LlamaIndex 🦙 @llama_index Twitter profile

Pinned Tweet

LlamaIndex 🦙

2 months

We’re excited to officially launch LlamaParse, the first genAI-native document parsing solution. Not only is it better at parsing out images/tables/charts 📊📈 than virtually every other parser, it is now steerable through natural language instructions - output the document in…

29

120

726

Last Seen Profiles

@cfvanguard_en

@boobataebubble

@digital_bathtub

@cnn_co_jp

@eddiehallWSM

@PinkelsPink

@dgn_893x

@rukasstar

@carolaam

@hinano_tachiba7

@circo_voador

@AcousticDarvin

@bibiloni

@duosec

@determinantfin

@pjbrown_III

@amourkiya_

@EEPA_EU

@diloyunu

@Dillon_Arkansas

@VedantThak83719

@wilkmilkk

@Tromp1Dona76652

@ArtByHornbuckle

@basquetplus

@hijabjilbab1

@betsyfigtree

@chillichelli

@binarydances

@well3official

@sugarsyrup31

@drunkhys

@fineeasssbri

@LennoxLewis

@ankarakulisi06

@Jkeown4

LlamaIndex 🦙

@llama_index

5 months

Parsing tables in PDFs is a super important RAG use case. We found that using the recent Table Transformer model ( @deepsmock ) combined with GPT-4V gives you superpowers 💪 The Table Transformer model extracts tables from PDFs using object detection 📊 We have a full notebook…

15

185

1K

LlamaIndex 🦙

@llama_index

4 months

Advanced RAG Cheat Sheet + Recipes 🧑‍🍳 We’re publishing a comprehensive diagram outlining all the different components of advanced RAG, the pain points they solve, and links to LlamaIndex resources. Here’s some core concepts that motivate advanced RAGs: 💡 Success metric for RAG…

13

218

931

LlamaIndex 🦙

@llama_index

6 months

Introducing MechGPT 🦾🤖 This project by @ProfBuehlerMIT is one of the coolest use cases of 1) fine-tuning an LLM, and 2) generating a knowledge graph that we’ve seen (powered by @llama_index 🦙). The end result is a system capable of understanding a diverse range of scientific…

15

179

915

LlamaIndex 🦙

@llama_index

3 months

📖 Complete Architecture for Building Enterprise RAG 🛠️ This architecture by @rungalileo provides a reference on both the algorithmic and system-level components needed to build production RAG 💫. There’s a lot in here 👇: It covers everything from the following broad…

14

185

915

LlamaIndex 🦙

@llama_index

5 months

Running @MistralAI 's Mixtral 8x7b on your laptop is now a one-liner! Check out this post in which we show you how to use @OLLAMA with LlamaIndex to create a completely local, open-source retrieval-augmented generation app complete with an API: Bonus: see…

9

146

807

LlamaIndex 🦙

@llama_index

3 months

Injecting Knowledge Graphs in RAG A common question we’ve heard from users is how to best include knowledge graphs (KGs) in a RAG pipeline. This is a fantastic post by @chiajy2000 that covers graph-related techniques across different stages - see diagram below for stages:…

7

179

840

LlamaIndex 🦙

@llama_index

5 months

RAG over Complex PDFs 📑 The issue with basic RAG strategies (chunking, top-k), is that they’re fine with plain .txt essays, but they do terribly over complex documents - w/ embedded objects like tables, diagrams 📊, and hierarchical sections 🪆 You can solve this with…

14

141

771

LlamaIndex 🦙

@llama_index

6 months

Introducing RAGs, a @streamlit app that allows you to create and customize your own RAG agent and then use it over your own data, all with natural language 🔥 Directly inspired by @OpenAI GPTs, you can converse with an agent to help you do search/retrieval over any data you…

12

160

734

LlamaIndex 🦙

@llama_index

3 months

12 RAG Pain Points and Proposed Solutions 💡 Building production RAG is hard. @wenqi_glantz compiled a list of 12 (!!) RAG pain points + added a full solution list to each one with @llama_index abstractions 🔥 We’ve put out cheatsheets before, but this one is much more…

8

182

742

LlamaIndex 🦙

@llama_index

5 months

Introducing RAGs v3 🌟: Build a RAG bot that can also search the web 🌐, to find answers that aren’t immediately in its corpus. Do this all in natural language, not code! 💬 Get a better experience than ChatGPT + Bing ⚡️ We used our integration with @metaphorsystems - a search…

16

116

677

LlamaIndex 🦙

@llama_index

4 months

A Comprehensive Survey of Advanced RAG 📖 If you’re looking for a one-stop shop for advanced RAG concepts, look no further 💫 @ivanilin9 details all the key concepts in this blog post 📚, and each section highlights @llama_index resources/guides that you can check out. Here…

6

119

674

LlamaIndex 🦙

@llama_index

3 months

Introducing RAG CLI 🧑‍💻🔎 - a dead-simple command-line tool that allows you to RAG literally any file on your local machine. Index any files including glob patterns, such as `$ llamaindex-cli rag --files "./docs/**/*.rst”` To search simply do `$ llamaindex-cli rag --question…

14

114

659

LlamaIndex 🦙

@llama_index

30 days

There’s thousands of RAG techniques and tutorials, but which ones perform the best? ARAGOG by Matous Eibich is one of the most comprehensive evaluation surveys on advanced RAG techniques, testing everything from “classic vector database” to reranking ( @cohere , LLM) to MMR to…

7

163

669

LlamaIndex 🦙

@llama_index

5 months

We’ve created SEVEN advanced retrieval LlamaPacks as templates to help you build advanced RAG 🔥 It’s never been easier; instead of following a notebook, you can now try each technique in ~1 line of code ⚡️ Here’s the full set of techniques below: ⭐️ Hybrid Fusion (vector +…

15

116

654

LlamaIndex 🦙

@llama_index

4 months

Full-stack RAG Starter Pack 🔎📦 - with @MongoDB , Flask, @render , and @nextjs It’s one thing to build RAG in a notebook, it’s another thing to build a full-stack chatbot web app, with storage, backend/frontend, and deployed to the web 🌐 Our mongodb-demo repo by @seldo is an…

8

103

547

LlamaIndex 🦙

@llama_index

6 months

We’re excited to feature NewsGPT (by timho102003) 📰🧠 - a production-grade news aggregator augmented with LLM capabilities. ✅ Daily pipeline of reliable news sources ✅ Tailored News Recommendations ✅ For any given article, chat with related articles Best of all, it’s fully…

8

126

616

LlamaIndex 🦙

@llama_index

6 months

Emotion Prompting ❤️‍🩹 The recent EmotionPrompt paper (Li et al.) shows that you can improve task performance across a ton of LLMs by simply adding statements like “This is very important to my career” Easily try it out + benchmark it yourself! 👇 We’ve added a full cookbook 🧑…

17

122

589

LlamaIndex 🦙

@llama_index

2 months

A good PDF parser that can understand embedded tables and figures is a necessary condition for building good RAG. Most PDF parsers struggle with representing tables, which sends a confusing representation to the LLM, leading to wrong answers. That’s where LlamaParse comes in.…

Jerry Liu

@jerryjliu0

3 months

I’ve talked about how a big step towards better RAG, no matter what downstream model you’re using (GPT-4, Mistral, Gemini 1.5 Pro, etc.) is to just have a really nice PDF parser. It’s so important because a good parser unlocks way more interesting indexing/retrieval strategies…

23

141

878

18

124

597

LlamaIndex 🦙

@llama_index

8 months

We’re excited to open-source - a full-stack, production-ready RAG app! 🦙🏦 Supports streaming, reasoning steps, citations, intuitive UI This can save you weeks/months of hard work in trying to build a prod LLM app from scratch🔥

10

102

568

LlamaIndex 🦙

@llama_index

6 months

✨ Big news! ✨ Today we're happy to release create-llama, a simple to use command line tool that generates a full-stack LlamaIndex application for you, with your choice of TypeScript or Python as backend! Get started chatting with your data in just a few seconds. All you need…

11

95

564

LlamaIndex 🦙

@llama_index

3 months

Introducing a Short Course Series on Advanced RAG Orchestration 🪄🤖 As an AI engineer, it can be daunting to dive into how to build high-quality, advanced RAG yourself - there’s literally hundreds of options at every stage of the pipeline. Easily stitch together custom modules…

5

80

557

LlamaIndex 🦙

@llama_index

2 months

A Comprehensive Guide to RAG and Agents with @MistralAI 🔥 Whether or not you’re at the @SHACK15sf hackathon this weekend, we’ve created a comprehensive set of resources on how you can use @llama_index , @MistralAI , and (optionally) LlamaParse to build advanced RAG and agents:…

9

111

542

LlamaIndex 🦙

@llama_index

2 months

RAG over Complex PDFs V2 📑 If you’re looking for a definitive tutorial on solving RAG over your messy, complicated PDFs (with messy formatting, fonts, tables, charts), this is the tutorial for you. In these settings, naive RAG doesn’t work ⛔️. This video by @AIMakerspace is a…

7

97

550

LlamaIndex 🦙

@llama_index

23 days

We’re excited to release a brand-new tutorial series 💫 : an introduction to agents and tools 🎬🤖 There’s a lot of well-deserved interest around agents, but there’s also a lot of ambiguity about core agent interfaces and applications. This short course is the perfect beginner…

5

98

550

LlamaIndex 🦙

@llama_index

2 months

Build an AI Browser Copilot in ~150 lines of code 🤖🌐 We’re excited to feature LaVague, a project by @dhuynh95 that uses RAG with local embeddings + Mixtral ( @MistralAI + @huggingface ) to generate Selenium code through a user query. The result: an agent that can perform browser…

6

110

536

LlamaIndex 🦙

@llama_index

1 month

RAFT - Retrieval Augmented Fine Tuning 🔥 RAFT offers a method to fine-tune pre-trained LLMs for specific domain RAG settings. Conventional RAG is like an open-book exam, retrieving documents from an index to provide context for answering queries. This makes it more effective…

14

113

537

LlamaIndex 🦙

@llama_index

18 days

DREAM - a Distributed RAG Experimentation Framework 🧑‍🔬 Building RAG comes with a lot of knobs that you need to tune, and it’s important that you setup the right experimentation infrastructure to build production RAG. This project by Aishwarya Prabhat provides a comprehensive…

13

118

534

LlamaIndex 🦙

@llama_index

6 months

7B LLMs are getting better and better. Zephyr-7b-beta ( @huggingface ) was just released. We ran it on @llama_index RAG/agent tasks and found it’s the only 7B LLM that can handle ReAct agent tasks over data 💫 Guide + benchmark 👇: Full credits @Haotianzh

8

106

517

LlamaIndex 🦙

@llama_index

4 months

In collaboration with the @googledevs team, we’re excited to release the most comprehensive workshop on building with Google Gemini - in both the advanced RAG and multi-modal settings! 🌟 Advanced RAG: use the Google semantic retriever, with the Google AQA model (with…

3

112

517

LlamaIndex 🦙

@llama_index

2 months

RAPTOR - a new tree-structured advanced RAG technique 🔥 A big issue with naive top-k RAG is that it retrieves low-level details best suited at answering questions over specific facts in the document. But it struggles with any questions over higher-level context. RAPTOR…

13

90

513

LlamaIndex 🦙

@llama_index

4 months

A Five Part Series to Building a Full-Stack RAG Chatbot This is one of the most comprehensive tutorials we’ve seen to help you build RAG end-to-end (algorithms, frontend, backend) - and it’s still ongoing! Marco Bertelli has published a series of blog posts taking you through…

28

90

482

LlamaIndex 🦙

@llama_index

4 months

Instead of using a global fixed chunk size for RAG, try splitting based on the semantics of the text ✂️💡 @GregKamradt proposed a super simple method to split long documents based on embedding similarity between sentences, with an auto-tuned threshold. If there’s sufficiently…

Greg Kamradt

@GregKamradt

4 months

5 Levels Of Text Splitting: Semantic Splitting Goal: Use embeddings to find chunks in our raw text Experimental method using embedding distances between sequential sentences to tease out 'breakpoints' If we find a good breakpoint, make a chunk Check out the full video on YT

27

54

413

8

84

502

LlamaIndex 🦙

@llama_index

5 months

GPT-4 is a popular choice for LLM evals, but it’s closed-source, subject to version changes, and super expensive 💸 We’re excited to feature Prometheus by @seungonekim et al., a fully-open source 13B LLM that is fine-tuned to be on par with GPT-4 eval capabilities 🔥…

9

87

472

LlamaIndex 🦙

@llama_index

1 month

Building Multi-Document Agents with @llama_index RAG with simple questions over a small set of data is easy, but a key goal for @llama_index is to solve complex QA over many docs. @andysingal presents an excellent overview of our multi-document agents. Instead of treating each…

4

105

503

LlamaIndex 🦙

@llama_index

5 months

Fully Local RAG Pipeline with 1 line of code 🔐 We've created a LlamaPack that gives you an out-of-the-box template for a RAG pipeline with fully local LLM / embedding models: ✅ Zephyr-7b as the LLM ( @huggingface ) ✅ bge-base as the embedding model Use the template on its own…

7

77

499

LlamaIndex 🦙

@llama_index

6 months

A common problem we’ve noticed with open-source LLMs (e.g. llama2) is they’re not great at outputting structured data. Fine-tuning can help!💡 We’ve successfully created created a process to get llama2-7b to output structured Pydantic objects 🔥. We have an easy-to-follow…

10

73

492

LlamaIndex 🦙

@llama_index

5 months

Introducing RAGs v5 - build a multi-modal RAG bot over your data with natural language, and view both text and image sources! 🖼️📝 In our latest release, you can index a folder of images+text in “multi-modal mode”. 1️⃣ Tell the agent about your folder of data 2️⃣ toggle our beta…

8

102

491

LlamaIndex 🦙

@llama_index

7 months

Want to save time and money over calling OpenAI to get embeddings for all the text in your RAG pipeline? Now you can run a super-fast local server to generate them yourself!

GitHub - huggingface/text-embeddings-inference: A blazing fast inference solution for text embedd...

A blazing fast inference solution for text embeddings models - huggingface/text-embeddings-inference

github.com

2

73

484

LlamaIndex 🦙

@llama_index

4 months

Automated LeetCode Crash Course with @llama_index + @OpenAI + @scikit_learn + networkx 🧑‍🏫 @kevinchwong created a fantastic project that indexes @LeetCode questions and clusters them into training materials per day to help any software engineer with technical interviews. It…

3

81

469

LlamaIndex 🦙

@llama_index

1 year

You can now `pip install llama-agi`! 🛠️🧠 Get access to a core set of abstractions/tools that allow you to easily build #babyAGI / #AutoGPT -like capabilities yourself 🔥 Example notebook here, it’s super easy to get started:

Llama AGI Demo

Colaboratory notebook

colab.research.google.com

7

112

465

LlamaIndex 🦙

@llama_index

5 months

Here's a fantastic article by @helloiamleonie outlining 12 strategies for tuning your RAG system: Ingestion 1. Data Cleaning 2. Chunking 3. Embedding models 4. Metadata 5. Multi-indexing 6. Indexing algorithms Inference 7. Query Transformations 8. Retrieval Parameters 9.…

4

96

467

LlamaIndex 🦙

@llama_index

5 months

We’re excited to introduce RAGs v2 - build, customize, and use multiple ChatGPTs over your data, all with natural language 💬 A huge upgrade vs. the initial launch: 💫 Easily create multiple RAG pipelines and save them 💫 Easily swap between and customize each one (e.g. over…

9

98

462

LlamaIndex 🦙

@llama_index

3 months

One-Click RAG Pipeline Generator We’re excited to feature RAGArch by @HarshadSurya1c , which provides a comprehensive @streamlit UI to pick and choose all the core components of a RAG system: LLM, embedding model, chunking, vector store. In one click you will 1) create a fully…

7

93

463

LlamaIndex 🦙

@llama_index

2 months

Here’s a cool chunking trick to improve RAG retrieval performance - Sub-Document Summaries 💡 We all know naive chunking == bad RAG performance. An issue is each chunk lacks global concept awareness. A common remedy to this problem is to inject document summaries as metadata to…

8

94

462

LlamaIndex 🦙

@llama_index

5 months

Advanced RAG Cheat Sheet 📖 There’s a lot of different ways to create “advanced RAG”, but it helps to think when and what to apply each technique 💡 ❓When should I try re-ranking? Changing chunk sizes? Fine-tuning embeddings? ❓When should I try adding an agent? ❓What are ways…

11

78

457

LlamaIndex 🦙

@llama_index

1 month

This is an excellent tutorial by @mesudarshan showing you how to build advanced PDF RAG with LlamaParse and purely local models for embedding, LLMs, and reranking ( @GroqInc and FastEmbed by @qdrant_engine , flag-embedding-reranker) Having a good extraction step is super important…

7

100

458

LlamaIndex 🦙

@llama_index

2 months

A Comprehensive Guide to Semantic Chunking for RAG 📑 A better approach to naive sentence/token chunking is to group semantically similar information, leading to better retrieval + more complete synthesis. This post by Florian June is a comprehensive guide towards semantic…

4

75

457

LlamaIndex 🦙

@llama_index

2 months

Build a Live RAG Chatbot from Google Drive / Sharepoint ♻️ Excited to feature a @streamlit blog by Anup Surendran and Berke Can Rizai on building a QA system over a file storage system that is dynamically changing. Using @pathway_com you can setup a a live ETL pipeline to…

7

98

454

LlamaIndex 🦙

@llama_index

4 months

Context-Augmented Agent for Food Delivery 🤖🍔 We’re excited to feature a full-stack repo by lucastonon showing you how to build a RAG agent that can not only look up relevant restaurants, but directly perform in-browser actions like opening a page, getting the menu, adding food…

11

83

448

LlamaIndex 🦙

@llama_index

4 months

Use RAG to build advanced text-to-SQL Vanna AI ( @zain_hoda ) is a project that gained overnight popularity for SQL generation given its easy-to-use but powerful interface that uses RAG for better performance: 1️⃣ Store and index DDL/table schemas 2️⃣ Store and index text…

4

104

450

LlamaIndex 🦙

@llama_index

3 months

Introducing LlamaCloud 🦙🌤️ Today we’re thrilled to introduce LlamaCloud, a managed service designed to bring production-grade data for your LLM and RAG app. Spend less time data wrangling and more time on application logic. Launching with the following components: 1️⃣…

16

94

444

LlamaIndex 🦙

@llama_index

4 months

Today we’re launching a repo that lets you setup a production ETL pipeline for your RAG/LLM app 💫 Index thousands of documents in seconds ⚡️ (and orders of magnitude faster than running on your laptop). It’s a full architecture which bundles LlamaIndex with other popular…

9

73

438

LlamaIndex 🦙

@llama_index

4 months

Chain-of-Table ⛓️📊: use LLMs to understand tabular data step-by-step Even the best LLMs have a hard time understanding tabular data: 🚫 Dumping the table in the prompt doesn’t work given attention limits 🚫 Text-to-SQL is flaky / inflexible. That’s when we discovered the…

16

107

442

LlamaIndex 🦙

@llama_index

4 months

Use RAG to do ArXiv Research 🌐 RAG-Maestro is a cool web app by Aymen Kallala that lets you lookup scientific concepts from any papers on @arxiv . 1️⃣ Extract keywords from search using RAKE 2️⃣ Query ArXiv search to retrieve the relevant papers 3️⃣ On-the-fly index them and…

7

110

435

LlamaIndex 🦙

@llama_index

5 months

Structured Hierarchical RAG 💫 Doing RAG well over many docs is hard. A popular existing approach is hierarchical retrieval: select the relevant doc summaries before retrieving the content inside. But selecting docs purely based on summaries is tough - a doc can have a bunch of…

6

76

432

LlamaIndex 🦙

@llama_index

2 months

Let’s walk through RAG pain points and solutions! 🧑‍🏫🎬 We’re excited to feature @wenqi_glantz for a video walkthrough video of her popular “12 RAG Pain Points and Solutions” blog post, which is the most comprehensive cheatsheet we’ve seen of pain points that occur at every stage…

3

96

432

LlamaIndex 🦙

@llama_index

5 months

If your RAG use case involves a lot of documents and a lot of metadata, you’ll want to check out our brand-new MultiDocAutoRetrieverPack 🦙📦 This is a full RAG template that will 1) index each document by a metadata dictionary, and 2) perform structured retrieval over that…

6

77

425

LlamaIndex 🦙

@llama_index

3 months

Our new RAG CLI tool lets you RAG any file on your filesystem, using only on-device LLMs/embeddings! 💾🔎 Using @llama_index , Mistral-7B on @ollama , and bge-m3, you have access to an LLM-powered grep that you can easily install, use, and customize. Can input any files including…

10

91

430

LlamaIndex 🦙

@llama_index

2 months

Anthropic Cookbook Series 🧑‍🍳🍱 Here’s a set of six notebooks and four videos ‼️by @ravithejads that show you how to use Claude 3 ( @AnthropicAI ) to build any context-augmented LLM app, from simple-to-advanced RAG to agents 🤖 1️⃣ Basic RAG with LlamaIndex 2️⃣ Routing for QA and…

8

82

429

LlamaIndex 🦙

@llama_index

4 months

Advanced RAG with Open-Source LLMs This article by Akash M. is a fantastic resource for setting up small-to-big retrieval (with child chunks referring to bigger parent chunks) using open-source LLM (zephyr-7b) and embedding models (instructor-large). A key idea is you can and…

8

76

425

LlamaIndex 🦙

@llama_index

4 months

Build RAG over the Web 🌐 AgentSearch is an awesome project by @ocolegro - the AgentSearch-v1 includes over 1 billion embeddings from 50million > documents from the web. It’s an awesome data source if you want to build search/retrieval systems over internet content without…

7

91

422

LlamaIndex 🦙

@llama_index

2 months

A Comprehensive Cookbook for Claude 3 🧑‍🍳 In a brand-new video guide 🎞️, we go through a comprehensive cookbook to show how Claude 3 can be used in a variety of different application use cases with @llama_index tooling: 1. Vanilla RAG 2. Routing 3. Sub-question query planning 4.…

4

87

420

LlamaIndex 🦙

@llama_index

1 month

Building a Finance Agent 📈 If you’re looking for a comprehensive toolkit for an LLM to perform financial analysis for any publicly traded company, then check out Hanane Dupouy’s tutorial - it covers all the functions you need to perform stock analysis (thanks to @YahooFinance +…

3

91

412

LlamaIndex 🦙

@llama_index

5 months

You can now spin up a RAG + @streamlit app in one line of code! ⚡️ Check out our brand-new `StreamlitChatPack` - all you have to do is download the pack, and you immediately get a RAG pipeline with a full @streamlit chat interface. It happens so quickly in the below video (<4…

5

87

410

LlamaIndex 🦙

@llama_index

24 days

Using LLM-generated Knowledge Graphs to Accelerate Biomaterials Discovery 🧬🧠 This paper by @ProfBuehlerMIT constructed a massive knowledge graph over 1000 scientific papers on biological materials, in a “local-to-global” approach. By creating this massive ontology, the paper…

5

110

409

LlamaIndex 🦙

@llama_index

1 month

Building RAG is easy, but designing it is hard 💡 This article by @MichalOleszak in @TDataScience offers a comprehensive overview of the big and small design choices you need to build high-performing RAG systems, across 5 main pillars: 1️⃣ Indexing: Embedding external data into…

6

77

411

LlamaIndex 🦙

@llama_index

5 months

There are so many open-source models and so many ways to run them. Here are 10+ ways you can run open-source models through our @llama_index integrations 🔌 1️⃣ @huggingface LLMs/embeddings: download models locally and run them 2️⃣ @huggingface Inference API/embeddings: a hosted…

7

73

401

LlamaIndex 🦙

@llama_index

6 months

We have over 250+ guides to help you build simple-to-advanced LLM/RAG apps over your data. But if you’re looking for a unified resource, this guide by @nanonets is one of the best that we’ve seen 👇 It’s concise yet comprehensive, covering 12+ parts including: ✅ Data…

5

66

398

LlamaIndex 🦙

@llama_index

2 months

Build an Advanced PDF RAG Agent from Scratch ✍️📑 This is an awesome tutorial By Ashish S. that shows you how to orchestrate an agentic RAG flow over multiple PDFs with both text and tables. 1️⃣ Use LlamaParse to parse out the text and tables 2️⃣ Define separate retrievers for a…

3

68

396

LlamaIndex 🦙

@llama_index

11 days

A 9-part series on RAG from Prototype to Production ⭐️ RAG in a notebook is easy, RAG serving live production users is hard. This tutorial series by Marco Bertelli is the perfect step-by-step resource to outline all the architectural components you need to productionize a full…

3

84

401

LlamaIndex 🦙

@llama_index

4 months

Our Open-Source Roadmap 🗺️ We have big plans in 2024 to make the @llama_index ecosystem even more powerful, accessible, and production-ready for all LLM developers building core use cases (RAG, agents, and more) over their data. We’re releasing our 3-6 month roadmap (thanks…

4

54

366

LlamaIndex 🦙

@llama_index

3 months

Building advanced RAG is complicated because there’s too many options to choose from 🤔 A way to simplify it 💡: identify core pain points at each component of the pipeline, and map out solutions for each pain point. We’re excited to publicly share the slides from @jerryjliu0 ’s…

7

83

389

LlamaIndex 🦙

@llama_index

6 months

🔥 Introducing LlamaIndex Chat 🦙💬 Create and share LLM chatbots over your data (customize sys prompts, avatars, etc.) It is ALSO a fully open-source template (MIT) and written with LlamaIndexTS Jumpstarting an LLM app has never been easier 👇

10

68

380

LlamaIndex 🦙

@llama_index

29 days

MetaGPT (Hong et al.) is an awesome multi-agent framework (ICLR 2024) that models agents as a software company following a structured SOP - PMs, architects, engineers, and more communicate with each other to solve the task at hand. We’re excited to feature RAG-enhanced MetaGPT,…

5

95

375

LlamaIndex 🦙

@llama_index

6 months

A big issue with RAG is that stuffing more context ≠ better. This both costs money 💸 and leads to lost in the middle problems 🚫 LongLLMLingua is a prompt compression method that solves both problems: boost accuracy by 20% while using ~25% of the tokens 🔥. You can use it as…

2

75

374

LlamaIndex 🦙

@llama_index

3 months

A key milestone in building advanced RAG is being able to answer multi-hop queries; building RAG should be way more than simple question answering! MultiHop-RAG is an awesome work by Tang et al. that provides the first dataset for multi-hop queries to benchmark your advanced RAG…

5

70

374

LlamaIndex 🦙

@llama_index

2 months

RAG for Complex PDF Comparisons (📑⚖️📑) Building a proper RAG system that can make comparisons on both text and tabular data across PDFs is hard. Here’s a cookbook 🧑‍🍳 showing how you can compose the right components: LlamaParse, recursive retrieval over text and tabular data,…

4

74

374

LlamaIndex 🦙

@llama_index

4 months

One thing we loved about 2023 was the volume of new research around RAG from the entire community ❤️. This survey by Gao et al. is the most comprehensive survey of this research we’ve seen yet - it covers 100+ papers, blog posts, and projects across every step of the RAG…

2

55

367

LlamaIndex 🦙

@llama_index

3 months

Build Conversational, Advanced RAG without writing Code 🧑‍🎨🔎 In our latest webinar, @henryhengzj gives a comprehensive overview of how to use @FlowiseAI to compose simple-to-advanced RAG pipelines purely through a drag-and-drop UI. 1️⃣ Build simple QA from scratch 2️⃣ Make it…

0

61

374

LlamaIndex 🦙

@llama_index

11 months

Parsing LLM outputs into structured formats is critical. But feeding in a “suggestion” into the input prompt doesn’t guarantee structure 🤔 In contrast, @Microsoft Guidance allows you to “force” a schema! 💡 You can now easily use with LlamaIndex: 📗

15

58

359

LlamaIndex 🦙

@llama_index

2 months

Build a RAG-based Job Assistant with LlamaParse + LlamaIndex 💼 This is a cool blog post by Kyosuke Morita showing you how to match a candidate to jobs based on their CV. LlamaParse helps to faithfully extract out relevant text from any CV, no matter how complicated the format.…

1

88

372

LlamaIndex 🦙

@llama_index

6 months

Introducing Llama Packs 🦙📦 Llama Packs are prepackaged modules and templates to kickstart your LLM app. Say goodbye to the hassle of assembling/tuning custom components for each use case. Features ✨: * 16+ versatile packs to help you get started: resume screener,…

2

92

370

LlamaIndex 🦙

@llama_index

5 months

Today we’re introducing Llama Datasets 🦙📝 - a set of community-contributed datasets that allow users to easily benchmark their RAG pipelines for different use cases. It’s hard to define a single right eval dataset for your LLM use case. Instead, you can pick and choose the…

6

82

363

LlamaIndex 🦙

@llama_index

6 months

Head-to-head 🥊: LlamaIndex vs. OpenAI Assistants API This is a fantastic in-depth analysis by @tonicfakedata comparing the RAG performance of the OpenAI Assistants API vs. LlamaIndex. tl;dr @llama_index is currently a lot faster (and better at multi-docs) 🔥 Some high-level…

11

72

360

LlamaIndex 🦙

@llama_index

3 months

Simple-to-Advanced Reranking 🔥 If you’re building RAG, you should add reranking, and this blog post by Florian June is one of the most accessible posts we’ve seen on this topic on different levels of reranking. 💡 Learn how to use a BGE-based reranker 💡Use an LLM-powered…

3

69

365

LlamaIndex 🦙

@llama_index

3 months

ColBERT ( @lateinteraction ) is a great model for reranking. It’s ~100x faster than BERT-based/cross-encoder models, letting you rerank large amounts of documents without worrying about latency. And of course it does better than standard dense retrieval. Thanks to @Haotianzh , it’s…

6

52

363

LlamaIndex 🦙

@llama_index

4 months

Advanced RAG pipelines are deeply custom and use-case specific. Our goal is to 1) identify common patterns, and 2) help you define complex RAG workflows with ease. Today we introduce Query Pipelines 💫, a declarative API that allows you to orchestrate simple-to-hard query…

9

52

356

LlamaIndex 🦙

@llama_index

14 days

Language Agent Tree Search 🤖🌲 As LLMs get faster, better, cheaper, developers will be able to compose agentic systems that are able to plan out an entire tree of possible futures, instead of just sequentially planning the next state (e.g. in ReAct). This is crucial for higher…

5

92

362

LlamaIndex 🦙

@llama_index

6 months

LlamaIndex + Deep Memory ( @activeloopai ) This is a super powerful, easy to use module that automatically fine-tunes your document/query embeddings during ingestion time. Get +15% improvements in RAG metrics 📈, and works on top of any existing embeddings! To use this, you…

5

60

349

LlamaIndex 🦙

@llama_index

6 months

Supercharge @OpenAI Assistants with Advanced Retrieval 🚀 We’re excited to release a full cookbook 🧑‍🍳 showing how you can build advanced RAG with the Assistants API - beyond just using the in-house Retrieval tool! Solve critical use cases + pain points with agent execution +…

5

62

351

LlamaIndex 🦙

@llama_index

3 months

Infer-Retrieve-Rerank ( @KarelDoostrlnck et al.) is a simple but powerful paradigm to use LLMs for complex classification problems with thousands of classes. Examples include medical reactions 🥼 and job skills/qualifications 👷. Use an LLM to infer a set of predictions, use…

4

71

353

LlamaIndex 🦙

@llama_index

4 months

RAG Assisted Auto Developer 🔎🧑‍💻 Here’s a neat cookbook by @quantoceanli to build a devbot that can 1) understand a codebase, 2) write additional code based on the codebase. It’s a nice mix of different tools: @llama_index to index an existing codebase, Autogen / OpenAI Code…

9

74

351

LlamaIndex 🦙

@llama_index

1 month

We’re excited to feature by @ivanilin9 - an LLM-powered, self-organizing digital library for professional and teams 🔥 This is way more than a simple “chat over your data”; it’s an AI-powered knowledge organizer where you can create, organize, annotate…

13

56

354

LlamaIndex 🦙

@llama_index

7 months

You can now get a full tracing/observability UI in *all* @llama_index RAG/agent pipelines, in one-line of code ⚡️ Bonus: all your data lives locally! 🔐 We're launching a native integration with @arizeai Phoenix 🔥. Full 🧵 below. Full Colab nb:

4

64

347

LlamaIndex 🦙

@llama_index

2 months

Search-in-the-Chain ⛓️🔎 This paper by Shicheng Xu et al. is a cool new way to interleave retrieval and planning for advanced question-answering, beyond naive RAG. Retrieval is used to verify whether or not a given step is correct, and can trigger replans if not. And now it’s…

7

79

352

LlamaIndex 🦙

@llama_index

4 months

Comprehensive Guide to LLM Quantization 🧑‍🏫 If you’re building with open-source LLMs, you’ll want to do quantization 💾 ⚡️ - get way lower latency/consumption with very little accuracy tradeoffs This reference guide by @wenqi_glantz teaches you how to quantize @MistralAI 7B…

5

80

326

LlamaIndex 🦙

@llama_index

4 months

Build a full-stack RAG-powered Voice Assistant 🎤 We’re excited to feature a full-stack template by @HarshadSurya1c to help you build a voice assistant over your data. It’s a great example of `create-llama`, our handy CLI tool for easily scaffolding the backend/frontend of an…

4

63

345

LlamaIndex 🦙

@llama_index

1 year

Users have mentioned that a key pain point of applying LLM’s to SQL db's is: too many tables+columns, can’t fit context in one prompt! LlamaIndex 0.4.12 helps solve that pain point: you can pass table context to our SQL index…and this context can be another index! 🧠👇

10

28

345

LlamaIndex 🦙

@llama_index

3 months

RAG Microservices 🔥🛠️ This is a fantastic tutorial by @wenqi_glantz showing you how to convert prototype notebook RAG into a full-stack application powered by ingestion and inference micro services. 1️⃣ Setup an ingestion service to handle data loading/indexing 2️⃣ Define an…

0

73

345