DROPGoogle launches Gemini 3.8 Flash TTS and Flash-Lite TTS///DROPGemini Omni brings 1080p generation to Google Vids///BREAKClaude Opus 5.5 is here: 1M context, $4 input / $20 output///BREAKOpenAI adds GPT-6 Sol and Luna to the GPT-6 family///PAPEROpus 5.5's system card documents gains—and evaluation limits///BREAKGrok 4.7 launches at $2 input / $6 output per million tokens///DROPGrok Voice Transcribe 2.0 targets difficult real-world audio///TRENDGoogle steers new Gemini API projects to 3.8 Flash or 3.5 Flash-Lite///DROPGoogle launches Gemini 3.8 Flash TTS and Flash-Lite TTS///DROPGemini Omni brings 1080p generation to Google Vids///BREAKClaude Opus 5.5 is here: 1M context, $4 input / $20 output///BREAKOpenAI adds GPT-6 Sol and Luna to the GPT-6 family///PAPEROpus 5.5's system card documents gains—and evaluation limits///BREAKGrok 4.7 launches at $2 input / $6 output per million tokens///DROPGrok Voice Transcribe 2.0 targets difficult real-world audio///TRENDGoogle steers new Gemini API projects to 3.8 Flash or 3.5 Flash-Lite///
DARC.DEV
Tool radar
L

Retrieval · Documentation review

LlamaIndex

Retrieval and evaluation building blocks for document-aware applications.

LlamaIndex provides building blocks around data ingestion, retrieval and LLM applications. Its evaluation documentation separates correctness, faithfulness and relevance from retrieval metrics such as hit rate and MRR. That separation makes it useful for diagnosing whether the right evidence was retrieved before judging the generated answer.

Official documentationReviewed 23 Sept 2026
Source-checked Sources & corrections

A good fit for

  • → Document assistants
  • → Retrieval experiments
  • → Comparing ingestion and ranking pipelines

Know the limits

  • → A faithfulness score does not prove the source is true.
  • → Synthetic test questions can overfit the corpus.
  • → Framework defaults should not decide document permissions.

Your first useful workflow

01

Build a labeled set

Pair representative questions with the source passages that should support the answer.

02

Test retrieval alone

Check whether the required evidence appears before asking a model to answer.

03

Score the answer

Evaluate correctness and citation support, including abstention cases.

The practical take

Measure retrieval separately from answer quality so you know which component failed.

Sources & evidence

Capabilities above are summarized from these official documents. Workflow suggestions are editorial guidance, not a claim of measured product superiority.