Problemsby IbisLlamaIndex lock-in makes switching costly
Cloud and tool cost2 posts from 2 people2d active+00 posts in the last 7 days, 1 the 7 days before (fading)Unverified
Posts per day
The posts behind it
2, newest first[Bug]: `SummaryIndexLLMRetriever.aretrieve` blocks the event loop (no async path; calls sync llm.predict)### Bug Description `SummaryIndexLLMRetriever` (alias `ListIndexLLMRetriever`) does not define `_aretrieve`, so `aretrieve()` falls back to `BaseRetriever._aretrieve`, which calls the sync `_retrieve`, which calls the blocking `self._llm.predict(...)` once per batch. While that...run-llama/llama_index · kavishkartha05Open ↗Bug: several query engines' _aquery() silently delegates to synchronous _query(), blocking the event loop### Bug Description While working on SQLJoinQueryEngine (#22400), I noticed several other query engines have `async def _aquery()` implementations that simply call the synchronous `_query()` - so `aquery()` is async in name only and every step runs blocking work directly on the...run-llama/llama_index · alwaysprince055 repliesOpen ↗
Companies and products named
About this problem
Evidence
2 posts from 2 people in 1 place, about 1 a week over 16 days. Mostly on run-llama/llama_index.
Frustration Frustration 0 of 3· Seen on GitHub issues
How it was grouped
Posts that state a pain and match the "vendor-lock" rule about LlamaIndex. First post Sep 28, 2026, latest Oct 13, 2026. Unverified: fewer than 3 posts, or one person or place only. Method
The same problem elsewhere
Vendor lock-in makes switching tools costlyGitHub lock-in makes switching costlyKubernetes lock-in makes switching costlyClaude Code lock-in makes switching costlyClaude lock-in makes switching costlyNVIDIA lock-in makes switching costlyllama.cpp lock-in makes switching costlyCodex lock-in makes switching costlyAnthropic lock-in makes switching costlypandas lock-in makes switching costlyApache Airflow lock-in makes switching costlyvLLM lock-in makes switching costly
Other LlamaIndex problems
LlamaIndex users keep filing bugsLlamaIndex upgrades break working setupsLlamaIndex fails to return valid structured outputTrouble with LlamaIndex returnsTrouble with LlamaIndex documentsTrouble with LlamaIndex eventsExperiments on LlamaIndex are hard to reproduce and trackLlamaIndex runs out of context on real workTrouble with LlamaIndex raisesLlamaIndex integrations break or are missingRAG on LlamaIndex returns irrelevant or missing contextLlamaIndex token costs are hard to predict
History
steady to fading
LlamaIndex lock-in makes switching costly (2 posts)