The writing model cannot use evidence that search failed to find. Test the embedding model and search system separately.
Test document search before the chat model
An embedding model does not write the final answer. It helps the system find document passages with a meaning close to the user's question.
- 1
Prepare thirty questions
For each question, mark the exact passage that contains the answer.
- 2
Build the search index
Use one embedding model for both the document passages and the user questions.
- 3
Search without generating
View the top five passages returned for every question. Do not ask the writing model to answer yet.
- 4
Count useful results
Record whether the correct passage appears first, in the top three, or in the top five.
- 5
Improve and repeat
Change one thing at a time, such as the embedding model or passage length. Build a new index after changing the embedding model.
- The correct passage appears near the top for most known questions.
- Questions with no answer do not return misleading evidence.
- The embedding model name and version are saved with the index.
Use the explanations below when you want to know why each step matters.
What an embedding model does
An embedding model turns text into a list of numbers called a vector. Text with a similar meaning should have vectors that sit close together.
The system saves a vector for each document piece. It also makes a vector for the user's question. It then looks for the closest matches.
Embeddings are not the final answer
The embedding model finds useful passages. A different model reads those passages and writes the final answer.
If the wrong passages are found, even a powerful writing model may give a weak or made-up answer.
How to choose an embedding model
- Language: choose a multilingual model when your files use several languages.
- Type of work: legal, code, science, and general writing may search differently.
- Text length: make sure long pieces are not cut off.
- Size: larger vectors use more storage and memory.
- License and support in your local AI tools.
- Results on your own questions.
Build a search test
- Create at least 30 real questions.
- Mark the correct source passage for each question.
- Check whether it appears in the top 1, top 3, and top 5 results.
- Include short forms, different wording, and multiple languages.
- Include questions with no answer.
- Test document size and embedding choice separately.
Avoid a hidden mistake
Do not create document vectors with one embedding model and question vectors with another. Their number systems are not the same.
Save the model name and version with the search index. Build a new index and test again whenever the embedding model or text process changes.
Official facts and real user evidence
Official documentation supports product and model facts. Community discussions show real setups, failures, and questions. A community result is supporting evidence, not a promise that another computer will perform the same way.
Find a model your computer can run.
MamiLens checks your hardware and shows a careful starting point.
Run the free compatibility check →This guide is educational. Model software, licenses, and hardware support can change. Check official sources before an important deployment.