Skip to content
Problems.

LlamaIndex users keep filing bugs

LLM apps9 posts from 9 people9d active+22 posts in the last 7 days, 2 the 7 days before (steady)

Posts per day

Posts per day9 posts, Aug 28 to Sep 25

The posts behind it

9, newest first
PostDate
PairwiseComparisonEvaluator: with enforce_consensus=True, a tie in the original order plus a decisive flipped order returns the flipped judge's score/passing unconverted (verdict inverted)`llama-index-core/llama_index/core/evaluation/pairwise.py:206-218` (HEAD `2232f3019f7aa581f455583262100111dff4a4d3`) The class contract (`pairwise.py:99`) is "Outputs whether the `response` given is better than the `reference` response", so `score`/`passing` are expressed in the...run-llama/llama_indexshaurya416Sep 24yesterday
[Documentation]: The API documentation cannot be used properly and cannot be scrolled to see more content.### Documentation Issue Description https://developers.llamaindex.ai/python/framework-api-reference/llms/ The API documentation cannot be used properly and cannot be scrolled to see more content. ### Documentation Link...run-llama/llama_indexxhc-codeSep 196 days ago
[Bug]: similarity() returns nan for zero-norm embeddings, corrupting top-k selection### Bug Description `similarity()` in `llama_index/core/base/embeddings/base.py` divides by the product of vector norms in the default cosine branch: When either embedding is a zero vector (e.g. some providers return zero embeddings for empty text), the norm product is 0 and the...run-llama/llama_indexbetacatslingSep 1411 days ago
ImportError: cannot import name 'GradientBaseModelLLM' from 'llama_index.llms'I am trying to run a script which uses GradientBaseLLM . Apparently the script was written by someone else couple of years back and I having tough time upgrading. I am importing. from llama_index.llms import GradientBaseLLM I am getting the following error:. ImportError: cannot...Stack Overflow [llama-index]BussllerSep 1312 days ago
JSONNodeParser emits empty-text nodes for {} and misreports valid scalar JSON as "invalid"### Bug description `JSONNodeParser.get_nodes_from_node` has two edge behaviors that produce silently wrong output: 1. An empty JSON object becomes a node with empty text. `JSONNodeParser().get_nodes_from_documents([Document(text="{}")])` returns one `TextNode` whose `text` is...run-llama/llama_indexHarsh23KashyapSep 102 weeks ago
Two llama-index-core docstrings omit parameters the rest of the Args block documents### Bug Description Two `llama-index-core` docstrings omit parameters that the surrounding docstring otherwise documents in full, so the omission reads as an oversight rather than a style choice. **1. `DynamicLLMPathExtractor.__init__`** -...run-llama/llama_indexiridescentWenSep 33 weeks ago
[Bug]: FunctionTool wraps a returned ToolOutput as a success and drops is_error### Bug Description `FunctionTool.call` / `acall` always build a **new** `ToolOutput` around the function's return value. `is_error` defaults to `False`. They never check whether the function already returned a `ToolOutput`. So this is a success: `FunctionAgent._call_tool` only...run-llama/llama_indexeemelipaSep 23 weeks ago
[Bug]: `Dispatcher.__init__` and model fields use mutable default arguments (`[]`)### Bug Description In `llama_index_instrumentation/dispatcher.py`, the `Dispatcher` class contains mutable default arguments in both its Pydantic `Field` declarations and its `__init__` constructor: 1. **Pydantic Model Fields** (lines 68-73): Using `default=[]` rather than...run-llama/llama_indexGracy769Aug 303 weeks ago
[Bug]: TokenTextSplitter emits chunks one token over chunk_size because splits are budgeted unstripped...sizes. On 4000 words of ordinary prose with `chunk_overlap=20`: Tracing `_merge` on the failing chunk above shows the budget and the emitted text disagreeing only at the strip: ### Relevant Logs/Tracebacksrun-llama/llama_indexaniketwaghhAug 284 weeks ago

Companies and products named

Company or productPosts naming it
LlamaIndex9
GitHub1
About this problem

Evidence

9 posts from 9 people in 2 places, about 2 a week over 28 days. Mostly on run-llama/llama_index, Stack Overflow [llama-index]. Tools named alongside: GitHub.

Frustration Frustration 0 of 3· Seen on GitHub issues, Stack Overflow

How it was grouped

Posts about LlamaIndex that state a pain but match no known issue yet. First post Aug 28, 2026, latest Sep 24, 2026. Corroborated: 3 or more posts from 2 or more people or places. Method

History

  • 2026-09-25 Statement: LlamaIndex users keep asking for help to LlamaIndex users keep filing bugs
  • 2026-09-25 Added: LlamaIndex users keep asking for help (9 posts)

Rising problems by email

Mondays: the problems in data, tech and AI that grew fastest that week.

Double opt-in. Unsubscribe any time.