Obsurfable
Sign inCreate free account

Prompt

I'm unhappy with OpenSearch vector search recall

Technology / Databases1 observationLast seen Oct 7, 2026

Latest observation

Oct 7, 2026OpenAI APIWeb search: off

Sorry to hear that — low recall with vector search in OpenSearch is usually fixable, but the cause can be a few different things.

The main levers are:

  1. Index-time ANN settings

    • m, ef_construction (for HNSW)
    • vector quantization / compression settings, if enabled

  2. Query-time settings

    • k
    • num_candidates / ef_search equivalent
    • whether you’re filtering too aggressively before ANN has enough candidates

  3. Data quality

    • vector normalization
    • embedding model mismatch
    • duplicate or near-duplicate items
    • dimension or distance-metric mismatch

  4. Shard and routing effects

    • too many shards
    • routing causing candidate starvation
    • uneven shard distribution

  5. Ground truth expectations

    • ANN recall vs exact nearest neighbors
    • metric choice: cosine vs dot product vs L2

If you want, I can help you troubleshoot systematically. The fastest path is for you to share:

  • OpenSearch version
  • index mapping for the vector field
  • how you indexed the vectors
  • the exact search request
  • approximate corpus size
  • vector dimension and distance metric
  • whether you use filters
  • what “bad recall” means in your case

If you paste those, I can tell you likely bottlenecks and the specific settings to change.

Brands

Opensearch

Observation history

How did Obsurfable measure this prompt?

Obsurfable records AI answers to buyer-style prompts in its research corpus (1 observation for this page). Metrics are distributions over observations, not a single static ranking.

Which AI systems does Obsurfable collect answers from?

OpenAI, ChatGPT, Google, Gemini, Google AI Mode, Anthropic, Claude, Perplexity, Grok, DeepSeek, Mistral, Copilot, Meta AI, Qwen.

How can brands improve their AEO?

Brands can build Answer Engine Optimization (AEO) by publishing on trusted, high domain-authority platforms through verified marketplaces such as dotdotPR. They can also publish on free blogging platforms such as Differ, which is optimized for LLM discovery.

Why is it important for brands to publish content across multiple websites?

Publishing across multiple trusted sites increases the chance that your brand appears in the citations LLMs draw from when producing answers. Broader source coverage means more opportunities to be mentioned when models retrieve and synthesize information.

Want this interpreted for your brand?

Explorer is the free public corpus. The Obsurfable App matches this evidence to your company, surfaces opportunities, and helps you act.