Knowledge Search Agent
The Knowledge Search Agent runs a search over one or more connected data sources and returns a ranked set of passages with source references that downstream agents can cite.
Use Cases
- Your AI Employee needs to retrieve information from uploaded documents, connected data sources, or indexed content.
- You are building a FAQ bot, policy lookup, or documentation search.
- You need grounded answers backed by source documents.
Inputs
| Input | Required | Description |
|---|---|---|
| Query | Yes | The search text. |
| Data Sources | No | The knowledge bases to search. Usually wired at config time, can also be overridden per run. |
| Filter by Filename | No | Comma separated file names to restrict the search to specific documents. Quoted names containing commas are supported. |
Outputs
| Output | Description |
|---|---|
| Search Results | A ranked list of passages. Each entry carries the text snippet, a reference to the source document, and a relevance score used for ranking downstream. |
Advanced Configurations
| Parameter | Description | Default |
|---|---|---|
| Number of Search Results | How many results to fetch from each connected data source before ranking. | 10 |
| Max Sources | Maximum number of source documents included in the final output after ranking. | 10 |
| Max Chunks per Result | Maximum number of content chunks pulled from each matched document. | 5 |
| Number of Previous Chunks | Neighboring chunks to include before each match, for surrounding context. | 0 |
| Number of Next Chunks | Neighboring chunks to include after each match, for surrounding context. | 0 |
| Disable Images | Turns off image retrieval. When off, image results are returned alongside text passages. | Off |
| Max Images | Maximum number of image results returned per match. | 5 |
| Enable Filtering by Document Validity Dates | Only returns documents whose validity window covers the current date. | Off |
How to Use This Agent
The standard search and respond pattern:
chat_trigger -> knowledge_search -> respond_agent -> workflow_outputWith conversation context for multi-turn:
chat_trigger -> conversation_summarizer -> knowledge_search -> respond_agent -> workflow_outputRelated Agents
- Respond Agent, the standard downstream agent for generating responses from search results.
- Conversation Summarizer, converts multi-turn conversations into search queries.
- Combine Search Results, merges results from multiple search agents.
- Rerank Search Results, LLM-based reranking for improved relevance.
- Agentic Search and Respond, for complex research that requires iterative searching.
- Document Synthesis, for searches that need image and table awareness.