Repository Issue Activity (beta)

#300 `list_documents()` returns all documents -> unusable with large workspaces

#354 Very good idea but awful coding

#316 Feature Request: Incremental Index Updates for Large Documents

#355 Markdown path: below --summary-token-threshold, node text is copied verbatim into summary (undocumented; diverges from PDF path)

#330 Bug: `get_leaf_nodes` raises KeyError on leaf nodes due to missing `nodes` key

#175 Hello everyone, I have some questions regarding Hybrid Tree Search and would appreciate your insights.

#345 Non-existent PageIndexClient.chat_completion method mentioned in cookbooks.

#234 支持私有化部署吗

#163 toc_transformer crashes on large TOCs (~800 page PDF) - JSON truncation + context overflow

#71 Reuse OpenAI clients to improve throughput

#196 litellm compromise

#236 <jemalloc>: Unsupported system page size

#324 Clarification on PageIndex Architecture: Usage of Chunking and LLMs

#75 Does it support the Java version? For instance, can PageIndex be integrated into langchain4j

#13 How to integrate with semantic vector-based search?

#93 Are there any plans to open-source the retrieval code?

#49 Difference between Open-Source vs Enterprise Version

#34 Can it be used for non structured docs?

#59 When PageIndex is used for querying, do we need to load the entire document structure tree?

#138 is there any databse（mysql、clickhouse、oss） to store the tree json result。

#201 这个支持txt文档以及word文档吗？

#23 Can I use MD original file use PageIndex parser & gen index?

#16 How to get the contents of the nodes

#40 cannot import name 'PageIndexClient' from 'pageindex' (d:\PageIndex\pageindex\__init__.py)

#53 Best LLM for Page-Index