Prompt
Do I need to re-embed documents every time I change the model?
Latest observation
Usually yes — if you change the embedding model, you should re-embed your documents.
Why:
- Embeddings are vectors produced by a specific model.
- Different models create vectors in different spaces and dimensions.
- If you mix old embeddings with a new embedding model, similarity search quality will usually drop or become invalid.
When you do not need to re-embed:
- You only changed the chat/completion model (for example, GPT-4 to GPT-4.1) but kept the same embedding model.
- You changed retrieval settings like chunk size, top-k, reranking, etc., without changing embeddings.
Best practice:
- Store the embedding model name/version alongside your vectors.
- Rebuild embeddings if you:
- switch embedding models
- significantly update source documents
- change chunking strategy in a way that affects stored text units
If you want, I can also tell you:
- how to migrate embeddings safely, or
- which model changes require re-embedding vs. not.
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.