llama_index · Issues· 808 open

[Bug]: IntelEmbedding RuntimeError

[Bug]: DashScope FunctionTool conversion drops nested JSON Schema definitions

[Bug]: Memory truncates highest-priority memory blocks first

LanceDBVectorStore.delete(), delete_nodes(), and get_nodes() build invalid SQL predicates — broke after lancedb#3825 changed double-quote parsing

Ingestion cache contract: stale node identity vs content-stable reuse after regenerated chunk IDs

Ingestion: UPSERTS_AND_DELETE misses a removed document when hashes collide, and the transformation cache key is not injective

[Bug]: CodeActAgent raises UnboundLocalError at codeact_agent.py:110 when code_act_system_prompt is a BasePromptTemplate and system_prompt is left at None

[Feature Request]: Deterministic tool I/O pre/post-processing (middleware/hooks) for agents (MCP motivating case)

[Bug]: RichPromptTemplate crashes on embedded audio/video files and corrupts embedded documents

[Bug]: TreeSelectLeafRetriever and tree insert silently pick the last node on 0-indexed LLM answers

[Bug]: LLM and pydantic selectors silently route to the last choice on 0-indexed answers

[Bug]: SimplePropertyGraphStore.get_rel_map returns duplicate triplets when the graph has cycles

[Bug]: MCP tool_call_logs_callback can receive empty logs when application logging is already configured

[Bug]: llama-index-vector-stores-qdrant caps requires-python at <3.14, blocking Python 3.14

[Bug]: MediaResource.hash is platform-dependent for paths — test_hash fails on Windows