LlamaIndex
@llamaindex.bsky.social
Build AI agents over your documents
We're listening 👂LlamaSheets is in beta and we want your feedback
Spreadsheets in the wild are messy—merged cells, broken layouts, headers spanning multiple rows. LlamaSheets (now in beta) extracts regions and tables from these files and outputs clean Parquet files you can actually use.
Spreadsheets in the wild are messy—merged cells, broken layouts, headers spanning multiple rows. LlamaSheets (now in beta) extracts regions and tables from these files and outputs clean Parquet files you can actually use.
January 2, 2026 at 8:14 PM
We're listening 👂LlamaSheets is in beta and we want your feedback
Spreadsheets in the wild are messy—merged cells, broken layouts, headers spanning multiple rows. LlamaSheets (now in beta) extracts regions and tables from these files and outputs clean Parquet files you can actually use.
Spreadsheets in the wild are messy—merged cells, broken layouts, headers spanning multiple rows. LlamaSheets (now in beta) extracts regions and tables from these files and outputs clean Parquet files you can actually use.
Agent Workflows are the fastest and most flexible way to build complex agentic systems, and we put them to the test.
January 2, 2026 at 5:08 PM
Agent Workflows are the fastest and most flexible way to build complex agentic systems, and we put them to the test.
As we wrap up 2025, we're incredibly proud of what this team shipped.
We set out to solve document AI reliability and help you develop your own task specific document agents. Take a look back on the year 2025 with us, from the launch of LlamaAgents to brand new MCP support 👇
We set out to solve document AI reliability and help you develop your own task specific document agents. Take a look back on the year 2025 with us, from the launch of LlamaAgents to brand new MCP support 👇
December 30, 2025 at 5:13 PM
As we wrap up 2025, we're incredibly proud of what this team shipped.
We set out to solve document AI reliability and help you develop your own task specific document agents. Take a look back on the year 2025 with us, from the launch of LlamaAgents to brand new MCP support 👇
We set out to solve document AI reliability and help you develop your own task specific document agents. Take a look back on the year 2025 with us, from the launch of LlamaAgents to brand new MCP support 👇
Get started with pre-built document agent templates that solve real-world problems out of the box.
We've created a collection of LlamaAgent templates through llamactl that cover the most common AI use cases, from simple document Q&A to complex invoice processing workflows:
We've created a collection of LlamaAgent templates through llamactl that cover the most common AI use cases, from simple document Q&A to complex invoice processing workflows:
December 29, 2025 at 5:03 PM
Get started with pre-built document agent templates that solve real-world problems out of the box.
We've created a collection of LlamaAgent templates through llamactl that cover the most common AI use cases, from simple document Q&A to complex invoice processing workflows:
We've created a collection of LlamaAgent templates through llamactl that cover the most common AI use cases, from simple document Q&A to complex invoice processing workflows:
Santa receives thousands of letters every year—Processing these manually takes a lot of time, so this year, we're helping him out 👇
We built an agent to automate extracting wish-list items from letters 🎅
We built an agent to automate extracting wish-list items from letters 🎅
December 23, 2025 at 7:28 PM
Santa receives thousands of letters every year—Processing these manually takes a lot of time, so this year, we're helping him out 👇
We built an agent to automate extracting wish-list items from letters 🎅
We built an agent to automate extracting wish-list items from letters 🎅
We love seeing all of the out of office emails around the holidays! So we thought we'd keep things light this week. We'll share some fun little demos, great way to get started with LlamaIndex too🎄
Today: check out this example where we build an agent that helps navigate a corrupted database!
Today: check out this example where we build an agent that helps navigate a corrupted database!
December 22, 2025 at 6:08 PM
We love seeing all of the out of office emails around the holidays! So we thought we'd keep things light this week. We'll share some fun little demos, great way to get started with LlamaIndex too🎄
Today: check out this example where we build an agent that helps navigate a corrupted database!
Today: check out this example where we build an agent that helps navigate a corrupted database!
Do you want to run coding agents safely, without damaging to your filesystem? 📁
Last week, we published a blog post and a demo showing exactly how to do this with Claude Code and AgentFS by Turso.
Last week, we published a blog post and a demo showing exactly how to do this with Claude Code and AgentFS by Turso.
December 19, 2025 at 5:13 PM
Do you want to run coding agents safely, without damaging to your filesystem? 📁
Last week, we published a blog post and a demo showing exactly how to do this with Claude Code and AgentFS by Turso.
Last week, we published a blog post and a demo showing exactly how to do this with Claude Code and AgentFS by Turso.
LlamaParse v2 is here: simpler configuration, better performance, and up to 50% cost reduction for document parsing.
We'v redesigned our approach based on user feedback to make production-ready document ingestion accessible without becoming a parsing expert.
We'v redesigned our approach based on user feedback to make production-ready document ingestion accessible without becoming a parsing expert.
December 18, 2025 at 8:16 PM
LlamaParse v2 is here: simpler configuration, better performance, and up to 50% cost reduction for document parsing.
We'v redesigned our approach based on user feedback to make production-ready document ingestion accessible without becoming a parsing expert.
We'v redesigned our approach based on user feedback to make production-ready document ingestion accessible without becoming a parsing expert.
See how The General Intelligence Company built Cofounder, an AI chief of staff turning business docs into agent-ready context.
LlamaParse ingests from sources every 30min with OCR, plus smart retrieval & lower costs vs managed RAG.
www.llamaindex.ai/customers/h...
LlamaParse ingests from sources every 30min with OCR, plus smart retrieval & lower costs vs managed RAG.
www.llamaindex.ai/customers/h...
December 17, 2025 at 8:13 PM
See how The General Intelligence Company built Cofounder, an AI chief of staff turning business docs into agent-ready context.
LlamaParse ingests from sources every 30min with OCR, plus smart retrieval & lower costs vs managed RAG.
www.llamaindex.ai/customers/h...
LlamaParse ingests from sources every 30min with OCR, plus smart retrieval & lower costs vs managed RAG.
www.llamaindex.ai/customers/h...
Ever opened a repo and thought:
“What does this codebase actually do?”
“Where did I put that file?” 🤔
You’re not alone.
With the release of Gemini 3 Flash ⚡ from Google DeepMind, we decided to build something fun (and useful): a file-system explorer agent that answers those questions for you. 🔍
“What does this codebase actually do?”
“Where did I put that file?” 🤔
You’re not alone.
With the release of Gemini 3 Flash ⚡ from Google DeepMind, we decided to build something fun (and useful): a file-system explorer agent that answers those questions for you. 🔍
December 17, 2025 at 4:10 PM
Ever opened a repo and thought:
“What does this codebase actually do?”
“Where did I put that file?” 🤔
You’re not alone.
With the release of Gemini 3 Flash ⚡ from Google DeepMind, we decided to build something fun (and useful): a file-system explorer agent that answers those questions for you. 🔍
“What does this codebase actually do?”
“Where did I put that file?” 🤔
You’re not alone.
With the release of Gemini 3 Flash ⚡ from Google DeepMind, we decided to build something fun (and useful): a file-system explorer agent that answers those questions for you. 🔍
LlamaSplit automatically separates bundled documents into distinct sections so you don't have to manually split them anymore.
December 16, 2025 at 5:27 PM
LlamaSplit automatically separates bundled documents into distinct sections so you don't have to manually split them anymore.
Secure your coding agents with virtual filesystems and better document understanding.
Building safe AI coding agents requires solving two critical challenges: filesystem access control and handling unstructured documents. We've created a solution using AgentFS, LlamaParse, and @claudeai.
Building safe AI coding agents requires solving two critical challenges: filesystem access control and handling unstructured documents. We've created a solution using AgentFS, LlamaParse, and @claudeai.
December 15, 2025 at 5:01 PM
Secure your coding agents with virtual filesystems and better document understanding.
Building safe AI coding agents requires solving two critical challenges: filesystem access control and handling unstructured documents. We've created a solution using AgentFS, LlamaParse, and @claudeai.
Building safe AI coding agents requires solving two critical challenges: filesystem access control and handling unstructured documents. We've created a solution using AgentFS, LlamaParse, and @claudeai.
LlamaSheets is our new way to handle complex, messy spreadsheets that come as many sheets disguised as one, multiple regions that provide different sets of information, and much more.
December 11, 2025 at 5:10 PM
LlamaSheets is our new way to handle complex, messy spreadsheets that come as many sheets disguised as one, multiple regions that provide different sets of information, and much more.
"ask" and you shall receive! SemTools now ships with a dedicated "ask" CLI command
- performs agentic search over documents
- combine with `parse` to create QA workflows over unstructured data
- cache your indexes with `workspaces`
Learn more: github.com/run-llama/s...
- performs agentic search over documents
- combine with `parse` to create QA workflows over unstructured data
- cache your indexes with `workspaces`
Learn more: github.com/run-llama/s...
New `ask` Command Shipping with v1.5 · run-llama semtools · Discussion #44
v1.5 is shipping with a new ask command in the CLI. This is essentially a RAG agent that will search your files and cite it's sources! # Perform agentic RAG search $ ask "What papers discu...
github.com
December 10, 2025 at 5:13 PM
"ask" and you shall receive! SemTools now ships with a dedicated "ask" CLI command
- performs agentic search over documents
- combine with `parse` to create QA workflows over unstructured data
- cache your indexes with `workspaces`
Learn more: github.com/run-llama/s...
- performs agentic search over documents
- combine with `parse` to create QA workflows over unstructured data
- cache your indexes with `workspaces`
Learn more: github.com/run-llama/s...
Split documents into distinct sections automatically with our new LlamaSplit API 📄✂️
December 9, 2025 at 10:13 PM
Split documents into distinct sections automatically with our new LlamaSplit API 📄✂️
Need to parse multiple PDFs efficiently? Learn how to use LlamaParse with async batch processing.
📁 Process entire folders of PDFs simultaneously instead of one-by-one
⚡ Use Asyncio and semaphores to control how many files parse concurrently
📁 Process entire folders of PDFs simultaneously instead of one-by-one
⚡ Use Asyncio and semaphores to control how many files parse concurrently
December 8, 2025 at 10:11 PM
Need to parse multiple PDFs efficiently? Learn how to use LlamaParse with async batch processing.
📁 Process entire folders of PDFs simultaneously instead of one-by-one
⚡ Use Asyncio and semaphores to control how many files parse concurrently
📁 Process entire folders of PDFs simultaneously instead of one-by-one
⚡ Use Asyncio and semaphores to control how many files parse concurrently
OCR benchmarks matter, so in this blog @jerryjliu0 analyzes OlmOCR-bench, one of the most influential document OCR benchmarks. TLDR: it’s an important step in the right direction, but doesn’t quite cover real-world document parsing needs.
December 4, 2025 at 5:48 PM
OCR benchmarks matter, so in this blog @jerryjliu0 analyzes OlmOCR-bench, one of the most influential document OCR benchmarks. TLDR: it’s an important step in the right direction, but doesn’t quite cover real-world document parsing needs.
Deploy production-ready agent workflows with just one click from LlamaCloud. Here's us deploying the SEC filling extract and review agent!
Our new Click-to-Deploy feature lets you build and deploy complete document processing pipelines without touching the command line:
Our new Click-to-Deploy feature lets you build and deploy complete document processing pipelines without touching the command line:
December 3, 2025 at 5:10 PM
Deploy production-ready agent workflows with just one click from LlamaCloud. Here's us deploying the SEC filling extract and review agent!
Our new Click-to-Deploy feature lets you build and deploy complete document processing pipelines without touching the command line:
Our new Click-to-Deploy feature lets you build and deploy complete document processing pipelines without touching the command line:
Calling all community members: Join us this Thursday for an office hours in our Discord server, all about LlamaAgents and LlamaSheets. This is a chance to ask anything on your mind about two of our latest releases, and learn about what's coming up next.
December 2, 2025 at 5:23 PM
Calling all community members: Join us this Thursday for an office hours in our Discord server, all about LlamaAgents and LlamaSheets. This is a chance to ask anything on your mind about two of our latest releases, and learn about what's coming up next.
Build scripts that automate spreadsheet analysis using coding agents and LlamaSheets to extract clean data from messy Excel files.
🤖 Set up coding agents like @claudeai and @cursor_ai to work with LlamaSheets-extracted parquet files and rich cell metadata
🤖 Set up coding agents like @claudeai and @cursor_ai to work with LlamaSheets-extracted parquet files and rich cell metadata
December 1, 2025 at 4:56 PM
Build scripts that automate spreadsheet analysis using coding agents and LlamaSheets to extract clean data from messy Excel files.
🤖 Set up coding agents like @claudeai and @cursor_ai to work with LlamaSheets-extracted parquet files and rich cell metadata
🤖 Set up coding agents like @claudeai and @cursor_ai to work with LlamaSheets-extracted parquet files and rich cell metadata
POV: You're building an agent and it keeps giving weird answers because your PDF parsing is broken 🫠
This is a great walkthrough by Sudarshan Koirala showing exactly how to use LlamaParse to fix this—from basic setup through advanced configs.
youtu.be/mUHPPBbumIs...
The video walks through:
This is a great walkthrough by Sudarshan Koirala showing exactly how to use LlamaParse to fix this—from basic setup through advanced configs.
youtu.be/mUHPPBbumIs...
The video walks through:
LlamaParse Tutorial: Transform Complex Documents into LLM-Ready Data for AI Applications
Learn how to transform messy PDFs into clean, AI-ready data using LlamaParse, the industry-leading document parsing platform trusted by 200k+ developers. Thi...
www.youtube.com
November 28, 2025 at 5:04 PM
POV: You're building an agent and it keeps giving weird answers because your PDF parsing is broken 🫠
This is a great walkthrough by Sudarshan Koirala showing exactly how to use LlamaParse to fix this—from basic setup through advanced configs.
youtu.be/mUHPPBbumIs...
The video walks through:
This is a great walkthrough by Sudarshan Koirala showing exactly how to use LlamaParse to fix this—from basic setup through advanced configs.
youtu.be/mUHPPBbumIs...
The video walks through:
Stop losing 80% of your data when extracting from long documents with repeating entities like catalogs, tables, and lists.
November 26, 2025 at 5:14 PM
Stop losing 80% of your data when extracting from long documents with repeating entities like catalogs, tables, and lists.
Announcing LlamaSheets in beta 🔥
Transform your messy spreadsheets into AI-ready data with our newest LlamaCloud API 📊
LlamaSheets (in beta) is a specialized API that automatically structures complex spreadsheets while preserving their semantic meaning and hierarchical context.
Transform your messy spreadsheets into AI-ready data with our newest LlamaCloud API 📊
LlamaSheets (in beta) is a specialized API that automatically structures complex spreadsheets while preserving their semantic meaning and hierarchical context.
November 25, 2025 at 4:53 PM
Announcing LlamaSheets in beta 🔥
Transform your messy spreadsheets into AI-ready data with our newest LlamaCloud API 📊
LlamaSheets (in beta) is a specialized API that automatically structures complex spreadsheets while preserving their semantic meaning and hierarchical context.
Transform your messy spreadsheets into AI-ready data with our newest LlamaCloud API 📊
LlamaSheets (in beta) is a specialized API that automatically structures complex spreadsheets while preserving their semantic meaning and hierarchical context.
Have a LlamaAgent organize your study material: meet StudyLlama, a web app that uses LlamaAgents to help you organize and gather insights from your notes and papers!
How it works:
How it works:
November 24, 2025 at 5:25 PM
Have a LlamaAgent organize your study material: meet StudyLlama, a web app that uses LlamaAgents to help you organize and gather insights from your notes and papers!
How it works:
How it works:
Extract data from table rows with precision using LlamaExtract's Table Row mode 📊
LlamaExtract now offers granular extraction capabilities that go beyond document-level processing, giving you powerful control over how your schema is applied:
LlamaExtract now offers granular extraction capabilities that go beyond document-level processing, giving you powerful control over how your schema is applied:
November 21, 2025 at 6:01 PM
Extract data from table rows with precision using LlamaExtract's Table Row mode 📊
LlamaExtract now offers granular extraction capabilities that go beyond document-level processing, giving you powerful control over how your schema is applied:
LlamaExtract now offers granular extraction capabilities that go beyond document-level processing, giving you powerful control over how your schema is applied: