> ## Documentation Index
> Fetch the complete documentation index at: https://docs.zeus.agentspro.cn/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent Tools

> Agent tools — search_knowledge_base and parse_resource_file

The knowledge base integrates with the DeepAgents framework through two Agent tools. When a user passes `knowledge_base_ids` in the `invoke()` request, these tools are automatically registered in the Agent's toolset.

***

## search\_knowledge\_base

The Agent proactively searches the knowledge base for relevant information. Supports parallel retrieval across multiple knowledge bases with adjustable retrieval weights.

<ParamField body="query" type="string" required>
  Search query (natural language)
</ParamField>

<ParamField body="knowledge_base_id" type="string">
  Specific knowledge base ID. If not specified, searches all configured knowledge bases
</ParamField>

<ParamField body="top_k" type="number" default="5">
  Number of results to return
</ParamField>

<ParamField body="vector_weight" type="number" default="0.6">
  Vector search weight (0-1)
</ParamField>

<ParamField body="keyword_weight" type="number" default="0.4">
  Keyword search weight (0-1)
</ParamField>

<ParamField body="use_rerank" type="boolean" default="true">
  Whether to use RRF reranking. When disabled, returns vector search results directly (faster)
</ParamField>

### Agent Call Examples

```python theme={null}
# Search all configured knowledge bases
search_knowledge_base("product usage instructions")

# Search a specific knowledge base
search_knowledge_base("XYZ-2000 product specifications", knowledge_base_id="kb_123")

# Increase keyword weight (suitable for exact term searches)
search_knowledge_base("getUserInfo API parameters", keyword_weight=0.7, vector_weight=0.3)

# Fast mode, skip RRF reranking
search_knowledge_base("quick query", use_rerank=False)
```

***

## parse\_resource\_file

Parses files uploaded by the user in the Resource panel. Supports all document formats and images (via Vision API).

<ParamField body="file_id" type="string" required>
  Resource file ID
</ParamField>

<ParamField body="parse_images" type="boolean" default="true">
  Whether to use Vision API to recognize image content
</ParamField>

<ParamField body="max_length" type="number" default="5000">
  Maximum returned text length
</ParamField>

### Agent Call Examples

```python theme={null}
# Parse an uploaded PDF document
parse_resource_file(file_id="res_abc123")

# Parse an image (using Vision API)
parse_resource_file(file_id="res_img456", parse_images=True)

# Limit return length
parse_resource_file(file_id="res_abc123", max_length=2000)
```