Starstruk Logo MarkStarstruk

v0.2.10

ruvnet/RuVectorv0.2.10Aug 19, 2026by github-actions[bot]

AI Summary

Initial stable release introducing the PageIndex SDK, featuring the Flash engine for faster indexing, unified local and cloud clients, and agent integration.

Key Highlights

  • Introduction of the PageIndex SDK with local and cloud modes.
  • Flash engine for much faster indexing (no LLM for structure generation).
  • Unified client API for submitting documents and chatting.
  • Agent integration via MCP tools.

New Features

  • PageIndexLocalClient and PageIndexCloudClient classes.
  • PageIndex Flash engine with concurrent node expansion.
  • Chat surfaces: `chat()`, `chat_completions()`, `responses()`, `messages()`.
  • Agent tool integration methods (`agent_tools`, `as_openai_tools`, etc.).

Full Release Notes

- New **PageIndex SDK**, **local** or **cloud** — vectorless, reasoning-based RAG, end to end.
- **Much faster Indexing** — the new **PageIndex Flash** engine gets the tree from layout stats: no LLM involved for the structure generation itself, LLMs only write the node summaries.

```python
client = PageIndexLocalClient(storage_path="./docs")
client.submit_document("report.pdf")
client.chat("What does the report conclude?")
```

Index, to chat, to agent integration, one client.
Local mode needs no server, no vector DB, no PageIndex API key.

## Highlights

- **Flash engine**: the local default (`mode="standard"` keeps the classic LLM pipeline). Embedded bookmarks are consumed when trustworthy, and tree optimization is on by default — `optimize="merge"` for the deterministic LLM-free pass, `"full"` (default) adds LLM expand.
- **One complete surface, local and cloud**: `PageIndexLocalClient(storage_path=...)` is the same client as cloud — submit, tree, page content, chat, and agent tools all present in both modes, so code moves between them unchanged.
- **Agent integration**: the cloud MCP tool contract, in-process — `client.agent_tools()` (plain functions), `as_openai_tools()`, `as_anthropic_tools()`, `as_claude_mcp()`, plus one-call `openai_agent_config()` / `anthropic_runner_config()` / `claude_agent_config()` bundles and `agent_instructions()` for the system prompt. Cloud clients get the live server tool set over the MCP bridge (read-only endpoint by default); local clients get the in-process subset with the same schemas and envelopes — agent prompts port unchanged.
- **Chat surfaces**: `chat()` — question in, answer out, on any backend; `chat_completions()` / `responses()` / `messages()` protocol doors with `doc_id` targeting, streaming, honest usage accounting, and prompt-cache continuity across turns.
- **Model & connection knobs**: `index_model` / `chat_model`, `index_backend` / `chat_backend` (and per-call `backend`) passed verbatim to each lane — LiteLLM-routed providers, keyless OpenAI-compatible servers, Azure/Bedrock/Vertex included.
- **Dependencies**: Python >= 3.10; `openai-agents` joins the base install (the chat engine); `[anthropic]` and `[claude]` extras for those SDKs.

*First stable release since 0.2.8 — 0.2.9 was never published, so everything above is new on the stable channel.*

**Full Changelog**: https://github.com/VectifyAI/PageIndex/compare/v0.2.8...v0.2.10