Perplexica/docs/architecture/README.md

# Perplexica's Architecture

Perplexica's architecture consists of the following key components:

1. **User Interface**: A web-based interface that allows users to interact with Perplexica for searching images, videos, and much more.
2. **Agent/Chains**: These components predict Perplexica's next actions, understand user queries, and decide whether a web search is necessary.
3. **SearXNG**: A metadata search engine used by Perplexica to search the web for sources.
4. **LLMs (Large Language Models)**: Utilized by agents and chains for tasks like understanding content, writing responses, and citing sources. Examples include Claude, GPTs, etc.
5. **Embedding Models**: To improve the accuracy of search results, embedding models re-rank the results using similarity search algorithms such as cosine similarity and dot product distance.
6. **Web Content**
   - 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 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 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).
chore(docs): fix Markdown lint issues in the docs 2024-11-15 07:04:45 +01:00			`# Perplexica's Architecture`
feat(message-actions): add speak message, bump version 2024-05-03 18:25:22 +05:30
feat(docs): add architecture docs 2024-05-03 16:31:58 +05:30			`Perplexica's architecture consists of the following key components:`

			`1. User Interface: A web-based interface that allows users to interact with Perplexica for searching images, videos, and much more.`
			`2. Agent/Chains: These components predict Perplexica's next actions, understand user queries, and decide whether a web search is necessary.`
			`3. SearXNG: A metadata search engine used by Perplexica to search the web for sources.`
			`4. LLMs (Large Language Models): Utilized by agents and chains for tasks like understanding content, writing responses, and citing sources. Examples include Claude, GPTs, etc.`
			`5. Embedding Models: To improve the accuracy of search results, embedding models re-rank the results using similarity search algorithms such as cosine similarity and dot product distance.`
feat(UI): allow system prompts and persona prompts to be saved server side and individually included or excluded from messages 2025-05-27 12:53:30 -06:00			`6. Web Content`
feat(agent): Pretty decent first pass at agent mode 2025-06-09 23:00:25 -06:00			`- 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`
feat(UI): allow system prompts and persona prompts to be saved server side and individually included or excluded from messages 2025-05-27 12:53:30 -06:00			`- In Speed mode, the application only uses the preview content returned by SearXNG`
feat(agent): Pretty decent first pass at agent mode 2025-06-09 23:00:25 -06:00			`- This content is provided by the search engines and contains minimal context from the actual web page`
feat(agent): Refactor search agents and implement SpeedSearchAgent - 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. 2025-06-28 17:59:12 -06:00			`- This mode prioritizes quick responses over accuracy`
feat(docs): update URLs 2024-05-03 16:34:32 +05:30
feat(message-actions): add speak message, bump version 2024-05-03 18:25:22 +05:30			`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).`