocoIndex now supports native #AmazonS3 integration — with built-in change data capture! Any file create / update / delete in your S3 bucket triggers instant reprocessing via Amazon SQS. Your data for #AIAgents stays fresh, always. ⚡ #LLM #AIAgents #RAG #Amazon
010
Linghua Jin @badmonster0.bsky.social · 25/05/2025
Founding is a loop of setbacks, self-doubt, and small wins. The secret isn’t genius. It’s not giving up when it’s hard — which is most of the time. Keep going. #buildinpublic
240
Linghua Jin @badmonster0.bsky.social · 25/05/2025
The best products aren’t built alone. 🚀 #opensource #devcommunity
020
Linghua Jin @badmonster0.bsky.social · 25/05/2025
I've been a big fan of #Rust before I leave my last job. It is my first choice on the #OpenSource project github.com/cocoindex-io... for the data framework because of 1) robustness 2) performance 3) ability to bind to different languages. #RustLang #buildinpublic #DataInfrastructure #programming
github.com
GitHub - cocoindex-io/cocoindex: Real-time data transformation framework for AI. Ultra performant, with incremental processing.
Real-time data transformation framework for AI. Ultra performant, with incremental processing. - cocoindex-io/cocoindex
040
Linghua Jin @badmonster0.bsky.social · 25/05/2025
In a pure dataflow system, every node is just a function of its inputs. Add side effects → lose determinism. Lineage isn’t just for audits — it’s the foundation for caching, re-computation, and trust. #DataEngineering #Lineage #FunctionalProgramming #DataFlow
110
Linghua Jin @badmonster0.bsky.social · 24/05/2025
Not giving up doesn’t mean pretending everything’s fine. It means choosing to keep going even when it’s not. It means adapting, rethinking, throwing away work you believed in, and still showing up the next day with fresh eyes. #buildinpublic
040
Linghua Jin @badmonster0.bsky.social · 24/05/2025
How to keep knowledge base up to date for AI 🌴 in production systems? #AI #RAG #LLM #DataInfrstructure #ETL #DataProcessing #RealTime #Streaming #VectorDatabase #Python #RustLang
cocoindex.io
Incremental Processing with CocoIndex | CocoIndex
CocoIndex helps to keep index up to date with source changes, super efficient and low latency - with the support of incremental processing.
120
Linghua Jin @badmonster0.bsky.social · 24/05/2025
CocoIndex is an ultra performant data transformation framework, with its core engine written in Rust. github.com/cocoindex-io...
github.com
GitHub - cocoindex-io/cocoindex: Real-time data transformation framework for AI. Ultra performant, with incremental processing.
Real-time data transformation framework for AI. Ultra performant, with incremental processing. - cocoindex-io/cocoindex
040
Linghua Jin @badmonster0.bsky.social · 23/05/2025
Text embeddings 101 - Build your own vector search in minutes. We walk through a minimal example — from file ingestion to embedding and querying with natural language, with step by step data insights 🧪 Tutorial: cocoindex.io/blogs/text-e... 🔗 Repo: github.com/cocoindex/co... #AI #LLM #opensource
cocoindex.io
How to build index with text embeddings | CocoIndex
Indexing text with CocoIndex and text embeddings, and query it with natural language.
041