> For the complete documentation index, see [llms.txt](https://docs.cherryai.com.cn/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cherryai.com.cn/docs/en-us/knowledge-base/emb-models-info.md).

# Model and Retrieval Settings

The knowledge base first parses the materials and splits them into chunks, then finds the content in those chunks most likely to answer the question. The embedding model, reranking model, and Top K determine “how to search, how to rank, and how many to keep in the end”; they cannot make up for missing body text or incorrect chunking.

{% hint style="info" %}
When tuning for the first time, first run one recall test with the current settings. After that, change only one parameter each round, and always retest with the same set of questions, so you can tell which setting caused the change.
{% endhint %}

## First understand the retrieval chain

<figure><img src="/files/6e98934885eff518d13a4942ff027d90687e8866" alt="从资料解析、分块、BM25 与向量检索到合并、重排和 Top K 的知识库检索架构图"><figcaption><p>BM25 can always work on its own; after configuring an embedding model, vector retrieval is added, and reranking is an optional step after merging candidates.</p></figcaption></figure>

Every layer in the diagram affects the final result: the material content determines whether there is an answer, parsing and chunking determine whether the answer is complete, and retrieval and reranking determine whether the correct chunk can be ranked near the front.

### Three common combinations

| Combination                       | Actual retrieval method                                                     | What kind of materials it suits                               | When to upgrade                                                                            |
| --------------------------------- | --------------------------------------------------------------------------- | ------------------------------------------------------------- | ------------------------------------------------------------------------------------------ |
| Do not use an embedding model     | BM25 keyword search only                                                    | Lots of clause numbers, product names, and proper nouns       | When using a different wording makes it hard to hit, add an embedding model                |
| Embedding model                   | Run BM25 and vector retrieval in parallel, then merge the candidate results | The user's wording differs greatly from the original material | When the correct chunk can be retrieved but the ranking is unstable, add a reranking model |
| Embedding model + reranking model | Re-score and rerank after hybrid retrieval                                  | Candidate chunks are similar and require stable ranking       | First keep the threshold at 0.0, then adjust it gradually according to the noise           |

{% hint style="success" %}
The knowledge base can work even without configuring an embedding model. Only after selecting a reranking model will the settings panel show \[Similarity Threshold].
{% endhint %}

## Open settings and confirm the current configuration

Open the left navigation \[Knowledge Base] → select a knowledge base → click \[Settings] in the upper right.

The default section includes \[Document Processing], \[Embedding Model], \[Reranking Model], and \[Top K]. For the first test, it is recommended to keep Top K at 6 and temporarily not raise the similarity threshold.

<figure><img src="/files/f58b283148c047af0110df2639056a1f06120c11" alt="知识库设置中的文档处理、嵌入模型、重排模型和 Top K"><figcaption><p>First confirm the model and Top K, then go to [Advanced Settings] to check chunking.</p></figcaption></figure>

### Recommended starting point

| Configuration item   | Initial interface values                     | Suggested starting point                                                           | Function and notes                                                                                                                                   |
| -------------------- | -------------------------------------------- | ---------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------- |
| Embedding model      | Do not use                                   | Keep it unused at first when keywords can reliably match                           | After adding it, keyword and vector retrieval will run at the same time; billing and data processing for cloud models depend on the service provider |
| Reranking model      | Do not use                                   | Enable it only when the correct chunk can be retrieved but the ranking is unstable | This adds one more model scoring step and more waiting time                                                                                          |
| Top K                | 6, optional 1–50                             | Keep 6 for now                                                                     | Too small may miss the answer; too large brings more noise and takes up more conversation context                                                    |
| Similarity threshold | 0.0, shown only when reranking is configured | Start from 0.0                                                                     | Only filters low-scoring results after reranking; setting it too high may remove the correct chunk as well                                           |

## Establish a baseline with fixed questions

Before you begin, prepare 3 to 5 real questions with clear answers. The questions should cover proper nouns in the materials, colloquial wording, and situations that require context to answer.

{% stepper %}
{% step %}

### 1. First check the material body and Chunks

Confirm that the answer really exists in the material, and that the conditions and conclusion were not split incorrectly. If there is a problem at this layer, handle parsing or chunking first; do not rush to adjust the model.
{% endstep %}

{% step %}

### 2. Complete the first recall test

Open \[Recall Test], enter the prepared questions one by one, and record the hit source, chunk content, order, and time taken.

<figure><img src="/files/c6f3bfaf5deb56fb89e9a46bf9e60343a52ba0e2" alt="召回测试中的命中来源、相关度、片段内容和排序"><figcaption><p>Do not just look at whether there is a result; also confirm that the source is correct, the chunk is complete, and the ranking is reasonable.</p></figcaption></figure>
{% endstep %}

{% step %}

### 3. Find the layer where the problem lies

* No correct chunk at all: first check the material content, parsing, and chunking.
* Keywords can find it, but a different wording cannot: try an embedding model.
* The correct chunk can appear, but it often ranks behind others: try a reranking model.
* The correct chunk is filtered out: lower the similarity threshold.
* The first few results are all relevant, but the answer is still incomplete: slightly increase Top K again.
  {% endstep %}

{% step %}

### 4. Change only one item each round

For example, adjust Top K first and save it; do not change the embedding model and chunk size at the same time. If old material chunks or existing vectors are involved, re-index or rebuild as described below.
{% endstep %}

{% step %}

### 5. Retest with the same set of questions

Compare the source, chunk completeness, ranking, and time taken before and after the adjustment. If there is no improvement, restore the previous settings and test the next item.
{% endstep %}
{% endstepper %}

## How to adjust when chunking is incomplete

Expand \[Advanced Settings], and you can see \[Smart Chunking], \[Delimiter], \[Chunk Size], and \[Overlap Size].

<figure><img src="/files/0359b26559db3bea6e323bf599d74c081ad91c93" alt="知识库高级设置中的智能分段、分隔符、分段大小和重叠大小"><figcaption><p>For general materials, you can start with smart chunking enabled, chunk size 1024, and overlap size 200.</p></figcaption></figure>

| Configuration item | Initial interface values | When to adjust                                                                                                       | Common side effects                                                                    |
| ------------------ | ------------------------ | -------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------- |
| Smart chunking     | Enable                   | Keep it enabled when the material has clear headings and paragraph structure                                         | After turning it off, split only by delimiters                                         |
| Delimiter          | `\n\n`                   | Adjust when the material has stable custom paragraph boundaries                                                      | When smart chunking is turned off, the delimiter cannot be empty                       |
| Chunk size         | 1024 tokens              | Decrease it when one chunk mixes multiple topics; increase it when conditions and conclusions are always split apart | Too large increases noise; too small loses context                                     |
| Overlap size       | 200 tokens               | Increase it slightly when key information often crosses chunk boundaries                                             | It must be smaller than the chunk size; if too large, it will create duplicate content |

{% hint style="warning" %}
Chunking settings only affect content added afterward. To make existing materials use the new settings, execute \[Re-index] in the material row menu, then retest with the same set of questions.
{% endhint %}

## Changing models and rebuilding the knowledge base

When enabling an embedding model for a knowledge base that previously used only BM25, you can directly complete vector indexing. When changing the embedding model for a knowledge base that already has vectors, the interface will enter the \[Rebuild Knowledge Base] process, because vectors generated by different embedding models cannot be mixed.

{% hint style="danger" %}
Before starting the rebuild, first confirm that the new embedding model can be called normally. After rebuilding, you need to re-establish the recall baseline; do not change the model and modify chunking in the same round, or you will not be able to tell where the change in results came from.
{% endhint %}

If you need to complete embeddings locally, open \[Settings] → \[Local Models], download an available model in the \[Embedding Model] section, and then return to the knowledge base settings to select it.

<figure><img src="/files/9085804a861312f65d0eca07b55ebb6d1c05b554" alt="本地模型设置中的嵌入模型下载入口"><figcaption><p>First complete the local model download, then return to the knowledge base to select it and build the index.</p></figcaption></figure>

## Tuning loop

<figure><img src="/files/8a987762d4b568b0fa1dd608f98a10abd15b021c" alt="用固定问题进行召回测试、定位问题、单项调整、重新索引并复测的知识库质量调优闭环"><figcaption><p>Fixed questions → check results → identify the layer → adjust one item → reindex if needed → retest.</p></figcaption></figure>

Only keep changes that stably improve the fixed test questions each time. If the result does not improve, restore the previous set of settings instead of stacking more changes.

## A complete example

Xiaolin maintains a set of employee travel expense rules. The material says “lodging expense standard,” but employees often ask “how much can be reimbursed at most for a hotel stay?”

1. He first tested with the default settings and found that queries using the original wording could hit, but colloquial wording was unstable.
2. He configured an embedding model and completed indexing, then retested with the same questions.
3. The correct chunk could appear stably, but occasionally ranked behind others, so he configured a reranking model as well.
4. He kept Top K at 6 and the threshold at 0.0, and only gradually raised the threshold when it was confirmed that irrelevant results were obvious.

The completion criterion is: the same lodging standard can be found within the first few results for three different phrasings, and the chunk contains both the applicable conditions and the reimbursement limit.

## Common questions

<details>

<summary>Can the knowledge base still search without using an embedding model?</summary>

Yes. The knowledge base will use BM25 keyword retrieval, which is suitable for clause numbers, proper nouns, and queries close to the original wording.

</details>

<details>

<summary>Why can’t I see [Similarity Threshold]?</summary>

Only after selecting a reranking model will the settings panel show \[Similarity Threshold].

</details>

<details>

<summary>Why didn’t old materials change after modifying the chunk size?</summary>

Chunking settings only affect content added afterward. Please execute \[Re-index] for the existing materials, then retest with the same questions.

</details>

<details>

<summary>The correct chunk never appears at all; should I first increase Top K?</summary>

First check the data main text and Chunks. If parsing or splitting is wrong, increasing Top K will only return more incorrect or incomplete fragments.

</details>

## Continue reading

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Knowledge base basics</strong></td><td>First build an overall understanding of how the knowledge base works.</td><td><a href="/pages/7140324ff22db2432f4def400aa0613550c21011">/pages/7140324ff22db2432f4def400aa0613550c21011</a></td></tr><tr><td><strong>Document parsing and OCR</strong></td><td>When the body text is missing or recognition is incorrect, troubleshoot from the material processing layer.</td><td><a href="/pages/7d495aecf9165aca96855bc0d74b3e925728dedc">/pages/7d495aecf9165aca96855bc0d74b3e925728dedc</a></td></tr><tr><td><strong>Add and organize materials</strong></td><td>Learn about re-indexing, material status, and content maintenance.</td><td><a href="/pages/53062e948442e1c25a4e6ad7b4ec9baf548deafc">/pages/53062e948442e1c25a4e6ad7b4ec9baf548deafc</a></td></tr><tr><td><strong>Check materials and recall</strong></td><td>Continue practicing recall tests and result judgment.</td><td><a href="/pages/7c7a6d04d1e906eb7a89261dabeedb48874a9b8e">/pages/7c7a6d04d1e906eb7a89261dabeedb48874a9b8e</a></td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.cherryai.com.cn/docs/en-us/knowledge-base/emb-models-info.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.