Loading video...

Video Failed to Load

Go Home

We've created a comprehensive Retrieval Harness for modern agentic retrieval in 2026. The harness provides a persistent data pipeline that can connect to a data source, index and update a large knowledge base, and expose a broad set of tools akin to filesystem operations (semantic/keyword search, regex grep, file...

jerryjliu0's profile picture

Jerry Liu

81,661 subscribers

57,000 views • 1 month ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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:
0:53

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 • 1 month ago

Semantic search alone doesn't cut it. Neither does brute-force grep. Agents need both. Today we're shipping the Retrieval Harness in LlamaParse Index: semantic search, server-side grep, and file-level navigation working together in a single agent reasoning loop. 🦙🌤️ Grep a file, list what's in an index, read past a chunk boundary, run hybrid search with reranking — all as native agent tools. Now in beta across all paid tiers. Full breakdown in the blog 👇 Learn More:
0:53

Semantic search alone doesn't cut it. Neither does brute-force grep. Agents need both. Today we're shipping the Retrieval Harness in LlamaParse Index: semantic search, server-side grep, and file-level navigation working together in a single agent reasoning loop. 🦙🌤️ Grep a file, list what's in an index, read past a chunk boundary, run hybrid search with reranking — all as native agent tools. Now in beta across all paid tiers. Full breakdown in the blog 👇 Learn More:

LlamaIndex 🦙

29,181 views • 1 month ago

Give Claude Code a semantic filesystem 🗃️🛠️ Giving Claude Code access to the right CLI tools over your filesystem turns it into a general agent capable of automating far more knowledge work beyond code - it can do dynamic financial/legal/medical/technical/backoffice analysis over any subset of documents. With our latest release of semtools 💫, you can now manually or *agentically* create a persistent workspace over any subset of files. This gives Claude Code the ability to get blazing-fast, local semantic search over any data, while still allowing it to chain with commands like grep/cat/etc. so that it can load in dynamic context instead of naive top-k vector search. The coding agent can dynamically index data and use those indexes, instead of having to rebuild it every time. So you get the benefits of fast search along with agentic reasoning over CLI tools mentioned above. Come check it out!
0:38

Give Claude Code a semantic filesystem 🗃️🛠️ Giving Claude Code access to the right CLI tools over your filesystem turns it into a general agent capable of automating far more knowledge work beyond code - it can do dynamic financial/legal/medical/technical/backoffice analysis over any subset of documents. With our latest release of semtools 💫, you can now manually or *agentically* create a persistent workspace over any subset of files. This gives Claude Code the ability to get blazing-fast, local semantic search over any data, while still allowing it to chain with commands like grep/cat/etc. so that it can load in dynamic context instead of naive top-k vector search. The coding agent can dynamically index data and use those indexes, instead of having to rebuild it every time. So you get the benefits of fast search along with agentic reasoning over CLI tools mentioned above. Come check it out!

Jerry Liu

77,373 views • 10 months ago

Knowledge graphs for representing information are unbeatable. After this, you will never build a RAG system without knowledge graphs. It will take you five lines of code to build a knowledge graph with your data. I recorded a video to show you how you can do this. I used Cognee, an open-source library that outperforms any basic vector search approach in terms of retrieval relevance. They are collaborating with me on this post. Cognee is: • Easy to use • Reduces hallucinations • Open-source Here is a link to the repository: They also offer a comprehensive platform and UI with Python notebooks you can utilize to manage your data. Here is the link:
6:02

Knowledge graphs for representing information are unbeatable. After this, you will never build a RAG system without knowledge graphs. It will take you five lines of code to build a knowledge graph with your data. I recorded a video to show you how you can do this. I used Cognee, an open-source library that outperforms any basic vector search approach in terms of retrieval relevance. They are collaborating with me on this post. Cognee is: • Easy to use • Reduces hallucinations • Open-source Here is a link to the repository: They also offer a comprehensive platform and UI with Python notebooks you can utilize to manage your data. Here is the link:

Santiago

126,434 views • 10 months ago

Build better RAG by letting a team of agents extract and connect your reference materials into a knowledge graph. Our new short course, “Agentic Knowledge Graph Construction,” taught by Neo4j Innovation Lead Andreas Kollegger, shows you how. Knowledge graphs are an important way to store information accurately but they are a lot of work to build manually. In this course you’ll learn how to build a team of agents that turn data– in this case product reviews and invoices from suppliers–into structured graphs of entities and relationships for RAG. Learn how agents can automatically handle the time-consuming work of building graphs — extracting entities and relationships (e.g., Product "contains" Assembly, Part "supplied_by" Supplier, Customer review "mentions" Product), deduplicating them, fact-checking them, and committing them to a graph database — so your retrieval system can find right information to generate accurate output. For example, you can use agents to help trace customer complaints directly to specific suppliers, manufacturing processes, and product hierarchies, thus turning fragmented information into queryable business intelligence. Skills you’ll gain: - Build, store, and access knowledge graphs using the Neo4j graph database - Build multi-agent systems using Google’s Agent Development Kit (ADK) - Set up a loop of agentic workflows to propose and refine a graph schema through fact-checking - Connect agent-generated graphs of unstructured and structured data into a unified knowledge graph This course gets into the practicum of why knowledge graphs give more accurate information retrieval than vector search alone, especially for high-stakes applications where precision matters more than fuzzy similarity matching. Sign up here:
2:26

Build better RAG by letting a team of agents extract and connect your reference materials into a knowledge graph. Our new short course, “Agentic Knowledge Graph Construction,” taught by Neo4j Innovation Lead Andreas Kollegger, shows you how. Knowledge graphs are an important way to store information accurately but they are a lot of work to build manually. In this course you’ll learn how to build a team of agents that turn data– in this case product reviews and invoices from suppliers–into structured graphs of entities and relationships for RAG. Learn how agents can automatically handle the time-consuming work of building graphs — extracting entities and relationships (e.g., Product "contains" Assembly, Part "supplied_by" Supplier, Customer review "mentions" Product), deduplicating them, fact-checking them, and committing them to a graph database — so your retrieval system can find right information to generate accurate output. For example, you can use agents to help trace customer complaints directly to specific suppliers, manufacturing processes, and product hierarchies, thus turning fragmented information into queryable business intelligence. Skills you’ll gain: - Build, store, and access knowledge graphs using the Neo4j graph database - Build multi-agent systems using Google’s Agent Development Kit (ADK) - Set up a loop of agentic workflows to propose and refine a graph schema through fact-checking - Connect agent-generated graphs of unstructured and structured data into a unified knowledge graph This course gets into the practicum of why knowledge graphs give more accurate information retrieval than vector search alone, especially for high-stakes applications where precision matters more than fuzzy similarity matching. Sign up here:

Andrew Ng

168,153 views • 11 months ago

i built vault, a self-improving knowledge base that can index your entire life (personal mini agi) it updates while you sleep, supports 50+ integrations like notion, snowflake, datadog, and more when you connect a source (like stripe), all the data becomes a filesystem built for both agents and humans, so you can interact with it through either cli or ui
2:30

i built vault, a self-improving knowledge base that can index your entire life (personal mini agi) it updates while you sleep, supports 50+ integrations like notion, snowflake, datadog, and more when you connect a source (like stripe), all the data becomes a filesystem built for both agents and humans, so you can interact with it through either cli or ui

Arlan

28,737 views • 4 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.
3:33

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

40,625 views • 1 year ago

We shipped big changes for Cloudflare Developers AI Search! Every agent needs search and it shouldn't take a week to set up. AI Search is the search primitive for your agents. Create an instance, upload your data, and search it. Comes with hybrid retrieval with vector and BM25.
0:24

We shipped big changes for Cloudflare Developers AI Search! Every agent needs search and it shouldn't take a week to set up. AI Search is the search primitive for your agents. Create an instance, upload your data, and search it. Comes with hybrid retrieval with vector and BM25.

Anni Wang

12,975 views • 4 months ago

Our new short course, Knowledge Graphs for RAG, is now available! Knowledge graphs are a data structure that is great at capturing complex relationships between data of multiple types. By enabling more sophisticated retrieval of text than similarity search alone, knowledge graphs can improve the context you pass to the LLM and the performance of your RAG applications. In this course, taught by Andreas Kollegger of Neo4j, you’ll - Explore how knowledge graphs work by building a graph of public financial documents from scratch - Learn to write queries that retrieve text and data from the graph and use it to enhance the context you pass to an LLM chatbot - Combine a knowledge graph with a question-answer chain to build better RAG-powered chat systems Sign up here!
3:46

Our new short course, Knowledge Graphs for RAG, is now available! Knowledge graphs are a data structure that is great at capturing complex relationships between data of multiple types. By enabling more sophisticated retrieval of text than similarity search alone, knowledge graphs can improve the context you pass to the LLM and the performance of your RAG applications. In this course, taught by Andreas Kollegger of Neo4j, you’ll - Explore how knowledge graphs work by building a graph of public financial documents from scratch - Learn to write queries that retrieve text and data from the graph and use it to enhance the context you pass to an LLM chatbot - Combine a knowledge graph with a question-answer chain to build better RAG-powered chat systems Sign up here!

Andrew Ng

244,403 views • 2 years ago

ChatGPT connecting to external data sources offers a glimpse into what AI interoperability looks like. Ask any question in ChatGPT and it can now pull data from Box. The future of AI is AI Agents that can access your systems and data to complete any task for you.
0:43

ChatGPT connecting to external data sources offers a glimpse into what AI interoperability looks like. Ask any question in ChatGPT and it can now pull data from Box. The future of AI is AI Agents that can access your systems and data to complete any task for you.

Aaron Levie

57,745 views • 1 year ago

With various LLMs and AI agents being deployed, Nodepay’s infrastructure for real time data retrieval is crucial for delivering up-to-date insights for any inquiry, action or task instantly. Envision a world where any model or AI agent can access real time data ensuring the most precise results to give you a competitive advantage. This is Node Search - Nodepay’s decentralized AI answer engine that makes this possible, powered by 1.8M global user nodes and $NC Nodecoin
0:24

With various LLMs and AI agents being deployed, Nodepay’s infrastructure for real time data retrieval is crucial for delivering up-to-date insights for any inquiry, action or task instantly. Envision a world where any model or AI agent can access real time data ensuring the most precise results to give you a competitive advantage. This is Node Search - Nodepay’s decentralized AI answer engine that makes this possible, powered by 1.8M global user nodes and $NC Nodecoin

Nodepay

183,603 views • 1 year 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:
0:33

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 • 5 months ago

The $KLED Enterprise Portal Full Demo – Search and License Any Data in Seconds: For the last 6 weeks, we've had thousands of users sign up for the first data marketplace. We've paid out over $200,000 to them for uploading their camera rolls, homework, dashcam footage, etc. We've now amassed petabytes and petabytes of data from these users and large enterprises, and tagged it all with rich metadata. Now OpenAI, xAI, Google AI, or any other large lab can easily search and license that data using our newly completed enterprise portal. If you're a large lab, send me a DM and get access to the largest, never-before-seen consumer dataset on the planet. This is the biggest update for Kled since launch.
4:40

The $KLED Enterprise Portal Full Demo – Search and License Any Data in Seconds: For the last 6 weeks, we've had thousands of users sign up for the first data marketplace. We've paid out over $200,000 to them for uploading their camera rolls, homework, dashcam footage, etc. We've now amassed petabytes and petabytes of data from these users and large enterprises, and tagged it all with rich metadata. Now OpenAI, xAI, Google AI, or any other large lab can easily search and license that data using our newly completed enterprise portal. If you're a large lab, send me a DM and get access to the largest, never-before-seen consumer dataset on the planet. This is the biggest update for Kled since launch.

Avi Patel

91,697 views • 1 year ago

Knowledge graphs are infinitely better than vector search for building the memory of AI agents. With five lines of code, you can build a knowledge graph with your data. When you see the results, you'll never go back to vector-mediocrity-land. Here is a quick video:
9:27

Knowledge graphs are infinitely better than vector search for building the memory of AI agents. With five lines of code, you can build a knowledge graph with your data. When you see the results, you'll never go back to vector-mediocrity-land. Here is a quick video:

Santiago

398,229 views • 1 year ago

This is probably the biggest news yet in software going headless, and will bring knowledge work agents to the masses. The new ChatGPT agents have access to any of the tools and data you want to work with, with complete coding and tool use available to them. Here's an example of a custom sales assistant agent uses Box as a knowledge source for accessing enterprise content securely to answer questions and generate new content on the fly. The workflows can obviously vastly far more complex as the agent can use any of the tools within Box available via MCP and CLI. This precisely what agents will start to look like for knowledge work. You'll be able to spin them up in the foreground or background to help augment work. Big opportunity right now for headless platforms, and for all the new builders and designers of these agents in the enterprise.
1:06

This is probably the biggest news yet in software going headless, and will bring knowledge work agents to the masses. The new ChatGPT agents have access to any of the tools and data you want to work with, with complete coding and tool use available to them. Here's an example of a custom sales assistant agent uses Box as a knowledge source for accessing enterprise content securely to answer questions and generate new content on the fly. The workflows can obviously vastly far more complex as the agent can use any of the tools within Box available via MCP and CLI. This precisely what agents will start to look like for knowledge work. You'll be able to spin them up in the foreground or background to help augment work. Big opportunity right now for headless platforms, and for all the new builders and designers of these agents in the enterprise.

Aaron Levie

420,133 views • 4 months ago

Today we announced the new Einstein Copilot Search and Salesforce Vector Database in Data Cloud to power semantic search and retrieval augmented generation. This will enhance Einstein Copilot's ability to understand, generate outputs, and automate actions across a wide variety of use cases, contexts, and data/content types. LLMs can't be relied on to recall specific data they were trained on, so the way to make them work in the enterprise, where accuracy is paramount, is to feed them with the right data using hybrid keyword and vector search-powered RAG. By bringing all this seamlessly into our apps and Einstein Copilot UX as well as Hyperforce cloud infrastructure, we can offer high performance, low latency, addressing data privacy, security, and residency requirements🌟
3:06

Today we announced the new Einstein Copilot Search and Salesforce Vector Database in Data Cloud to power semantic search and retrieval augmented generation. This will enhance Einstein Copilot's ability to understand, generate outputs, and automate actions across a wide variety of use cases, contexts, and data/content types. LLMs can't be relied on to recall specific data they were trained on, so the way to make them work in the enterprise, where accuracy is paramount, is to feed them with the right data using hybrid keyword and vector search-powered RAG. By bringing all this seamlessly into our apps and Einstein Copilot UX as well as Hyperforce cloud infrastructure, we can offer high performance, low latency, addressing data privacy, security, and residency requirements🌟

Clara Shih

49,634 views • 2 years ago

Another example of the power of headless software with agents. With Claude Tag, you can give Claude access to any corporate files in Box that you can interact with from Slack. Now all of your enterprise content becomes a portable knowledge base.
0:36

Another example of the power of headless software with agents. With Claude Tag, you can give Claude access to any corporate files in Box that you can interact with from Slack. Now all of your enterprise content becomes a portable knowledge base.

Aaron Levie

74,286 views • 1 month ago

Announcing Fire Enrich V2 - our open-source Clay-like data enrichment platform you can run with any LLM! Upload a CSV, spawn sub-agents using @Firecrawl_dev's /search and /scrape to find real-time company data, funding, or any data point. Fork the example today 👇
0:30

Announcing Fire Enrich V2 - our open-source Clay-like data enrichment platform you can run with any LLM! Upload a CSV, spawn sub-agents using @Firecrawl_dev's /search and /scrape to find real-time company data, funding, or any data point. Fork the example today 👇

Nicolas Camara

43,766 views • 10 months ago

🚀 The team at Google DeepMind just released Gemini Embedding 2, a frontier embeddings model with 3072 dimensions and state-of-the-art semantic quality. 👩‍💻 We built a demo showing how to integrate it across the LlamaIndex ecosystem, from LlamaParse to LlamaAgents: 𝗮𝘂𝗱𝗶𝗼-𝗸𝗯, a knowledge base for your audio notes. With audio-kb, you can: 🔹 Upload an MP3 or record directly from your terminal 🔹 LlamaParse extracts the transcript from the audio 🔹 Gemini Embedding 2 generates embeddings 🔹 Metadata + vectors are stored in SurrealDB and indexed with HNSW 🔍 Once ingested, you can search all your audio notes directly from the terminal. 🎙️ Perfect for turning voice memos, meetings, or lectures into a searchable knowledge base. 📖 Full blog: 💻 GitHub: ⚡ Try LlamaParse:
0:21

🚀 The team at Google DeepMind just released Gemini Embedding 2, a frontier embeddings model with 3072 dimensions and state-of-the-art semantic quality. 👩‍💻 We built a demo showing how to integrate it across the LlamaIndex ecosystem, from LlamaParse to LlamaAgents: 𝗮𝘂𝗱𝗶𝗼-𝗸𝗯, a knowledge base for your audio notes. With audio-kb, you can: 🔹 Upload an MP3 or record directly from your terminal 🔹 LlamaParse extracts the transcript from the audio 🔹 Gemini Embedding 2 generates embeddings 🔹 Metadata + vectors are stored in SurrealDB and indexed with HNSW 🔍 Once ingested, you can search all your audio notes directly from the terminal. 🎙️ Perfect for turning voice memos, meetings, or lectures into a searchable knowledge base. 📖 Full blog: 💻 GitHub: ⚡ Try LlamaParse:

LlamaIndex 🦙

34,945 views • 5 months ago