I turned the complete course notes into a searchable knowledge base with citations back to the original source material.

The goal is to make long technical documents easier to explore without losing traceability.

https://chat.pageindex.ai/explore/stanford-cs229

Comments URL: https://news.ycombinator.com/item?id=48903854

Points: 4

# Comments: 0

Github repo: https://github.com/VectifyAI/OpenKB

Comments URL: https://news.ycombinator.com/item?id=47752392

Points: 6

# Comments: 2

Comments URL: https://news.ycombinator.com/item?id=47016081

Points: 5

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47014232

Points: 3

# Comments: 0

Any feedback is welcome!

Comments URL: https://news.ycombinator.com/item?id=45743316

Points: 7

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=45721772

Points: 4

# Comments: 2

What makes it different:

- Reasoning-based retrieval: Understands structure, logic, and meaning, not just semantic similarity.

- Page-level references: Every answer includes precise citations for easy verification.

- Cross-section reasoning: Connects information across sections and appendices to find true answers.

- Human-in-the-loop: You can guide, refine, and verify its reasoning.

- Multi-document comparison: Analyze and contrast multiple reports at once.

Comments URL: https://news.ycombinator.com/item?id=45694799

Points: 1

# Comments: 1

Unlike traditional RAG or "chat-with-your-doc" tools that rely on vector similarity search, PageIndex builds a hierarchical tree index of your document (like a table of contents), and then reasons over this index to retrieve and interpret relevant sections. It doesn’t search by keywords or embeddings — it reads, understands, and reasons through the document like a human expert.

What makes it different:

- Reasoning-based retrieval – Understands structure, logic, and meaning, not just semantic similarity. - Page-level references – Every answer includes precise citations for easy verification. - Cross-section reasoning – Connects information across sections and appendices to find true answers. - Human-in-the-loop – You can guide, refine, and verify its reasoning. - Multi-document comparison – Analyze and contrast multiple reports at once.

Comments URL: https://news.ycombinator.com/item?id=45666487

Points: 6

# Comments: 1

Unlike traditional RAG or "chat-with-your-doc" tools that rely on vector similarity search, PageIndex builds a hierarchical tree index of your document (like a table of contents), and then reasons over this index to retrieve and interpret relevant sections. It doesn’t search by keywords or embeddings — it reads, understands, and reasons through the document like a human expert.

What makes it different:

- Reasoning-based retrieval – Understands structure, logic, and meaning, not just semantic similarity. - Page-level references – Every answer includes precise citations for easy verification. - Cross-section reasoning – Connects information across sections and appendices to find true answers. - Human-in-the-loop – You can guide, refine, and verify its reasoning. - Multi-document comparison – Analyze and contrast multiple reports at once.

Comments URL: https://news.ycombinator.com/item?id=45663609

Points: 4

# Comments: 1

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.

Comments URL: https://news.ycombinator.com/item?id=45529851

Points: 5

# Comments: 0

1. The LLM itself selects the most relevant documents — no vector database needed.

2. The selected documents are then placed directly into the context for generation.

This kind of in-context retrieval approach greatly improves retrieval accuracy compared to traditional vector-based retrieval methods.

Comments URL: https://news.ycombinator.com/item?id=45529216

Points: 6

# Comments: 1