Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Our OSS engineer Clelia Bertelli (🦙/acc) recently built 𝗹𝗶𝘁𝗲𝘀𝗲𝗮𝗿𝗰𝗵, a fully local document ingestion and retrieval CLI/TUI application powered by LiteParse ⚡ litesearch demonstrates how developers can assemble a high-performance, local-first retrieval pipeline using open tools from across the ecosystem: • Parsing: LiteParse, the fast and accurate document parser... we recently open sourced • Chunking: Chonkie • Embeddings: A local Nomic model via Hugging Face transformers.js • Vector storage: A local Qdrant edge shard (custom-built in Rust and compiled as a native add-on) • Retrieval: Query stored files with optional path-based filtering and configurable relevance thresholds • Runtime: Bun for speed and versatility 💻 Check out the repository and try it yourself: 📚 LiteParse docs:show more

LlamaIndex 🦙

116,533 subscribers

14,856 views • 3 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🚀 The Google DeepMind team just added Gemini 3.1 to the Live API, so we built a small demo showing how Gemini voice agents can plug directly into the document processing ecosystem powered by LlamaIndex. 🔥 In this example, we integrate LiteParse to enable fast, fully-local document parsing. With our TUI-based voice assistant, you can literally talk to your terminal: - Speak commands - Trigger live document parsing via tool calls - Hear the agent read back results in real time 🔊 The assistant can extract content from single files or entire folders, leveraging the lightning-fast local parsing that LiteParse provides ⚡ Take a look at the demo👇 👩‍💻 GitHub repo 📚 LiteParse docs

🚀 The Google DeepMind team just added Gemini 3.1 to the Live API, so we built a small demo showing how Gemini voice agents can plug directly into the document processing ecosystem powered by LlamaIndex. 🔥 In this example, we integrate LiteParse to enable fast, fully-local document parsing. With our TUI-based voice assistant, you can literally talk to your terminal: - Speak commands - Trigger live document parsing via tool calls - Hear the agent read back results in real time 🔊 The assistant can extract content from single files or entire folders, leveraging the lightning-fast local parsing that LiteParse provides ⚡ Take a look at the demo👇 👩‍💻 GitHub repo 📚 LiteParse docs

LlamaIndex 🦙

14,766 views • 3 months ago

We've spent years building LlamaParse into the most accurate document parser for production AI. Along the way, we learned a lot about what fast, lightweight parsing actually looks like under the hood. Today, we're open-sourcing a light-weight core of that tech as LiteParse 🦙 It's a CLI + TS-native library for layout-aware text parsing from PDFs, Office docs, and images. Local, zero Python dependencies, and built specifically for agents and LLM pipelines. Think of it as our way of giving the community a solid starting point for document parsing: npm i -g @llamaindex/liteparse lit parse anything.pdf - preserves spatial layout (columns, tables, alignment) - built-in local OCR, or bring your own server - screenshots for multimodal LLMs - handles PDFs, office docs, images Blog: Repo:

We've spent years building LlamaParse into the most accurate document parser for production AI. Along the way, we learned a lot about what fast, lightweight parsing actually looks like under the hood. Today, we're open-sourcing a light-weight core of that tech as LiteParse 🦙 It's a CLI + TS-native library for layout-aware text parsing from PDFs, Office docs, and images. Local, zero Python dependencies, and built specifically for agents and LLM pipelines. Think of it as our way of giving the community a solid starting point for document parsing: npm i -g @llamaindex/liteparse lit parse anything.pdf - preserves spatial layout (columns, tables, alignment) - built-in local OCR, or bring your own server - screenshots for multimodal LLMs - handles PDFs, office docs, images Blog: Repo:

LlamaIndex 🦙

581,217 views • 4 months ago

We built the fastest PDF -> markdown parser in the world 🚀⚡️ AND it’s more accurate than any other open-source, model-free parser (pymupdf4llm, opendataloader, pdf-inspector, markitdown) on 3 standardized benchmarks: olmOCR0-bench, opendataloader-bench, ParseBench Introducing LiteParse v2.1. The v2 base version was already the fastest document->text parser on the planet, and with this new release we’ve introduced markdown. It is fully open-source (Apache 2.0) and free, is usable from CLI/Rust/Node/Python/WASM, and is also installable as a one-click agent skill. Check it out: Come check out LiteParse:

We built the fastest PDF -> markdown parser in the world 🚀⚡️ AND it’s more accurate than any other open-source, model-free parser (pymupdf4llm, opendataloader, pdf-inspector, markitdown) on 3 standardized benchmarks: olmOCR0-bench, opendataloader-bench, ParseBench Introducing LiteParse v2.1. The v2 base version was already the fastest document->text parser on the planet, and with this new release we’ve introduced markdown. It is fully open-source (Apache 2.0) and free, is usable from CLI/Rust/Node/Python/WASM, and is also installable as a one-click agent skill. Check it out: Come check out LiteParse:

Jerry Liu

329,900 views • 1 month ago

We analyzed Anthropic’s memory architecture and built something better: a persistent, human-inspectable, and token-efficient memory layer that scales with your projects. Today, it’s OPEN-SOURCE. ByteRover CLI gives agents (like OpenClaw, Claude Code, and Hermes) persistent, structured memory. Built on the exact architecture that became the #1 memory system for OpenClaw (30,000+ downloads in a week), it lets developers curate project knowledge into a file-based hierarchy. This guarantees highly accurate, lightning-fast retrieval, even with lightweight models. 👉Highly Accurate: >92% retrieval accuracy across long-running sessions - the highest proven production accuracy on the market. ⚡Fast: ~1.6s average retrieval time. 💰Economic: Maintains >90% accuracy even with lightweight models, saving 50-70% on token costs. ☁ Portable: Runs locally by default, with cloud-sync to share memory across agents and teammates.

We analyzed Anthropic’s memory architecture and built something better: a persistent, human-inspectable, and token-efficient memory layer that scales with your projects. Today, it’s OPEN-SOURCE. ByteRover CLI gives agents (like OpenClaw, Claude Code, and Hermes) persistent, structured memory. Built on the exact architecture that became the #1 memory system for OpenClaw (30,000+ downloads in a week), it lets developers curate project knowledge into a file-based hierarchy. This guarantees highly accurate, lightning-fast retrieval, even with lightweight models. 👉Highly Accurate: >92% retrieval accuracy across long-running sessions - the highest proven production accuracy on the market. ⚡Fast: ~1.6s average retrieval time. 💰Economic: Maintains >90% accuracy even with lightweight models, saving 50-70% on token costs. ☁ Portable: Runs locally by default, with cloud-sync to share memory across agents and teammates.

andy nguyen

28,980 views • 3 months ago

Introducing LiteParse - the best model-free document parsing tool for AI agents 💫 ✅ It’s completely open-source and free. ✅ No GPU required, will process ~500 pages in 2 seconds on commodity hardware ✅ More accurate than PyPDF, PyMuPDF, Markdown. Also way more readable - see below for how we parse tables!! ✅ Supports 50+ file formats, from PDFs to Office docs to images ✅ Is designed to plug and play with Claude Code, OpenClaw, and any other AI agent with a one-line skills install. Supports native screenshotting capabilities. We spent years building up LlamaParse by orchestrating state-of-the-art VLMs over the most complex documents. Along the way we realized that you could get quite far on most docs through fast and cheap text parsing. Take a look at the video below. For really complex tables within PDFs, we output them in a spatial grid that’s both AI and human-interpretable. Any other free/light parser light PyPDF will destroy the representation of this table and output a sequential list. This is not a replacement for a VLM-based OCR tool (it requires 0 GPUs and doesn’t use models), but it is shocking how good it is to parse most documents. Huge shoutout to Logan Markewich and Clelia Bertelli (🦙/acc) for all the work here. Come check it out: Repo:

Introducing LiteParse - the best model-free document parsing tool for AI agents 💫 ✅ It’s completely open-source and free. ✅ No GPU required, will process ~500 pages in 2 seconds on commodity hardware ✅ More accurate than PyPDF, PyMuPDF, Markdown. Also way more readable - see below for how we parse tables!! ✅ Supports 50+ file formats, from PDFs to Office docs to images ✅ Is designed to plug and play with Claude Code, OpenClaw, and any other AI agent with a one-line skills install. Supports native screenshotting capabilities. We spent years building up LlamaParse by orchestrating state-of-the-art VLMs over the most complex documents. Along the way we realized that you could get quite far on most docs through fast and cheap text parsing. Take a look at the video below. For really complex tables within PDFs, we output them in a spatial grid that’s both AI and human-interpretable. Any other free/light parser light PyPDF will destroy the representation of this table and output a sequential list. This is not a replacement for a VLM-based OCR tool (it requires 0 GPUs and doesn’t use models), but it is shocking how good it is to parse most documents. Huge shoutout to Logan Markewich and Clelia Bertelli (🦙/acc) for all the work here. Come check it out: Repo:

Jerry Liu

256,399 views • 4 months ago

We're excited to introduce the Retrieval Harness in LlamaParse - which is the 2026 version of RAG over documents Generalized agents need the right set of tools to scalably search and read through an arbitrary corpus of data (from 10 docs to 1m+ docs). They can already demonstrate great retrieval performance over a local filesystem, need a proper backend for a large collection of managed data. The Retrieval Harness exposes a diverse set of tools for various needs: 1. Hybrid Retrieval: Combine vector search with keyword search, let the agent set the alpha value to toggle between the two 2. List Files: a scalable version of `ls` to list files within an index 3. File Grep: enable regex search within a given file 4. File Read: Allow agents to read a subsection from an existing document. The agent can choose to interleave any sequence of these tools in order to complete a variety of tasks, from simple to hard. Come check it out! Blog: Sign up to LlamaParse:

We're excited to introduce the Retrieval Harness in LlamaParse - which is the 2026 version of RAG over documents Generalized agents need the right set of tools to scalably search and read through an arbitrary corpus of data (from 10 docs to 1m+ docs). They can already demonstrate great retrieval performance over a local filesystem, need a proper backend for a large collection of managed data. The Retrieval Harness exposes a diverse set of tools for various needs: 1. Hybrid Retrieval: Combine vector search with keyword search, let the agent set the alpha value to toggle between the two 2. List Files: a scalable version of `ls` to list files within an index 3. File Grep: enable regex search within a given file 4. File Read: Allow agents to read a subsection from an existing document. The agent can choose to interleave any sequence of these tools in order to complete a variety of tasks, from simple to hard. Come check it out! Blog: Sign up to LlamaParse:

Jerry Liu

18,615 views • 19 days ago

Web scraping will never be the same. (100% open-source visual search at scale) PixelRAG is a retrieval system that skips HTML parsing completely. Instead of scraping a page into text and embedding chunks, it screenshots the page and retrieves the image. A vision-language model reads the answer straight off the pixels. Why that matters: parsing is where web RAG quietly loses information. - A single HTML-to-text parser can drop 40%+ of a page. - Tables, charts, and layout get flattened or thrown out. - Swapping parsers alone can move accuracy ~10 points on the same docs. PixelRAG indexes the page a person actually sees. The team built a visual index of all of Wikipedia, 30M+ screenshots, and it still beats the strongest text RAG baseline by 18.1% on text-only QA. The repo also ships a Claude Code plugin that gives Claude eyes. It lets Claude screenshot any URL and read the rendered page instead of scraping the DOM. So you can hand it a live page, an arXiv paper, or your local site and ask what it actually looks like. One setup script. No MCP server, no backend. How the pipeline works: - Renders each document (web, PDF, image) to image tiles. - Embeds them with Qwen3-VL-Embedding, LoRA fine-tuned on screenshots. - Builds a FAISS index and serves a search API. A stronger reader model lifts accuracy with no re-indexing, since the index is just pixels. Everything is open-source under Apache-2.0. GitHub repo: Talking about RAG, I recently wrote an article on a new approach that makes retrieval much more efficient by cutting corpus size by 40x, reducing tokens per query by 3x, and improving vector search relevance by 2.3x. The article is quoted below.

Web scraping will never be the same. (100% open-source visual search at scale) PixelRAG is a retrieval system that skips HTML parsing completely. Instead of scraping a page into text and embedding chunks, it screenshots the page and retrieves the image. A vision-language model reads the answer straight off the pixels. Why that matters: parsing is where web RAG quietly loses information. - A single HTML-to-text parser can drop 40%+ of a page. - Tables, charts, and layout get flattened or thrown out. - Swapping parsers alone can move accuracy ~10 points on the same docs. PixelRAG indexes the page a person actually sees. The team built a visual index of all of Wikipedia, 30M+ screenshots, and it still beats the strongest text RAG baseline by 18.1% on text-only QA. The repo also ships a Claude Code plugin that gives Claude eyes. It lets Claude screenshot any URL and read the rendered page instead of scraping the DOM. So you can hand it a live page, an arXiv paper, or your local site and ask what it actually looks like. One setup script. No MCP server, no backend. How the pipeline works: - Renders each document (web, PDF, image) to image tiles. - Embeds them with Qwen3-VL-Embedding, LoRA fine-tuned on screenshots. - Builds a FAISS index and serves a search API. A stronger reader model lifts accuracy with no re-indexing, since the index is just pixels. Everything is open-source under Apache-2.0. GitHub repo: Talking about RAG, I recently wrote an article on a new approach that makes retrieval much more efficient by cutting corpus size by 40x, reducing tokens per query by 3x, and improving vector search relevance by 2.3x. The article is quoted below.

Akshay 🚀

937,884 views • 28 days ago

We built a neat tool that lets you convert a directory of Powerpoint files into clean, structured markdown - that Claude Code / agent SDK / any generalized agent wrapper can easily understand. The pptx skill in Claude Code is quite basic and doesn’t have high-fidelity understanding over graphics/charts/tables. Our project Surreal Slides uses LlamaParse to convert presentations into clean structured data that you can put into a db (SurrealDB) for simple retrieval, without having to take screenshots of the data on the fly. Thanks to Clelia Bertelli (🦙/acc) for this project, check it out:

We built a neat tool that lets you convert a directory of Powerpoint files into clean, structured markdown - that Claude Code / agent SDK / any generalized agent wrapper can easily understand. The pptx skill in Claude Code is quite basic and doesn’t have high-fidelity understanding over graphics/charts/tables. Our project Surreal Slides uses LlamaParse to convert presentations into clean structured data that you can put into a db (SurrealDB) for simple retrieval, without having to take screenshots of the data on the fly. Thanks to Clelia Bertelli (🦙/acc) for this project, check it out:

Jerry Liu

39,872 views • 4 months ago

Startups have raised $1B+ to crack Enterprise AI search. Now someone open-sourced it for FREE. The video below shows a self-hosted Slack assistant that answers your questions by searching across all your company's tools in a single query. It's built on top of Airweave, an open-source context retrieval layer that makes all your tools searchable for Agents using semantic, keyword, and agentic search. Here's how the app works: - The app watches for questions in Slack. - It searches every connected tool at once using Airweave (Notion, GitHub, Jira, Linear, etc.) to find relevant context. - The Airweave engine ranks the results by relevance and returns references to the original docs. - An LLM generates the final response and sends it back to Slack with citations. The entire stack is self-hostable via Docker. Find the project in the replies!

Startups have raised $1B+ to crack Enterprise AI search. Now someone open-sourced it for FREE. The video below shows a self-hosted Slack assistant that answers your questions by searching across all your company's tools in a single query. It's built on top of Airweave, an open-source context retrieval layer that makes all your tools searchable for Agents using semantic, keyword, and agentic search. Here's how the app works: - The app watches for questions in Slack. - It searches every connected tool at once using Airweave (Notion, GitHub, Jira, Linear, etc.) to find relevant context. - The Airweave engine ranks the results by relevance and returns references to the original docs. - An LLM generates the final response and sends it back to Slack with citations. The entire stack is self-hostable via Docker. Find the project in the replies!

Avi Chawla

11,927 views • 3 months ago

Researchers built a new RAG approach that: - does not need a vector DB. - does not embed data. - involves no chunking. - performs no similarity search. And it hit 98.7% accuracy on a financial benchmark (SOTA). Here's the core problem with RAG that this new approach solves: Traditional RAG chunks documents, embeds them into vectors, and retrieves based on semantic similarity. But similarity ≠ relevance. When you ask "What were the debt trends in 2023?", a vector search returns chunks that look similar. But the actual answer might be buried in some Appendix, referenced on some page, in a section that shares zero semantic overlap with your query. Traditional RAG would likely never find it. PageIndex (open-source) solves this. Instead of chunking and embedding, PageIndex builds a hierarchical tree structure from your documents, like an intelligent table of contents. Then it uses reasoning to traverse that tree. For instance, the model doesn't ask: "What text looks similar to this query?" Instead, it asks: "Based on this document's structure, where would a human expert look for this answer?" That's a fundamentally different approach with: - No arbitrary chunking that breaks context. - No vector DB infrastructure to maintain. - Traceable retrieval to see exactly why it chose a specific section. - The ability to see in-document references ("see Table 5.3") the way a human would. But here's the deeper issue that it solves. Vector search treats every query as independent. But documents have structure and logic, like sections that reference other sections and context that builds across pages. PageIndex respects that structure instead of flattening it into embeddings. Do note that this approach may not make sense in every use case since traditional vector search is still fast, simple, and works well for many applications. But for professional documents that require domain expertise and multi-step reasoning, this tree-based, reasoning-first approach shines. For instance, PageIndex achieved 98.7% accuracy on FinanceBench, significantly outperforming traditional vector-based RAG systems on complex financial document analysis. Everything is fully open-source, so you can see the full implementation in GitHub and try it yourself. I have shared the GitHub repo in the replies!

Researchers built a new RAG approach that: - does not need a vector DB. - does not embed data. - involves no chunking. - performs no similarity search. And it hit 98.7% accuracy on a financial benchmark (SOTA). Here's the core problem with RAG that this new approach solves: Traditional RAG chunks documents, embeds them into vectors, and retrieves based on semantic similarity. But similarity ≠ relevance. When you ask "What were the debt trends in 2023?", a vector search returns chunks that look similar. But the actual answer might be buried in some Appendix, referenced on some page, in a section that shares zero semantic overlap with your query. Traditional RAG would likely never find it. PageIndex (open-source) solves this. Instead of chunking and embedding, PageIndex builds a hierarchical tree structure from your documents, like an intelligent table of contents. Then it uses reasoning to traverse that tree. For instance, the model doesn't ask: "What text looks similar to this query?" Instead, it asks: "Based on this document's structure, where would a human expert look for this answer?" That's a fundamentally different approach with: - No arbitrary chunking that breaks context. - No vector DB infrastructure to maintain. - Traceable retrieval to see exactly why it chose a specific section. - The ability to see in-document references ("see Table 5.3") the way a human would. But here's the deeper issue that it solves. Vector search treats every query as independent. But documents have structure and logic, like sections that reference other sections and context that builds across pages. PageIndex respects that structure instead of flattening it into embeddings. Do note that this approach may not make sense in every use case since traditional vector search is still fast, simple, and works well for many applications. But for professional documents that require domain expertise and multi-step reasoning, this tree-based, reasoning-first approach shines. For instance, PageIndex achieved 98.7% accuracy on FinanceBench, significantly outperforming traditional vector-based RAG systems on complex financial document analysis. Everything is fully open-source, so you can see the full implementation in GitHub and try it yourself. I have shared the GitHub repo in the replies!

Avi Chawla

972,347 views • 5 months ago

New course: Gemini CLI: Code & Create with an Open-Source Agent, built with Google Cloud Tech/Gemini CLI and taught by Jack Wotherspoon. Agentic coding assistants like Gemini CLI are transforming how developers work. This short course teaches you to use Google's open-source agent to coordinate local tools and cloud services for coding and non-coding workflows. Gemini CLI works from your terminal, so it works with your local files and development tools. You can also connect it to services through MCP. Then provide high-level instructions, and it autonomously plans and executes complex workflows. Skills you'll gain: - Build website features and automate code reviews with GitHub ActionsCreate data dashboards that combine local files with cloud data sources - Use MCP servers and extensions to orchestrate workflows across GitHub, Canva, and Google Workspace - Generate social media content from multimedia files like conference recordings I particularly appreciate that Gemini CLI is open-source. You can see exactly how it works, read the prompts it uses, and understand its architecture. The community has contributed thousands of pull requests. Since Gemini 3’s release I've found Gemini CLI highly capable - this is a tool worth having in your toolbox! Whether you're prototyping applications, automating workflows, or working with multimedia content, join to learn to delegate complex tasks and build faster:

New course: Gemini CLI: Code & Create with an Open-Source Agent, built with Google Cloud Tech/Gemini CLI and taught by Jack Wotherspoon. Agentic coding assistants like Gemini CLI are transforming how developers work. This short course teaches you to use Google's open-source agent to coordinate local tools and cloud services for coding and non-coding workflows. Gemini CLI works from your terminal, so it works with your local files and development tools. You can also connect it to services through MCP. Then provide high-level instructions, and it autonomously plans and executes complex workflows. Skills you'll gain: - Build website features and automate code reviews with GitHub ActionsCreate data dashboards that combine local files with cloud data sources - Use MCP servers and extensions to orchestrate workflows across GitHub, Canva, and Google Workspace - Generate social media content from multimedia files like conference recordings I particularly appreciate that Gemini CLI is open-source. You can see exactly how it works, read the prompts it uses, and understand its architecture. The community has contributed thousands of pull requests. Since Gemini 3’s release I've found Gemini CLI highly capable - this is a tool worth having in your toolbox! Whether you're prototyping applications, automating workflows, or working with multimedia content, join to learn to delegate complex tasks and build faster:

Andrew Ng

124,823 views • 5 months ago

New short course: Build AI Apps with MCP Servers: Working with Box Files, built with Box and taught by Ben Kus , their CTO. Many AI applications require custom code for basic file operations. The Model Context Protocol (MCP) standardizes this by letting you offload file tasks to dedicated servers that provide tools an LLM can use directly. In this course, you'll process documents stored in a Box folder using the Box MCP server. Rather than writing custom integration code to connect to the Box API and download files, you'll design your application to use the tools provided via MCP. Skills you'll gain: - Build an LLM-powered document processing app, using the Box MCP server to access files - Design a multi-agent system using Google's Agent Development Kit (ADK), consisting of specialized agents for file operations - Coordinate the multi-agent workflow through an orchestrator that uses the Agent2Agent (A2A) protocol to connect to the agents You'll start with a local file-processing app, refactor it to work with Box's MCP server, then evolve it into a multi-agent system. Sign up here:

New short course: Build AI Apps with MCP Servers: Working with Box Files, built with Box and taught by Ben Kus , their CTO. Many AI applications require custom code for basic file operations. The Model Context Protocol (MCP) standardizes this by letting you offload file tasks to dedicated servers that provide tools an LLM can use directly. In this course, you'll process documents stored in a Box folder using the Box MCP server. Rather than writing custom integration code to connect to the Box API and download files, you'll design your application to use the tools provided via MCP. Skills you'll gain: - Build an LLM-powered document processing app, using the Box MCP server to access files - Design a multi-agent system using Google's Agent Development Kit (ADK), consisting of specialized agents for file operations - Coordinate the multi-agent workflow through an orchestrator that uses the Agent2Agent (A2A) protocol to connect to the agents You'll start with a local file-processing app, refactor it to work with Box's MCP server, then evolve it into a multi-agent system. Sign up here:

Andrew Ng

81,696 views • 10 months ago

Traditional data pipelines don't work for RAG applications. There are 3 issues with them: 1. Traditional data engineering solutions are optimized to handle structured data. RAG applications rely primarily on unstructured data. 2. The connector ecosystem to load data from unstructured data sources is very immature. 3. Traditional solutions do not offer any way to transform unstructured data into an optimized vector search index. The goal of a RAG Pipeline is to solve these problems. The number one objective is to create a reliable vector search index using factual knowledge and relevant context. This sounds easy, but it's one of the biggest challenges we face when building RAG applications. At a high level, there are four different stages in the architecture of a RAG pipeline: 1. Ingestion: Here is where the pipeline loads the information from the data source. 2. Extraction: Where the pipeline processes the input data and decides how to retrieve the text contained inside them. 3. Transform: Where the pipeline chunks the data and generates document embeddings. 4. Load: Where the pipeline creates a search index in a vector database and loads the document embeddings. There are different rabbit holes at each one of these stages. Here are three of them: 1. Ingesting data once is simple. The hard part is refreshing the vector database whenever the original data source changes. 2. Extracting the content of a plain text document is simple. The hard part is to extract content from complex documents containing tables, images, or cross-references. 3. A simple continual chunking strategy with an overlap is simple. The hard part is to find the optimal strategy for your specific knowledge base and the way you are planning to query it. In the attached video, I'll show you how you can build an enterprise-grade RAG Pipeline that solves every one of the above problems. I'll use Vectorize. They partnered with me on this post. You can use them to build RAG pipelines optimized for accurate context retrieval. If you have a few documents lying around, set up a free account and give it a try.

Traditional data pipelines don't work for RAG applications. There are 3 issues with them: 1. Traditional data engineering solutions are optimized to handle structured data. RAG applications rely primarily on unstructured data. 2. The connector ecosystem to load data from unstructured data sources is very immature. 3. Traditional solutions do not offer any way to transform unstructured data into an optimized vector search index. The goal of a RAG Pipeline is to solve these problems. The number one objective is to create a reliable vector search index using factual knowledge and relevant context. This sounds easy, but it's one of the biggest challenges we face when building RAG applications. At a high level, there are four different stages in the architecture of a RAG pipeline: 1. Ingestion: Here is where the pipeline loads the information from the data source. 2. Extraction: Where the pipeline processes the input data and decides how to retrieve the text contained inside them. 3. Transform: Where the pipeline chunks the data and generates document embeddings. 4. Load: Where the pipeline creates a search index in a vector database and loads the document embeddings. There are different rabbit holes at each one of these stages. Here are three of them: 1. Ingesting data once is simple. The hard part is refreshing the vector database whenever the original data source changes. 2. Extracting the content of a plain text document is simple. The hard part is to extract content from complex documents containing tables, images, or cross-references. 3. A simple continual chunking strategy with an overlap is simple. The hard part is to find the optimal strategy for your specific knowledge base and the way you are planning to query it. In the attached video, I'll show you how you can build an enterprise-grade RAG Pipeline that solves every one of the above problems. I'll use Vectorize. They partnered with me on this post. You can use them to build RAG pipelines optimized for accurate context retrieval. If you have a few documents lying around, set up a free account and give it a try.

Santiago

40,441 views • 1 year ago

Sharing a super simple, user-owned memory module we've been playing around: nanomem The basic idea is to treat memory as a pure intelligence problem: ingestion, structuring, and (selective) retrieval are all just LLM calls & agent loops on a on-device markdown file tree. Each file lists a set of facts w/ metadata (timestamp, confidence, source, etc.); no embeddings/RAG/training of any kind. For example: - `nanomem add ` starts an agent loop to walk the tree, read relevant files, and edit. - `nanomem retrieve ` walks the tree and returns a single summary string (possibly assembled from many subtrees) related to the query. What’s nice about this approach is that the memory system is, by construction: 1. partitionable (human/agents can easily separate `hobbies/snowboard.md` from `tax/residency.md` for data minimization + relevance) 2. portable and user-owned (it’s just text files) 3. interpretable (you know exactly what’s written and you can manually edit) 4. forward-compatible (future models can read memory files just the same, and memory quality/speed improves as models get better) 5. modularized (you can optimize ingestion/retrieval/compaction prompts separately) Privacy & utility. I'm most excited about the ability to partition + selectively disclose memory at inference-time. Selective disclosure helps with both privacy (principle of least privilege & “need-to-know”) and utility (as too much context for a query can harm answer quality). Composability. An inference-time memory module means: (1) you can run such a module with confidential inference (LLMs on TEEs) for provable privacy, and (2) you can selectively disclose context over unlinkable inference of remote models (demo below). We built nanomem as part of the Open Anonymity project ( but it’s meant to be a standalone module for humans and agents (e.g., you can write a SKILL for using the CLI tool). Still polishing the rough edges! - GitHub (MIT): - Blog: - Beta implementation in chat client soon: Work done with amazing project co-leads Amelia Kuang Coco Xu Erik Chi !!

Sharing a super simple, user-owned memory module we've been playing around: nanomem The basic idea is to treat memory as a pure intelligence problem: ingestion, structuring, and (selective) retrieval are all just LLM calls & agent loops on a on-device markdown file tree. Each file lists a set of facts w/ metadata (timestamp, confidence, source, etc.); no embeddings/RAG/training of any kind. For example: - `nanomem add ` starts an agent loop to walk the tree, read relevant files, and edit. - `nanomem retrieve ` walks the tree and returns a single summary string (possibly assembled from many subtrees) related to the query. What’s nice about this approach is that the memory system is, by construction: 1. partitionable (human/agents can easily separate `hobbies/snowboard.md` from `tax/residency.md` for data minimization + relevance) 2. portable and user-owned (it’s just text files) 3. interpretable (you know exactly what’s written and you can manually edit) 4. forward-compatible (future models can read memory files just the same, and memory quality/speed improves as models get better) 5. modularized (you can optimize ingestion/retrieval/compaction prompts separately) Privacy & utility. I'm most excited about the ability to partition + selectively disclose memory at inference-time. Selective disclosure helps with both privacy (principle of least privilege & “need-to-know”) and utility (as too much context for a query can harm answer quality). Composability. An inference-time memory module means: (1) you can run such a module with confidential inference (LLMs on TEEs) for provable privacy, and (2) you can selectively disclose context over unlinkable inference of remote models (demo below). We built nanomem as part of the Open Anonymity project ( but it’s meant to be a standalone module for humans and agents (e.g., you can write a SKILL for using the CLI tool). Still polishing the rough edges! - GitHub (MIT): - Blog: - Beta implementation in chat client soon: Work done with amazing project co-leads Amelia Kuang Coco Xu Erik Chi !!

Ken Liu

73,767 views • 3 months ago

We've been obsessing a lot about creating the best possible AI support experience Dub.co. And I think we've found the magic formula. The stack: ✦ Mintlify → docs + help articles ✦ Upstash vector → vector search ✦ AI SDK + Claude sonnet → LLM/retrieval ✦ Plain → support infra Here's how it works: We consolidated our docs + help articles on Mintlify (best-in-class docs platform) so all our support content is now in one place. On every push to main, we sync changes to our Upstash Vector DB. We also built a custom chat interface that retrieves content from Upstash Vector and generates responses via AI SDK + Claude sonnet. The best part: The AI agent uses 𝚝𝚘𝚘𝚕() from AI SDK to retrieve the user's workspace / partner data to provide accurate responses. Finally, if the user needs to speak to a human, we generate a 𝚃𝚒𝚌𝚔𝚎𝚝𝚄𝚙𝚕𝚘𝚊𝚍 UI that lets users upload screenshots + add more context, before creating a ticket on Plain. Cherry on top: The chat interface is embeddable, so we're able to embed it both in our Mintlify docs + support portal 👇 Since we launched this, it's been a gamechanger for scaling support – reducing support workload and creating a much better experience for our users. Highly recommend giving this a try!

We've been obsessing a lot about creating the best possible AI support experience Dub.co. And I think we've found the magic formula. The stack: ✦ Mintlify → docs + help articles ✦ Upstash vector → vector search ✦ AI SDK + Claude sonnet → LLM/retrieval ✦ Plain → support infra Here's how it works: We consolidated our docs + help articles on Mintlify (best-in-class docs platform) so all our support content is now in one place. On every push to main, we sync changes to our Upstash Vector DB. We also built a custom chat interface that retrieves content from Upstash Vector and generates responses via AI SDK + Claude sonnet. The best part: The AI agent uses 𝚝𝚘𝚘𝚕() from AI SDK to retrieve the user's workspace / partner data to provide accurate responses. Finally, if the user needs to speak to a human, we generate a 𝚃𝚒𝚌𝚔𝚎𝚝𝚄𝚙𝚕𝚘𝚊𝚍 UI that lets users upload screenshots + add more context, before creating a ticket on Plain. Cherry on top: The chat interface is embeddable, so we're able to embed it both in our Mintlify docs + support portal 👇 Since we launched this, it's been a gamechanger for scaling support – reducing support workload and creating a much better experience for our users. Highly recommend giving this a try!

Steven Tey

22,654 views • 4 months ago

💥 A 450M model just beat bigger VLAs on real robot tasks, and it’s 100% open source [📍 bookmark for later] Came across SmolVLA, a new vision-language-action model for robotics that’s compact, fast, and trained entirely on open community datasets from LeRobot via Hugging Face. What stood out to me is how it matches or outperforms much larger models like ACT using noisy, real-world community data instead of giant private datasets. Why it’s worth a look ✅ 26% performance boost from pretraining on open-source data ✅ Runs on consumer hardware, even a MacBook ✅ 30% faster responses with async inference and smart architecture tweaks ✅ Strong results across Meta-World, LIBERO, SO100, and SO101 ✅ Fully open source: weights, code, training pipeline, eval stack They also introduced smart efficiency tricks like using fewer visual tokens, pulling outputs from mid-layer, and separating perception from action to make it all run fast. SmolVLA is a strong case for what can happen when the robotics community shares data and builds in the open. Definitely worth keeping an eye on.

💥 A 450M model just beat bigger VLAs on real robot tasks, and it’s 100% open source [📍 bookmark for later] Came across SmolVLA, a new vision-language-action model for robotics that’s compact, fast, and trained entirely on open community datasets from LeRobot via Hugging Face. What stood out to me is how it matches or outperforms much larger models like ACT using noisy, real-world community data instead of giant private datasets. Why it’s worth a look ✅ 26% performance boost from pretraining on open-source data ✅ Runs on consumer hardware, even a MacBook ✅ 30% faster responses with async inference and smart architecture tweaks ✅ Strong results across Meta-World, LIBERO, SO100, and SO101 ✅ Fully open source: weights, code, training pipeline, eval stack They also introduced smart efficiency tricks like using fewer visual tokens, pulling outputs from mid-layer, and separating perception from action to make it all run fast. SmolVLA is a strong case for what can happen when the robotics community shares data and builds in the open. Definitely worth keeping an eye on.

Ilir Aliu - eu/acc

17,353 views • 10 months ago

GeoLibre v1.10.0 is here! GeoLibre is a free and open-source, lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. It runs everywhere you do, in the web browser, on the desktop, on mobile, and inside Jupyter notebooks, all while keeping your data local and private. This release brings photorealistic city-scale 3D to the map, adds OGC API vector tiles, and makes vector tiles and live editing easier to work with. What's new in v1.10.0 - Google Photorealistic 3D Tiles: drape entire cities in photorealistic 3D right in the map, streamed and rendered through - ArcGIS I3S scene layers: stream Integrated Mesh and 3D Object scene layers and render them in 3D on the shared instance. - OGC API vector tiles: add standards-based OGC API - Tiles vector tile services as a remote source, right alongside XYZ and ArcGIS vector tiles. - Local HDF5 and NetCDF-4 loading: open scientific HDF5 and NetCDF-4 files straight from disk, no cloud references required. - GeoEditor from the current view: pull the vector features currently visible in the map into the GeoEditor and start editing what you are looking at, without re-importing the source data. Try it out - Launch GeoLibre Web: - GitHub: - Documentation: - Release notes: #GIS #Geospatial #OpenSource #RemoteSensing #DataVisualization #MapLibre

GeoLibre v1.10.0 is here! GeoLibre is a free and open-source, lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. It runs everywhere you do, in the web browser, on the desktop, on mobile, and inside Jupyter notebooks, all while keeping your data local and private. This release brings photorealistic city-scale 3D to the map, adds OGC API vector tiles, and makes vector tiles and live editing easier to work with. What's new in v1.10.0 - Google Photorealistic 3D Tiles: drape entire cities in photorealistic 3D right in the map, streamed and rendered through - ArcGIS I3S scene layers: stream Integrated Mesh and 3D Object scene layers and render them in 3D on the shared instance. - OGC API vector tiles: add standards-based OGC API - Tiles vector tile services as a remote source, right alongside XYZ and ArcGIS vector tiles. - Local HDF5 and NetCDF-4 loading: open scientific HDF5 and NetCDF-4 files straight from disk, no cloud references required. - GeoEditor from the current view: pull the vector features currently visible in the map into the GeoEditor and start editing what you are looking at, without re-importing the source data. Try it out - Launch GeoLibre Web: - GitHub: - Documentation: - Release notes: #GIS #Geospatial #OpenSource #RemoteSensing #DataVisualization #MapLibre

Qiusheng Wu

23,612 views • 12 days ago

GeoLibre v1.2.0 is here! GeoLibre is a free and open-source, lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. One application that runs everywhere: in your web browser, as a native desktop app, on your phone, and inside a Jupyter notebook. No account, no server, no cost. Everything runs locally and your data stays private. This release packs in 35+ pull requests of new capabilities. A few highlights: - Run SQL right in the browser. The SQL Workspace pairs DuckDB Spatial with a new in-browser PostGIS engine (PGlite), so you can query layers, local files, and remote URLs without a server. - A smarter attribute table. Add fields, run a field calculator, and explore your data with a built-in Charts panel (histogram, scatter, bar, line, and box plots). - More ways to add data. OpenStreetMap PBF extracts, Cloud-Optimized NetCDF/HDF via kerchunk, georeferenced video overlays, authenticated 3D Tiles, and a Layer builder for custom overlays. - Better visualization. Heatmap rendering, point clustering, and H3 hexagonal grids for spatial binning. - New analysis and routing. A Directions plugin, plus Spatial Join, Select by Value, and Select by Location vector tools. - Print and share. A print layout composer that exports your map to PNG or PDF. - Work faster. A command palette (Ctrl/Cmd + K), global keyboard shortcuts, and undo/redo for layer and style operations. - Built for everyone. New internationalization framework, an accessibility pass with automated axe checks, an installable offline-capable PWA web build, React error boundaries, and Playwright end-to-end tests. Try the live demo: Star it on GitHub: Docs and roadmap: Release notes: #GIS #OpenSource #Geospatial #MapLibre #WebGIS #DuckDB #GeoLibre

GeoLibre v1.2.0 is here! GeoLibre is a free and open-source, lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. One application that runs everywhere: in your web browser, as a native desktop app, on your phone, and inside a Jupyter notebook. No account, no server, no cost. Everything runs locally and your data stays private. This release packs in 35+ pull requests of new capabilities. A few highlights: - Run SQL right in the browser. The SQL Workspace pairs DuckDB Spatial with a new in-browser PostGIS engine (PGlite), so you can query layers, local files, and remote URLs without a server. - A smarter attribute table. Add fields, run a field calculator, and explore your data with a built-in Charts panel (histogram, scatter, bar, line, and box plots). - More ways to add data. OpenStreetMap PBF extracts, Cloud-Optimized NetCDF/HDF via kerchunk, georeferenced video overlays, authenticated 3D Tiles, and a Layer builder for custom overlays. - Better visualization. Heatmap rendering, point clustering, and H3 hexagonal grids for spatial binning. - New analysis and routing. A Directions plugin, plus Spatial Join, Select by Value, and Select by Location vector tools. - Print and share. A print layout composer that exports your map to PNG or PDF. - Work faster. A command palette (Ctrl/Cmd + K), global keyboard shortcuts, and undo/redo for layer and style operations. - Built for everyone. New internationalization framework, an accessibility pass with automated axe checks, an installable offline-capable PWA web build, React error boundaries, and Playwright end-to-end tests. Try the live demo: Star it on GitHub: Docs and roadmap: Release notes: #GIS #OpenSource #Geospatial #MapLibre #WebGIS #DuckDB #GeoLibre

Qiusheng Wu

39,608 views • 1 month ago

GeoLibre v1.6.0 is here! GeoLibre is a free and open-source, lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. It runs everywhere you do, in the web browser, on the desktop, on mobile, and inside Jupyter notebooks, all while keeping your data local and private. This release brings multi-map layouts, advanced cartographic symbology and labeling, and a one-click way to install external plugins from a zip. What's new in v1.6.0 - Multi-map grid: Split the workspace into a grid of synchronized map views to compare basemaps, layers, or time steps side by side. - Advanced symbology: Style features with a rule-based renderer, proportional symbols, fill patterns, and a built-in marker library. - Label engine: Label vector features by any attribute, with full placement and styling control. - Install plugins from a zip: Add external plugins from an uploaded zip on both desktop and web. - New vector analysis: Movement, space-time, and cell-coverage tools under Processing. - Faster sample data: Ready-to-load example datasets from a dropdown in every Add Data panel. - Place search in the layer panel: Geocode and fly to a location without leaving the Layers panel. Try it out - Live demo: - GitHub: - Documentation: - Release notes: #GIS #GeospatialData #OpenSource #RemoteSensing #DataVisualization #MapLibre #Python #Cartography

GeoLibre v1.6.0 is here! GeoLibre is a free and open-source, lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. It runs everywhere you do, in the web browser, on the desktop, on mobile, and inside Jupyter notebooks, all while keeping your data local and private. This release brings multi-map layouts, advanced cartographic symbology and labeling, and a one-click way to install external plugins from a zip. What's new in v1.6.0 - Multi-map grid: Split the workspace into a grid of synchronized map views to compare basemaps, layers, or time steps side by side. - Advanced symbology: Style features with a rule-based renderer, proportional symbols, fill patterns, and a built-in marker library. - Label engine: Label vector features by any attribute, with full placement and styling control. - Install plugins from a zip: Add external plugins from an uploaded zip on both desktop and web. - New vector analysis: Movement, space-time, and cell-coverage tools under Processing. - Faster sample data: Ready-to-load example datasets from a dropdown in every Add Data panel. - Place search in the layer panel: Geocode and fly to a location without leaving the Layers panel. Try it out - Live demo: - GitHub: - Documentation: - Release notes: #GIS #GeospatialData #OpenSource #RemoteSensing #DataVisualization #MapLibre #Python #Cartography

Qiusheng Wu

15,293 views • 26 days ago

✨ Personal AI is the next computing platform. AI is shifting from something you access to something you build with, locally, at the edge, and across systems. We’re unlocking new possibilities for developers: • AMD Ryzen AI Halo, a local-first developer system, preorder starting in June, develop AI without limits on your desk • Gorgon Halo with up to 192GB unified memory, supporting 300B+ parameter models locally, run massive models locally We’re excited to partner with clem 🤗🤗, Co-founder and CEO of Hugging Face, to advance open-source AI for Ryzen AI. Our focus is seamless AI, from model to deployment. Cloud, edge, device. One continuum. Multi-agent systems, local inference at scale, open models as infrastructure. This is the next computing era 🚀

✨ Personal AI is the next computing platform. AI is shifting from something you access to something you build with, locally, at the edge, and across systems. We’re unlocking new possibilities for developers: • AMD Ryzen AI Halo, a local-first developer system, preorder starting in June, develop AI without limits on your desk • Gorgon Halo with up to 192GB unified memory, supporting 300B+ parameter models locally, run massive models locally We’re excited to partner with clem 🤗🤗, Co-founder and CEO of Hugging Face, to advance open-source AI for Ryzen AI. Our focus is seamless AI, from model to deployment. Cloud, edge, device. One continuum. Multi-agent systems, local inference at scale, open models as infrastructure. This is the next computing era 🚀

Jack Huynh

47,822 views • 1 month ago