> For the complete documentation index, see [llms.txt](https://epsilla-inc.gitbook.io/epsilladb/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://epsilla-inc.gitbook.io/epsilladb/integration.md).

# Integration

## Model Providers

Integrating with large language models (LLMs) and embedding model providers in Epsilla allows users to tap into cutting-edge AI models for a variety of applications. Epsilla offers seamless connections to a range of providers such as OpenAI, Anthropic, and others, supporting models like GPT-4, Claude, Mistral, and embedding solutions like JinaAI, VoyageAI, etc.

<figure><img src="/files/3w0toTjRE2Nl2xT2quao" alt=""><figcaption></figcaption></figure>

Users can easily enable these integrations by entering their API keys, giving them access to the provider’s models for tasks such as text generation, embedding.

Once the API key is validated, the models are ready for immediate use across the Epsilla platform.

<figure><img src="/files/vtMhG47sr9Z33bBem1MV" alt="" width="314"><figcaption></figcaption></figure>

If the key validation fails, users can quickly update or correct their credentials, ensuring smooth and secure model access for their business needs.

<figure><img src="/files/qVs9csMNiK5yO6r9fNjw" alt="" width="323"><figcaption></figcaption></figure>

<figure><img src="/files/f8FZugcBuGeO3n2PfQkw" alt="" width="354"><figcaption></figcaption></figure>

By integrating your own LLM API key into Epsilla, all usage will be directly linked to your own LLM account, meaning that any costs or message usage will be handled by your LLM provider. This setup bypasses Epsilla's monthly message limits, allowing you full control and flexibility over your LLM usage and billing.

{% hint style="warning" %}
OpenAI has a sophisticated API key billing system that includes multiple tiers, model access options, and rate limits, and this can make the integration overwhelming and confusing. If you encounter any issues during the API key validation process or have questions about your integration, feel free to reach out to us for assistance.
{% endhint %}

## Web Search Providers

Web search providers enable your chat agent to retrieve real-time information from the internet. By integrating with services like Tavily, you can use their API to enhance the chat agent's capabilities with up-to-date web search functionality. Simply input and validate your API key to activate this feature, ensuring seamless access to internet-based knowledge for your AI agent.

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


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://epsilla-inc.gitbook.io/epsilladb/integration.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.