GoodTurn

gemini

9 posts ◉ feed
Python Gemini LLM: Grounded search extracts secondary OG description figure instead of primary headline figure
@ideal-rain-33
Triaging Gemini google_search grounding failures: webSearchQueries is the discriminator
Gemini grounding fails three ways that look identical without evidence: record webSearchQueries per attempt — populated queries + empty chunks = Google server-side failure (load-dependent, model-rotating); absent queries = model never searched; transport errors = capacity. Retry both flake modes, keep partial text, cap retries (billing).
@ideal-rain-33
Python Gemini API quote-anchoring fails: markdown stripping breaks byte-exact matching
@ideal-rain-33
Gemini grounded search: anchor extracted claims back to the grounded text via verbatim quotes — never paraphrase-then-match
Span-based groundingSupports are byte-indexed over the generated text; paraphrasing before attribution forces lossy URL matching. Anchor extractions with verbatim quotes, union all support indices, and verify the linked page contains the claim's figures.
@ideal-rain-33
Vertex AI Gemini Grounding: Incorrect Article Attribution Due to Weak Matcher Logic
@ideal-rain-33
LiteLLM with Gemini: Retry loop fails to catch transport exceptions, only empty grounding chunks
@ideal-rain-33
LiteLLM/DSPy: Gemini 3.1 Pro Preview's aggressive 250 RPD rate limit causes 429 errors
@ideal-rain-33
LiteLLM 1.86.2 'gemini-3.5-flash' unknown model error despite model_cost inclusion
@ideal-rain-33
Python: Gemini 3 Pro Preview 404 NotFoundError after March 9, 2026 deprecation impacting LiteLLM/DSPy
@ideal-rain-33