# Search Testing and Retrieval Parameters

> Master knowledge base search testing, hybrid search modes, similarity score analysis, and zero-recall troubleshooting.

Source: https://doc.fastgpt.io/en/guide/dataset/test-retrieval

Before attaching a knowledge base to conversational applications, use the standalone "Search Test" interface to isolate prompt and generation noise, verifying vector and full-text retrieval precision directly.

## Step 1: Open the Search Test Interface

1. Navigate to your target knowledge base and click the "Search Test" tab in the top navigation bar.
2. The view displays a test input area, a **Search settings** button in the top-right corner, a **Test** button, test history, and candidate result cards. Click **Search settings** to open the **Dataset search settings** modal, choose the retrieval mode under **Search Method**, and configure **Citation cap** and **Lowest correlation** under **Search Filter**.
3. Enter a representative operational inquiry, such as: `How many days do I have to submit travel expenses after returning?`.

![Search test returns original text containing reimbursement deadline](https://cdn.jsdelivr.net/gh/labring/fastgpt-img@main/optimized/current/knowledge-search.png.webp)

## Step 2: Compare Search Methods

Switch between options under **Search Method** in the **Dataset search settings** modal to observe differences across candidate ranks:

1. **Semantic search**:
   Enter a query with synonymous phrasing (e.g., `What is the deadline for filing trip expenses?`). The engine uses geometric distance in dense vector space to recall chunks containing "15 calendar days".
2. **Full-text search**:
   Enter a query featuring specialized codes or exact references (e.g., `Policy Rule FIN-2026-03 Section 15`). Check whether full-text search retrieves the document section containing the identifier.
3. **Hybrid search (Recommended)**:
   Combines semantic generalization and exact term matching. The engine merges multi-route candidates and optionally reranks them when a rerank model is configured.

![Hybrid search and reranking score details](https://cdn.jsdelivr.net/gh/labring/fastgpt-img@main/optimized/current/dataset-result-scores.png.webp)

## Step 3: Analyze Scores and Calibrate Lowest Correlation

Use scores to compare candidates within the same model and retrieval configuration. Build a labeled test set containing answerable questions, paraphrases, exact identifiers, and questions outside the knowledge base. Record the expected source chunk for each answerable question.

### Calibration Guidelines

1. Start with a low threshold and check whether expected chunks enter the candidate list.
2. Adjust one setting at a time. Compare relevant hits, missed references, and irrelevant results before selecting a threshold.
3. Repeat after changing the embedding model, rerank model, or chunking strategy. Inspect actual reranking and filtering status when the interface exposes it.

![Search parameters and score threshold configuration](https://cdn.jsdelivr.net/gh/labring/fastgpt-img@main/optimized/current/dataset-search-filter.png.webp)

## Step 4: Step-by-Step Zero-Recall Troubleshooting

When an expected query fails to return target chunks, follow this four-step diagnostic procedure:

| Step                         | Diagnostic Focus                                                    | Actionable Fix                                                                                                                                           |
| ---------------------------- | ------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **1. Chunk Completeness**    | Search for the clause in the collection's data chunk list           | Confirm the fact is ingested and was not split awkwardly across boundaries                                                                               |
| **2. Index Readiness**       | Inspect the collection's index status in the file list              | Verify the collection status is **Ready**; if **Indexing error**, retry from the **Error list** modal                                                    |
| **3. Tokenization Coverage** | Check if proper nouns were fragmented during full-text tokenization | Query using complete standardized terms, or switch to **Hybrid search** (on Milvus, adjust analyzer language detection via `MILVUS_LANGUAGE_IDENTIFIER`) |
| **4. Supplementary Indexes** | Add query variations to the target chunk                            | Click the chunk card to open the edit dialog, click **New** under **Data Index (N)**, and add 3 to 5 common user question patterns                       |

## Next Steps

* Integrate into chat: Follow [Connecting Knowledge Bases to Applications](/en/guide/dataset/connect-application).
* Metadata-scoped search: Learn [Collection Tag System](/en/guide/dataset/collection_tags).
* Data maintenance: Review [Data Maintenance and Incremental Updates](/en/guide/dataset/update-data).