Skip to content

v0.2.10

Latest
Latest

Choose a tag to compare

View all tags
@github-actions github-actions released this 19 Aug 14:06
· 3 commits to main since this release
v0.2.10
ba0ef02
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
  • 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 statistics: no LLM involved for the structure generation itself, LLMs only write the node summaries.
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 surface.
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.

Hardened by the review record in #400: contract parity with the cloud MCP server is frozen and live-tested, and five max-effort review rounds ran over the final diff (#413).

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

Full Changelog: v0.2.8...v0.2.10

Assets 6
Loading