# Explore App Portal

The **Epsilla App Portal** provides a centralized platform for users to **browse** and **interact with AI agents** created by the Epsilla community. The Portal is designed to offer a straightforward experience for those looking to explore a variety of applications built on Retrieval-Augmented Generation (RAG) technology.

Through the Portal, users can select and try out AI agents designed for various purposes, from everyday tasks to more complex decision-making support. Each AI agent is based on user-provided data and models, allowing for tailored solutions across different industries and use cases.

<figure><img src="/files/oft8ctGovVFidw4z0npl" alt=""><figcaption></figcaption></figure>

There are two types of agents: Chatbot Agents and Smart Search Agents.

### Chatbot Agents

Chatbot agents provide an interactive conversational experience similar to **ChatGPT**. Users can engage with these chatbots by asking questions or discussing various topics in natural language. The agents are designed to generate context-aware, coherent responses, making them ideal for customer support, personal assistance, or domain-specific conversations. Chatbot agents are often tailored to specific knowledge base, allowing for personalized and accurate information delivery:

{% embed url="<https://youtu.be/8J_R18c5aHY>" %}

Chatbot responses are grounded in documents. Click the citations to view the references side by side, with PDF highlighting:

<figure><img src="/files/enWO83M3fJElA59ulMR8" alt=""><figcaption></figcaption></figure>

Provide feedback to assist the agent creator in improving the agent:

<div><figure><img src="/files/gLsVJ4VjC3vW3Wyb06vb" alt=""><figcaption></figcaption></figure> <figure><img src="/files/siCgIwsGHNEbNTAEL2fo" alt=""><figcaption></figcaption></figure></div>

If you find a conversation inspiring, share it with your community:

<div><figure><img src="/files/txrOQQbvTC96aj0IU2ru" alt=""><figcaption></figcaption></figure> <figure><img src="/files/axrglkDvHImPoGzJlHHL" alt=""><figcaption></figcaption></figure></div>

### Smart Search Agents

Smart Search Agents are modeled after platforms like **Perplexity**. They are optimized for retrieving and presenting relevant information quickly and efficiently. Instead of focusing on conversational flow, these agents excel in conducting searches and returning precise, factual answers based on user queries. Smart Search agents are particularly useful for research, content discovery, and data-driven decision-making, leveraging advanced retrieval techniques for accuracy and relevance:

{% embed url="<https://youtu.be/jYGBhSEdHI0>" %}

Search responses are grounded in documents. Click the citations to view the references side by side, with PDF highlighting:

<figure><img src="/files/kmveKxjt61b4WWUQPrIx" alt=""><figcaption></figcaption></figure>

Provide feedback to assist the agent creator in improving the agent:

<div><figure><img src="/files/XjksxmUYZm6lohIUMdqf" alt=""><figcaption></figcaption></figure> <figure><img src="/files/XBGuzm7SYetZmKpSBzls" alt=""><figcaption></figcaption></figure></div>

If you find a search result inspiring, share it with your community:

<figure><img src="/files/VTcjNjmWT8tRjOe9SxV8" alt=""><figcaption></figcaption></figure>

Click the hamburger button at top right corner:

<figure><img src="/files/J0EcjFwox4Or9SjtOcg9" alt="" width="68"><figcaption></figcaption></figure>

and you open the side navigation bar for viewing search history:

<figure><img src="/files/Zj50Gs3FRsBodLW4HWpe" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://epsilla-inc.gitbook.io/epsilladb/readme/explore-app-portal.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.