sk/Perplexica
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

feat(agent): Refactor search agents and implement SpeedSearchAgent

Browse source 
- Updated FileSearchAgent to improve code readability and formatting.
- Refactored SynthesizerAgent for better prompt handling and document processing.
- Enhanced TaskManagerAgent with clearer file context handling.
- Modified AgentSearch to maintain consistent parameter formatting.
- Introduced SpeedSearchAgent for optimized search functionality.
- Updated metaSearchAgent to support new SpeedSearchAgent.
- Improved file processing utilities for better document handling.
- Added test attachments for sporting events queries.
This commit is contained in:
Willie Zutz 2025-06-28 17:59:12 -06:00
parent de3d26fb15
commit d66300e78e
19 changed files with 832 additions and 996 deletions
Download patch file Download diff file Expand all files Collapse all files

1
docs/API/SEARCH.md
View file

@ -60,7 +60,6 @@ The API accepts a JSON object in the request body, where you define the focus mo
- **`optimizationMode`** (string, optional): Specifies the optimization mode to control the balance between performance and quality. Available modes:
- `speed`: Prioritize speed and get the quickest possible answer. Minimum effort retrieving web content. - Only uses SearXNG result previews.
- `balanced`: Find the right balance between speed and accuracy. Medium effort retrieving web content. - Uses web scraping technologies to retrieve partial content from full web pages.
- `agent`: Use an agentic workflow to answer complex multi-part questions. This mode requires a model that is trained for tool use.
- **`query`** (string, required): The search query or question.

4
docs/architecture/README.md
View file

@ -11,10 +11,8 @@ Perplexica's architecture consists of the following key components:
- In Agent mode, the application uses an agentic workflow to answer complex multi-part questions
- The agent can use reasoning steps to provide comprehensive answers to complex questions
- Agent mode is experimental and may consume lots of tokens and take a long time to produce responses
- In Balanced mode, the application retrieves web content using Playwright and Mozilla Readability to extract relevant segments of web content
- Because it only uses segments of web content, it can be less accurate than Agent mode
- In Speed mode, the application only uses the preview content returned by SearXNG
- This content is provided by the search engines and contains minimal context from the actual web page
- This mode is the least accurate and is often prone to hallucination
- This mode prioritizes quick responses over accuracy
For a more detailed explanation of how these components work together, see [WORKING.md](https://github.com/ItzCrazyKns/Perplexica/tree/master/docs/architecture/WORKING.md).