apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-06-12 19:55:17 +02:00
Code Issues Projects Releases Packages Wiki Activity
305 commits 10 branches 0 tags 64 MiB
Commit graph

305 commits

This branch
This branch
All branches
Author SHA1 Message Date
BukeLy
de1992def1 refactor(filesystem): make pifs providers configurable 2026-05-27 02:12:34 +08:00
BukeLy
7c021a7dd0 refactor(filesystem): unify pifs metadata state 2026-05-27 02:12:34 +08:00
BukeLy
fc0be1aeee fix(filesystem): restore summary vector search in cli 2026-05-27 02:12:34 +08:00
BukeLy
7e70b580f0 fix(filesystem): show generated metadata in stat 2026-05-27 02:12:34 +08:00
BukeLy
5c948d0840 fix(filesystem): require metadata evidence in chat 2026-05-27 02:12:34 +08:00
BukeLy
8ae94ade19 fix(filesystem): render root folder path correctly 2026-05-27 02:12:34 +08:00
BukeLy
ec96812e6b fix(filesystem): scope pifs chat identity 2026-05-27 02:12:34 +08:00
BukeLy
c12c2de65b fix(filesystem): guide structural node reads 2026-05-27 02:12:34 +08:00
BukeLy
beed21647f fix(filesystem): remove chat request started noise 2026-05-27 02:12:34 +08:00
BukeLy
cb1bfb00fa fix(filesystem): reuse agent session in pifs chat 2026-05-27 02:12:34 +08:00
BukeLy
b2089712b3 refactor(filesystem): remove reference id concept 2026-05-27 02:12:34 +08:00
BukeLy
a80b84dae4 fix(filesystem): remove session ref aliases from cli output 2026-05-27 02:12:34 +08:00
BukeLy
06d8553a0a fix(filesystem): clarify folder path metadata errors 2026-05-27 02:12:34 +08:00
BukeLy
144e8ba325 feat(pifs): add find maxdepth traversal limit 2026-05-27 02:12:34 +08:00
BukeLy
5a78131509 fix(filesystem): suppress chat input echo while streaming 2026-05-27 02:12:34 +08:00
BukeLy
b9ee711087 fix(filesystem): require target-first cat syntax 2026-05-27 02:12:34 +08:00
BukeLy
3d62293a1e fix(filesystem): avoid duplicate pifs chat output 2026-05-27 02:12:34 +08:00
BukeLy
3625a592f2 fix(filesystem): stream pifs chat by default 2026-05-27 02:12:34 +08:00
BukeLy
e074bf1765 fix(filesystem): package pifs cli entrypoint 2026-05-27 02:12:34 +08:00
BukeLy
574125d7dd fix(filesystem): add pifs ask and chat commands 2026-05-27 02:12:34 +08:00
BukeLy
74d0600261 feat(filesystem): add PageIndex filesystem shell 2026-05-27 02:12:34 +08:00
Ray
7592163e2a
Update README (#271)
Some checks failed
CodeQL / Analyze (actions) (push) Has been cancelled
 2026-05-12 03:28:29 +08:00
Ray
f50e529753
update README (#262)
Some checks failed
CodeQL / Analyze (actions) (push) Has been cancelled
 2026-05-08 02:08:33 +08:00
Ray
c1a0f94fd3
update README (#261) 2026-05-08 01:57:33 +08:00
Ray
e7dfc5e1ff
update README (#259) 2026-05-07 20:57:14 +08:00
Ray
dcda5656ba Fix Agentic RAG entry formatting in Updates
Some checks failed
CodeQL / Analyze (actions) (push) Has been cancelled
 2026-05-06 04:53:41 +08:00
Ray
495e8929b5 Trim Cloud Service note in README 2026-05-06 04:40:32 +08:00
Ray
46244aed33 update README
Some checks are pending
CodeQL / Analyze (actions) (push) Waiting to run
 2026-05-06 00:57:25 +08:00
Bukely_
a51d97f63c
Add security CI workflows (#248)
Some checks failed
CodeQL / Analyze (actions) (push) Has been cancelled
* Add security CI workflows

* Remove duplicate Python CodeQL workflow
 2026-04-25 00:46:01 +08:00
dependabot[bot]
40073375ff
Bump the pip group across 1 directory with 2 updates (#247) 
Bumps the pip group with 2 updates in the / directory: [litellm](https://github.com/BerriAI/litellm) and [python-dotenv](https://github.com/theskumar/python-dotenv).


Updates `litellm` from 1.83.0 to 1.83.7
- [Release notes](https://github.com/BerriAI/litellm/releases)
- [Commits](https://github.com/BerriAI/litellm/commits)

Updates `python-dotenv` from 1.1.0 to 1.2.2
- [Release notes](https://github.com/theskumar/python-dotenv/releases)
- [Changelog](https://github.com/theskumar/python-dotenv/blob/main/CHANGELOG.md)
- [Commits](https://github.com/theskumar/python-dotenv/compare/v1.1.0...v1.2.2)

---
updated-dependencies:
- dependency-name: litellm
  dependency-version: 1.83.7
  dependency-type: direct:production
  dependency-group: pip
- dependency-name: python-dotenv
  dependency-version: 1.2.2
  dependency-type: direct:production
  dependency-group: pip
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2026-04-25 00:19:47 +08:00
Bukely_
29b240a689
Add Dependabot config for GitHub Actions updates (#241) 
Weekly scan to open PRs upgrading third-party actions used in CI.
pip dependencies remain pinned and are covered by Dependabot security
updates separately.
 2026-04-23 23:59:26 +08:00
Xinyan Zhou
f2dcffc0b7
Merge pull request #214 from VectifyAI/dependabot/pip/pip-480c85e8a1 
Bump litellm from 1.82.0 to 1.83.0 in the pip group across 1 directory
 2026-04-08 18:19:25 +08:00
dependabot[bot]
eb57d2a10c
Bump litellm from 1.82.0 to 1.83.0 in the pip group across 1 directory 
Bumps the pip group with 1 update in the / directory: [litellm](https://github.com/BerriAI/litellm).


Updates `litellm` from 1.82.0 to 1.83.0
- [Release notes](https://github.com/BerriAI/litellm/releases)
- [Commits](https://github.com/BerriAI/litellm/commits)

---
updated-dependencies:
- dependency-name: litellm
  dependency-version: 1.83.0
  dependency-type: direct:production
  dependency-group: pip
...

Signed-off-by: dependabot[bot] <support@github.com>
 2026-04-03 22:16:59 +00:00
Ray
8f1ed7783b Update README 2026-03-30 01:34:45 +08:00
Ray
0ba6206ef0 Update developer links 2026-03-29 20:01:58 +08:00
Ray
28542de889 Polish agent system prompt wording 2026-03-29 05:31:02 +08:00
Ray
54542f03e6
Merge pull request #197 from VectifyAI/polish/demo-docstring-and-pathlib 
Polish demo docstring and migrate to pathlib
 2026-03-29 05:03:50 +08:00
Ray
ce9cbc2ed0 Polish demo docstring and migrate to pathlib 2026-03-29 04:56:27 +08:00
Ray
a108c021ae
Disable agent tracing and auto-add litellm/ prefix for retrieve_model 
* Disable agent tracing and auto-add litellm/ prefix for retrieve_model

* Preserve supported retrieve_model prefixes

* Remove temporary retrieve_model tests

* Limit tracing disablement to demo execution
 2026-03-29 00:55:57 +08:00
Ray
d50c293309
Simplify agentic vectorless RAG demo (#191) 
* Simplify and fix agentic RAG demo

* Show labeled reasoning output in RAG demo

* Comment out reasoning model settings by default
 2026-03-28 09:42:46 +08:00
Ray
4002dc94de Rename demo script and update README wording 2026-03-28 04:56:05 +08:00
Ray
77722838e1
Restructure examples directory and improve document storage (#189) 
* Consolidate tests/ into examples/documents/

* Add line_count and reorder structure keys

* Lazy-load documents with _meta.json index

* Update demo script and add pre-shipped workspace

* Extract shared helpers for JSON reading and meta entry building
 2026-03-28 04:28:59 +08:00
Ray
74e549a23a
Merge pull request #184 from VectifyAI/cleanup/simplify-root-directory 
Simplify root directory
 2026-03-27 16:33:24 +08:00
Ray
a7a9985223 Update README 2026-03-27 03:55:07 +08:00
Ray
e5ac754828 Simplify root directory 2026-03-27 03:30:13 +08:00
Ray
d7d5aed668 Update README 2026-03-27 03:21:20 +08:00
Ray
88ef448d1a Add agentic vectorless RAG example to README highlights 2026-03-27 02:31:40 +08:00
Ray
9798aaae19 Update demo example paper and polish README 2026-03-27 01:22:03 +08:00
Kylin
5d4491f3bf
Add PageIndexClient with agent-based retrieval via OpenAI Agents SDK (#125) 
* Add PageIndexClient with retrieve, streaming support and litellm integration
* Add OpenAI agents demo example
* Update README with example agent demo section
* Support separate retrieve_model configuration for index and retrieve
 2026-03-26 23:19:50 +08:00
Kylin
2403be8f27
Integrate LiteLLM for multi-provider LLM support (#168) 
* Integrate litellm for multi-provider LLM support

* recover the default config yaml

* Use litellm.acompletion for native async support

* fix tob

* Rename llm_complete/allm_complete to llm_completion/llm_acompletion, remove unused llm_complete_stream

* Pin litellm to version 1.82.0

* resolve comments

* args from cli is used to overrides config.yaml

* Fix get_page_tokens hardcoded model default

Pass opt.model to get_page_tokens so tokenization respects the
configured model instead of always using gpt-4o-2024-11-20.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Remove explicit openai dependency from requirements.txt

openai is no longer directly imported; it comes in as a transitive
dependency of litellm. Pinning it explicitly risks version conflicts.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Restore openai==1.101.0 pin in requirements.txt

litellm==1.82.0 and openai-agents have conflicting openai version
requirements, but openai==1.101.0 works at runtime for both.
The pin is necessary to prevent litellm from pulling in openai>=2.x
which would break openai-agents.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Remove explicit openai dependency from requirements.txt

openai is not directly used; it comes in as a transitive dependency
of litellm. No openai-agents in this branch so no pin needed.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* fix an litellm error log

* resolve comments

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-03-20 18:47:07 +08:00