Repository Issue Activity (beta)

#214 [feature] The compilation pipeline would benefit from an automatic sel…

#205 Ollama tool-calling loop does not complete for query/chat on v0.4.5 and v0.5.0-rc1

#204 openkb-web chat/REST can't authenticate to Amazon Bedrock with SIGV4 / role credentials — forces API-key (bearer) auth, no SIGV4 fallback (CLI works)

#36 performance

#203 Bulk ingestion: per-document rewrites of entity/concept pages scale ~O(N²) on large, topically-dense corpora — propose a two-phase (map/reduce) consolidation mode

#196 [ERROR] Query failed: litellm.AuthenticationError: AuthenticationError: MoonshotException - Invalid Authentication

#197 Documents pane shows only title, no way to read a document's actual converted text

#140 Has anyone actually succeeded in using OpenKB on a mac/M3 pro (36GB) with LM Studio runtime?

#190 Use the DeepSeek model to parse the document and execute an OpenKB query to identify errors.

#187 [ERROR]: Query failed: 1 validation error for InputTokensDetails: messing field cache_write_tokens

#164 Requesting retry logic when model is overloaded

#178 Feature Request: Native integration with Agno Framework

#173 if compile concurrency can be a parameter?

#176 Installing latest version from GitHub failing on Python 3.14

#175 Issue when using Amazon Bedrock

#157 [bug] Gemini ingest always fails: cache_control can't be combined with system_instruction/tools

#166 Long-doc (PageIndex) images are extracted but never surface in the rendered wiki

#162 DOCX embedded images are lost during conversion

#148 compiler: concept update can write partial pages after finish_reason=length

#158 Bug Report: Concept generation fails with `'list' object has no attribute 'get'`

#39 feat: opt-in OpenRouter Response Caching for compiler retry path

#33 LLM-Wiki Deep Research

#66 Over-reliant on TOC, why not target index pages?

#132 [Feature] Support passing timeout parameter to LiteLLM

#88 [Feature] Support importing existing PageIndex Cloud indices