In-Context Index for In-Context Retrieval
RAG pipelines have become bloated: embeddings, vector DBs, rerankers, and ad-hoc pipelines everywhere. Projects like Claude Code showed a simpler path: In-Context Retrieval — letting the LLM reason directly over context for retrieval instead of outsourcing search to external infrastructure. PageIndex takes that one step further with In-Context Indexing. If retrieval happens in-context, the index should live there too. Each document is transformed into a hierarchical, human-readable tree structure (like a table-of-contents tree index) inside the model's context window. The LLM reads the…
What it does
In the maker’s words, at launch
RAG pipelines have become bloated: embeddings, vector DBs, rerankers, and ad-hoc pipelines everywhere. Projects like Claude Code showed a simpler path: In-Context Retrieval — letting the LLM reason directly over context for retrieval instead of outsourcing search to external infrastructure. PageIndex takes that one step further with In-Context Indexing. If retrieval happens in-context, the index should live there too. Each document is transformed into a hierarchical, human-readable tree structure (like a table-of-contents tree index) inside the model's context window. The LLM reads the structure, identifies relevant branches, opens them, and reasons through for retrieval — no embeddings, no chunking, no opaque vector indexes the model can't interpret. Retrieval and indexing, both inside the model.
Does the same job
all alternatives →- PVPageIndex – Vectorless RAG2025 · github.com · ▲192
Not all improvements come from adding complexity — sometimes it's about removing it. PageIndex takes a different approach to RAG. Instead of relying on vector databases or artificial chunking, it builds a hierarchical tree structure from documents and uses reasoning-based tree search to locate the most relevant sections. This mirrors how humans approach reading: navigating through sections and context rather than matching embeddings. As a result, the retrieval feels transparent, structured, and explainable. It moves RAG away from approximate "semantic vibes" and toward explicit reasoning…
- HLHuman-like RAG — no vectors2025 · github.com · ▲11
Not all improvements come from adding complexity — sometimes it's about removing it. PageIndex takes a different approach to RAG. Instead of relying on vector databases or artificial chunking, it builds a hierarchical tree structure from documents and uses reasoning-based tree search to locate the most relevant sections. This mirrors how humans actually read: navigating through sections and context rather than relying on embedding similarity. As a result, the retrieval feels transparent, structured, and explainable. It moves RAG away from approximate "semantic vibes" and toward explicit…
- FBFastGraphRAG – Better RAG using good old PageRank2024 · github.com · ▲457
Hey there HN! We’re Antonio, Luca, and Yuhang, and we’re excited to introduce Fast GraphRAG, an open-source RAG approach that leverages knowledge graphs and the 25 years old PageRank for better information retrieval and reasoning. Building a good RAG pipeline these days takes a lot of manual optimizations. Most engineers intuitively start from naive RAG: throw everything in a vector database and hope that semantic search is powerful enough. This can work for use cases where accuracy isn’t too important and hallucinations are tolerable, but it doesn’t work for more difficult queries that…
- RNRAG, No Vectors2025 · github.com · ▲11
We built PageIndex, a document indexing system that turns documents into hierarchical search trees to support reasoning-based RAG. Traditional vector-based RAG often struggles with retrieval accuracy because it optimizes for similarity, not relevance. But what we really need in retrieval is relevance — which requires reasoning. When working with professional documents that demand domain expertise and multi-step reasoning, vector-based RAG and similarity search often fall short. So we started exploring a more reasoning-driven approach to RAG. Reasoning-based RAG enables LLMs to think and…
- IUI used Claude Code to discover connections between 100 booksJan 2026 · trails.pieterma.es · ▲524
I think LLMs are overused to summarise and underused to help us read deeper. I built a system for Claude Code to browse 100 non-fiction books and find interesting connections between them. I started out with a pipeline in stages, chaining together LLM calls to build up a context of the library. I was mainly getting back the insight that I was baking into the prompts, and the results weren't particularly surprising. On a whim, I gave CC access to my debug CLI tools and found that it wiped the floor with that approach. It gave actually interesting results and required very little orchestration…
- AVA Vectorless LLM-Native Document Index MethodOct 2025 · github.com · ▲14
The word "index" originally came from how humans retrieve info: book indexes and tables of contents that guide us to the right place in documents. Computers later borrowed the term for data structures: e.g., B-trees, hash tables, and more recently, vector indexes. They are highly efficient for machines; but abstract and unnatural: not something a human, or an LLM, can understand and directly use as a reasoning aid. This creates a gap between how indexes work for computers and how they should work for models that reason like humans. PageIndex is a new step that "looks back to move forward".…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, October 2025
the whole month →
- SA
I went down the rabbit hole on a side project and ended up building this: Strange Attractors(https://blog.shashanktomar.com/posts/strange-attractors). It’s built with three.js. Working on it reminded me of the little "maths for fun" exercises I used to do while learning programming in early days. Just trying things out, getting fascinated and geeky, and being surprised by the results. I spent way too much time on this, but it was extreme fun. My favorite part: someone pointed me to the Simone Attractor on Threads. It is a 2D attractor and I asked GPT to extrapolate it to…
AI · Oct 2025 · blog.shashanktomar.com
- ASAutism Simulator▲779
Hey all, I built this. It’s not trying to capture every autistic experience (that’d be impossible). It’s based on my own lived experience as well as that of friends on the spectrum. I'm trying to give people a feel for what masking, decision fatigue, and burnout can look like day-to-day. That’s hard to explain in words, but easier to show through choices and stats. I'm not trying to "define autism". I’ve gotten good feedback here about resilience, meds, and difficulty tuning. I’ll keep tweaking it. If even a few people walk away thinking, "ah, maybe that’s why my coworker struggles in those…
Life & fun · Oct 2025 · autism-simulator.vercel.app
